wandb: Currently logged in as: 804703098. Use `wandb login --relogin` to force relogin
wandb: wandb version 0.17.0 is available!  To upgrade, please run:
wandb:  $ pip install wandb --upgrade
wandb: Tracking run with wandb version 0.16.6
wandb: Run data is saved locally in /home/user/zhangyang/PycharmProjects/Nips2024-ITPC-v2/Nips2024-ITPC-v2/onpolicy/scripts/results/MPE/simple_tag_tr/rmappotrsyn/exp_train_continue_tag_base_CMT_s2r2_v1/wandb/run-20240508_193312-ipiauwxx
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run MPE_7
wandb: ⭐️ View project at https://wandb.ai/804703098/Continue_Tag_Base_v1
wandb: 🚀 View run at https://wandb.ai/804703098/Continue_Tag_Base_v1/runs/ipiauwxx
choose to use cpu...
idv policy and team policy use same initial params!

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 0/10000 episodes, total num timesteps 200/2000000, FPS 345.

team_policy eval average step individual rewards of agent0: 0.017985025718446786
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 4
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: -0.05428706313346443
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: -0.08429763548613683
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.09872054143008656
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.03859402363216083
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 2
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: -0.10442569975890426
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.11809659323084322
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: 0.14581401404912228
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 9
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: 0.09627533107807178
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 7
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.012702502304974807
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 3
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1/10000 episodes, total num timesteps 400/2000000, FPS 275.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2/10000 episodes, total num timesteps 600/2000000, FPS 303.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3/10000 episodes, total num timesteps 800/2000000, FPS 302.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 4/10000 episodes, total num timesteps 1000/2000000, FPS 310.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 5/10000 episodes, total num timesteps 1200/2000000, FPS 319.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 6/10000 episodes, total num timesteps 1400/2000000, FPS 321.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 7/10000 episodes, total num timesteps 1600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 8/10000 episodes, total num timesteps 1800/2000000, FPS 322.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 9/10000 episodes, total num timesteps 2000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 10/10000 episodes, total num timesteps 2200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 11/10000 episodes, total num timesteps 2400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 12/10000 episodes, total num timesteps 2600/2000000, FPS 323.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 13/10000 episodes, total num timesteps 2800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 14/10000 episodes, total num timesteps 3000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 15/10000 episodes, total num timesteps 3200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 16/10000 episodes, total num timesteps 3400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 17/10000 episodes, total num timesteps 3600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 18/10000 episodes, total num timesteps 3800/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 19/10000 episodes, total num timesteps 4000/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 20/10000 episodes, total num timesteps 4200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 21/10000 episodes, total num timesteps 4400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 22/10000 episodes, total num timesteps 4600/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 23/10000 episodes, total num timesteps 4800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 24/10000 episodes, total num timesteps 5000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 25/10000 episodes, total num timesteps 5200/2000000, FPS 331.

team_policy eval average step individual rewards of agent0: -0.047130144845362126
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: 0.06141910740905395
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 6
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: 0.11170598469076266
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 8
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: 0.04399081648746672
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 5
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.003225570669026316
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 4
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: 0.04710252765463352
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 5
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: 0.08740486218197413
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 6
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.037728565157647956
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: 0.1647824501153771
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 9
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.03771517761061361
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 26/10000 episodes, total num timesteps 5400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 27/10000 episodes, total num timesteps 5600/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 28/10000 episodes, total num timesteps 5800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 29/10000 episodes, total num timesteps 6000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 30/10000 episodes, total num timesteps 6200/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 31/10000 episodes, total num timesteps 6400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 32/10000 episodes, total num timesteps 6600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 33/10000 episodes, total num timesteps 6800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 34/10000 episodes, total num timesteps 7000/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 35/10000 episodes, total num timesteps 7200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 36/10000 episodes, total num timesteps 7400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 37/10000 episodes, total num timesteps 7600/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 38/10000 episodes, total num timesteps 7800/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 39/10000 episodes, total num timesteps 8000/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 40/10000 episodes, total num timesteps 8200/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 41/10000 episodes, total num timesteps 8400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 42/10000 episodes, total num timesteps 8600/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 43/10000 episodes, total num timesteps 8800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 44/10000 episodes, total num timesteps 9000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 45/10000 episodes, total num timesteps 9200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 46/10000 episodes, total num timesteps 9400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 47/10000 episodes, total num timesteps 9600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 48/10000 episodes, total num timesteps 9800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 49/10000 episodes, total num timesteps 10000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 50/10000 episodes, total num timesteps 10200/2000000, FPS 332.

team_policy eval average step individual rewards of agent0: -0.09512836928607764
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: -0.000809571928985815
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 3
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: -0.04236688555582797
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 2
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.004931290480521442
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 3
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.023367548430379814
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 2
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: -0.02495851695822747
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.05911650033922112
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.036300651976429926
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.02865546703182966
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.07249838223371512
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 0
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 51/10000 episodes, total num timesteps 10400/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 52/10000 episodes, total num timesteps 10600/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 53/10000 episodes, total num timesteps 10800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 54/10000 episodes, total num timesteps 11000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 55/10000 episodes, total num timesteps 11200/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 56/10000 episodes, total num timesteps 11400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 57/10000 episodes, total num timesteps 11600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 58/10000 episodes, total num timesteps 11800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 59/10000 episodes, total num timesteps 12000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 60/10000 episodes, total num timesteps 12200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 61/10000 episodes, total num timesteps 12400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 62/10000 episodes, total num timesteps 12600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 63/10000 episodes, total num timesteps 12800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 64/10000 episodes, total num timesteps 13000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 65/10000 episodes, total num timesteps 13200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 66/10000 episodes, total num timesteps 13400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 67/10000 episodes, total num timesteps 13600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 68/10000 episodes, total num timesteps 13800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 69/10000 episodes, total num timesteps 14000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 70/10000 episodes, total num timesteps 14200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 71/10000 episodes, total num timesteps 14400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 72/10000 episodes, total num timesteps 14600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 73/10000 episodes, total num timesteps 14800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 74/10000 episodes, total num timesteps 15000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 75/10000 episodes, total num timesteps 15200/2000000, FPS 334.

team_policy eval average step individual rewards of agent0: -0.08403856166998161
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: -0.0066757915522486265
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 3
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: -0.03556736863099796
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 2
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.0723516395007359
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.04626333454644341
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 2
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: 0.0655889586662389
idv_policy eval average team episode rewards of agent0: 2.5
idv_policy eval idv catch total num of agent0: 6
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent1: -0.08173333056030571
idv_policy eval average team episode rewards of agent1: 2.5
idv_policy eval idv catch total num of agent1: 0
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent2: 0.05353033144002914
idv_policy eval average team episode rewards of agent2: 2.5
idv_policy eval idv catch total num of agent2: 5
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent3: 0.052413793008576126
idv_policy eval average team episode rewards of agent3: 2.5
idv_policy eval idv catch total num of agent3: 5
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent4: 0.009926533217857303
idv_policy eval average team episode rewards of agent4: 2.5
idv_policy eval idv catch total num of agent4: 4
idv_policy eval team catch total num: 1

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 76/10000 episodes, total num timesteps 15400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 77/10000 episodes, total num timesteps 15600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 78/10000 episodes, total num timesteps 15800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 79/10000 episodes, total num timesteps 16000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 80/10000 episodes, total num timesteps 16200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 81/10000 episodes, total num timesteps 16400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 82/10000 episodes, total num timesteps 16600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 83/10000 episodes, total num timesteps 16800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 84/10000 episodes, total num timesteps 17000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 85/10000 episodes, total num timesteps 17200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 86/10000 episodes, total num timesteps 17400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 87/10000 episodes, total num timesteps 17600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 88/10000 episodes, total num timesteps 17800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 89/10000 episodes, total num timesteps 18000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 90/10000 episodes, total num timesteps 18200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 91/10000 episodes, total num timesteps 18400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 92/10000 episodes, total num timesteps 18600/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 93/10000 episodes, total num timesteps 18800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 94/10000 episodes, total num timesteps 19000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 95/10000 episodes, total num timesteps 19200/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 96/10000 episodes, total num timesteps 19400/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 97/10000 episodes, total num timesteps 19600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 98/10000 episodes, total num timesteps 19800/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 99/10000 episodes, total num timesteps 20000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 100/10000 episodes, total num timesteps 20200/2000000, FPS 334.

team_policy eval average step individual rewards of agent0: -0.05281821694552388
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: 0.012734492207123133
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 4
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: 0.010834461432297333
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 4
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.027130705486236337
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 2
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.0695239572107676
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: -0.021147430432348183
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.038155739415827054
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.059594968688036015
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.09235328152106487
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.041765650992014874
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 101/10000 episodes, total num timesteps 20400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 102/10000 episodes, total num timesteps 20600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 103/10000 episodes, total num timesteps 20800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 104/10000 episodes, total num timesteps 21000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 105/10000 episodes, total num timesteps 21200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 106/10000 episodes, total num timesteps 21400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 107/10000 episodes, total num timesteps 21600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 108/10000 episodes, total num timesteps 21800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 109/10000 episodes, total num timesteps 22000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 110/10000 episodes, total num timesteps 22200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 111/10000 episodes, total num timesteps 22400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 112/10000 episodes, total num timesteps 22600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 113/10000 episodes, total num timesteps 22800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 114/10000 episodes, total num timesteps 23000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 115/10000 episodes, total num timesteps 23200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 116/10000 episodes, total num timesteps 23400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 117/10000 episodes, total num timesteps 23600/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 118/10000 episodes, total num timesteps 23800/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 119/10000 episodes, total num timesteps 24000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 120/10000 episodes, total num timesteps 24200/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 121/10000 episodes, total num timesteps 24400/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 122/10000 episodes, total num timesteps 24600/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 123/10000 episodes, total num timesteps 24800/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 124/10000 episodes, total num timesteps 25000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 125/10000 episodes, total num timesteps 25200/2000000, FPS 334.

team_policy eval average step individual rewards of agent0: 0.11019680908135478
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 8
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: 0.03335288540604387
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 4
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: 0.013835902788492014
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 4
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.08539203780776797
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.05382124797644125
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: -0.028076882730936704
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.06513192677981315
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: 0.012956426262287482
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 4
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.004857439427134213
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.09133745976782376
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 0
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 126/10000 episodes, total num timesteps 25400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 127/10000 episodes, total num timesteps 25600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 128/10000 episodes, total num timesteps 25800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 129/10000 episodes, total num timesteps 26000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 130/10000 episodes, total num timesteps 26200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 131/10000 episodes, total num timesteps 26400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 132/10000 episodes, total num timesteps 26600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 133/10000 episodes, total num timesteps 26800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 134/10000 episodes, total num timesteps 27000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 135/10000 episodes, total num timesteps 27200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 136/10000 episodes, total num timesteps 27400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 137/10000 episodes, total num timesteps 27600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 138/10000 episodes, total num timesteps 27800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 139/10000 episodes, total num timesteps 28000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 140/10000 episodes, total num timesteps 28200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 141/10000 episodes, total num timesteps 28400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 142/10000 episodes, total num timesteps 28600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 143/10000 episodes, total num timesteps 28800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 144/10000 episodes, total num timesteps 29000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 145/10000 episodes, total num timesteps 29200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 146/10000 episodes, total num timesteps 29400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 147/10000 episodes, total num timesteps 29600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 148/10000 episodes, total num timesteps 29800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 149/10000 episodes, total num timesteps 30000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 150/10000 episodes, total num timesteps 30200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.003953236715188435
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 4
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: -0.009020979012247767
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 3
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: -0.04611184454069722
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 2
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.01994038286651415
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 3
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.05176168096115721
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 2
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: -0.09796974198082299
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.10588784767202884
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: 0.13189025534066925
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 8
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.07502321089264627
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.10748760425772468
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 0
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 151/10000 episodes, total num timesteps 30400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 152/10000 episodes, total num timesteps 30600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 153/10000 episodes, total num timesteps 30800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 154/10000 episodes, total num timesteps 31000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 155/10000 episodes, total num timesteps 31200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 156/10000 episodes, total num timesteps 31400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 157/10000 episodes, total num timesteps 31600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 158/10000 episodes, total num timesteps 31800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 159/10000 episodes, total num timesteps 32000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 160/10000 episodes, total num timesteps 32200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 161/10000 episodes, total num timesteps 32400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 162/10000 episodes, total num timesteps 32600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 163/10000 episodes, total num timesteps 32800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 164/10000 episodes, total num timesteps 33000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 165/10000 episodes, total num timesteps 33200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 166/10000 episodes, total num timesteps 33400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 167/10000 episodes, total num timesteps 33600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 168/10000 episodes, total num timesteps 33800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 169/10000 episodes, total num timesteps 34000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 170/10000 episodes, total num timesteps 34200/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 171/10000 episodes, total num timesteps 34400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 172/10000 episodes, total num timesteps 34600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 173/10000 episodes, total num timesteps 34800/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 174/10000 episodes, total num timesteps 35000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 175/10000 episodes, total num timesteps 35200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: -0.09535196937308607
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: -0.06671769895822834
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: -0.08491313665566032
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.09032652362861868
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.0330342584693242
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 2
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: 0.015195630523394081
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 4
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: 0.03764644449284791
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.0882609859186967
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.0703855145083417
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.005488734380824178
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 3
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 176/10000 episodes, total num timesteps 35400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 177/10000 episodes, total num timesteps 35600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 178/10000 episodes, total num timesteps 35800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 179/10000 episodes, total num timesteps 36000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 180/10000 episodes, total num timesteps 36200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 181/10000 episodes, total num timesteps 36400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 182/10000 episodes, total num timesteps 36600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 183/10000 episodes, total num timesteps 36800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 184/10000 episodes, total num timesteps 37000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 185/10000 episodes, total num timesteps 37200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 186/10000 episodes, total num timesteps 37400/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 187/10000 episodes, total num timesteps 37600/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 188/10000 episodes, total num timesteps 37800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 189/10000 episodes, total num timesteps 38000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 190/10000 episodes, total num timesteps 38200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 191/10000 episodes, total num timesteps 38400/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 192/10000 episodes, total num timesteps 38600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 193/10000 episodes, total num timesteps 38800/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 194/10000 episodes, total num timesteps 39000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 195/10000 episodes, total num timesteps 39200/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 196/10000 episodes, total num timesteps 39400/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 197/10000 episodes, total num timesteps 39600/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 198/10000 episodes, total num timesteps 39800/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 199/10000 episodes, total num timesteps 40000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 200/10000 episodes, total num timesteps 40200/2000000, FPS 334.

team_policy eval average step individual rewards of agent0: -0.10616048631873987
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: -0.08790164510501407
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: -0.055565206886446374
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 2
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.10243620508518289
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.07146788429340523
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: -0.08076828375374215
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.04267653926479728
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.14286248136165003
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.14325082106212764
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.14307942972694657
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 0
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 201/10000 episodes, total num timesteps 40400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 202/10000 episodes, total num timesteps 40600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 203/10000 episodes, total num timesteps 40800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 204/10000 episodes, total num timesteps 41000/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 205/10000 episodes, total num timesteps 41200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 206/10000 episodes, total num timesteps 41400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 207/10000 episodes, total num timesteps 41600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 208/10000 episodes, total num timesteps 41800/2000000, FPS 334.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 209/10000 episodes, total num timesteps 42000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 210/10000 episodes, total num timesteps 42200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 211/10000 episodes, total num timesteps 42400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 212/10000 episodes, total num timesteps 42600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 213/10000 episodes, total num timesteps 42800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 214/10000 episodes, total num timesteps 43000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 215/10000 episodes, total num timesteps 43200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 216/10000 episodes, total num timesteps 43400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 217/10000 episodes, total num timesteps 43600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 218/10000 episodes, total num timesteps 43800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 219/10000 episodes, total num timesteps 44000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 220/10000 episodes, total num timesteps 44200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 221/10000 episodes, total num timesteps 44400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 222/10000 episodes, total num timesteps 44600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 223/10000 episodes, total num timesteps 44800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 224/10000 episodes, total num timesteps 45000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 225/10000 episodes, total num timesteps 45200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: -0.04460510924768724
team_policy eval average team episode rewards of agent0: 2.5
team_policy eval idv catch total num of agent0: 2
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent1: -0.051845590579656674
team_policy eval average team episode rewards of agent1: 2.5
team_policy eval idv catch total num of agent1: 2
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent2: -0.044332540676388706
team_policy eval average team episode rewards of agent2: 2.5
team_policy eval idv catch total num of agent2: 2
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent3: 0.026036085364306273
team_policy eval average team episode rewards of agent3: 2.5
team_policy eval idv catch total num of agent3: 4
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent4: -0.07992286348462305
team_policy eval average team episode rewards of agent4: 2.5
team_policy eval idv catch total num of agent4: 0
team_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent0: -0.12673208079925335
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.1645555722503061
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.11867423239129728
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.1314812005731628
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.1376523395737294
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 0
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 226/10000 episodes, total num timesteps 45400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 227/10000 episodes, total num timesteps 45600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 228/10000 episodes, total num timesteps 45800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 229/10000 episodes, total num timesteps 46000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 230/10000 episodes, total num timesteps 46200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 231/10000 episodes, total num timesteps 46400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 232/10000 episodes, total num timesteps 46600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 233/10000 episodes, total num timesteps 46800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 234/10000 episodes, total num timesteps 47000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 235/10000 episodes, total num timesteps 47200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 236/10000 episodes, total num timesteps 47400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 237/10000 episodes, total num timesteps 47600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 238/10000 episodes, total num timesteps 47800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 239/10000 episodes, total num timesteps 48000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 240/10000 episodes, total num timesteps 48200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 241/10000 episodes, total num timesteps 48400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 242/10000 episodes, total num timesteps 48600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 243/10000 episodes, total num timesteps 48800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 244/10000 episodes, total num timesteps 49000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 245/10000 episodes, total num timesteps 49200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 246/10000 episodes, total num timesteps 49400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 247/10000 episodes, total num timesteps 49600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 248/10000 episodes, total num timesteps 49800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 249/10000 episodes, total num timesteps 50000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 250/10000 episodes, total num timesteps 50200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: -0.012808672915054293
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 3
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: -0.1131590503319513
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: -0.04315069829803563
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 3
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.06283542883959996
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: 0.029069807777517474
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 5
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: -0.08100075665768354
idv_policy eval average team episode rewards of agent0: 2.5
idv_policy eval idv catch total num of agent0: 0
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent1: 0.003128721483458863
idv_policy eval average team episode rewards of agent1: 2.5
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent2: -0.005156784449067225
idv_policy eval average team episode rewards of agent2: 2.5
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent3: -0.01618478061078206
idv_policy eval average team episode rewards of agent3: 2.5
idv_policy eval idv catch total num of agent3: 3
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent4: -0.07643101996980559
idv_policy eval average team episode rewards of agent4: 2.5
idv_policy eval idv catch total num of agent4: 1
idv_policy eval team catch total num: 1

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 251/10000 episodes, total num timesteps 50400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 252/10000 episodes, total num timesteps 50600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 253/10000 episodes, total num timesteps 50800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 254/10000 episodes, total num timesteps 51000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 255/10000 episodes, total num timesteps 51200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 256/10000 episodes, total num timesteps 51400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 257/10000 episodes, total num timesteps 51600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 258/10000 episodes, total num timesteps 51800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 259/10000 episodes, total num timesteps 52000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 260/10000 episodes, total num timesteps 52200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 261/10000 episodes, total num timesteps 52400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 262/10000 episodes, total num timesteps 52600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 263/10000 episodes, total num timesteps 52800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 264/10000 episodes, total num timesteps 53000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 265/10000 episodes, total num timesteps 53200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 266/10000 episodes, total num timesteps 53400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 267/10000 episodes, total num timesteps 53600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 268/10000 episodes, total num timesteps 53800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 269/10000 episodes, total num timesteps 54000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 270/10000 episodes, total num timesteps 54200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 271/10000 episodes, total num timesteps 54400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 272/10000 episodes, total num timesteps 54600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 273/10000 episodes, total num timesteps 54800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 274/10000 episodes, total num timesteps 55000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 275/10000 episodes, total num timesteps 55200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: -0.05563073357732934
team_policy eval average team episode rewards of agent0: 2.5
team_policy eval idv catch total num of agent0: 2
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent1: -0.07204251587170839
team_policy eval average team episode rewards of agent1: 2.5
team_policy eval idv catch total num of agent1: 1
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent2: -0.07004868090397756
team_policy eval average team episode rewards of agent2: 2.5
team_policy eval idv catch total num of agent2: 1
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent3: -0.07406318878404267
team_policy eval average team episode rewards of agent3: 2.5
team_policy eval idv catch total num of agent3: 1
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent4: 0.0815431395108912
team_policy eval average team episode rewards of agent4: 2.5
team_policy eval idv catch total num of agent4: 7
team_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent0: 0.11100777902419523
idv_policy eval average team episode rewards of agent0: 2.5
idv_policy eval idv catch total num of agent0: 8
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent1: -0.05580355378732669
idv_policy eval average team episode rewards of agent1: 2.5
idv_policy eval idv catch total num of agent1: 1
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent2: -0.009231705206587965
idv_policy eval average team episode rewards of agent2: 2.5
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent3: 0.05247517797723255
idv_policy eval average team episode rewards of agent3: 2.5
idv_policy eval idv catch total num of agent3: 5
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent4: -0.011966683762949204
idv_policy eval average team episode rewards of agent4: 2.5
idv_policy eval idv catch total num of agent4: 3
idv_policy eval team catch total num: 1

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 276/10000 episodes, total num timesteps 55400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 277/10000 episodes, total num timesteps 55600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 278/10000 episodes, total num timesteps 55800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 279/10000 episodes, total num timesteps 56000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 280/10000 episodes, total num timesteps 56200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 281/10000 episodes, total num timesteps 56400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 282/10000 episodes, total num timesteps 56600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 283/10000 episodes, total num timesteps 56800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 284/10000 episodes, total num timesteps 57000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 285/10000 episodes, total num timesteps 57200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 286/10000 episodes, total num timesteps 57400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 287/10000 episodes, total num timesteps 57600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 288/10000 episodes, total num timesteps 57800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 289/10000 episodes, total num timesteps 58000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 290/10000 episodes, total num timesteps 58200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 291/10000 episodes, total num timesteps 58400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 292/10000 episodes, total num timesteps 58600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 293/10000 episodes, total num timesteps 58800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 294/10000 episodes, total num timesteps 59000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 295/10000 episodes, total num timesteps 59200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 296/10000 episodes, total num timesteps 59400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 297/10000 episodes, total num timesteps 59600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 298/10000 episodes, total num timesteps 59800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 299/10000 episodes, total num timesteps 60000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 300/10000 episodes, total num timesteps 60200/2000000, FPS 332.

team_policy eval average step individual rewards of agent0: -0.025178084161223344
team_policy eval average team episode rewards of agent0: 5.0
team_policy eval idv catch total num of agent0: 2
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent1: 0.07640107776330946
team_policy eval average team episode rewards of agent1: 5.0
team_policy eval idv catch total num of agent1: 6
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent2: -0.026286841762500863
team_policy eval average team episode rewards of agent2: 5.0
team_policy eval idv catch total num of agent2: 2
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent3: -0.0005826061266239458
team_policy eval average team episode rewards of agent3: 5.0
team_policy eval idv catch total num of agent3: 3
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent4: 0.06798665978506621
team_policy eval average team episode rewards of agent4: 5.0
team_policy eval idv catch total num of agent4: 6
team_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent0: -0.07751782973814049
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: 0.11807003872737681
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 8
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: 0.004465514179773833
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.021714144563506593
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: 0.0026634964102958424
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 3
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 301/10000 episodes, total num timesteps 60400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 302/10000 episodes, total num timesteps 60600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 303/10000 episodes, total num timesteps 60800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 304/10000 episodes, total num timesteps 61000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 305/10000 episodes, total num timesteps 61200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 306/10000 episodes, total num timesteps 61400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 307/10000 episodes, total num timesteps 61600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 308/10000 episodes, total num timesteps 61800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 309/10000 episodes, total num timesteps 62000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 310/10000 episodes, total num timesteps 62200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 311/10000 episodes, total num timesteps 62400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 312/10000 episodes, total num timesteps 62600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 313/10000 episodes, total num timesteps 62800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 314/10000 episodes, total num timesteps 63000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 315/10000 episodes, total num timesteps 63200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 316/10000 episodes, total num timesteps 63400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 317/10000 episodes, total num timesteps 63600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 318/10000 episodes, total num timesteps 63800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 319/10000 episodes, total num timesteps 64000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 320/10000 episodes, total num timesteps 64200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 321/10000 episodes, total num timesteps 64400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 322/10000 episodes, total num timesteps 64600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 323/10000 episodes, total num timesteps 64800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 324/10000 episodes, total num timesteps 65000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 325/10000 episodes, total num timesteps 65200/2000000, FPS 332.

team_policy eval average step individual rewards of agent0: 0.14525446130199085
team_policy eval average team episode rewards of agent0: 10.0
team_policy eval idv catch total num of agent0: 8
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent1: 0.08858452458544114
team_policy eval average team episode rewards of agent1: 10.0
team_policy eval idv catch total num of agent1: 6
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent2: 0.07142264667716895
team_policy eval average team episode rewards of agent2: 10.0
team_policy eval idv catch total num of agent2: 5
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent3: 0.1318792075252847
team_policy eval average team episode rewards of agent3: 10.0
team_policy eval idv catch total num of agent3: 8
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent4: 0.17111866146112933
team_policy eval average team episode rewards of agent4: 10.0
team_policy eval idv catch total num of agent4: 9
team_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent0: 0.13307726321229954
idv_policy eval average team episode rewards of agent0: 15.0
idv_policy eval idv catch total num of agent0: 8
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent1: 0.09387042129756978
idv_policy eval average team episode rewards of agent1: 15.0
idv_policy eval idv catch total num of agent1: 6
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent2: -0.06815650327745337
idv_policy eval average team episode rewards of agent2: 15.0
idv_policy eval idv catch total num of agent2: 0
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent3: 0.08966038634834193
idv_policy eval average team episode rewards of agent3: 15.0
idv_policy eval idv catch total num of agent3: 6
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent4: 0.06661026581915615
idv_policy eval average team episode rewards of agent4: 15.0
idv_policy eval idv catch total num of agent4: 5
idv_policy eval team catch total num: 6

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 326/10000 episodes, total num timesteps 65400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 327/10000 episodes, total num timesteps 65600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 328/10000 episodes, total num timesteps 65800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 329/10000 episodes, total num timesteps 66000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 330/10000 episodes, total num timesteps 66200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 331/10000 episodes, total num timesteps 66400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 332/10000 episodes, total num timesteps 66600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 333/10000 episodes, total num timesteps 66800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 334/10000 episodes, total num timesteps 67000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 335/10000 episodes, total num timesteps 67200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 336/10000 episodes, total num timesteps 67400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 337/10000 episodes, total num timesteps 67600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 338/10000 episodes, total num timesteps 67800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 339/10000 episodes, total num timesteps 68000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 340/10000 episodes, total num timesteps 68200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 341/10000 episodes, total num timesteps 68400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 342/10000 episodes, total num timesteps 68600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 343/10000 episodes, total num timesteps 68800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 344/10000 episodes, total num timesteps 69000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 345/10000 episodes, total num timesteps 69200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 346/10000 episodes, total num timesteps 69400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 347/10000 episodes, total num timesteps 69600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 348/10000 episodes, total num timesteps 69800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 349/10000 episodes, total num timesteps 70000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 350/10000 episodes, total num timesteps 70200/2000000, FPS 332.

team_policy eval average step individual rewards of agent0: -0.022375216111566783
team_policy eval average team episode rewards of agent0: 2.5
team_policy eval idv catch total num of agent0: 2
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent1: -0.0026853327925413797
team_policy eval average team episode rewards of agent1: 2.5
team_policy eval idv catch total num of agent1: 3
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent2: -0.09085350664819672
team_policy eval average team episode rewards of agent2: 2.5
team_policy eval idv catch total num of agent2: 0
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent3: 0.002420002538493571
team_policy eval average team episode rewards of agent3: 2.5
team_policy eval idv catch total num of agent3: 3
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent4: 0.026240470031127262
team_policy eval average team episode rewards of agent4: 2.5
team_policy eval idv catch total num of agent4: 4
team_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent0: -0.09828242912680263
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.06051597857387825
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.10720133236523323
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.10103920203525016
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: 0.001672780670588656
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 4
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 351/10000 episodes, total num timesteps 70400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 352/10000 episodes, total num timesteps 70600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 353/10000 episodes, total num timesteps 70800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 354/10000 episodes, total num timesteps 71000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 355/10000 episodes, total num timesteps 71200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 356/10000 episodes, total num timesteps 71400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 357/10000 episodes, total num timesteps 71600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 358/10000 episodes, total num timesteps 71800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 359/10000 episodes, total num timesteps 72000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 360/10000 episodes, total num timesteps 72200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 361/10000 episodes, total num timesteps 72400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 362/10000 episodes, total num timesteps 72600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 363/10000 episodes, total num timesteps 72800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 364/10000 episodes, total num timesteps 73000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 365/10000 episodes, total num timesteps 73200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 366/10000 episodes, total num timesteps 73400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 367/10000 episodes, total num timesteps 73600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 368/10000 episodes, total num timesteps 73800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 369/10000 episodes, total num timesteps 74000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 370/10000 episodes, total num timesteps 74200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 371/10000 episodes, total num timesteps 74400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 372/10000 episodes, total num timesteps 74600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 373/10000 episodes, total num timesteps 74800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 374/10000 episodes, total num timesteps 75000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 375/10000 episodes, total num timesteps 75200/2000000, FPS 332.

team_policy eval average step individual rewards of agent0: 0.03768069390644982
team_policy eval average team episode rewards of agent0: 2.5
team_policy eval idv catch total num of agent0: 4
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent1: -0.058934617417268596
team_policy eval average team episode rewards of agent1: 2.5
team_policy eval idv catch total num of agent1: 0
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent2: 0.05755141525324941
team_policy eval average team episode rewards of agent2: 2.5
team_policy eval idv catch total num of agent2: 5
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent3: -0.03909031884441745
team_policy eval average team episode rewards of agent3: 2.5
team_policy eval idv catch total num of agent3: 1
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent4: 0.06593339239067335
team_policy eval average team episode rewards of agent4: 2.5
team_policy eval idv catch total num of agent4: 5
team_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent0: -0.03703709309399774
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: 0.03657736795455821
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: 0.02755752795090203
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 4
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: 0.00715239342483466
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.020054067599402727
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 376/10000 episodes, total num timesteps 75400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 377/10000 episodes, total num timesteps 75600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 378/10000 episodes, total num timesteps 75800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 379/10000 episodes, total num timesteps 76000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 380/10000 episodes, total num timesteps 76200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 381/10000 episodes, total num timesteps 76400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 382/10000 episodes, total num timesteps 76600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 383/10000 episodes, total num timesteps 76800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 384/10000 episodes, total num timesteps 77000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 385/10000 episodes, total num timesteps 77200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 386/10000 episodes, total num timesteps 77400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 387/10000 episodes, total num timesteps 77600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 388/10000 episodes, total num timesteps 77800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 389/10000 episodes, total num timesteps 78000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 390/10000 episodes, total num timesteps 78200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 391/10000 episodes, total num timesteps 78400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 392/10000 episodes, total num timesteps 78600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 393/10000 episodes, total num timesteps 78800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 394/10000 episodes, total num timesteps 79000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 395/10000 episodes, total num timesteps 79200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 396/10000 episodes, total num timesteps 79400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 397/10000 episodes, total num timesteps 79600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 398/10000 episodes, total num timesteps 79800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 399/10000 episodes, total num timesteps 80000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 400/10000 episodes, total num timesteps 80200/2000000, FPS 332.

team_policy eval average step individual rewards of agent0: 0.21963611524681784
team_policy eval average team episode rewards of agent0: 20.0
team_policy eval idv catch total num of agent0: 11
team_policy eval team catch total num: 8
team_policy eval average step individual rewards of agent1: 0.09233757024299177
team_policy eval average team episode rewards of agent1: 20.0
team_policy eval idv catch total num of agent1: 6
team_policy eval team catch total num: 8
team_policy eval average step individual rewards of agent2: 0.01637542799432338
team_policy eval average team episode rewards of agent2: 20.0
team_policy eval idv catch total num of agent2: 3
team_policy eval team catch total num: 8
team_policy eval average step individual rewards of agent3: 0.1167531457301732
team_policy eval average team episode rewards of agent3: 20.0
team_policy eval idv catch total num of agent3: 7
team_policy eval team catch total num: 8
team_policy eval average step individual rewards of agent4: 0.16485530288445346
team_policy eval average team episode rewards of agent4: 20.0
team_policy eval idv catch total num of agent4: 9
team_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent0: 0.12355279891205001
idv_policy eval average team episode rewards of agent0: 5.0
idv_policy eval idv catch total num of agent0: 7
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent1: -0.03933214705795024
idv_policy eval average team episode rewards of agent1: 5.0
idv_policy eval idv catch total num of agent1: 1
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent2: -0.01239536640437997
idv_policy eval average team episode rewards of agent2: 5.0
idv_policy eval idv catch total num of agent2: 2
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent3: 0.27189602669449725
idv_policy eval average team episode rewards of agent3: 5.0
idv_policy eval idv catch total num of agent3: 13
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent4: -0.0054228296621159
idv_policy eval average team episode rewards of agent4: 5.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 2

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 401/10000 episodes, total num timesteps 80400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 402/10000 episodes, total num timesteps 80600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 403/10000 episodes, total num timesteps 80800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 404/10000 episodes, total num timesteps 81000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 405/10000 episodes, total num timesteps 81200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 406/10000 episodes, total num timesteps 81400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 407/10000 episodes, total num timesteps 81600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 408/10000 episodes, total num timesteps 81800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 409/10000 episodes, total num timesteps 82000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 410/10000 episodes, total num timesteps 82200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 411/10000 episodes, total num timesteps 82400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 412/10000 episodes, total num timesteps 82600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 413/10000 episodes, total num timesteps 82800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 414/10000 episodes, total num timesteps 83000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 415/10000 episodes, total num timesteps 83200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 416/10000 episodes, total num timesteps 83400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 417/10000 episodes, total num timesteps 83600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 418/10000 episodes, total num timesteps 83800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 419/10000 episodes, total num timesteps 84000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 420/10000 episodes, total num timesteps 84200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 421/10000 episodes, total num timesteps 84400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 422/10000 episodes, total num timesteps 84600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 423/10000 episodes, total num timesteps 84800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 424/10000 episodes, total num timesteps 85000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 425/10000 episodes, total num timesteps 85200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.08127136949967413
team_policy eval average team episode rewards of agent0: 7.5
team_policy eval idv catch total num of agent0: 6
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent1: -0.02752502396878385
team_policy eval average team episode rewards of agent1: 7.5
team_policy eval idv catch total num of agent1: 2
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent2: 0.07543795663808982
team_policy eval average team episode rewards of agent2: 7.5
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent3: 0.07642622955397373
team_policy eval average team episode rewards of agent3: 7.5
team_policy eval idv catch total num of agent3: 6
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent4: 0.03311548316099694
team_policy eval average team episode rewards of agent4: 7.5
team_policy eval idv catch total num of agent4: 4
team_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent0: -0.017666443397163792
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.07230453382850946
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.02165768782643239
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.04904410448858724
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.04110864400429106
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 1
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 426/10000 episodes, total num timesteps 85400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 427/10000 episodes, total num timesteps 85600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 428/10000 episodes, total num timesteps 85800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 429/10000 episodes, total num timesteps 86000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 430/10000 episodes, total num timesteps 86200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 431/10000 episodes, total num timesteps 86400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 432/10000 episodes, total num timesteps 86600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 433/10000 episodes, total num timesteps 86800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 434/10000 episodes, total num timesteps 87000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 435/10000 episodes, total num timesteps 87200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 436/10000 episodes, total num timesteps 87400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 437/10000 episodes, total num timesteps 87600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 438/10000 episodes, total num timesteps 87800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 439/10000 episodes, total num timesteps 88000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 440/10000 episodes, total num timesteps 88200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 441/10000 episodes, total num timesteps 88400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 442/10000 episodes, total num timesteps 88600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 443/10000 episodes, total num timesteps 88800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 444/10000 episodes, total num timesteps 89000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 445/10000 episodes, total num timesteps 89200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 446/10000 episodes, total num timesteps 89400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 447/10000 episodes, total num timesteps 89600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 448/10000 episodes, total num timesteps 89800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 449/10000 episodes, total num timesteps 90000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 450/10000 episodes, total num timesteps 90200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.1144470038690174
team_policy eval average team episode rewards of agent0: 5.0
team_policy eval idv catch total num of agent0: 7
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent1: 0.008603698171086131
team_policy eval average team episode rewards of agent1: 5.0
team_policy eval idv catch total num of agent1: 3
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent2: -0.020861197291675012
team_policy eval average team episode rewards of agent2: 5.0
team_policy eval idv catch total num of agent2: 2
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent3: 0.012954193038700473
team_policy eval average team episode rewards of agent3: 5.0
team_policy eval idv catch total num of agent3: 3
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent4: -0.03626784057971153
team_policy eval average team episode rewards of agent4: 5.0
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent0: -0.02525480784589985
idv_policy eval average team episode rewards of agent0: 5.0
idv_policy eval idv catch total num of agent0: 2
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent1: 0.021321540214971253
idv_policy eval average team episode rewards of agent1: 5.0
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent2: 0.0023262644203563697
idv_policy eval average team episode rewards of agent2: 5.0
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent3: -0.028581344494944587
idv_policy eval average team episode rewards of agent3: 5.0
idv_policy eval idv catch total num of agent3: 2
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent4: 0.027959807145978947
idv_policy eval average team episode rewards of agent4: 5.0
idv_policy eval idv catch total num of agent4: 4
idv_policy eval team catch total num: 2

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 451/10000 episodes, total num timesteps 90400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 452/10000 episodes, total num timesteps 90600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 453/10000 episodes, total num timesteps 90800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 454/10000 episodes, total num timesteps 91000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 455/10000 episodes, total num timesteps 91200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 456/10000 episodes, total num timesteps 91400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 457/10000 episodes, total num timesteps 91600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 458/10000 episodes, total num timesteps 91800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 459/10000 episodes, total num timesteps 92000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 460/10000 episodes, total num timesteps 92200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 461/10000 episodes, total num timesteps 92400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 462/10000 episodes, total num timesteps 92600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 463/10000 episodes, total num timesteps 92800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 464/10000 episodes, total num timesteps 93000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 465/10000 episodes, total num timesteps 93200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 466/10000 episodes, total num timesteps 93400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 467/10000 episodes, total num timesteps 93600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 468/10000 episodes, total num timesteps 93800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 469/10000 episodes, total num timesteps 94000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 470/10000 episodes, total num timesteps 94200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 471/10000 episodes, total num timesteps 94400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 472/10000 episodes, total num timesteps 94600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 473/10000 episodes, total num timesteps 94800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 474/10000 episodes, total num timesteps 95000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 475/10000 episodes, total num timesteps 95200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.06925790797885596
team_policy eval average team episode rewards of agent0: 2.5
team_policy eval idv catch total num of agent0: 5
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent1: 0.048603170610605206
team_policy eval average team episode rewards of agent1: 2.5
team_policy eval idv catch total num of agent1: 4
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent2: 0.1154218836901503
team_policy eval average team episode rewards of agent2: 2.5
team_policy eval idv catch total num of agent2: 7
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent3: 0.015630305570681118
team_policy eval average team episode rewards of agent3: 2.5
team_policy eval idv catch total num of agent3: 3
team_policy eval team catch total num: 1
team_policy eval average step individual rewards of agent4: -0.039036985011647714
team_policy eval average team episode rewards of agent4: 2.5
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent0: 0.1255477227591249
idv_policy eval average team episode rewards of agent0: 5.0
idv_policy eval idv catch total num of agent0: 7
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent1: 0.12472523023461735
idv_policy eval average team episode rewards of agent1: 5.0
idv_policy eval idv catch total num of agent1: 7
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent2: 0.044732121370061675
idv_policy eval average team episode rewards of agent2: 5.0
idv_policy eval idv catch total num of agent2: 4
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent3: 0.01775114209372299
idv_policy eval average team episode rewards of agent3: 5.0
idv_policy eval idv catch total num of agent3: 3
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent4: -0.013684387126068476
idv_policy eval average team episode rewards of agent4: 5.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 2

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 476/10000 episodes, total num timesteps 95400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 477/10000 episodes, total num timesteps 95600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 478/10000 episodes, total num timesteps 95800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 479/10000 episodes, total num timesteps 96000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 480/10000 episodes, total num timesteps 96200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 481/10000 episodes, total num timesteps 96400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 482/10000 episodes, total num timesteps 96600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 483/10000 episodes, total num timesteps 96800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 484/10000 episodes, total num timesteps 97000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 485/10000 episodes, total num timesteps 97200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 486/10000 episodes, total num timesteps 97400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 487/10000 episodes, total num timesteps 97600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 488/10000 episodes, total num timesteps 97800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 489/10000 episodes, total num timesteps 98000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 490/10000 episodes, total num timesteps 98200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 491/10000 episodes, total num timesteps 98400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 492/10000 episodes, total num timesteps 98600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 493/10000 episodes, total num timesteps 98800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 494/10000 episodes, total num timesteps 99000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 495/10000 episodes, total num timesteps 99200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 496/10000 episodes, total num timesteps 99400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 497/10000 episodes, total num timesteps 99600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 498/10000 episodes, total num timesteps 99800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 499/10000 episodes, total num timesteps 100000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 500/10000 episodes, total num timesteps 100200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.05389965523768292
team_policy eval average team episode rewards of agent0: 10.0
team_policy eval idv catch total num of agent0: 4
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent1: 0.17011735596052616
team_policy eval average team episode rewards of agent1: 10.0
team_policy eval idv catch total num of agent1: 9
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent2: 0.16916346072041474
team_policy eval average team episode rewards of agent2: 10.0
team_policy eval idv catch total num of agent2: 9
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent3: 0.048763097143394205
team_policy eval average team episode rewards of agent3: 10.0
team_policy eval idv catch total num of agent3: 4
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent4: 0.07351344346993238
team_policy eval average team episode rewards of agent4: 10.0
team_policy eval idv catch total num of agent4: 5
team_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent0: 0.11001340233227015
idv_policy eval average team episode rewards of agent0: 15.0
idv_policy eval idv catch total num of agent0: 7
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent1: 0.04684032490768025
idv_policy eval average team episode rewards of agent1: 15.0
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent2: 0.1465890697340178
idv_policy eval average team episode rewards of agent2: 15.0
idv_policy eval idv catch total num of agent2: 8
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent3: 0.09841389683732184
idv_policy eval average team episode rewards of agent3: 15.0
idv_policy eval idv catch total num of agent3: 6
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent4: 0.21722056147683866
idv_policy eval average team episode rewards of agent4: 15.0
idv_policy eval idv catch total num of agent4: 11
idv_policy eval team catch total num: 6

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 501/10000 episodes, total num timesteps 100400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 502/10000 episodes, total num timesteps 100600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 503/10000 episodes, total num timesteps 100800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 504/10000 episodes, total num timesteps 101000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 505/10000 episodes, total num timesteps 101200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 506/10000 episodes, total num timesteps 101400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 507/10000 episodes, total num timesteps 101600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 508/10000 episodes, total num timesteps 101800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 509/10000 episodes, total num timesteps 102000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 510/10000 episodes, total num timesteps 102200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 511/10000 episodes, total num timesteps 102400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 512/10000 episodes, total num timesteps 102600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 513/10000 episodes, total num timesteps 102800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 514/10000 episodes, total num timesteps 103000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 515/10000 episodes, total num timesteps 103200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 516/10000 episodes, total num timesteps 103400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 517/10000 episodes, total num timesteps 103600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 518/10000 episodes, total num timesteps 103800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 519/10000 episodes, total num timesteps 104000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 520/10000 episodes, total num timesteps 104200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 521/10000 episodes, total num timesteps 104400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 522/10000 episodes, total num timesteps 104600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 523/10000 episodes, total num timesteps 104800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 524/10000 episodes, total num timesteps 105000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 525/10000 episodes, total num timesteps 105200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.10707506647899927
team_policy eval average team episode rewards of agent0: 7.5
team_policy eval idv catch total num of agent0: 7
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent1: 0.07525015434283627
team_policy eval average team episode rewards of agent1: 7.5
team_policy eval idv catch total num of agent1: 6
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent2: 0.02581425707988337
team_policy eval average team episode rewards of agent2: 7.5
team_policy eval idv catch total num of agent2: 4
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent3: -0.0231458346142566
team_policy eval average team episode rewards of agent3: 7.5
team_policy eval idv catch total num of agent3: 2
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent4: -0.003668931864397278
team_policy eval average team episode rewards of agent4: 7.5
team_policy eval idv catch total num of agent4: 3
team_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent0: -0.041836568997332665
idv_policy eval average team episode rewards of agent0: 7.5
idv_policy eval idv catch total num of agent0: 1
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent1: 0.08112467406374164
idv_policy eval average team episode rewards of agent1: 7.5
idv_policy eval idv catch total num of agent1: 6
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent2: 0.006982434627990459
idv_policy eval average team episode rewards of agent2: 7.5
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent3: 0.03568766588927035
idv_policy eval average team episode rewards of agent3: 7.5
idv_policy eval idv catch total num of agent3: 4
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent4: 0.08122937222736905
idv_policy eval average team episode rewards of agent4: 7.5
idv_policy eval idv catch total num of agent4: 6
idv_policy eval team catch total num: 3

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 526/10000 episodes, total num timesteps 105400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 527/10000 episodes, total num timesteps 105600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 528/10000 episodes, total num timesteps 105800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 529/10000 episodes, total num timesteps 106000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 530/10000 episodes, total num timesteps 106200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 531/10000 episodes, total num timesteps 106400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 532/10000 episodes, total num timesteps 106600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 533/10000 episodes, total num timesteps 106800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 534/10000 episodes, total num timesteps 107000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 535/10000 episodes, total num timesteps 107200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 536/10000 episodes, total num timesteps 107400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 537/10000 episodes, total num timesteps 107600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 538/10000 episodes, total num timesteps 107800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 539/10000 episodes, total num timesteps 108000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 540/10000 episodes, total num timesteps 108200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 541/10000 episodes, total num timesteps 108400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 542/10000 episodes, total num timesteps 108600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 543/10000 episodes, total num timesteps 108800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 544/10000 episodes, total num timesteps 109000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 545/10000 episodes, total num timesteps 109200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 546/10000 episodes, total num timesteps 109400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 547/10000 episodes, total num timesteps 109600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 548/10000 episodes, total num timesteps 109800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 549/10000 episodes, total num timesteps 110000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 550/10000 episodes, total num timesteps 110200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: -0.02146752332851044
team_policy eval average team episode rewards of agent0: 0.0
team_policy eval idv catch total num of agent0: 2
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent1: -0.01542732612989934
team_policy eval average team episode rewards of agent1: 0.0
team_policy eval idv catch total num of agent1: 2
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent2: -0.06531189053174086
team_policy eval average team episode rewards of agent2: 0.0
team_policy eval idv catch total num of agent2: 0
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent3: -0.04272501305927273
team_policy eval average team episode rewards of agent3: 0.0
team_policy eval idv catch total num of agent3: 1
team_policy eval team catch total num: 0
team_policy eval average step individual rewards of agent4: -0.0207828318501386
team_policy eval average team episode rewards of agent4: 0.0
team_policy eval idv catch total num of agent4: 2
team_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent0: -0.07485226553513526
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.044607879831367755
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: 0.004855466040123452
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.0728928079037504
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.022617564695154836
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 551/10000 episodes, total num timesteps 110400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 552/10000 episodes, total num timesteps 110600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 553/10000 episodes, total num timesteps 110800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 554/10000 episodes, total num timesteps 111000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 555/10000 episodes, total num timesteps 111200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 556/10000 episodes, total num timesteps 111400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 557/10000 episodes, total num timesteps 111600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 558/10000 episodes, total num timesteps 111800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 559/10000 episodes, total num timesteps 112000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 560/10000 episodes, total num timesteps 112200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 561/10000 episodes, total num timesteps 112400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 562/10000 episodes, total num timesteps 112600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 563/10000 episodes, total num timesteps 112800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 564/10000 episodes, total num timesteps 113000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 565/10000 episodes, total num timesteps 113200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 566/10000 episodes, total num timesteps 113400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 567/10000 episodes, total num timesteps 113600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 568/10000 episodes, total num timesteps 113800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 569/10000 episodes, total num timesteps 114000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 570/10000 episodes, total num timesteps 114200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 571/10000 episodes, total num timesteps 114400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 572/10000 episodes, total num timesteps 114600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 573/10000 episodes, total num timesteps 114800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 574/10000 episodes, total num timesteps 115000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 575/10000 episodes, total num timesteps 115200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.3654711702823475
team_policy eval average team episode rewards of agent0: 35.0
team_policy eval idv catch total num of agent0: 17
team_policy eval team catch total num: 14
team_policy eval average step individual rewards of agent1: 0.04139372975638539
team_policy eval average team episode rewards of agent1: 35.0
team_policy eval idv catch total num of agent1: 4
team_policy eval team catch total num: 14
team_policy eval average step individual rewards of agent2: 0.09900274933671219
team_policy eval average team episode rewards of agent2: 35.0
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 14
team_policy eval average step individual rewards of agent3: 0.45205403823180257
team_policy eval average team episode rewards of agent3: 35.0
team_policy eval idv catch total num of agent3: 20
team_policy eval team catch total num: 14
team_policy eval average step individual rewards of agent4: 0.11313999205448282
team_policy eval average team episode rewards of agent4: 35.0
team_policy eval idv catch total num of agent4: 7
team_policy eval team catch total num: 14
idv_policy eval average step individual rewards of agent0: -0.04391827205004947
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: -0.012645310594073445
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 2
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: 0.014065678934372218
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.036393853259371195
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.012053237146810518
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 576/10000 episodes, total num timesteps 115400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 577/10000 episodes, total num timesteps 115600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 578/10000 episodes, total num timesteps 115800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 579/10000 episodes, total num timesteps 116000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 580/10000 episodes, total num timesteps 116200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 581/10000 episodes, total num timesteps 116400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 582/10000 episodes, total num timesteps 116600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 583/10000 episodes, total num timesteps 116800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 584/10000 episodes, total num timesteps 117000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 585/10000 episodes, total num timesteps 117200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 586/10000 episodes, total num timesteps 117400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 587/10000 episodes, total num timesteps 117600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 588/10000 episodes, total num timesteps 117800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 589/10000 episodes, total num timesteps 118000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 590/10000 episodes, total num timesteps 118200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 591/10000 episodes, total num timesteps 118400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 592/10000 episodes, total num timesteps 118600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 593/10000 episodes, total num timesteps 118800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 594/10000 episodes, total num timesteps 119000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 595/10000 episodes, total num timesteps 119200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 596/10000 episodes, total num timesteps 119400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 597/10000 episodes, total num timesteps 119600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 598/10000 episodes, total num timesteps 119800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 599/10000 episodes, total num timesteps 120000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 600/10000 episodes, total num timesteps 120200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.07909912824551715
team_policy eval average team episode rewards of agent0: 10.0
team_policy eval idv catch total num of agent0: 5
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent1: 0.3233697865545315
team_policy eval average team episode rewards of agent1: 10.0
team_policy eval idv catch total num of agent1: 15
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent2: 0.32411201730107014
team_policy eval average team episode rewards of agent2: 10.0
team_policy eval idv catch total num of agent2: 15
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent3: 0.0761287639925862
team_policy eval average team episode rewards of agent3: 10.0
team_policy eval idv catch total num of agent3: 5
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent4: 0.06982523617876801
team_policy eval average team episode rewards of agent4: 10.0
team_policy eval idv catch total num of agent4: 5
team_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent0: 0.0912343673478778
idv_policy eval average team episode rewards of agent0: 12.5
idv_policy eval idv catch total num of agent0: 6
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent1: 0.007232240684859556
idv_policy eval average team episode rewards of agent1: 12.5
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent2: 0.1366328381208549
idv_policy eval average team episode rewards of agent2: 12.5
idv_policy eval idv catch total num of agent2: 8
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent3: -0.07140978113815753
idv_policy eval average team episode rewards of agent3: 12.5
idv_policy eval idv catch total num of agent3: 0
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent4: 0.08738275242157698
idv_policy eval average team episode rewards of agent4: 12.5
idv_policy eval idv catch total num of agent4: 6
idv_policy eval team catch total num: 5

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 601/10000 episodes, total num timesteps 120400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 602/10000 episodes, total num timesteps 120600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 603/10000 episodes, total num timesteps 120800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 604/10000 episodes, total num timesteps 121000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 605/10000 episodes, total num timesteps 121200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 606/10000 episodes, total num timesteps 121400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 607/10000 episodes, total num timesteps 121600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 608/10000 episodes, total num timesteps 121800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 609/10000 episodes, total num timesteps 122000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 610/10000 episodes, total num timesteps 122200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 611/10000 episodes, total num timesteps 122400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 612/10000 episodes, total num timesteps 122600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 613/10000 episodes, total num timesteps 122800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 614/10000 episodes, total num timesteps 123000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 615/10000 episodes, total num timesteps 123200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 616/10000 episodes, total num timesteps 123400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 617/10000 episodes, total num timesteps 123600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 618/10000 episodes, total num timesteps 123800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 619/10000 episodes, total num timesteps 124000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 620/10000 episodes, total num timesteps 124200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 621/10000 episodes, total num timesteps 124400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 622/10000 episodes, total num timesteps 124600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 623/10000 episodes, total num timesteps 124800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 624/10000 episodes, total num timesteps 125000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 625/10000 episodes, total num timesteps 125200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.15413620320826546
team_policy eval average team episode rewards of agent0: 22.5
team_policy eval idv catch total num of agent0: 9
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent1: 0.05975591554803448
team_policy eval average team episode rewards of agent1: 22.5
team_policy eval idv catch total num of agent1: 5
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent2: 0.08826708968263612
team_policy eval average team episode rewards of agent2: 22.5
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent3: 0.08831658769096527
team_policy eval average team episode rewards of agent3: 22.5
team_policy eval idv catch total num of agent3: 6
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent4: 0.10988188897894803
team_policy eval average team episode rewards of agent4: 22.5
team_policy eval idv catch total num of agent4: 7
team_policy eval team catch total num: 9
idv_policy eval average step individual rewards of agent0: 0.1714336663573476
idv_policy eval average team episode rewards of agent0: 30.0
idv_policy eval idv catch total num of agent0: 9
idv_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent1: 0.1633956278705648
idv_policy eval average team episode rewards of agent1: 30.0
idv_policy eval idv catch total num of agent1: 9
idv_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent2: 0.26931836433640405
idv_policy eval average team episode rewards of agent2: 30.0
idv_policy eval idv catch total num of agent2: 13
idv_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent3: 0.1677799089308753
idv_policy eval average team episode rewards of agent3: 30.0
idv_policy eval idv catch total num of agent3: 9
idv_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent4: 0.017493137645583495
idv_policy eval average team episode rewards of agent4: 30.0
idv_policy eval idv catch total num of agent4: 3
idv_policy eval team catch total num: 12

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 626/10000 episodes, total num timesteps 125400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 627/10000 episodes, total num timesteps 125600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 628/10000 episodes, total num timesteps 125800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 629/10000 episodes, total num timesteps 126000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 630/10000 episodes, total num timesteps 126200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 631/10000 episodes, total num timesteps 126400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 632/10000 episodes, total num timesteps 126600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 633/10000 episodes, total num timesteps 126800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 634/10000 episodes, total num timesteps 127000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 635/10000 episodes, total num timesteps 127200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 636/10000 episodes, total num timesteps 127400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 637/10000 episodes, total num timesteps 127600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 638/10000 episodes, total num timesteps 127800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 639/10000 episodes, total num timesteps 128000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 640/10000 episodes, total num timesteps 128200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 641/10000 episodes, total num timesteps 128400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 642/10000 episodes, total num timesteps 128600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 643/10000 episodes, total num timesteps 128800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 644/10000 episodes, total num timesteps 129000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 645/10000 episodes, total num timesteps 129200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 646/10000 episodes, total num timesteps 129400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 647/10000 episodes, total num timesteps 129600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 648/10000 episodes, total num timesteps 129800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 649/10000 episodes, total num timesteps 130000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 650/10000 episodes, total num timesteps 130200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.0701596591113318
team_policy eval average team episode rewards of agent0: 10.0
team_policy eval idv catch total num of agent0: 5
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent1: -0.00598561173409432
team_policy eval average team episode rewards of agent1: 10.0
team_policy eval idv catch total num of agent1: 2
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent2: 0.040413386222806824
team_policy eval average team episode rewards of agent2: 10.0
team_policy eval idv catch total num of agent2: 4
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent3: 0.16442374382446057
team_policy eval average team episode rewards of agent3: 10.0
team_policy eval idv catch total num of agent3: 9
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent4: -0.02834345542965841
team_policy eval average team episode rewards of agent4: 10.0
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent0: 0.24723350388257892
idv_policy eval average team episode rewards of agent0: 20.0
idv_policy eval idv catch total num of agent0: 12
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent1: 0.07205752421918918
idv_policy eval average team episode rewards of agent1: 20.0
idv_policy eval idv catch total num of agent1: 5
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent2: 0.09184347028378724
idv_policy eval average team episode rewards of agent2: 20.0
idv_policy eval idv catch total num of agent2: 6
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent3: 0.16364397765215116
idv_policy eval average team episode rewards of agent3: 20.0
idv_policy eval idv catch total num of agent3: 9
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent4: 0.06031902930669169
idv_policy eval average team episode rewards of agent4: 20.0
idv_policy eval idv catch total num of agent4: 5
idv_policy eval team catch total num: 8

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 651/10000 episodes, total num timesteps 130400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 652/10000 episodes, total num timesteps 130600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 653/10000 episodes, total num timesteps 130800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 654/10000 episodes, total num timesteps 131000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 655/10000 episodes, total num timesteps 131200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 656/10000 episodes, total num timesteps 131400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 657/10000 episodes, total num timesteps 131600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 658/10000 episodes, total num timesteps 131800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 659/10000 episodes, total num timesteps 132000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 660/10000 episodes, total num timesteps 132200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 661/10000 episodes, total num timesteps 132400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 662/10000 episodes, total num timesteps 132600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 663/10000 episodes, total num timesteps 132800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 664/10000 episodes, total num timesteps 133000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 665/10000 episodes, total num timesteps 133200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 666/10000 episodes, total num timesteps 133400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 667/10000 episodes, total num timesteps 133600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 668/10000 episodes, total num timesteps 133800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 669/10000 episodes, total num timesteps 134000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 670/10000 episodes, total num timesteps 134200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 671/10000 episodes, total num timesteps 134400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 672/10000 episodes, total num timesteps 134600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 673/10000 episodes, total num timesteps 134800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 674/10000 episodes, total num timesteps 135000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 675/10000 episodes, total num timesteps 135200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.021078648792030173
team_policy eval average team episode rewards of agent0: 7.5
team_policy eval idv catch total num of agent0: 4
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent1: 0.027690942367802472
team_policy eval average team episode rewards of agent1: 7.5
team_policy eval idv catch total num of agent1: 4
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent2: 0.13141202659894616
team_policy eval average team episode rewards of agent2: 7.5
team_policy eval idv catch total num of agent2: 8
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent3: 0.05624620167110706
team_policy eval average team episode rewards of agent3: 7.5
team_policy eval idv catch total num of agent3: 5
team_policy eval team catch total num: 3
team_policy eval average step individual rewards of agent4: 0.04782809127686855
team_policy eval average team episode rewards of agent4: 7.5
team_policy eval idv catch total num of agent4: 5
team_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent0: -0.00987041011459743
idv_policy eval average team episode rewards of agent0: 10.0
idv_policy eval idv catch total num of agent0: 2
idv_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent1: 0.058874649249102434
idv_policy eval average team episode rewards of agent1: 10.0
idv_policy eval idv catch total num of agent1: 5
idv_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent2: 0.033424642177493705
idv_policy eval average team episode rewards of agent2: 10.0
idv_policy eval idv catch total num of agent2: 4
idv_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent3: 0.09886397422227639
idv_policy eval average team episode rewards of agent3: 10.0
idv_policy eval idv catch total num of agent3: 7
idv_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent4: 0.08489218247813828
idv_policy eval average team episode rewards of agent4: 10.0
idv_policy eval idv catch total num of agent4: 6
idv_policy eval team catch total num: 4

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 676/10000 episodes, total num timesteps 135400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 677/10000 episodes, total num timesteps 135600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 678/10000 episodes, total num timesteps 135800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 679/10000 episodes, total num timesteps 136000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 680/10000 episodes, total num timesteps 136200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 681/10000 episodes, total num timesteps 136400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 682/10000 episodes, total num timesteps 136600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 683/10000 episodes, total num timesteps 136800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 684/10000 episodes, total num timesteps 137000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 685/10000 episodes, total num timesteps 137200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 686/10000 episodes, total num timesteps 137400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 687/10000 episodes, total num timesteps 137600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 688/10000 episodes, total num timesteps 137800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 689/10000 episodes, total num timesteps 138000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 690/10000 episodes, total num timesteps 138200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 691/10000 episodes, total num timesteps 138400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 692/10000 episodes, total num timesteps 138600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 693/10000 episodes, total num timesteps 138800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 694/10000 episodes, total num timesteps 139000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 695/10000 episodes, total num timesteps 139200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 696/10000 episodes, total num timesteps 139400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 697/10000 episodes, total num timesteps 139600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 698/10000 episodes, total num timesteps 139800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 699/10000 episodes, total num timesteps 140000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 700/10000 episodes, total num timesteps 140200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.12183544283242112
team_policy eval average team episode rewards of agent0: 25.0
team_policy eval idv catch total num of agent0: 7
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent1: 0.07279089825451714
team_policy eval average team episode rewards of agent1: 25.0
team_policy eval idv catch total num of agent1: 5
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent2: 0.22638929788752485
team_policy eval average team episode rewards of agent2: 25.0
team_policy eval idv catch total num of agent2: 11
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent3: 0.2210191519813563
team_policy eval average team episode rewards of agent3: 25.0
team_policy eval idv catch total num of agent3: 11
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent4: 0.12458538124012503
team_policy eval average team episode rewards of agent4: 25.0
team_policy eval idv catch total num of agent4: 7
team_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent0: 0.10866621113170183
idv_policy eval average team episode rewards of agent0: 20.0
idv_policy eval idv catch total num of agent0: 7
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent1: 0.10859451186535818
idv_policy eval average team episode rewards of agent1: 20.0
idv_policy eval idv catch total num of agent1: 7
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent2: 0.10734015891432115
idv_policy eval average team episode rewards of agent2: 20.0
idv_policy eval idv catch total num of agent2: 7
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent3: 0.15754257616164735
idv_policy eval average team episode rewards of agent3: 20.0
idv_policy eval idv catch total num of agent3: 9
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent4: 0.12872915956978218
idv_policy eval average team episode rewards of agent4: 20.0
idv_policy eval idv catch total num of agent4: 8
idv_policy eval team catch total num: 8

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 701/10000 episodes, total num timesteps 140400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 702/10000 episodes, total num timesteps 140600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 703/10000 episodes, total num timesteps 140800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 704/10000 episodes, total num timesteps 141000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 705/10000 episodes, total num timesteps 141200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 706/10000 episodes, total num timesteps 141400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 707/10000 episodes, total num timesteps 141600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 708/10000 episodes, total num timesteps 141800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 709/10000 episodes, total num timesteps 142000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 710/10000 episodes, total num timesteps 142200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 711/10000 episodes, total num timesteps 142400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 712/10000 episodes, total num timesteps 142600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 713/10000 episodes, total num timesteps 142800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 714/10000 episodes, total num timesteps 143000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 715/10000 episodes, total num timesteps 143200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 716/10000 episodes, total num timesteps 143400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 717/10000 episodes, total num timesteps 143600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 718/10000 episodes, total num timesteps 143800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 719/10000 episodes, total num timesteps 144000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 720/10000 episodes, total num timesteps 144200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 721/10000 episodes, total num timesteps 144400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 722/10000 episodes, total num timesteps 144600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 723/10000 episodes, total num timesteps 144800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 724/10000 episodes, total num timesteps 145000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 725/10000 episodes, total num timesteps 145200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.14607012811436001
team_policy eval average team episode rewards of agent0: 17.5
team_policy eval idv catch total num of agent0: 8
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent1: 0.16695073205008285
team_policy eval average team episode rewards of agent1: 17.5
team_policy eval idv catch total num of agent1: 9
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent2: 0.22165240408672326
team_policy eval average team episode rewards of agent2: 17.5
team_policy eval idv catch total num of agent2: 11
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent3: -0.0072074354683470164
team_policy eval average team episode rewards of agent3: 17.5
team_policy eval idv catch total num of agent3: 2
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent4: 0.14943232999942715
team_policy eval average team episode rewards of agent4: 17.5
team_policy eval idv catch total num of agent4: 8
team_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent0: 0.09036316841857203
idv_policy eval average team episode rewards of agent0: 15.0
idv_policy eval idv catch total num of agent0: 6
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent1: 0.01097568165430251
idv_policy eval average team episode rewards of agent1: 15.0
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent2: 0.06765934705221331
idv_policy eval average team episode rewards of agent2: 15.0
idv_policy eval idv catch total num of agent2: 5
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent3: 0.2163780251412383
idv_policy eval average team episode rewards of agent3: 15.0
idv_policy eval idv catch total num of agent3: 11
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent4: 0.193421239447257
idv_policy eval average team episode rewards of agent4: 15.0
idv_policy eval idv catch total num of agent4: 10
idv_policy eval team catch total num: 6

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 726/10000 episodes, total num timesteps 145400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 727/10000 episodes, total num timesteps 145600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 728/10000 episodes, total num timesteps 145800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 729/10000 episodes, total num timesteps 146000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 730/10000 episodes, total num timesteps 146200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 731/10000 episodes, total num timesteps 146400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 732/10000 episodes, total num timesteps 146600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 733/10000 episodes, total num timesteps 146800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 734/10000 episodes, total num timesteps 147000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 735/10000 episodes, total num timesteps 147200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 736/10000 episodes, total num timesteps 147400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 737/10000 episodes, total num timesteps 147600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 738/10000 episodes, total num timesteps 147800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 739/10000 episodes, total num timesteps 148000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 740/10000 episodes, total num timesteps 148200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 741/10000 episodes, total num timesteps 148400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 742/10000 episodes, total num timesteps 148600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 743/10000 episodes, total num timesteps 148800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 744/10000 episodes, total num timesteps 149000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 745/10000 episodes, total num timesteps 149200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 746/10000 episodes, total num timesteps 149400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 747/10000 episodes, total num timesteps 149600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 748/10000 episodes, total num timesteps 149800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 749/10000 episodes, total num timesteps 150000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 750/10000 episodes, total num timesteps 150200/2000000, FPS 333.

team_policy eval average step individual rewards of agent0: 0.11453061689597556
team_policy eval average team episode rewards of agent0: 25.0
team_policy eval idv catch total num of agent0: 7
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent1: 0.14168962197246007
team_policy eval average team episode rewards of agent1: 25.0
team_policy eval idv catch total num of agent1: 8
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent2: 0.1669726486337842
team_policy eval average team episode rewards of agent2: 25.0
team_policy eval idv catch total num of agent2: 9
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent3: 0.11662595079925758
team_policy eval average team episode rewards of agent3: 25.0
team_policy eval idv catch total num of agent3: 7
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent4: 0.3490217719588901
team_policy eval average team episode rewards of agent4: 25.0
team_policy eval idv catch total num of agent4: 16
team_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent0: 0.0037670119451532424
idv_policy eval average team episode rewards of agent0: 2.5
idv_policy eval idv catch total num of agent0: 3
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent1: 0.006374588974953779
idv_policy eval average team episode rewards of agent1: 2.5
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent2: -0.07117421095812473
idv_policy eval average team episode rewards of agent2: 2.5
idv_policy eval idv catch total num of agent2: 0
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent3: -0.048261204974967845
idv_policy eval average team episode rewards of agent3: 2.5
idv_policy eval idv catch total num of agent3: 1
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent4: -0.049064875569264414
idv_policy eval average team episode rewards of agent4: 2.5
idv_policy eval idv catch total num of agent4: 1
idv_policy eval team catch total num: 1

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 751/10000 episodes, total num timesteps 150400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 752/10000 episodes, total num timesteps 150600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 753/10000 episodes, total num timesteps 150800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 754/10000 episodes, total num timesteps 151000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 755/10000 episodes, total num timesteps 151200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 756/10000 episodes, total num timesteps 151400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 757/10000 episodes, total num timesteps 151600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 758/10000 episodes, total num timesteps 151800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 759/10000 episodes, total num timesteps 152000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 760/10000 episodes, total num timesteps 152200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 761/10000 episodes, total num timesteps 152400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 762/10000 episodes, total num timesteps 152600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 763/10000 episodes, total num timesteps 152800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 764/10000 episodes, total num timesteps 153000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 765/10000 episodes, total num timesteps 153200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 766/10000 episodes, total num timesteps 153400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 767/10000 episodes, total num timesteps 153600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 768/10000 episodes, total num timesteps 153800/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 769/10000 episodes, total num timesteps 154000/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 770/10000 episodes, total num timesteps 154200/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 771/10000 episodes, total num timesteps 154400/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 772/10000 episodes, total num timesteps 154600/2000000, FPS 333.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 773/10000 episodes, total num timesteps 154800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 774/10000 episodes, total num timesteps 155000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 775/10000 episodes, total num timesteps 155200/2000000, FPS 332.

team_policy eval average step individual rewards of agent0: 0.22019758085429253
team_policy eval average team episode rewards of agent0: 17.5
team_policy eval idv catch total num of agent0: 11
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent1: 0.08789730311872532
team_policy eval average team episode rewards of agent1: 17.5
team_policy eval idv catch total num of agent1: 6
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent2: 0.09189014837433111
team_policy eval average team episode rewards of agent2: 17.5
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent3: 0.16732522334433397
team_policy eval average team episode rewards of agent3: 17.5
team_policy eval idv catch total num of agent3: 9
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent4: 0.1923267396537996
team_policy eval average team episode rewards of agent4: 17.5
team_policy eval idv catch total num of agent4: 10
team_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent0: 0.17072306673213533
idv_policy eval average team episode rewards of agent0: 15.0
idv_policy eval idv catch total num of agent0: 9
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent1: 0.04840883005995827
idv_policy eval average team episode rewards of agent1: 15.0
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent2: 0.06827685903576312
idv_policy eval average team episode rewards of agent2: 15.0
idv_policy eval idv catch total num of agent2: 5
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent3: 0.07249214558473382
idv_policy eval average team episode rewards of agent3: 15.0
idv_policy eval idv catch total num of agent3: 5
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent4: 0.14487265641882163
idv_policy eval average team episode rewards of agent4: 15.0
idv_policy eval idv catch total num of agent4: 8
idv_policy eval team catch total num: 6

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 776/10000 episodes, total num timesteps 155400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 777/10000 episodes, total num timesteps 155600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 778/10000 episodes, total num timesteps 155800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 779/10000 episodes, total num timesteps 156000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 780/10000 episodes, total num timesteps 156200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 781/10000 episodes, total num timesteps 156400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 782/10000 episodes, total num timesteps 156600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 783/10000 episodes, total num timesteps 156800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 784/10000 episodes, total num timesteps 157000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 785/10000 episodes, total num timesteps 157200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 786/10000 episodes, total num timesteps 157400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 787/10000 episodes, total num timesteps 157600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 788/10000 episodes, total num timesteps 157800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 789/10000 episodes, total num timesteps 158000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 790/10000 episodes, total num timesteps 158200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 791/10000 episodes, total num timesteps 158400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 792/10000 episodes, total num timesteps 158600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 793/10000 episodes, total num timesteps 158800/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 794/10000 episodes, total num timesteps 159000/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 795/10000 episodes, total num timesteps 159200/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 796/10000 episodes, total num timesteps 159400/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 797/10000 episodes, total num timesteps 159600/2000000, FPS 332.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 798/10000 episodes, total num timesteps 159800/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 799/10000 episodes, total num timesteps 160000/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 800/10000 episodes, total num timesteps 160200/2000000, FPS 331.

team_policy eval average step individual rewards of agent0: -0.044755338500146465
team_policy eval average team episode rewards of agent0: 15.0
team_policy eval idv catch total num of agent0: 1
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent1: 0.0827474559511974
team_policy eval average team episode rewards of agent1: 15.0
team_policy eval idv catch total num of agent1: 6
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent2: 0.03491745915104667
team_policy eval average team episode rewards of agent2: 15.0
team_policy eval idv catch total num of agent2: 4
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent3: 0.10770184822523991
team_policy eval average team episode rewards of agent3: 15.0
team_policy eval idv catch total num of agent3: 7
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent4: 0.11118486254430442
team_policy eval average team episode rewards of agent4: 15.0
team_policy eval idv catch total num of agent4: 7
team_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent0: 0.23492428583906752
idv_policy eval average team episode rewards of agent0: 10.0
idv_policy eval idv catch total num of agent0: 12
idv_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent1: 0.07603289974501301
idv_policy eval average team episode rewards of agent1: 10.0
idv_policy eval idv catch total num of agent1: 6
idv_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent2: 0.03953792327919046
idv_policy eval average team episode rewards of agent2: 10.0
idv_policy eval idv catch total num of agent2: 4
idv_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent3: 0.0016951628172139088
idv_policy eval average team episode rewards of agent3: 10.0
idv_policy eval idv catch total num of agent3: 3
idv_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent4: 0.0078157147029198
idv_policy eval average team episode rewards of agent4: 10.0
idv_policy eval idv catch total num of agent4: 3
idv_policy eval team catch total num: 4

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 801/10000 episodes, total num timesteps 160400/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 802/10000 episodes, total num timesteps 160600/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 803/10000 episodes, total num timesteps 160800/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 804/10000 episodes, total num timesteps 161000/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 805/10000 episodes, total num timesteps 161200/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 806/10000 episodes, total num timesteps 161400/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 807/10000 episodes, total num timesteps 161600/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 808/10000 episodes, total num timesteps 161800/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 809/10000 episodes, total num timesteps 162000/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 810/10000 episodes, total num timesteps 162200/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 811/10000 episodes, total num timesteps 162400/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 812/10000 episodes, total num timesteps 162600/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 813/10000 episodes, total num timesteps 162800/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 814/10000 episodes, total num timesteps 163000/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 815/10000 episodes, total num timesteps 163200/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 816/10000 episodes, total num timesteps 163400/2000000, FPS 331.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 817/10000 episodes, total num timesteps 163600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 818/10000 episodes, total num timesteps 163800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 819/10000 episodes, total num timesteps 164000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 820/10000 episodes, total num timesteps 164200/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 821/10000 episodes, total num timesteps 164400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 822/10000 episodes, total num timesteps 164600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 823/10000 episodes, total num timesteps 164800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 824/10000 episodes, total num timesteps 165000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 825/10000 episodes, total num timesteps 165200/2000000, FPS 330.

team_policy eval average step individual rewards of agent0: 0.04302725372118513
team_policy eval average team episode rewards of agent0: 12.5
team_policy eval idv catch total num of agent0: 4
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent1: 0.12125280444814912
team_policy eval average team episode rewards of agent1: 12.5
team_policy eval idv catch total num of agent1: 7
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent2: 0.0952873360993966
team_policy eval average team episode rewards of agent2: 12.5
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent3: 0.0711527834229598
team_policy eval average team episode rewards of agent3: 12.5
team_policy eval idv catch total num of agent3: 5
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent4: -0.029892653685326467
team_policy eval average team episode rewards of agent4: 12.5
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent0: 0.1758134692530085
idv_policy eval average team episode rewards of agent0: 20.0
idv_policy eval idv catch total num of agent0: 9
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent1: 0.20147291750185048
idv_policy eval average team episode rewards of agent1: 20.0
idv_policy eval idv catch total num of agent1: 10
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent2: 0.04432590595061658
idv_policy eval average team episode rewards of agent2: 20.0
idv_policy eval idv catch total num of agent2: 4
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent3: 0.15210251320925905
idv_policy eval average team episode rewards of agent3: 20.0
idv_policy eval idv catch total num of agent3: 8
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent4: 0.07218238504393203
idv_policy eval average team episode rewards of agent4: 20.0
idv_policy eval idv catch total num of agent4: 5
idv_policy eval team catch total num: 8

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 826/10000 episodes, total num timesteps 165400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 827/10000 episodes, total num timesteps 165600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 828/10000 episodes, total num timesteps 165800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 829/10000 episodes, total num timesteps 166000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 830/10000 episodes, total num timesteps 166200/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 831/10000 episodes, total num timesteps 166400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 832/10000 episodes, total num timesteps 166600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 833/10000 episodes, total num timesteps 166800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 834/10000 episodes, total num timesteps 167000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 835/10000 episodes, total num timesteps 167200/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 836/10000 episodes, total num timesteps 167400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 837/10000 episodes, total num timesteps 167600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 838/10000 episodes, total num timesteps 167800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 839/10000 episodes, total num timesteps 168000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 840/10000 episodes, total num timesteps 168200/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 841/10000 episodes, total num timesteps 168400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 842/10000 episodes, total num timesteps 168600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 843/10000 episodes, total num timesteps 168800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 844/10000 episodes, total num timesteps 169000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 845/10000 episodes, total num timesteps 169200/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 846/10000 episodes, total num timesteps 169400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 847/10000 episodes, total num timesteps 169600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 848/10000 episodes, total num timesteps 169800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 849/10000 episodes, total num timesteps 170000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 850/10000 episodes, total num timesteps 170200/2000000, FPS 330.

team_policy eval average step individual rewards of agent0: -0.013226657314388195
team_policy eval average team episode rewards of agent0: 12.5
team_policy eval idv catch total num of agent0: 2
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent1: 0.12730740958542278
team_policy eval average team episode rewards of agent1: 12.5
team_policy eval idv catch total num of agent1: 8
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent2: 0.0385231224916456
team_policy eval average team episode rewards of agent2: 12.5
team_policy eval idv catch total num of agent2: 4
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent3: 0.01048478747872613
team_policy eval average team episode rewards of agent3: 12.5
team_policy eval idv catch total num of agent3: 3
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent4: -0.01745039292851103
team_policy eval average team episode rewards of agent4: 12.5
team_policy eval idv catch total num of agent4: 2
team_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent0: 0.091186030160331
idv_policy eval average team episode rewards of agent0: 30.0
idv_policy eval idv catch total num of agent0: 6
idv_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent1: 0.14001547789964255
idv_policy eval average team episode rewards of agent1: 30.0
idv_policy eval idv catch total num of agent1: 8
idv_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent2: 0.1882090662528997
idv_policy eval average team episode rewards of agent2: 30.0
idv_policy eval idv catch total num of agent2: 10
idv_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent3: 0.144900201563097
idv_policy eval average team episode rewards of agent3: 30.0
idv_policy eval idv catch total num of agent3: 8
idv_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent4: 0.18540363559773065
idv_policy eval average team episode rewards of agent4: 30.0
idv_policy eval idv catch total num of agent4: 10
idv_policy eval team catch total num: 12

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 851/10000 episodes, total num timesteps 170400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 852/10000 episodes, total num timesteps 170600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 853/10000 episodes, total num timesteps 170800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 854/10000 episodes, total num timesteps 171000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 855/10000 episodes, total num timesteps 171200/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 856/10000 episodes, total num timesteps 171400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 857/10000 episodes, total num timesteps 171600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 858/10000 episodes, total num timesteps 171800/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 859/10000 episodes, total num timesteps 172000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 860/10000 episodes, total num timesteps 172200/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 861/10000 episodes, total num timesteps 172400/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 862/10000 episodes, total num timesteps 172600/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 863/10000 episodes, total num timesteps 172800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 864/10000 episodes, total num timesteps 173000/2000000, FPS 330.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 865/10000 episodes, total num timesteps 173200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 866/10000 episodes, total num timesteps 173400/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 867/10000 episodes, total num timesteps 173600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 868/10000 episodes, total num timesteps 173800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 869/10000 episodes, total num timesteps 174000/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 870/10000 episodes, total num timesteps 174200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 871/10000 episodes, total num timesteps 174400/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 872/10000 episodes, total num timesteps 174600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 873/10000 episodes, total num timesteps 174800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 874/10000 episodes, total num timesteps 175000/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 875/10000 episodes, total num timesteps 175200/2000000, FPS 329.

team_policy eval average step individual rewards of agent0: 0.051220250511026945
team_policy eval average team episode rewards of agent0: 10.0
team_policy eval idv catch total num of agent0: 4
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent1: 0.20269064080896115
team_policy eval average team episode rewards of agent1: 10.0
team_policy eval idv catch total num of agent1: 10
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent2: 0.09945164356290516
team_policy eval average team episode rewards of agent2: 10.0
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent3: 0.07155505494407223
team_policy eval average team episode rewards of agent3: 10.0
team_policy eval idv catch total num of agent3: 5
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent4: -0.0333780142923737
team_policy eval average team episode rewards of agent4: 10.0
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent0: 0.008954113295417763
idv_policy eval average team episode rewards of agent0: 7.5
idv_policy eval idv catch total num of agent0: 3
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent1: 0.05238637144321502
idv_policy eval average team episode rewards of agent1: 7.5
idv_policy eval idv catch total num of agent1: 5
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent2: 0.010452823466112891
idv_policy eval average team episode rewards of agent2: 7.5
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent3: 0.007576589808622618
idv_policy eval average team episode rewards of agent3: 7.5
idv_policy eval idv catch total num of agent3: 3
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent4: -0.04561883019194224
idv_policy eval average team episode rewards of agent4: 7.5
idv_policy eval idv catch total num of agent4: 1
idv_policy eval team catch total num: 3

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 876/10000 episodes, total num timesteps 175400/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 877/10000 episodes, total num timesteps 175600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 878/10000 episodes, total num timesteps 175800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 879/10000 episodes, total num timesteps 176000/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 880/10000 episodes, total num timesteps 176200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 881/10000 episodes, total num timesteps 176400/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 882/10000 episodes, total num timesteps 176600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 883/10000 episodes, total num timesteps 176800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 884/10000 episodes, total num timesteps 177000/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 885/10000 episodes, total num timesteps 177200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 886/10000 episodes, total num timesteps 177400/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 887/10000 episodes, total num timesteps 177600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 888/10000 episodes, total num timesteps 177800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 889/10000 episodes, total num timesteps 178000/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 890/10000 episodes, total num timesteps 178200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 891/10000 episodes, total num timesteps 178400/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 892/10000 episodes, total num timesteps 178600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 893/10000 episodes, total num timesteps 178800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 894/10000 episodes, total num timesteps 179000/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 895/10000 episodes, total num timesteps 179200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 896/10000 episodes, total num timesteps 179400/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 897/10000 episodes, total num timesteps 179600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 898/10000 episodes, total num timesteps 179800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 899/10000 episodes, total num timesteps 180000/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 900/10000 episodes, total num timesteps 180200/2000000, FPS 329.

team_policy eval average step individual rewards of agent0: -0.0335454865863982
team_policy eval average team episode rewards of agent0: 5.0
team_policy eval idv catch total num of agent0: 1
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent1: -0.009104757405540825
team_policy eval average team episode rewards of agent1: 5.0
team_policy eval idv catch total num of agent1: 2
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent2: 0.09357928149132054
team_policy eval average team episode rewards of agent2: 5.0
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent3: 0.09303908240606999
team_policy eval average team episode rewards of agent3: 5.0
team_policy eval idv catch total num of agent3: 6
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent4: 0.012109472067389548
team_policy eval average team episode rewards of agent4: 5.0
team_policy eval idv catch total num of agent4: 3
team_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent0: 0.1449003051852444
idv_policy eval average team episode rewards of agent0: 52.5
idv_policy eval idv catch total num of agent0: 8
idv_policy eval team catch total num: 21
idv_policy eval average step individual rewards of agent1: 0.27560278607418665
idv_policy eval average team episode rewards of agent1: 52.5
idv_policy eval idv catch total num of agent1: 13
idv_policy eval team catch total num: 21
idv_policy eval average step individual rewards of agent2: 0.5610900723404226
idv_policy eval average team episode rewards of agent2: 52.5
idv_policy eval idv catch total num of agent2: 24
idv_policy eval team catch total num: 21
idv_policy eval average step individual rewards of agent3: 0.3000037834009991
idv_policy eval average team episode rewards of agent3: 52.5
idv_policy eval idv catch total num of agent3: 14
idv_policy eval team catch total num: 21
idv_policy eval average step individual rewards of agent4: 0.631755203161958
idv_policy eval average team episode rewards of agent4: 52.5
idv_policy eval idv catch total num of agent4: 27
idv_policy eval team catch total num: 21

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 901/10000 episodes, total num timesteps 180400/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 902/10000 episodes, total num timesteps 180600/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 903/10000 episodes, total num timesteps 180800/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 904/10000 episodes, total num timesteps 181000/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 905/10000 episodes, total num timesteps 181200/2000000, FPS 329.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 906/10000 episodes, total num timesteps 181400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 907/10000 episodes, total num timesteps 181600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 908/10000 episodes, total num timesteps 181800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 909/10000 episodes, total num timesteps 182000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 910/10000 episodes, total num timesteps 182200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 911/10000 episodes, total num timesteps 182400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 912/10000 episodes, total num timesteps 182600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 913/10000 episodes, total num timesteps 182800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 914/10000 episodes, total num timesteps 183000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 915/10000 episodes, total num timesteps 183200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 916/10000 episodes, total num timesteps 183400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 917/10000 episodes, total num timesteps 183600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 918/10000 episodes, total num timesteps 183800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 919/10000 episodes, total num timesteps 184000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 920/10000 episodes, total num timesteps 184200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 921/10000 episodes, total num timesteps 184400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 922/10000 episodes, total num timesteps 184600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 923/10000 episodes, total num timesteps 184800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 924/10000 episodes, total num timesteps 185000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 925/10000 episodes, total num timesteps 185200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.01737565191207011
team_policy eval average team episode rewards of agent0: 10.0
team_policy eval idv catch total num of agent0: 3
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent1: 0.04282372304182913
team_policy eval average team episode rewards of agent1: 10.0
team_policy eval idv catch total num of agent1: 4
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent2: 0.1432435817857807
team_policy eval average team episode rewards of agent2: 10.0
team_policy eval idv catch total num of agent2: 8
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent3: 0.04276049832029046
team_policy eval average team episode rewards of agent3: 10.0
team_policy eval idv catch total num of agent3: 4
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent4: 0.08603147741197983
team_policy eval average team episode rewards of agent4: 10.0
team_policy eval idv catch total num of agent4: 6
team_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent0: 0.01255091149665921
idv_policy eval average team episode rewards of agent0: 5.0
idv_policy eval idv catch total num of agent0: 3
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent1: -0.044981492798322475
idv_policy eval average team episode rewards of agent1: 5.0
idv_policy eval idv catch total num of agent1: 1
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent2: 0.03317262789219939
idv_policy eval average team episode rewards of agent2: 5.0
idv_policy eval idv catch total num of agent2: 4
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent3: -0.019364251411025876
idv_policy eval average team episode rewards of agent3: 5.0
idv_policy eval idv catch total num of agent3: 2
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent4: -0.022237208886638313
idv_policy eval average team episode rewards of agent4: 5.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 2

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 926/10000 episodes, total num timesteps 185400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 927/10000 episodes, total num timesteps 185600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 928/10000 episodes, total num timesteps 185800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 929/10000 episodes, total num timesteps 186000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 930/10000 episodes, total num timesteps 186200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 931/10000 episodes, total num timesteps 186400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 932/10000 episodes, total num timesteps 186600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 933/10000 episodes, total num timesteps 186800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 934/10000 episodes, total num timesteps 187000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 935/10000 episodes, total num timesteps 187200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 936/10000 episodes, total num timesteps 187400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 937/10000 episodes, total num timesteps 187600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 938/10000 episodes, total num timesteps 187800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 939/10000 episodes, total num timesteps 188000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 940/10000 episodes, total num timesteps 188200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 941/10000 episodes, total num timesteps 188400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 942/10000 episodes, total num timesteps 188600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 943/10000 episodes, total num timesteps 188800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 944/10000 episodes, total num timesteps 189000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 945/10000 episodes, total num timesteps 189200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 946/10000 episodes, total num timesteps 189400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 947/10000 episodes, total num timesteps 189600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 948/10000 episodes, total num timesteps 189800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 949/10000 episodes, total num timesteps 190000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 950/10000 episodes, total num timesteps 190200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.07674233431330493
team_policy eval average team episode rewards of agent0: 15.0
team_policy eval idv catch total num of agent0: 5
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent1: 0.16593153451246487
team_policy eval average team episode rewards of agent1: 15.0
team_policy eval idv catch total num of agent1: 9
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent2: 0.09974006763121214
team_policy eval average team episode rewards of agent2: 15.0
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent3: 0.14534311205566725
team_policy eval average team episode rewards of agent3: 15.0
team_policy eval idv catch total num of agent3: 8
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent4: 0.14783675944348862
team_policy eval average team episode rewards of agent4: 15.0
team_policy eval idv catch total num of agent4: 8
team_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent0: 0.03839062668466347
idv_policy eval average team episode rewards of agent0: 17.5
idv_policy eval idv catch total num of agent0: 4
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent1: 0.019561656766934176
idv_policy eval average team episode rewards of agent1: 17.5
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent2: 0.2730488318978396
idv_policy eval average team episode rewards of agent2: 17.5
idv_policy eval idv catch total num of agent2: 13
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent3: -0.009664651758787154
idv_policy eval average team episode rewards of agent3: 17.5
idv_policy eval idv catch total num of agent3: 2
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent4: 0.09216308434896148
idv_policy eval average team episode rewards of agent4: 17.5
idv_policy eval idv catch total num of agent4: 6
idv_policy eval team catch total num: 7

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 951/10000 episodes, total num timesteps 190400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 952/10000 episodes, total num timesteps 190600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 953/10000 episodes, total num timesteps 190800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 954/10000 episodes, total num timesteps 191000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 955/10000 episodes, total num timesteps 191200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 956/10000 episodes, total num timesteps 191400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 957/10000 episodes, total num timesteps 191600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 958/10000 episodes, total num timesteps 191800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 959/10000 episodes, total num timesteps 192000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 960/10000 episodes, total num timesteps 192200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 961/10000 episodes, total num timesteps 192400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 962/10000 episodes, total num timesteps 192600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 963/10000 episodes, total num timesteps 192800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 964/10000 episodes, total num timesteps 193000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 965/10000 episodes, total num timesteps 193200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 966/10000 episodes, total num timesteps 193400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 967/10000 episodes, total num timesteps 193600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 968/10000 episodes, total num timesteps 193800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 969/10000 episodes, total num timesteps 194000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 970/10000 episodes, total num timesteps 194200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 971/10000 episodes, total num timesteps 194400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 972/10000 episodes, total num timesteps 194600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 973/10000 episodes, total num timesteps 194800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 974/10000 episodes, total num timesteps 195000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 975/10000 episodes, total num timesteps 195200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.21876537386193334
team_policy eval average team episode rewards of agent0: 25.0
team_policy eval idv catch total num of agent0: 11
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent1: 0.16577310997045763
team_policy eval average team episode rewards of agent1: 25.0
team_policy eval idv catch total num of agent1: 9
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent2: 0.10894156257761475
team_policy eval average team episode rewards of agent2: 25.0
team_policy eval idv catch total num of agent2: 7
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent3: 0.14247971216075786
team_policy eval average team episode rewards of agent3: 25.0
team_policy eval idv catch total num of agent3: 8
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent4: 0.08631172311389483
team_policy eval average team episode rewards of agent4: 25.0
team_policy eval idv catch total num of agent4: 6
team_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent0: 0.07356193351399247
idv_policy eval average team episode rewards of agent0: 17.5
idv_policy eval idv catch total num of agent0: 5
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent1: 0.03626237924563176
idv_policy eval average team episode rewards of agent1: 17.5
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent2: 0.1473742207366724
idv_policy eval average team episode rewards of agent2: 17.5
idv_policy eval idv catch total num of agent2: 8
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent3: 0.04649066353835073
idv_policy eval average team episode rewards of agent3: 17.5
idv_policy eval idv catch total num of agent3: 4
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent4: 0.14829793843577144
idv_policy eval average team episode rewards of agent4: 17.5
idv_policy eval idv catch total num of agent4: 8
idv_policy eval team catch total num: 7

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 976/10000 episodes, total num timesteps 195400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 977/10000 episodes, total num timesteps 195600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 978/10000 episodes, total num timesteps 195800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 979/10000 episodes, total num timesteps 196000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 980/10000 episodes, total num timesteps 196200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 981/10000 episodes, total num timesteps 196400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 982/10000 episodes, total num timesteps 196600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 983/10000 episodes, total num timesteps 196800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 984/10000 episodes, total num timesteps 197000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 985/10000 episodes, total num timesteps 197200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 986/10000 episodes, total num timesteps 197400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 987/10000 episodes, total num timesteps 197600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 988/10000 episodes, total num timesteps 197800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 989/10000 episodes, total num timesteps 198000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 990/10000 episodes, total num timesteps 198200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 991/10000 episodes, total num timesteps 198400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 992/10000 episodes, total num timesteps 198600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 993/10000 episodes, total num timesteps 198800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 994/10000 episodes, total num timesteps 199000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 995/10000 episodes, total num timesteps 199200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 996/10000 episodes, total num timesteps 199400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 997/10000 episodes, total num timesteps 199600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 998/10000 episodes, total num timesteps 199800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 999/10000 episodes, total num timesteps 200000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1000/10000 episodes, total num timesteps 200200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.08693274435026545
team_policy eval average team episode rewards of agent0: 17.5
team_policy eval idv catch total num of agent0: 6
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent1: 0.04045926079543908
team_policy eval average team episode rewards of agent1: 17.5
team_policy eval idv catch total num of agent1: 4
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent2: 0.09036181045987454
team_policy eval average team episode rewards of agent2: 17.5
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent3: 0.11432965151716466
team_policy eval average team episode rewards of agent3: 17.5
team_policy eval idv catch total num of agent3: 7
team_policy eval team catch total num: 7
team_policy eval average step individual rewards of agent4: 0.11469922078261068
team_policy eval average team episode rewards of agent4: 17.5
team_policy eval idv catch total num of agent4: 7
team_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent0: 0.06972913111178962
idv_policy eval average team episode rewards of agent0: 12.5
idv_policy eval idv catch total num of agent0: 5
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent1: 0.04754177224568178
idv_policy eval average team episode rewards of agent1: 12.5
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent2: 0.017997927306156302
idv_policy eval average team episode rewards of agent2: 12.5
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent3: 0.14952323707925466
idv_policy eval average team episode rewards of agent3: 12.5
idv_policy eval idv catch total num of agent3: 8
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent4: 0.07509610039156664
idv_policy eval average team episode rewards of agent4: 12.5
idv_policy eval idv catch total num of agent4: 5
idv_policy eval team catch total num: 5

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1001/10000 episodes, total num timesteps 200400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1002/10000 episodes, total num timesteps 200600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1003/10000 episodes, total num timesteps 200800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1004/10000 episodes, total num timesteps 201000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1005/10000 episodes, total num timesteps 201200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1006/10000 episodes, total num timesteps 201400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1007/10000 episodes, total num timesteps 201600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1008/10000 episodes, total num timesteps 201800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1009/10000 episodes, total num timesteps 202000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1010/10000 episodes, total num timesteps 202200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1011/10000 episodes, total num timesteps 202400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1012/10000 episodes, total num timesteps 202600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1013/10000 episodes, total num timesteps 202800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1014/10000 episodes, total num timesteps 203000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1015/10000 episodes, total num timesteps 203200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1016/10000 episodes, total num timesteps 203400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1017/10000 episodes, total num timesteps 203600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1018/10000 episodes, total num timesteps 203800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1019/10000 episodes, total num timesteps 204000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1020/10000 episodes, total num timesteps 204200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1021/10000 episodes, total num timesteps 204400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1022/10000 episodes, total num timesteps 204600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1023/10000 episodes, total num timesteps 204800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1024/10000 episodes, total num timesteps 205000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1025/10000 episodes, total num timesteps 205200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.09845302784800289
team_policy eval average team episode rewards of agent0: 20.0
team_policy eval idv catch total num of agent0: 6
team_policy eval team catch total num: 8
team_policy eval average step individual rewards of agent1: 0.22273582572977657
team_policy eval average team episode rewards of agent1: 20.0
team_policy eval idv catch total num of agent1: 11
team_policy eval team catch total num: 8
team_policy eval average step individual rewards of agent2: 0.1505905946886699
team_policy eval average team episode rewards of agent2: 20.0
team_policy eval idv catch total num of agent2: 8
team_policy eval team catch total num: 8
team_policy eval average step individual rewards of agent3: 0.06666912947010635
team_policy eval average team episode rewards of agent3: 20.0
team_policy eval idv catch total num of agent3: 5
team_policy eval team catch total num: 8
team_policy eval average step individual rewards of agent4: 0.14825049837449766
team_policy eval average team episode rewards of agent4: 20.0
team_policy eval idv catch total num of agent4: 8
team_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent0: 0.21918485958823733
idv_policy eval average team episode rewards of agent0: 17.5
idv_policy eval idv catch total num of agent0: 11
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent1: 0.016544767742787306
idv_policy eval average team episode rewards of agent1: 17.5
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent2: 0.011430077095084257
idv_policy eval average team episode rewards of agent2: 17.5
idv_policy eval idv catch total num of agent2: 3
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent3: 0.14312201744292558
idv_policy eval average team episode rewards of agent3: 17.5
idv_policy eval idv catch total num of agent3: 8
idv_policy eval team catch total num: 7
idv_policy eval average step individual rewards of agent4: 0.2438645940811233
idv_policy eval average team episode rewards of agent4: 17.5
idv_policy eval idv catch total num of agent4: 12
idv_policy eval team catch total num: 7

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1026/10000 episodes, total num timesteps 205400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1027/10000 episodes, total num timesteps 205600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1028/10000 episodes, total num timesteps 205800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1029/10000 episodes, total num timesteps 206000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1030/10000 episodes, total num timesteps 206200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1031/10000 episodes, total num timesteps 206400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1032/10000 episodes, total num timesteps 206600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1033/10000 episodes, total num timesteps 206800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1034/10000 episodes, total num timesteps 207000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1035/10000 episodes, total num timesteps 207200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1036/10000 episodes, total num timesteps 207400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1037/10000 episodes, total num timesteps 207600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1038/10000 episodes, total num timesteps 207800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1039/10000 episodes, total num timesteps 208000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1040/10000 episodes, total num timesteps 208200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1041/10000 episodes, total num timesteps 208400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1042/10000 episodes, total num timesteps 208600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1043/10000 episodes, total num timesteps 208800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1044/10000 episodes, total num timesteps 209000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1045/10000 episodes, total num timesteps 209200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1046/10000 episodes, total num timesteps 209400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1047/10000 episodes, total num timesteps 209600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1048/10000 episodes, total num timesteps 209800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1049/10000 episodes, total num timesteps 210000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1050/10000 episodes, total num timesteps 210200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.065017560656706
team_policy eval average team episode rewards of agent0: 10.0
team_policy eval idv catch total num of agent0: 5
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent1: -0.008128270828446343
team_policy eval average team episode rewards of agent1: 10.0
team_policy eval idv catch total num of agent1: 2
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent2: 0.0942707418802607
team_policy eval average team episode rewards of agent2: 10.0
team_policy eval idv catch total num of agent2: 6
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent3: 0.16678653309188782
team_policy eval average team episode rewards of agent3: 10.0
team_policy eval idv catch total num of agent3: 9
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent4: 0.021355804012107273
team_policy eval average team episode rewards of agent4: 10.0
team_policy eval idv catch total num of agent4: 3
team_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent0: 0.013368744197136762
idv_policy eval average team episode rewards of agent0: 7.5
idv_policy eval idv catch total num of agent0: 3
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent1: -0.012145028877117684
idv_policy eval average team episode rewards of agent1: 7.5
idv_policy eval idv catch total num of agent1: 2
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent2: 0.16175027918380022
idv_policy eval average team episode rewards of agent2: 7.5
idv_policy eval idv catch total num of agent2: 9
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent3: 0.011136575032206475
idv_policy eval average team episode rewards of agent3: 7.5
idv_policy eval idv catch total num of agent3: 3
idv_policy eval team catch total num: 3
idv_policy eval average step individual rewards of agent4: -0.01830784470126387
idv_policy eval average team episode rewards of agent4: 7.5
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 3

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1051/10000 episodes, total num timesteps 210400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1052/10000 episodes, total num timesteps 210600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1053/10000 episodes, total num timesteps 210800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1054/10000 episodes, total num timesteps 211000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1055/10000 episodes, total num timesteps 211200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1056/10000 episodes, total num timesteps 211400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1057/10000 episodes, total num timesteps 211600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1058/10000 episodes, total num timesteps 211800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1059/10000 episodes, total num timesteps 212000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1060/10000 episodes, total num timesteps 212200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1061/10000 episodes, total num timesteps 212400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1062/10000 episodes, total num timesteps 212600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1063/10000 episodes, total num timesteps 212800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1064/10000 episodes, total num timesteps 213000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1065/10000 episodes, total num timesteps 213200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1066/10000 episodes, total num timesteps 213400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1067/10000 episodes, total num timesteps 213600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1068/10000 episodes, total num timesteps 213800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1069/10000 episodes, total num timesteps 214000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1070/10000 episodes, total num timesteps 214200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1071/10000 episodes, total num timesteps 214400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1072/10000 episodes, total num timesteps 214600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1073/10000 episodes, total num timesteps 214800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1074/10000 episodes, total num timesteps 215000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1075/10000 episodes, total num timesteps 215200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.2234978295486843
team_policy eval average team episode rewards of agent0: 10.0
team_policy eval idv catch total num of agent0: 11
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent1: 0.06320067776320991
team_policy eval average team episode rewards of agent1: 10.0
team_policy eval idv catch total num of agent1: 5
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent2: 0.2452069967975644
team_policy eval average team episode rewards of agent2: 10.0
team_policy eval idv catch total num of agent2: 12
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent3: 0.11958724237457959
team_policy eval average team episode rewards of agent3: 10.0
team_policy eval idv catch total num of agent3: 7
team_policy eval team catch total num: 4
team_policy eval average step individual rewards of agent4: 0.06363772606861322
team_policy eval average team episode rewards of agent4: 10.0
team_policy eval idv catch total num of agent4: 5
team_policy eval team catch total num: 4
idv_policy eval average step individual rewards of agent0: 0.16976559962847904
idv_policy eval average team episode rewards of agent0: 20.0
idv_policy eval idv catch total num of agent0: 9
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent1: 0.021211018778709994
idv_policy eval average team episode rewards of agent1: 20.0
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent2: 0.12547865105643868
idv_policy eval average team episode rewards of agent2: 20.0
idv_policy eval idv catch total num of agent2: 7
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent3: 0.07171407180978057
idv_policy eval average team episode rewards of agent3: 20.0
idv_policy eval idv catch total num of agent3: 5
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent4: 0.2034233927780499
idv_policy eval average team episode rewards of agent4: 20.0
idv_policy eval idv catch total num of agent4: 10
idv_policy eval team catch total num: 8

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1076/10000 episodes, total num timesteps 215400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1077/10000 episodes, total num timesteps 215600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1078/10000 episodes, total num timesteps 215800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1079/10000 episodes, total num timesteps 216000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1080/10000 episodes, total num timesteps 216200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1081/10000 episodes, total num timesteps 216400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1082/10000 episodes, total num timesteps 216600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1083/10000 episodes, total num timesteps 216800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1084/10000 episodes, total num timesteps 217000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1085/10000 episodes, total num timesteps 217200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1086/10000 episodes, total num timesteps 217400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1087/10000 episodes, total num timesteps 217600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1088/10000 episodes, total num timesteps 217800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1089/10000 episodes, total num timesteps 218000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1090/10000 episodes, total num timesteps 218200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1091/10000 episodes, total num timesteps 218400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1092/10000 episodes, total num timesteps 218600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1093/10000 episodes, total num timesteps 218800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1094/10000 episodes, total num timesteps 219000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1095/10000 episodes, total num timesteps 219200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1096/10000 episodes, total num timesteps 219400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1097/10000 episodes, total num timesteps 219600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1098/10000 episodes, total num timesteps 219800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1099/10000 episodes, total num timesteps 220000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1100/10000 episodes, total num timesteps 220200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.10082855998608518
team_policy eval average team episode rewards of agent0: 27.5
team_policy eval idv catch total num of agent0: 6
team_policy eval team catch total num: 11
team_policy eval average step individual rewards of agent1: 0.22687658341125908
team_policy eval average team episode rewards of agent1: 27.5
team_policy eval idv catch total num of agent1: 11
team_policy eval team catch total num: 11
team_policy eval average step individual rewards of agent2: 0.25769464025974026
team_policy eval average team episode rewards of agent2: 27.5
team_policy eval idv catch total num of agent2: 12
team_policy eval team catch total num: 11
team_policy eval average step individual rewards of agent3: 0.2338661384030628
team_policy eval average team episode rewards of agent3: 27.5
team_policy eval idv catch total num of agent3: 11
team_policy eval team catch total num: 11
team_policy eval average step individual rewards of agent4: 0.15457578335869493
team_policy eval average team episode rewards of agent4: 27.5
team_policy eval idv catch total num of agent4: 8
team_policy eval team catch total num: 11
idv_policy eval average step individual rewards of agent0: 0.08854161448965259
idv_policy eval average team episode rewards of agent0: 2.5
idv_policy eval idv catch total num of agent0: 6
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent1: 0.08259665670235179
idv_policy eval average team episode rewards of agent1: 2.5
idv_policy eval idv catch total num of agent1: 5
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent2: 0.06540245677654659
idv_policy eval average team episode rewards of agent2: 2.5
idv_policy eval idv catch total num of agent2: 5
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent3: 0.0020759067522016926
idv_policy eval average team episode rewards of agent3: 2.5
idv_policy eval idv catch total num of agent3: 2
idv_policy eval team catch total num: 1
idv_policy eval average step individual rewards of agent4: 0.07606790242136909
idv_policy eval average team episode rewards of agent4: 2.5
idv_policy eval idv catch total num of agent4: 5
idv_policy eval team catch total num: 1

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1101/10000 episodes, total num timesteps 220400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1102/10000 episodes, total num timesteps 220600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1103/10000 episodes, total num timesteps 220800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1104/10000 episodes, total num timesteps 221000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1105/10000 episodes, total num timesteps 221200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1106/10000 episodes, total num timesteps 221400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1107/10000 episodes, total num timesteps 221600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1108/10000 episodes, total num timesteps 221800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1109/10000 episodes, total num timesteps 222000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1110/10000 episodes, total num timesteps 222200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1111/10000 episodes, total num timesteps 222400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1112/10000 episodes, total num timesteps 222600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1113/10000 episodes, total num timesteps 222800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1114/10000 episodes, total num timesteps 223000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1115/10000 episodes, total num timesteps 223200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1116/10000 episodes, total num timesteps 223400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1117/10000 episodes, total num timesteps 223600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1118/10000 episodes, total num timesteps 223800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1119/10000 episodes, total num timesteps 224000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1120/10000 episodes, total num timesteps 224200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1121/10000 episodes, total num timesteps 224400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1122/10000 episodes, total num timesteps 224600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1123/10000 episodes, total num timesteps 224800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1124/10000 episodes, total num timesteps 225000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1125/10000 episodes, total num timesteps 225200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: 0.3506673383593019
team_policy eval average team episode rewards of agent0: 35.0
team_policy eval idv catch total num of agent0: 16
team_policy eval team catch total num: 14
team_policy eval average step individual rewards of agent1: 0.27580450689737934
team_policy eval average team episode rewards of agent1: 35.0
team_policy eval idv catch total num of agent1: 13
team_policy eval team catch total num: 14
team_policy eval average step individual rewards of agent2: 0.3296042771353393
team_policy eval average team episode rewards of agent2: 35.0
team_policy eval idv catch total num of agent2: 15
team_policy eval team catch total num: 14
team_policy eval average step individual rewards of agent3: 0.17120329985946905
team_policy eval average team episode rewards of agent3: 35.0
team_policy eval idv catch total num of agent3: 9
team_policy eval team catch total num: 14
team_policy eval average step individual rewards of agent4: 0.1743485607583382
team_policy eval average team episode rewards of agent4: 35.0
team_policy eval idv catch total num of agent4: 9
team_policy eval team catch total num: 14
idv_policy eval average step individual rewards of agent0: 0.14586889013013685
idv_policy eval average team episode rewards of agent0: 32.5
idv_policy eval idv catch total num of agent0: 8
idv_policy eval team catch total num: 13
idv_policy eval average step individual rewards of agent1: 0.07359231078526175
idv_policy eval average team episode rewards of agent1: 32.5
idv_policy eval idv catch total num of agent1: 5
idv_policy eval team catch total num: 13
idv_policy eval average step individual rewards of agent2: 0.2982639608121185
idv_policy eval average team episode rewards of agent2: 32.5
idv_policy eval idv catch total num of agent2: 14
idv_policy eval team catch total num: 13
idv_policy eval average step individual rewards of agent3: 0.2769223350192498
idv_policy eval average team episode rewards of agent3: 32.5
idv_policy eval idv catch total num of agent3: 13
idv_policy eval team catch total num: 13
idv_policy eval average step individual rewards of agent4: 0.17301411549171758
idv_policy eval average team episode rewards of agent4: 32.5
idv_policy eval idv catch total num of agent4: 9
idv_policy eval team catch total num: 13

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1126/10000 episodes, total num timesteps 225400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1127/10000 episodes, total num timesteps 225600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1128/10000 episodes, total num timesteps 225800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1129/10000 episodes, total num timesteps 226000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1130/10000 episodes, total num timesteps 226200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1131/10000 episodes, total num timesteps 226400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1132/10000 episodes, total num timesteps 226600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1133/10000 episodes, total num timesteps 226800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1134/10000 episodes, total num timesteps 227000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1135/10000 episodes, total num timesteps 227200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1136/10000 episodes, total num timesteps 227400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1137/10000 episodes, total num timesteps 227600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1138/10000 episodes, total num timesteps 227800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1139/10000 episodes, total num timesteps 228000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1140/10000 episodes, total num timesteps 228200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1141/10000 episodes, total num timesteps 228400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1142/10000 episodes, total num timesteps 228600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1143/10000 episodes, total num timesteps 228800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1144/10000 episodes, total num timesteps 229000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1145/10000 episodes, total num timesteps 229200/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1146/10000 episodes, total num timesteps 229400/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1147/10000 episodes, total num timesteps 229600/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1148/10000 episodes, total num timesteps 229800/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1149/10000 episodes, total num timesteps 230000/2000000, FPS 328.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1150/10000 episodes, total num timesteps 230200/2000000, FPS 328.

team_policy eval average step individual rewards of agent0: -0.04005314445150112
team_policy eval average team episode rewards of agent0: 5.0
team_policy eval idv catch total num of agent0: 1
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent1: 0.033484439177503454
team_policy eval average team episode rewards of agent1: 5.0
team_policy eval idv catch total num of agent1: 4
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent2: -0.013050364085220962
team_policy eval average team episode rewards of agent2: 5.0
team_policy eval idv catch total num of agent2: 2
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent3: -0.06817865281193561
team_policy eval average team episode rewards of agent3: 5.0
team_policy eval idv catch total num of agent3: 0
team_policy eval team catch total num: 2
team_policy eval average step individual rewards of agent4: -0.010360918477617427
team_policy eval average team episode rewards of agent4: 5.0
team_policy eval idv catch total num of agent4: 2
team_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent0: 0.013590561582378057
idv_policy eval average team episode rewards of agent0: 0.0
idv_policy eval idv catch total num of agent0: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent1: 0.014560767805524621
idv_policy eval average team episode rewards of agent1: 0.0
idv_policy eval idv catch total num of agent1: 3
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent2: -0.06857213908141206
idv_policy eval average team episode rewards of agent2: 0.0
idv_policy eval idv catch total num of agent2: 0
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent3: -0.03412592931480102
idv_policy eval average team episode rewards of agent3: 0.0
idv_policy eval idv catch total num of agent3: 1
idv_policy eval team catch total num: 0
idv_policy eval average step individual rewards of agent4: -0.06532806788928053
idv_policy eval average team episode rewards of agent4: 0.0
idv_policy eval idv catch total num of agent4: 0
idv_policy eval team catch total num: 0

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1151/10000 episodes, total num timesteps 230400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1152/10000 episodes, total num timesteps 230600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1153/10000 episodes, total num timesteps 230800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1154/10000 episodes, total num timesteps 231000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1155/10000 episodes, total num timesteps 231200/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1156/10000 episodes, total num timesteps 231400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1157/10000 episodes, total num timesteps 231600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1158/10000 episodes, total num timesteps 231800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1159/10000 episodes, total num timesteps 232000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1160/10000 episodes, total num timesteps 232200/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1161/10000 episodes, total num timesteps 232400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1162/10000 episodes, total num timesteps 232600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1163/10000 episodes, total num timesteps 232800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1164/10000 episodes, total num timesteps 233000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1165/10000 episodes, total num timesteps 233200/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1166/10000 episodes, total num timesteps 233400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1167/10000 episodes, total num timesteps 233600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1168/10000 episodes, total num timesteps 233800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1169/10000 episodes, total num timesteps 234000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1170/10000 episodes, total num timesteps 234200/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1171/10000 episodes, total num timesteps 234400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1172/10000 episodes, total num timesteps 234600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1173/10000 episodes, total num timesteps 234800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1174/10000 episodes, total num timesteps 235000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1175/10000 episodes, total num timesteps 235200/2000000, FPS 327.

team_policy eval average step individual rewards of agent0: 0.15321841653682047
team_policy eval average team episode rewards of agent0: 12.5
team_policy eval idv catch total num of agent0: 8
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent1: 0.15089977586448586
team_policy eval average team episode rewards of agent1: 12.5
team_policy eval idv catch total num of agent1: 8
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent2: 0.1255288644336941
team_policy eval average team episode rewards of agent2: 12.5
team_policy eval idv catch total num of agent2: 7
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent3: 0.12126472324639145
team_policy eval average team episode rewards of agent3: 12.5
team_policy eval idv catch total num of agent3: 7
team_policy eval team catch total num: 5
team_policy eval average step individual rewards of agent4: 0.11722644620977477
team_policy eval average team episode rewards of agent4: 12.5
team_policy eval idv catch total num of agent4: 7
team_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent0: 0.07405160401910614
idv_policy eval average team episode rewards of agent0: 5.0
idv_policy eval idv catch total num of agent0: 5
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent1: 0.0377642608769365
idv_policy eval average team episode rewards of agent1: 5.0
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent2: 0.14375068087905202
idv_policy eval average team episode rewards of agent2: 5.0
idv_policy eval idv catch total num of agent2: 8
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent3: 0.06408038726919196
idv_policy eval average team episode rewards of agent3: 5.0
idv_policy eval idv catch total num of agent3: 5
idv_policy eval team catch total num: 2
idv_policy eval average step individual rewards of agent4: 0.012947205579462863
idv_policy eval average team episode rewards of agent4: 5.0
idv_policy eval idv catch total num of agent4: 3
idv_policy eval team catch total num: 2

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1176/10000 episodes, total num timesteps 235400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1177/10000 episodes, total num timesteps 235600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1178/10000 episodes, total num timesteps 235800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1179/10000 episodes, total num timesteps 236000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1180/10000 episodes, total num timesteps 236200/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1181/10000 episodes, total num timesteps 236400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1182/10000 episodes, total num timesteps 236600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1183/10000 episodes, total num timesteps 236800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1184/10000 episodes, total num timesteps 237000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1185/10000 episodes, total num timesteps 237200/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1186/10000 episodes, total num timesteps 237400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1187/10000 episodes, total num timesteps 237600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1188/10000 episodes, total num timesteps 237800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1189/10000 episodes, total num timesteps 238000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1190/10000 episodes, total num timesteps 238200/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1191/10000 episodes, total num timesteps 238400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1192/10000 episodes, total num timesteps 238600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1193/10000 episodes, total num timesteps 238800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1194/10000 episodes, total num timesteps 239000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1195/10000 episodes, total num timesteps 239200/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1196/10000 episodes, total num timesteps 239400/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1197/10000 episodes, total num timesteps 239600/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1198/10000 episodes, total num timesteps 239800/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1199/10000 episodes, total num timesteps 240000/2000000, FPS 327.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1200/10000 episodes, total num timesteps 240200/2000000, FPS 327.

team_policy eval average step individual rewards of agent0: 0.24322305607481445
team_policy eval average team episode rewards of agent0: 25.0
team_policy eval idv catch total num of agent0: 12
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent1: 0.1793946115516887
team_policy eval average team episode rewards of agent1: 25.0
team_policy eval idv catch total num of agent1: 9
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent2: 0.34950054543929404
team_policy eval average team episode rewards of agent2: 25.0
team_policy eval idv catch total num of agent2: 16
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent3: -0.012067797381017488
team_policy eval average team episode rewards of agent3: 25.0
team_policy eval idv catch total num of agent3: 2
team_policy eval team catch total num: 10
team_policy eval average step individual rewards of agent4: 0.2033786189390299
team_policy eval average team episode rewards of agent4: 25.0
team_policy eval idv catch total num of agent4: 10
team_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent0: 0.24583368416652157
idv_policy eval average team episode rewards of agent0: 27.5
idv_policy eval idv catch total num of agent0: 12
idv_policy eval team catch total num: 11
idv_policy eval average step individual rewards of agent1: 0.16788708612870828
idv_policy eval average team episode rewards of agent1: 27.5
idv_policy eval idv catch total num of agent1: 9
idv_policy eval team catch total num: 11
idv_policy eval average step individual rewards of agent2: 0.11122171610140859
idv_policy eval average team episode rewards of agent2: 27.5
idv_policy eval idv catch total num of agent2: 7
idv_policy eval team catch total num: 11
idv_policy eval average step individual rewards of agent3: 0.11991314704566036
idv_policy eval average team episode rewards of agent3: 27.5
idv_policy eval idv catch total num of agent3: 7
idv_policy eval team catch total num: 11
idv_policy eval average step individual rewards of agent4: 0.24874992211791927
idv_policy eval average team episode rewards of agent4: 27.5
idv_policy eval idv catch total num of agent4: 12
idv_policy eval team catch total num: 11

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1201/10000 episodes, total num timesteps 240400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1202/10000 episodes, total num timesteps 240600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1203/10000 episodes, total num timesteps 240800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1204/10000 episodes, total num timesteps 241000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1205/10000 episodes, total num timesteps 241200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1206/10000 episodes, total num timesteps 241400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1207/10000 episodes, total num timesteps 241600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1208/10000 episodes, total num timesteps 241800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1209/10000 episodes, total num timesteps 242000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1210/10000 episodes, total num timesteps 242200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1211/10000 episodes, total num timesteps 242400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1212/10000 episodes, total num timesteps 242600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1213/10000 episodes, total num timesteps 242800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1214/10000 episodes, total num timesteps 243000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1215/10000 episodes, total num timesteps 243200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1216/10000 episodes, total num timesteps 243400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1217/10000 episodes, total num timesteps 243600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1218/10000 episodes, total num timesteps 243800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1219/10000 episodes, total num timesteps 244000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1220/10000 episodes, total num timesteps 244200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1221/10000 episodes, total num timesteps 244400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1222/10000 episodes, total num timesteps 244600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1223/10000 episodes, total num timesteps 244800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1224/10000 episodes, total num timesteps 245000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1225/10000 episodes, total num timesteps 245200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.11394318448282569
team_policy eval average team episode rewards of agent0: 30.0
team_policy eval idv catch total num of agent0: 7
team_policy eval team catch total num: 12
team_policy eval average step individual rewards of agent1: 0.11616194781090991
team_policy eval average team episode rewards of agent1: 30.0
team_policy eval idv catch total num of agent1: 7
team_policy eval team catch total num: 12
team_policy eval average step individual rewards of agent2: 0.24848610470001886
team_policy eval average team episode rewards of agent2: 30.0
team_policy eval idv catch total num of agent2: 12
team_policy eval team catch total num: 12
team_policy eval average step individual rewards of agent3: 0.2632920176758099
team_policy eval average team episode rewards of agent3: 30.0
team_policy eval idv catch total num of agent3: 13
team_policy eval team catch total num: 12
team_policy eval average step individual rewards of agent4: 0.2920003986215769
team_policy eval average team episode rewards of agent4: 30.0
team_policy eval idv catch total num of agent4: 14
team_policy eval team catch total num: 12
idv_policy eval average step individual rewards of agent0: 0.19421040360745587
idv_policy eval average team episode rewards of agent0: 15.0
idv_policy eval idv catch total num of agent0: 10
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent1: 0.11510614125725896
idv_policy eval average team episode rewards of agent1: 15.0
idv_policy eval idv catch total num of agent1: 7
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent2: 0.17319736172516817
idv_policy eval average team episode rewards of agent2: 15.0
idv_policy eval idv catch total num of agent2: 9
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent3: 0.1370762286950059
idv_policy eval average team episode rewards of agent3: 15.0
idv_policy eval idv catch total num of agent3: 8
idv_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent4: 0.14695918655011309
idv_policy eval average team episode rewards of agent4: 15.0
idv_policy eval idv catch total num of agent4: 8
idv_policy eval team catch total num: 6

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1226/10000 episodes, total num timesteps 245400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1227/10000 episodes, total num timesteps 245600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1228/10000 episodes, total num timesteps 245800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1229/10000 episodes, total num timesteps 246000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1230/10000 episodes, total num timesteps 246200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1231/10000 episodes, total num timesteps 246400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1232/10000 episodes, total num timesteps 246600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1233/10000 episodes, total num timesteps 246800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1234/10000 episodes, total num timesteps 247000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1235/10000 episodes, total num timesteps 247200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1236/10000 episodes, total num timesteps 247400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1237/10000 episodes, total num timesteps 247600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1238/10000 episodes, total num timesteps 247800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1239/10000 episodes, total num timesteps 248000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1240/10000 episodes, total num timesteps 248200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1241/10000 episodes, total num timesteps 248400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1242/10000 episodes, total num timesteps 248600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1243/10000 episodes, total num timesteps 248800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1244/10000 episodes, total num timesteps 249000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1245/10000 episodes, total num timesteps 249200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1246/10000 episodes, total num timesteps 249400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1247/10000 episodes, total num timesteps 249600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1248/10000 episodes, total num timesteps 249800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1249/10000 episodes, total num timesteps 250000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1250/10000 episodes, total num timesteps 250200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.09815768416811105
team_policy eval average team episode rewards of agent0: 15.0
team_policy eval idv catch total num of agent0: 6
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent1: 0.06791018989614743
team_policy eval average team episode rewards of agent1: 15.0
team_policy eval idv catch total num of agent1: 5
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent2: 0.15397312538794522
team_policy eval average team episode rewards of agent2: 15.0
team_policy eval idv catch total num of agent2: 8
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent3: 0.20262437965684016
team_policy eval average team episode rewards of agent3: 15.0
team_policy eval idv catch total num of agent3: 10
team_policy eval team catch total num: 6
team_policy eval average step individual rewards of agent4: 0.1043022840283584
team_policy eval average team episode rewards of agent4: 15.0
team_policy eval idv catch total num of agent4: 6
team_policy eval team catch total num: 6
idv_policy eval average step individual rewards of agent0: 0.4609128844145625
idv_policy eval average team episode rewards of agent0: 50.0
idv_policy eval idv catch total num of agent0: 20
idv_policy eval team catch total num: 20
idv_policy eval average step individual rewards of agent1: 0.34957623355940426
idv_policy eval average team episode rewards of agent1: 50.0
idv_policy eval idv catch total num of agent1: 16
idv_policy eval team catch total num: 20
idv_policy eval average step individual rewards of agent2: 0.2863412087071827
idv_policy eval average team episode rewards of agent2: 50.0
idv_policy eval idv catch total num of agent2: 13
idv_policy eval team catch total num: 20
idv_policy eval average step individual rewards of agent3: 0.3378429812445869
idv_policy eval average team episode rewards of agent3: 50.0
idv_policy eval idv catch total num of agent3: 15
idv_policy eval team catch total num: 20
idv_policy eval average step individual rewards of agent4: 0.22112157725735276
idv_policy eval average team episode rewards of agent4: 50.0
idv_policy eval idv catch total num of agent4: 11
idv_policy eval team catch total num: 20

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1251/10000 episodes, total num timesteps 250400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1252/10000 episodes, total num timesteps 250600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1253/10000 episodes, total num timesteps 250800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1254/10000 episodes, total num timesteps 251000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1255/10000 episodes, total num timesteps 251200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1256/10000 episodes, total num timesteps 251400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1257/10000 episodes, total num timesteps 251600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1258/10000 episodes, total num timesteps 251800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1259/10000 episodes, total num timesteps 252000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1260/10000 episodes, total num timesteps 252200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1261/10000 episodes, total num timesteps 252400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1262/10000 episodes, total num timesteps 252600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1263/10000 episodes, total num timesteps 252800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1264/10000 episodes, total num timesteps 253000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1265/10000 episodes, total num timesteps 253200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1266/10000 episodes, total num timesteps 253400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1267/10000 episodes, total num timesteps 253600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1268/10000 episodes, total num timesteps 253800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1269/10000 episodes, total num timesteps 254000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1270/10000 episodes, total num timesteps 254200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1271/10000 episodes, total num timesteps 254400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1272/10000 episodes, total num timesteps 254600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1273/10000 episodes, total num timesteps 254800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1274/10000 episodes, total num timesteps 255000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1275/10000 episodes, total num timesteps 255200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.33365324058791757
team_policy eval average team episode rewards of agent0: 32.5
team_policy eval idv catch total num of agent0: 15
team_policy eval team catch total num: 13
team_policy eval average step individual rewards of agent1: 0.26017795278538863
team_policy eval average team episode rewards of agent1: 32.5
team_policy eval idv catch total num of agent1: 12
team_policy eval team catch total num: 13
team_policy eval average step individual rewards of agent2: 0.19789720683240475
team_policy eval average team episode rewards of agent2: 32.5
team_policy eval idv catch total num of agent2: 10
team_policy eval team catch total num: 13
team_policy eval average step individual rewards of agent3: 0.3838904843514175
team_policy eval average team episode rewards of agent3: 32.5
team_policy eval idv catch total num of agent3: 17
team_policy eval team catch total num: 13
team_policy eval average step individual rewards of agent4: 0.26339040372706785
team_policy eval average team episode rewards of agent4: 32.5
team_policy eval idv catch total num of agent4: 12
team_policy eval team catch total num: 13
idv_policy eval average step individual rewards of agent0: 0.3575609694745887
idv_policy eval average team episode rewards of agent0: 47.5
idv_policy eval idv catch total num of agent0: 16
idv_policy eval team catch total num: 19
idv_policy eval average step individual rewards of agent1: 0.1789352711509339
idv_policy eval average team episode rewards of agent1: 47.5
idv_policy eval idv catch total num of agent1: 9
idv_policy eval team catch total num: 19
idv_policy eval average step individual rewards of agent2: 0.32586026684761493
idv_policy eval average team episode rewards of agent2: 47.5
idv_policy eval idv catch total num of agent2: 15
idv_policy eval team catch total num: 19
idv_policy eval average step individual rewards of agent3: 0.2518867476749953
idv_policy eval average team episode rewards of agent3: 47.5
idv_policy eval idv catch total num of agent3: 12
idv_policy eval team catch total num: 19
idv_policy eval average step individual rewards of agent4: 0.27270108111220154
idv_policy eval average team episode rewards of agent4: 47.5
idv_policy eval idv catch total num of agent4: 13
idv_policy eval team catch total num: 19

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1276/10000 episodes, total num timesteps 255400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1277/10000 episodes, total num timesteps 255600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1278/10000 episodes, total num timesteps 255800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1279/10000 episodes, total num timesteps 256000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1280/10000 episodes, total num timesteps 256200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1281/10000 episodes, total num timesteps 256400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1282/10000 episodes, total num timesteps 256600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1283/10000 episodes, total num timesteps 256800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1284/10000 episodes, total num timesteps 257000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1285/10000 episodes, total num timesteps 257200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1286/10000 episodes, total num timesteps 257400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1287/10000 episodes, total num timesteps 257600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1288/10000 episodes, total num timesteps 257800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1289/10000 episodes, total num timesteps 258000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1290/10000 episodes, total num timesteps 258200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1291/10000 episodes, total num timesteps 258400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1292/10000 episodes, total num timesteps 258600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1293/10000 episodes, total num timesteps 258800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1294/10000 episodes, total num timesteps 259000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1295/10000 episodes, total num timesteps 259200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1296/10000 episodes, total num timesteps 259400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1297/10000 episodes, total num timesteps 259600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1298/10000 episodes, total num timesteps 259800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1299/10000 episodes, total num timesteps 260000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1300/10000 episodes, total num timesteps 260200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.2273672778756171
team_policy eval average team episode rewards of agent0: 37.5
team_policy eval idv catch total num of agent0: 11
team_policy eval team catch total num: 15
team_policy eval average step individual rewards of agent1: 0.37758591247694073
team_policy eval average team episode rewards of agent1: 37.5
team_policy eval idv catch total num of agent1: 17
team_policy eval team catch total num: 15
team_policy eval average step individual rewards of agent2: 0.19442291880027585
team_policy eval average team episode rewards of agent2: 37.5
team_policy eval idv catch total num of agent2: 10
team_policy eval team catch total num: 15
team_policy eval average step individual rewards of agent3: 0.15052275165925888
team_policy eval average team episode rewards of agent3: 37.5
team_policy eval idv catch total num of agent3: 8
team_policy eval team catch total num: 15
team_policy eval average step individual rewards of agent4: 0.16866336865216486
team_policy eval average team episode rewards of agent4: 37.5
team_policy eval idv catch total num of agent4: 9
team_policy eval team catch total num: 15
idv_policy eval average step individual rewards of agent0: 0.11959210355789483
idv_policy eval average team episode rewards of agent0: 25.0
idv_policy eval idv catch total num of agent0: 7
idv_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent1: 0.22331429774410633
idv_policy eval average team episode rewards of agent1: 25.0
idv_policy eval idv catch total num of agent1: 11
idv_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent2: 0.14004157847092125
idv_policy eval average team episode rewards of agent2: 25.0
idv_policy eval idv catch total num of agent2: 8
idv_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent3: 0.2728453243748683
idv_policy eval average team episode rewards of agent3: 25.0
idv_policy eval idv catch total num of agent3: 13
idv_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent4: -0.010036757495776049
idv_policy eval average team episode rewards of agent4: 25.0
idv_policy eval idv catch total num of agent4: 2
idv_policy eval team catch total num: 10

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1301/10000 episodes, total num timesteps 260400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1302/10000 episodes, total num timesteps 260600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1303/10000 episodes, total num timesteps 260800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1304/10000 episodes, total num timesteps 261000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1305/10000 episodes, total num timesteps 261200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1306/10000 episodes, total num timesteps 261400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1307/10000 episodes, total num timesteps 261600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1308/10000 episodes, total num timesteps 261800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1309/10000 episodes, total num timesteps 262000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1310/10000 episodes, total num timesteps 262200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1311/10000 episodes, total num timesteps 262400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1312/10000 episodes, total num timesteps 262600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1313/10000 episodes, total num timesteps 262800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1314/10000 episodes, total num timesteps 263000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1315/10000 episodes, total num timesteps 263200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1316/10000 episodes, total num timesteps 263400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1317/10000 episodes, total num timesteps 263600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1318/10000 episodes, total num timesteps 263800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1319/10000 episodes, total num timesteps 264000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1320/10000 episodes, total num timesteps 264200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1321/10000 episodes, total num timesteps 264400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1322/10000 episodes, total num timesteps 264600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1323/10000 episodes, total num timesteps 264800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1324/10000 episodes, total num timesteps 265000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1325/10000 episodes, total num timesteps 265200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.11586749587632256
team_policy eval average team episode rewards of agent0: 22.5
team_policy eval idv catch total num of agent0: 7
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent1: 0.1802344023182711
team_policy eval average team episode rewards of agent1: 22.5
team_policy eval idv catch total num of agent1: 9
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent2: 0.12548963965831608
team_policy eval average team episode rewards of agent2: 22.5
team_policy eval idv catch total num of agent2: 7
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent3: 0.12078004860246219
team_policy eval average team episode rewards of agent3: 22.5
team_policy eval idv catch total num of agent3: 7
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent4: 0.32976193311158186
team_policy eval average team episode rewards of agent4: 22.5
team_policy eval idv catch total num of agent4: 15
team_policy eval team catch total num: 9
idv_policy eval average step individual rewards of agent0: 0.3250035158359897
idv_policy eval average team episode rewards of agent0: 25.0
idv_policy eval idv catch total num of agent0: 15
idv_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent1: 0.05191024598840812
idv_policy eval average team episode rewards of agent1: 25.0
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent2: 0.15618547403256772
idv_policy eval average team episode rewards of agent2: 25.0
idv_policy eval idv catch total num of agent2: 8
idv_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent3: 0.2766109044682819
idv_policy eval average team episode rewards of agent3: 25.0
idv_policy eval idv catch total num of agent3: 13
idv_policy eval team catch total num: 10
idv_policy eval average step individual rewards of agent4: 0.04768404010388179
idv_policy eval average team episode rewards of agent4: 25.0
idv_policy eval idv catch total num of agent4: 4
idv_policy eval team catch total num: 10

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1326/10000 episodes, total num timesteps 265400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1327/10000 episodes, total num timesteps 265600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1328/10000 episodes, total num timesteps 265800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1329/10000 episodes, total num timesteps 266000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1330/10000 episodes, total num timesteps 266200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1331/10000 episodes, total num timesteps 266400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1332/10000 episodes, total num timesteps 266600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1333/10000 episodes, total num timesteps 266800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1334/10000 episodes, total num timesteps 267000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1335/10000 episodes, total num timesteps 267200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1336/10000 episodes, total num timesteps 267400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1337/10000 episodes, total num timesteps 267600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1338/10000 episodes, total num timesteps 267800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1339/10000 episodes, total num timesteps 268000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1340/10000 episodes, total num timesteps 268200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1341/10000 episodes, total num timesteps 268400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1342/10000 episodes, total num timesteps 268600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1343/10000 episodes, total num timesteps 268800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1344/10000 episodes, total num timesteps 269000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1345/10000 episodes, total num timesteps 269200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1346/10000 episodes, total num timesteps 269400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1347/10000 episodes, total num timesteps 269600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1348/10000 episodes, total num timesteps 269800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1349/10000 episodes, total num timesteps 270000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1350/10000 episodes, total num timesteps 270200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.019808093568090303
team_policy eval average team episode rewards of agent0: 22.5
team_policy eval idv catch total num of agent0: 3
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent1: 0.19808879597050968
team_policy eval average team episode rewards of agent1: 22.5
team_policy eval idv catch total num of agent1: 10
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent2: 0.20640124903035667
team_policy eval average team episode rewards of agent2: 22.5
team_policy eval idv catch total num of agent2: 10
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent3: 0.2748833751079043
team_policy eval average team episode rewards of agent3: 22.5
team_policy eval idv catch total num of agent3: 13
team_policy eval team catch total num: 9
team_policy eval average step individual rewards of agent4: 0.33181662566378334
team_policy eval average team episode rewards of agent4: 22.5
team_policy eval idv catch total num of agent4: 15
team_policy eval team catch total num: 9
idv_policy eval average step individual rewards of agent0: 0.47771295935708047
idv_policy eval average team episode rewards of agent0: 65.0
idv_policy eval idv catch total num of agent0: 21
idv_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent1: 0.6852271085244739
idv_policy eval average team episode rewards of agent1: 65.0
idv_policy eval idv catch total num of agent1: 29
idv_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent2: 0.4839482082483776
idv_policy eval average team episode rewards of agent2: 65.0
idv_policy eval idv catch total num of agent2: 21
idv_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent3: 0.6900084437781896
idv_policy eval average team episode rewards of agent3: 65.0
idv_policy eval idv catch total num of agent3: 29
idv_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent4: 0.43239899892863576
idv_policy eval average team episode rewards of agent4: 65.0
idv_policy eval idv catch total num of agent4: 19
idv_policy eval team catch total num: 26

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1351/10000 episodes, total num timesteps 270400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1352/10000 episodes, total num timesteps 270600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1353/10000 episodes, total num timesteps 270800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1354/10000 episodes, total num timesteps 271000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1355/10000 episodes, total num timesteps 271200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1356/10000 episodes, total num timesteps 271400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1357/10000 episodes, total num timesteps 271600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1358/10000 episodes, total num timesteps 271800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1359/10000 episodes, total num timesteps 272000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1360/10000 episodes, total num timesteps 272200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1361/10000 episodes, total num timesteps 272400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1362/10000 episodes, total num timesteps 272600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1363/10000 episodes, total num timesteps 272800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1364/10000 episodes, total num timesteps 273000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1365/10000 episodes, total num timesteps 273200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1366/10000 episodes, total num timesteps 273400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1367/10000 episodes, total num timesteps 273600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1368/10000 episodes, total num timesteps 273800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1369/10000 episodes, total num timesteps 274000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1370/10000 episodes, total num timesteps 274200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1371/10000 episodes, total num timesteps 274400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1372/10000 episodes, total num timesteps 274600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1373/10000 episodes, total num timesteps 274800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1374/10000 episodes, total num timesteps 275000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1375/10000 episodes, total num timesteps 275200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.41067870905252535
team_policy eval average team episode rewards of agent0: 52.5
team_policy eval idv catch total num of agent0: 18
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent1: 0.38146274030457616
team_policy eval average team episode rewards of agent1: 52.5
team_policy eval idv catch total num of agent1: 17
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent2: 0.6391911069332569
team_policy eval average team episode rewards of agent2: 52.5
team_policy eval idv catch total num of agent2: 27
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent3: 0.3867976506357638
team_policy eval average team episode rewards of agent3: 52.5
team_policy eval idv catch total num of agent3: 17
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent4: 0.41390763436872957
team_policy eval average team episode rewards of agent4: 52.5
team_policy eval idv catch total num of agent4: 18
team_policy eval team catch total num: 21
idv_policy eval average step individual rewards of agent0: 0.3308038290524516
idv_policy eval average team episode rewards of agent0: 20.0
idv_policy eval idv catch total num of agent0: 15
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent1: 0.04047828675389375
idv_policy eval average team episode rewards of agent1: 20.0
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent2: 0.1446788933384013
idv_policy eval average team episode rewards of agent2: 20.0
idv_policy eval idv catch total num of agent2: 8
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent3: 0.22653380164020961
idv_policy eval average team episode rewards of agent3: 20.0
idv_policy eval idv catch total num of agent3: 11
idv_policy eval team catch total num: 8
idv_policy eval average step individual rewards of agent4: 0.2297557518178096
idv_policy eval average team episode rewards of agent4: 20.0
idv_policy eval idv catch total num of agent4: 11
idv_policy eval team catch total num: 8

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1376/10000 episodes, total num timesteps 275400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1377/10000 episodes, total num timesteps 275600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1378/10000 episodes, total num timesteps 275800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1379/10000 episodes, total num timesteps 276000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1380/10000 episodes, total num timesteps 276200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1381/10000 episodes, total num timesteps 276400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1382/10000 episodes, total num timesteps 276600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1383/10000 episodes, total num timesteps 276800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1384/10000 episodes, total num timesteps 277000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1385/10000 episodes, total num timesteps 277200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1386/10000 episodes, total num timesteps 277400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1387/10000 episodes, total num timesteps 277600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1388/10000 episodes, total num timesteps 277800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1389/10000 episodes, total num timesteps 278000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1390/10000 episodes, total num timesteps 278200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1391/10000 episodes, total num timesteps 278400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1392/10000 episodes, total num timesteps 278600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1393/10000 episodes, total num timesteps 278800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1394/10000 episodes, total num timesteps 279000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1395/10000 episodes, total num timesteps 279200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1396/10000 episodes, total num timesteps 279400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1397/10000 episodes, total num timesteps 279600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1398/10000 episodes, total num timesteps 279800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1399/10000 episodes, total num timesteps 280000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1400/10000 episodes, total num timesteps 280200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.22928500757211487
team_policy eval average team episode rewards of agent0: 27.5
team_policy eval idv catch total num of agent0: 11
team_policy eval team catch total num: 11
team_policy eval average step individual rewards of agent1: 0.07546819271887244
team_policy eval average team episode rewards of agent1: 27.5
team_policy eval idv catch total num of agent1: 5
team_policy eval team catch total num: 11
team_policy eval average step individual rewards of agent2: 0.14915158943257054
team_policy eval average team episode rewards of agent2: 27.5
team_policy eval idv catch total num of agent2: 8
team_policy eval team catch total num: 11
team_policy eval average step individual rewards of agent3: 0.33106030897341854
team_policy eval average team episode rewards of agent3: 27.5
team_policy eval idv catch total num of agent3: 15
team_policy eval team catch total num: 11
team_policy eval average step individual rewards of agent4: 0.3578568043708868
team_policy eval average team episode rewards of agent4: 27.5
team_policy eval idv catch total num of agent4: 16
team_policy eval team catch total num: 11
idv_policy eval average step individual rewards of agent0: 0.2560268005861241
idv_policy eval average team episode rewards of agent0: 12.5
idv_policy eval idv catch total num of agent0: 12
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent1: 0.042521358520685844
idv_policy eval average team episode rewards of agent1: 12.5
idv_policy eval idv catch total num of agent1: 4
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent2: 0.07033985242343739
idv_policy eval average team episode rewards of agent2: 12.5
idv_policy eval idv catch total num of agent2: 5
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent3: 0.019102925355348892
idv_policy eval average team episode rewards of agent3: 12.5
idv_policy eval idv catch total num of agent3: 3
idv_policy eval team catch total num: 5
idv_policy eval average step individual rewards of agent4: 0.02515665392896118
idv_policy eval average team episode rewards of agent4: 12.5
idv_policy eval idv catch total num of agent4: 3
idv_policy eval team catch total num: 5

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1401/10000 episodes, total num timesteps 280400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1402/10000 episodes, total num timesteps 280600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1403/10000 episodes, total num timesteps 280800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1404/10000 episodes, total num timesteps 281000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1405/10000 episodes, total num timesteps 281200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1406/10000 episodes, total num timesteps 281400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1407/10000 episodes, total num timesteps 281600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1408/10000 episodes, total num timesteps 281800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1409/10000 episodes, total num timesteps 282000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1410/10000 episodes, total num timesteps 282200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1411/10000 episodes, total num timesteps 282400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1412/10000 episodes, total num timesteps 282600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1413/10000 episodes, total num timesteps 282800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1414/10000 episodes, total num timesteps 283000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1415/10000 episodes, total num timesteps 283200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1416/10000 episodes, total num timesteps 283400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1417/10000 episodes, total num timesteps 283600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1418/10000 episodes, total num timesteps 283800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1419/10000 episodes, total num timesteps 284000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1420/10000 episodes, total num timesteps 284200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1421/10000 episodes, total num timesteps 284400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1422/10000 episodes, total num timesteps 284600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1423/10000 episodes, total num timesteps 284800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1424/10000 episodes, total num timesteps 285000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1425/10000 episodes, total num timesteps 285200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.32828556738619274
team_policy eval average team episode rewards of agent0: 67.5
team_policy eval idv catch total num of agent0: 15
team_policy eval team catch total num: 27
team_policy eval average step individual rewards of agent1: 0.47969978812404224
team_policy eval average team episode rewards of agent1: 67.5
team_policy eval idv catch total num of agent1: 21
team_policy eval team catch total num: 27
team_policy eval average step individual rewards of agent2: 0.35092619981371853
team_policy eval average team episode rewards of agent2: 67.5
team_policy eval idv catch total num of agent2: 16
team_policy eval team catch total num: 27
team_policy eval average step individual rewards of agent3: 0.5861720488400053
team_policy eval average team episode rewards of agent3: 67.5
team_policy eval idv catch total num of agent3: 25
team_policy eval team catch total num: 27
team_policy eval average step individual rewards of agent4: 0.6386525038064864
team_policy eval average team episode rewards of agent4: 67.5
team_policy eval idv catch total num of agent4: 27
team_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent0: 0.42704122039121684
idv_policy eval average team episode rewards of agent0: 82.5
idv_policy eval idv catch total num of agent0: 19
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent1: 0.528214212319336
idv_policy eval average team episode rewards of agent1: 82.5
idv_policy eval idv catch total num of agent1: 23
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent2: 0.36369791023054915
idv_policy eval average team episode rewards of agent2: 82.5
idv_policy eval idv catch total num of agent2: 16
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent3: 0.7564374941211963
idv_policy eval average team episode rewards of agent3: 82.5
idv_policy eval idv catch total num of agent3: 32
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent4: 0.5043087978148106
idv_policy eval average team episode rewards of agent4: 82.5
idv_policy eval idv catch total num of agent4: 22
idv_policy eval team catch total num: 33

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1426/10000 episodes, total num timesteps 285400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1427/10000 episodes, total num timesteps 285600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1428/10000 episodes, total num timesteps 285800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1429/10000 episodes, total num timesteps 286000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1430/10000 episodes, total num timesteps 286200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1431/10000 episodes, total num timesteps 286400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1432/10000 episodes, total num timesteps 286600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1433/10000 episodes, total num timesteps 286800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1434/10000 episodes, total num timesteps 287000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1435/10000 episodes, total num timesteps 287200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1436/10000 episodes, total num timesteps 287400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1437/10000 episodes, total num timesteps 287600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1438/10000 episodes, total num timesteps 287800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1439/10000 episodes, total num timesteps 288000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1440/10000 episodes, total num timesteps 288200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1441/10000 episodes, total num timesteps 288400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1442/10000 episodes, total num timesteps 288600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1443/10000 episodes, total num timesteps 288800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1444/10000 episodes, total num timesteps 289000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1445/10000 episodes, total num timesteps 289200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1446/10000 episodes, total num timesteps 289400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1447/10000 episodes, total num timesteps 289600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1448/10000 episodes, total num timesteps 289800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1449/10000 episodes, total num timesteps 290000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1450/10000 episodes, total num timesteps 290200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.6201848924614608
team_policy eval average team episode rewards of agent0: 65.0
team_policy eval idv catch total num of agent0: 26
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent1: 0.8155776405323536
team_policy eval average team episode rewards of agent1: 65.0
team_policy eval idv catch total num of agent1: 34
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent2: 0.5374833937791292
team_policy eval average team episode rewards of agent2: 65.0
team_policy eval idv catch total num of agent2: 23
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent3: 0.45786309145640197
team_policy eval average team episode rewards of agent3: 65.0
team_policy eval idv catch total num of agent3: 20
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent4: 0.45577431541449187
team_policy eval average team episode rewards of agent4: 65.0
team_policy eval idv catch total num of agent4: 20
team_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent0: 0.48494379587028363
idv_policy eval average team episode rewards of agent0: 60.0
idv_policy eval idv catch total num of agent0: 21
idv_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent1: 0.44161454459606836
idv_policy eval average team episode rewards of agent1: 60.0
idv_policy eval idv catch total num of agent1: 19
idv_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent2: 0.6824962857597419
idv_policy eval average team episode rewards of agent2: 60.0
idv_policy eval idv catch total num of agent2: 29
idv_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent3: 0.6406952449054376
idv_policy eval average team episode rewards of agent3: 60.0
idv_policy eval idv catch total num of agent3: 27
idv_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent4: 0.46112976680656104
idv_policy eval average team episode rewards of agent4: 60.0
idv_policy eval idv catch total num of agent4: 20
idv_policy eval team catch total num: 24

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1451/10000 episodes, total num timesteps 290400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1452/10000 episodes, total num timesteps 290600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1453/10000 episodes, total num timesteps 290800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1454/10000 episodes, total num timesteps 291000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1455/10000 episodes, total num timesteps 291200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1456/10000 episodes, total num timesteps 291400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1457/10000 episodes, total num timesteps 291600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1458/10000 episodes, total num timesteps 291800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1459/10000 episodes, total num timesteps 292000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1460/10000 episodes, total num timesteps 292200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1461/10000 episodes, total num timesteps 292400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1462/10000 episodes, total num timesteps 292600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1463/10000 episodes, total num timesteps 292800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1464/10000 episodes, total num timesteps 293000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1465/10000 episodes, total num timesteps 293200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1466/10000 episodes, total num timesteps 293400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1467/10000 episodes, total num timesteps 293600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1468/10000 episodes, total num timesteps 293800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1469/10000 episodes, total num timesteps 294000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1470/10000 episodes, total num timesteps 294200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1471/10000 episodes, total num timesteps 294400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1472/10000 episodes, total num timesteps 294600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1473/10000 episodes, total num timesteps 294800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1474/10000 episodes, total num timesteps 295000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1475/10000 episodes, total num timesteps 295200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.7646706016462023
team_policy eval average team episode rewards of agent0: 75.0
team_policy eval idv catch total num of agent0: 32
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent1: 0.7418912180711391
team_policy eval average team episode rewards of agent1: 75.0
team_policy eval idv catch total num of agent1: 31
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent2: 0.6468873144852865
team_policy eval average team episode rewards of agent2: 75.0
team_policy eval idv catch total num of agent2: 27
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent3: 0.5587510592579176
team_policy eval average team episode rewards of agent3: 75.0
team_policy eval idv catch total num of agent3: 24
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent4: 0.3643872296993507
team_policy eval average team episode rewards of agent4: 75.0
team_policy eval idv catch total num of agent4: 16
team_policy eval team catch total num: 30
idv_policy eval average step individual rewards of agent0: 0.4143677404596162
idv_policy eval average team episode rewards of agent0: 40.0
idv_policy eval idv catch total num of agent0: 18
idv_policy eval team catch total num: 16
idv_policy eval average step individual rewards of agent1: 0.23411625670911462
idv_policy eval average team episode rewards of agent1: 40.0
idv_policy eval idv catch total num of agent1: 11
idv_policy eval team catch total num: 16
idv_policy eval average step individual rewards of agent2: 0.40504779435699967
idv_policy eval average team episode rewards of agent2: 40.0
idv_policy eval idv catch total num of agent2: 18
idv_policy eval team catch total num: 16
idv_policy eval average step individual rewards of agent3: 0.23311929763983003
idv_policy eval average team episode rewards of agent3: 40.0
idv_policy eval idv catch total num of agent3: 11
idv_policy eval team catch total num: 16
idv_policy eval average step individual rewards of agent4: 0.5308398735602475
idv_policy eval average team episode rewards of agent4: 40.0
idv_policy eval idv catch total num of agent4: 23
idv_policy eval team catch total num: 16

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1476/10000 episodes, total num timesteps 295400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1477/10000 episodes, total num timesteps 295600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1478/10000 episodes, total num timesteps 295800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1479/10000 episodes, total num timesteps 296000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1480/10000 episodes, total num timesteps 296200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1481/10000 episodes, total num timesteps 296400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1482/10000 episodes, total num timesteps 296600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1483/10000 episodes, total num timesteps 296800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1484/10000 episodes, total num timesteps 297000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1485/10000 episodes, total num timesteps 297200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1486/10000 episodes, total num timesteps 297400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1487/10000 episodes, total num timesteps 297600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1488/10000 episodes, total num timesteps 297800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1489/10000 episodes, total num timesteps 298000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1490/10000 episodes, total num timesteps 298200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1491/10000 episodes, total num timesteps 298400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1492/10000 episodes, total num timesteps 298600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1493/10000 episodes, total num timesteps 298800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1494/10000 episodes, total num timesteps 299000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1495/10000 episodes, total num timesteps 299200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1496/10000 episodes, total num timesteps 299400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1497/10000 episodes, total num timesteps 299600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1498/10000 episodes, total num timesteps 299800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1499/10000 episodes, total num timesteps 300000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1500/10000 episodes, total num timesteps 300200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.646450511996419
team_policy eval average team episode rewards of agent0: 92.5
team_policy eval idv catch total num of agent0: 27
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent1: 0.9711671014499931
team_policy eval average team episode rewards of agent1: 92.5
team_policy eval idv catch total num of agent1: 40
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent2: 0.6451293190338014
team_policy eval average team episode rewards of agent2: 92.5
team_policy eval idv catch total num of agent2: 27
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent3: 0.6920153156164719
team_policy eval average team episode rewards of agent3: 92.5
team_policy eval idv catch total num of agent3: 29
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent4: 0.46648953015120925
team_policy eval average team episode rewards of agent4: 92.5
team_policy eval idv catch total num of agent4: 20
team_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent0: 0.3768236728776307
idv_policy eval average team episode rewards of agent0: 45.0
idv_policy eval idv catch total num of agent0: 17
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent1: 0.5658158973146488
idv_policy eval average team episode rewards of agent1: 45.0
idv_policy eval idv catch total num of agent1: 24
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent2: 0.482360719112554
idv_policy eval average team episode rewards of agent2: 45.0
idv_policy eval idv catch total num of agent2: 21
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent3: 0.23611870742593485
idv_policy eval average team episode rewards of agent3: 45.0
idv_policy eval idv catch total num of agent3: 11
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent4: 0.353862886249982
idv_policy eval average team episode rewards of agent4: 45.0
idv_policy eval idv catch total num of agent4: 16
idv_policy eval team catch total num: 18

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1501/10000 episodes, total num timesteps 300400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1502/10000 episodes, total num timesteps 300600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1503/10000 episodes, total num timesteps 300800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1504/10000 episodes, total num timesteps 301000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1505/10000 episodes, total num timesteps 301200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1506/10000 episodes, total num timesteps 301400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1507/10000 episodes, total num timesteps 301600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1508/10000 episodes, total num timesteps 301800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1509/10000 episodes, total num timesteps 302000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1510/10000 episodes, total num timesteps 302200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1511/10000 episodes, total num timesteps 302400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1512/10000 episodes, total num timesteps 302600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1513/10000 episodes, total num timesteps 302800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1514/10000 episodes, total num timesteps 303000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1515/10000 episodes, total num timesteps 303200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1516/10000 episodes, total num timesteps 303400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1517/10000 episodes, total num timesteps 303600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1518/10000 episodes, total num timesteps 303800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1519/10000 episodes, total num timesteps 304000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1520/10000 episodes, total num timesteps 304200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1521/10000 episodes, total num timesteps 304400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1522/10000 episodes, total num timesteps 304600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1523/10000 episodes, total num timesteps 304800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1524/10000 episodes, total num timesteps 305000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1525/10000 episodes, total num timesteps 305200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.48297596492789174
team_policy eval average team episode rewards of agent0: 60.0
team_policy eval idv catch total num of agent0: 21
team_policy eval team catch total num: 24
team_policy eval average step individual rewards of agent1: 0.24978318074109676
team_policy eval average team episode rewards of agent1: 60.0
team_policy eval idv catch total num of agent1: 12
team_policy eval team catch total num: 24
team_policy eval average step individual rewards of agent2: 0.41508668642848817
team_policy eval average team episode rewards of agent2: 60.0
team_policy eval idv catch total num of agent2: 18
team_policy eval team catch total num: 24
team_policy eval average step individual rewards of agent3: 0.3218702978747786
team_policy eval average team episode rewards of agent3: 60.0
team_policy eval idv catch total num of agent3: 15
team_policy eval team catch total num: 24
team_policy eval average step individual rewards of agent4: 0.41619518596961186
team_policy eval average team episode rewards of agent4: 60.0
team_policy eval idv catch total num of agent4: 18
team_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent0: 0.4172579875045476
idv_policy eval average team episode rewards of agent0: 45.0
idv_policy eval idv catch total num of agent0: 19
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent1: 0.5575345422966879
idv_policy eval average team episode rewards of agent1: 45.0
idv_policy eval idv catch total num of agent1: 24
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent2: 0.4067068241156368
idv_policy eval average team episode rewards of agent2: 45.0
idv_policy eval idv catch total num of agent2: 18
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent3: 0.2841113626850607
idv_policy eval average team episode rewards of agent3: 45.0
idv_policy eval idv catch total num of agent3: 14
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent4: 0.22421904418679467
idv_policy eval average team episode rewards of agent4: 45.0
idv_policy eval idv catch total num of agent4: 11
idv_policy eval team catch total num: 18

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1526/10000 episodes, total num timesteps 305400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1527/10000 episodes, total num timesteps 305600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1528/10000 episodes, total num timesteps 305800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1529/10000 episodes, total num timesteps 306000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1530/10000 episodes, total num timesteps 306200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1531/10000 episodes, total num timesteps 306400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1532/10000 episodes, total num timesteps 306600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1533/10000 episodes, total num timesteps 306800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1534/10000 episodes, total num timesteps 307000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1535/10000 episodes, total num timesteps 307200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1536/10000 episodes, total num timesteps 307400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1537/10000 episodes, total num timesteps 307600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1538/10000 episodes, total num timesteps 307800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1539/10000 episodes, total num timesteps 308000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1540/10000 episodes, total num timesteps 308200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1541/10000 episodes, total num timesteps 308400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1542/10000 episodes, total num timesteps 308600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1543/10000 episodes, total num timesteps 308800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1544/10000 episodes, total num timesteps 309000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1545/10000 episodes, total num timesteps 309200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1546/10000 episodes, total num timesteps 309400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1547/10000 episodes, total num timesteps 309600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1548/10000 episodes, total num timesteps 309800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1549/10000 episodes, total num timesteps 310000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1550/10000 episodes, total num timesteps 310200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.4291071045074346
team_policy eval average team episode rewards of agent0: 52.5
team_policy eval idv catch total num of agent0: 19
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent1: 0.4722699759214373
team_policy eval average team episode rewards of agent1: 52.5
team_policy eval idv catch total num of agent1: 21
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent2: 0.44293007123021055
team_policy eval average team episode rewards of agent2: 52.5
team_policy eval idv catch total num of agent2: 19
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent3: 0.3617219221298102
team_policy eval average team episode rewards of agent3: 52.5
team_policy eval idv catch total num of agent3: 16
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent4: 0.40993365885884486
team_policy eval average team episode rewards of agent4: 52.5
team_policy eval idv catch total num of agent4: 18
team_policy eval team catch total num: 21
idv_policy eval average step individual rewards of agent0: 0.6956073040341181
idv_policy eval average team episode rewards of agent0: 100.0
idv_policy eval idv catch total num of agent0: 29
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent1: 0.2863168680999233
idv_policy eval average team episode rewards of agent1: 100.0
idv_policy eval idv catch total num of agent1: 13
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent2: 0.7151251214401264
idv_policy eval average team episode rewards of agent2: 100.0
idv_policy eval idv catch total num of agent2: 30
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent3: 0.7921955099714876
idv_policy eval average team episode rewards of agent3: 100.0
idv_policy eval idv catch total num of agent3: 33
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent4: 0.6161367156500287
idv_policy eval average team episode rewards of agent4: 100.0
idv_policy eval idv catch total num of agent4: 26
idv_policy eval team catch total num: 40

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1551/10000 episodes, total num timesteps 310400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1552/10000 episodes, total num timesteps 310600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1553/10000 episodes, total num timesteps 310800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1554/10000 episodes, total num timesteps 311000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1555/10000 episodes, total num timesteps 311200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1556/10000 episodes, total num timesteps 311400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1557/10000 episodes, total num timesteps 311600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1558/10000 episodes, total num timesteps 311800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1559/10000 episodes, total num timesteps 312000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1560/10000 episodes, total num timesteps 312200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1561/10000 episodes, total num timesteps 312400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1562/10000 episodes, total num timesteps 312600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1563/10000 episodes, total num timesteps 312800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1564/10000 episodes, total num timesteps 313000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1565/10000 episodes, total num timesteps 313200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1566/10000 episodes, total num timesteps 313400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1567/10000 episodes, total num timesteps 313600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1568/10000 episodes, total num timesteps 313800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1569/10000 episodes, total num timesteps 314000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1570/10000 episodes, total num timesteps 314200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1571/10000 episodes, total num timesteps 314400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1572/10000 episodes, total num timesteps 314600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1573/10000 episodes, total num timesteps 314800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1574/10000 episodes, total num timesteps 315000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1575/10000 episodes, total num timesteps 315200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.8411039583859727
team_policy eval average team episode rewards of agent0: 110.0
team_policy eval idv catch total num of agent0: 35
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent1: 0.6929531472858553
team_policy eval average team episode rewards of agent1: 110.0
team_policy eval idv catch total num of agent1: 29
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent2: 0.8450426908542894
team_policy eval average team episode rewards of agent2: 110.0
team_policy eval idv catch total num of agent2: 35
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent3: 0.7636344863486653
team_policy eval average team episode rewards of agent3: 110.0
team_policy eval idv catch total num of agent3: 32
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent4: 0.7577499499818035
team_policy eval average team episode rewards of agent4: 110.0
team_policy eval idv catch total num of agent4: 32
team_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent0: 0.3021096336034992
idv_policy eval average team episode rewards of agent0: 70.0
idv_policy eval idv catch total num of agent0: 14
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent1: 0.5911049097570615
idv_policy eval average team episode rewards of agent1: 70.0
idv_policy eval idv catch total num of agent1: 25
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent2: 0.5142041035333569
idv_policy eval average team episode rewards of agent2: 70.0
idv_policy eval idv catch total num of agent2: 22
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent3: 0.5061867257985735
idv_policy eval average team episode rewards of agent3: 70.0
idv_policy eval idv catch total num of agent3: 22
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent4: 0.4436030642113086
idv_policy eval average team episode rewards of agent4: 70.0
idv_policy eval idv catch total num of agent4: 19
idv_policy eval team catch total num: 28

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1576/10000 episodes, total num timesteps 315400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1577/10000 episodes, total num timesteps 315600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1578/10000 episodes, total num timesteps 315800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1579/10000 episodes, total num timesteps 316000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1580/10000 episodes, total num timesteps 316200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1581/10000 episodes, total num timesteps 316400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1582/10000 episodes, total num timesteps 316600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1583/10000 episodes, total num timesteps 316800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1584/10000 episodes, total num timesteps 317000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1585/10000 episodes, total num timesteps 317200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1586/10000 episodes, total num timesteps 317400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1587/10000 episodes, total num timesteps 317600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1588/10000 episodes, total num timesteps 317800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1589/10000 episodes, total num timesteps 318000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1590/10000 episodes, total num timesteps 318200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1591/10000 episodes, total num timesteps 318400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1592/10000 episodes, total num timesteps 318600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1593/10000 episodes, total num timesteps 318800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1594/10000 episodes, total num timesteps 319000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1595/10000 episodes, total num timesteps 319200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1596/10000 episodes, total num timesteps 319400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1597/10000 episodes, total num timesteps 319600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1598/10000 episodes, total num timesteps 319800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1599/10000 episodes, total num timesteps 320000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1600/10000 episodes, total num timesteps 320200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.4679277028678379
team_policy eval average team episode rewards of agent0: 52.5
team_policy eval idv catch total num of agent0: 20
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent1: 0.4939682951098699
team_policy eval average team episode rewards of agent1: 52.5
team_policy eval idv catch total num of agent1: 21
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent2: 0.6081386798170485
team_policy eval average team episode rewards of agent2: 52.5
team_policy eval idv catch total num of agent2: 26
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent3: 0.32938730261587534
team_policy eval average team episode rewards of agent3: 52.5
team_policy eval idv catch total num of agent3: 15
team_policy eval team catch total num: 21
team_policy eval average step individual rewards of agent4: 0.47799106430056976
team_policy eval average team episode rewards of agent4: 52.5
team_policy eval idv catch total num of agent4: 21
team_policy eval team catch total num: 21
idv_policy eval average step individual rewards of agent0: 0.5098215204493162
idv_policy eval average team episode rewards of agent0: 102.5
idv_policy eval idv catch total num of agent0: 22
idv_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent1: 0.5704183998382301
idv_policy eval average team episode rewards of agent1: 102.5
idv_policy eval idv catch total num of agent1: 24
idv_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent2: 0.8112830345436577
idv_policy eval average team episode rewards of agent2: 102.5
idv_policy eval idv catch total num of agent2: 34
idv_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent3: 1.0161345871444687
idv_policy eval average team episode rewards of agent3: 102.5
idv_policy eval idv catch total num of agent3: 42
idv_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent4: 0.8080577697069498
idv_policy eval average team episode rewards of agent4: 102.5
idv_policy eval idv catch total num of agent4: 34
idv_policy eval team catch total num: 41

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1601/10000 episodes, total num timesteps 320400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1602/10000 episodes, total num timesteps 320600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1603/10000 episodes, total num timesteps 320800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1604/10000 episodes, total num timesteps 321000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1605/10000 episodes, total num timesteps 321200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1606/10000 episodes, total num timesteps 321400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1607/10000 episodes, total num timesteps 321600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1608/10000 episodes, total num timesteps 321800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1609/10000 episodes, total num timesteps 322000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1610/10000 episodes, total num timesteps 322200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1611/10000 episodes, total num timesteps 322400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1612/10000 episodes, total num timesteps 322600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1613/10000 episodes, total num timesteps 322800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1614/10000 episodes, total num timesteps 323000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1615/10000 episodes, total num timesteps 323200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1616/10000 episodes, total num timesteps 323400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1617/10000 episodes, total num timesteps 323600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1618/10000 episodes, total num timesteps 323800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1619/10000 episodes, total num timesteps 324000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1620/10000 episodes, total num timesteps 324200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1621/10000 episodes, total num timesteps 324400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1622/10000 episodes, total num timesteps 324600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1623/10000 episodes, total num timesteps 324800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1624/10000 episodes, total num timesteps 325000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1625/10000 episodes, total num timesteps 325200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.3448233325375176
team_policy eval average team episode rewards of agent0: 62.5
team_policy eval idv catch total num of agent0: 16
team_policy eval team catch total num: 25
team_policy eval average step individual rewards of agent1: 0.7113499979206698
team_policy eval average team episode rewards of agent1: 62.5
team_policy eval idv catch total num of agent1: 30
team_policy eval team catch total num: 25
team_policy eval average step individual rewards of agent2: 0.43512793939162253
team_policy eval average team episode rewards of agent2: 62.5
team_policy eval idv catch total num of agent2: 19
team_policy eval team catch total num: 25
team_policy eval average step individual rewards of agent3: 0.5176494127296547
team_policy eval average team episode rewards of agent3: 62.5
team_policy eval idv catch total num of agent3: 23
team_policy eval team catch total num: 25
team_policy eval average step individual rewards of agent4: 0.2493736979684131
team_policy eval average team episode rewards of agent4: 62.5
team_policy eval idv catch total num of agent4: 12
team_policy eval team catch total num: 25
idv_policy eval average step individual rewards of agent0: 0.6360736895703221
idv_policy eval average team episode rewards of agent0: 87.5
idv_policy eval idv catch total num of agent0: 27
idv_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent1: 0.691833522704932
idv_policy eval average team episode rewards of agent1: 87.5
idv_policy eval idv catch total num of agent1: 29
idv_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent2: 0.8721770298220767
idv_policy eval average team episode rewards of agent2: 87.5
idv_policy eval idv catch total num of agent2: 36
idv_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent3: 0.46862025258247714
idv_policy eval average team episode rewards of agent3: 87.5
idv_policy eval idv catch total num of agent3: 20
idv_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent4: 0.538518344225738
idv_policy eval average team episode rewards of agent4: 87.5
idv_policy eval idv catch total num of agent4: 23
idv_policy eval team catch total num: 35

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1626/10000 episodes, total num timesteps 325400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1627/10000 episodes, total num timesteps 325600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1628/10000 episodes, total num timesteps 325800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1629/10000 episodes, total num timesteps 326000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1630/10000 episodes, total num timesteps 326200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1631/10000 episodes, total num timesteps 326400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1632/10000 episodes, total num timesteps 326600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1633/10000 episodes, total num timesteps 326800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1634/10000 episodes, total num timesteps 327000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1635/10000 episodes, total num timesteps 327200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1636/10000 episodes, total num timesteps 327400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1637/10000 episodes, total num timesteps 327600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1638/10000 episodes, total num timesteps 327800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1639/10000 episodes, total num timesteps 328000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1640/10000 episodes, total num timesteps 328200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1641/10000 episodes, total num timesteps 328400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1642/10000 episodes, total num timesteps 328600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1643/10000 episodes, total num timesteps 328800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1644/10000 episodes, total num timesteps 329000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1645/10000 episodes, total num timesteps 329200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1646/10000 episodes, total num timesteps 329400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1647/10000 episodes, total num timesteps 329600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1648/10000 episodes, total num timesteps 329800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1649/10000 episodes, total num timesteps 330000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1650/10000 episodes, total num timesteps 330200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.8292596400901079
team_policy eval average team episode rewards of agent0: 120.0
team_policy eval idv catch total num of agent0: 35
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent1: 0.862400606400986
team_policy eval average team episode rewards of agent1: 120.0
team_policy eval idv catch total num of agent1: 36
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent2: 1.0348747140047347
team_policy eval average team episode rewards of agent2: 120.0
team_policy eval idv catch total num of agent2: 43
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent3: 0.4043142912833786
team_policy eval average team episode rewards of agent3: 120.0
team_policy eval idv catch total num of agent3: 18
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent4: 1.0115387099618713
team_policy eval average team episode rewards of agent4: 120.0
team_policy eval idv catch total num of agent4: 42
team_policy eval team catch total num: 48
idv_policy eval average step individual rewards of agent0: 0.7012860612045293
idv_policy eval average team episode rewards of agent0: 60.0
idv_policy eval idv catch total num of agent0: 30
idv_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent1: 0.3734626407131192
idv_policy eval average team episode rewards of agent1: 60.0
idv_policy eval idv catch total num of agent1: 17
idv_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent2: 0.4755752367492512
idv_policy eval average team episode rewards of agent2: 60.0
idv_policy eval idv catch total num of agent2: 21
idv_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent3: 0.24295660170910705
idv_policy eval average team episode rewards of agent3: 60.0
idv_policy eval idv catch total num of agent3: 12
idv_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent4: 0.34132341534238253
idv_policy eval average team episode rewards of agent4: 60.0
idv_policy eval idv catch total num of agent4: 16
idv_policy eval team catch total num: 24

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1651/10000 episodes, total num timesteps 330400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1652/10000 episodes, total num timesteps 330600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1653/10000 episodes, total num timesteps 330800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1654/10000 episodes, total num timesteps 331000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1655/10000 episodes, total num timesteps 331200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1656/10000 episodes, total num timesteps 331400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1657/10000 episodes, total num timesteps 331600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1658/10000 episodes, total num timesteps 331800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1659/10000 episodes, total num timesteps 332000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1660/10000 episodes, total num timesteps 332200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1661/10000 episodes, total num timesteps 332400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1662/10000 episodes, total num timesteps 332600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1663/10000 episodes, total num timesteps 332800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1664/10000 episodes, total num timesteps 333000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1665/10000 episodes, total num timesteps 333200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1666/10000 episodes, total num timesteps 333400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1667/10000 episodes, total num timesteps 333600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1668/10000 episodes, total num timesteps 333800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1669/10000 episodes, total num timesteps 334000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1670/10000 episodes, total num timesteps 334200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1671/10000 episodes, total num timesteps 334400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1672/10000 episodes, total num timesteps 334600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1673/10000 episodes, total num timesteps 334800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1674/10000 episodes, total num timesteps 335000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1675/10000 episodes, total num timesteps 335200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.8683302297832026
team_policy eval average team episode rewards of agent0: 85.0
team_policy eval idv catch total num of agent0: 36
team_policy eval team catch total num: 34
team_policy eval average step individual rewards of agent1: 0.5261112857272954
team_policy eval average team episode rewards of agent1: 85.0
team_policy eval idv catch total num of agent1: 23
team_policy eval team catch total num: 34
team_policy eval average step individual rewards of agent2: 0.6272999947453318
team_policy eval average team episode rewards of agent2: 85.0
team_policy eval idv catch total num of agent2: 27
team_policy eval team catch total num: 34
team_policy eval average step individual rewards of agent3: 0.6622245085133173
team_policy eval average team episode rewards of agent3: 85.0
team_policy eval idv catch total num of agent3: 28
team_policy eval team catch total num: 34
team_policy eval average step individual rewards of agent4: 0.5423574511617343
team_policy eval average team episode rewards of agent4: 85.0
team_policy eval idv catch total num of agent4: 23
team_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent0: 0.48690502889130605
idv_policy eval average team episode rewards of agent0: 70.0
idv_policy eval idv catch total num of agent0: 21
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent1: 0.6899076441772158
idv_policy eval average team episode rewards of agent1: 70.0
idv_policy eval idv catch total num of agent1: 29
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent2: 0.7129704070161559
idv_policy eval average team episode rewards of agent2: 70.0
idv_policy eval idv catch total num of agent2: 30
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent3: 0.509903445150969
idv_policy eval average team episode rewards of agent3: 70.0
idv_policy eval idv catch total num of agent3: 22
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent4: 0.32787841141686186
idv_policy eval average team episode rewards of agent4: 70.0
idv_policy eval idv catch total num of agent4: 15
idv_policy eval team catch total num: 28

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1676/10000 episodes, total num timesteps 335400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1677/10000 episodes, total num timesteps 335600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1678/10000 episodes, total num timesteps 335800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1679/10000 episodes, total num timesteps 336000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1680/10000 episodes, total num timesteps 336200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1681/10000 episodes, total num timesteps 336400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1682/10000 episodes, total num timesteps 336600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1683/10000 episodes, total num timesteps 336800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1684/10000 episodes, total num timesteps 337000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1685/10000 episodes, total num timesteps 337200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1686/10000 episodes, total num timesteps 337400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1687/10000 episodes, total num timesteps 337600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1688/10000 episodes, total num timesteps 337800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1689/10000 episodes, total num timesteps 338000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1690/10000 episodes, total num timesteps 338200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1691/10000 episodes, total num timesteps 338400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1692/10000 episodes, total num timesteps 338600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1693/10000 episodes, total num timesteps 338800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1694/10000 episodes, total num timesteps 339000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1695/10000 episodes, total num timesteps 339200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1696/10000 episodes, total num timesteps 339400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1697/10000 episodes, total num timesteps 339600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1698/10000 episodes, total num timesteps 339800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1699/10000 episodes, total num timesteps 340000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1700/10000 episodes, total num timesteps 340200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.5731775007815385
team_policy eval average team episode rewards of agent0: 55.0
team_policy eval idv catch total num of agent0: 24
team_policy eval team catch total num: 22
team_policy eval average step individual rewards of agent1: 0.5339848351898786
team_policy eval average team episode rewards of agent1: 55.0
team_policy eval idv catch total num of agent1: 23
team_policy eval team catch total num: 22
team_policy eval average step individual rewards of agent2: 0.25386758472603616
team_policy eval average team episode rewards of agent2: 55.0
team_policy eval idv catch total num of agent2: 12
team_policy eval team catch total num: 22
team_policy eval average step individual rewards of agent3: 0.767643313513675
team_policy eval average team episode rewards of agent3: 55.0
team_policy eval idv catch total num of agent3: 32
team_policy eval team catch total num: 22
team_policy eval average step individual rewards of agent4: -0.02248613069460865
team_policy eval average team episode rewards of agent4: 55.0
team_policy eval idv catch total num of agent4: 1
team_policy eval team catch total num: 22
idv_policy eval average step individual rewards of agent0: 0.6793899861819152
idv_policy eval average team episode rewards of agent0: 70.0
idv_policy eval idv catch total num of agent0: 29
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent1: 0.5742727080403549
idv_policy eval average team episode rewards of agent1: 70.0
idv_policy eval idv catch total num of agent1: 26
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent2: 0.7054714205124186
idv_policy eval average team episode rewards of agent2: 70.0
idv_policy eval idv catch total num of agent2: 30
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent3: 0.29462943587417584
idv_policy eval average team episode rewards of agent3: 70.0
idv_policy eval idv catch total num of agent3: 14
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent4: 0.8418325476713729
idv_policy eval average team episode rewards of agent4: 70.0
idv_policy eval idv catch total num of agent4: 35
idv_policy eval team catch total num: 28

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1701/10000 episodes, total num timesteps 340400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1702/10000 episodes, total num timesteps 340600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1703/10000 episodes, total num timesteps 340800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1704/10000 episodes, total num timesteps 341000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1705/10000 episodes, total num timesteps 341200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1706/10000 episodes, total num timesteps 341400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1707/10000 episodes, total num timesteps 341600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1708/10000 episodes, total num timesteps 341800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1709/10000 episodes, total num timesteps 342000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1710/10000 episodes, total num timesteps 342200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1711/10000 episodes, total num timesteps 342400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1712/10000 episodes, total num timesteps 342600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1713/10000 episodes, total num timesteps 342800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1714/10000 episodes, total num timesteps 343000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1715/10000 episodes, total num timesteps 343200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1716/10000 episodes, total num timesteps 343400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1717/10000 episodes, total num timesteps 343600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1718/10000 episodes, total num timesteps 343800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1719/10000 episodes, total num timesteps 344000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1720/10000 episodes, total num timesteps 344200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1721/10000 episodes, total num timesteps 344400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1722/10000 episodes, total num timesteps 344600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1723/10000 episodes, total num timesteps 344800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1724/10000 episodes, total num timesteps 345000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1725/10000 episodes, total num timesteps 345200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.9943933379803056
team_policy eval average team episode rewards of agent0: 80.0
team_policy eval idv catch total num of agent0: 41
team_policy eval team catch total num: 32
team_policy eval average step individual rewards of agent1: 0.3470063997196148
team_policy eval average team episode rewards of agent1: 80.0
team_policy eval idv catch total num of agent1: 16
team_policy eval team catch total num: 32
team_policy eval average step individual rewards of agent2: 0.35244141416155317
team_policy eval average team episode rewards of agent2: 80.0
team_policy eval idv catch total num of agent2: 16
team_policy eval team catch total num: 32
team_policy eval average step individual rewards of agent3: 0.4517438532280269
team_policy eval average team episode rewards of agent3: 80.0
team_policy eval idv catch total num of agent3: 20
team_policy eval team catch total num: 32
team_policy eval average step individual rewards of agent4: 0.5797276763781017
team_policy eval average team episode rewards of agent4: 80.0
team_policy eval idv catch total num of agent4: 25
team_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent0: 0.5863467874103572
idv_policy eval average team episode rewards of agent0: 85.0
idv_policy eval idv catch total num of agent0: 25
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent1: 0.40460059420031597
idv_policy eval average team episode rewards of agent1: 85.0
idv_policy eval idv catch total num of agent1: 18
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent2: 0.7421356301962183
idv_policy eval average team episode rewards of agent2: 85.0
idv_policy eval idv catch total num of agent2: 31
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent3: 0.5921443900126561
idv_policy eval average team episode rewards of agent3: 85.0
idv_policy eval idv catch total num of agent3: 25
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent4: 0.5460621177686766
idv_policy eval average team episode rewards of agent4: 85.0
idv_policy eval idv catch total num of agent4: 23
idv_policy eval team catch total num: 34

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1726/10000 episodes, total num timesteps 345400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1727/10000 episodes, total num timesteps 345600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1728/10000 episodes, total num timesteps 345800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1729/10000 episodes, total num timesteps 346000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1730/10000 episodes, total num timesteps 346200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1731/10000 episodes, total num timesteps 346400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1732/10000 episodes, total num timesteps 346600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1733/10000 episodes, total num timesteps 346800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1734/10000 episodes, total num timesteps 347000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1735/10000 episodes, total num timesteps 347200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1736/10000 episodes, total num timesteps 347400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1737/10000 episodes, total num timesteps 347600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1738/10000 episodes, total num timesteps 347800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1739/10000 episodes, total num timesteps 348000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1740/10000 episodes, total num timesteps 348200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1741/10000 episodes, total num timesteps 348400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1742/10000 episodes, total num timesteps 348600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1743/10000 episodes, total num timesteps 348800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1744/10000 episodes, total num timesteps 349000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1745/10000 episodes, total num timesteps 349200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1746/10000 episodes, total num timesteps 349400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1747/10000 episodes, total num timesteps 349600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1748/10000 episodes, total num timesteps 349800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1749/10000 episodes, total num timesteps 350000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1750/10000 episodes, total num timesteps 350200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.5079385843505224
team_policy eval average team episode rewards of agent0: 82.5
team_policy eval idv catch total num of agent0: 22
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent1: 1.0685881349193758
team_policy eval average team episode rewards of agent1: 82.5
team_policy eval idv catch total num of agent1: 44
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent2: 0.5040059191967255
team_policy eval average team episode rewards of agent2: 82.5
team_policy eval idv catch total num of agent2: 22
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent3: 0.5341738789801779
team_policy eval average team episode rewards of agent3: 82.5
team_policy eval idv catch total num of agent3: 23
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent4: 0.4246758908076364
team_policy eval average team episode rewards of agent4: 82.5
team_policy eval idv catch total num of agent4: 19
team_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent0: 0.7353736784223713
idv_policy eval average team episode rewards of agent0: 80.0
idv_policy eval idv catch total num of agent0: 31
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent1: 0.4818665273700978
idv_policy eval average team episode rewards of agent1: 80.0
idv_policy eval idv catch total num of agent1: 21
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent2: 0.6134716769310314
idv_policy eval average team episode rewards of agent2: 80.0
idv_policy eval idv catch total num of agent2: 26
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent3: 0.5873889557679974
idv_policy eval average team episode rewards of agent3: 80.0
idv_policy eval idv catch total num of agent3: 25
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent4: 0.7274342268955678
idv_policy eval average team episode rewards of agent4: 80.0
idv_policy eval idv catch total num of agent4: 31
idv_policy eval team catch total num: 32

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1751/10000 episodes, total num timesteps 350400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1752/10000 episodes, total num timesteps 350600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1753/10000 episodes, total num timesteps 350800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1754/10000 episodes, total num timesteps 351000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1755/10000 episodes, total num timesteps 351200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1756/10000 episodes, total num timesteps 351400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1757/10000 episodes, total num timesteps 351600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1758/10000 episodes, total num timesteps 351800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1759/10000 episodes, total num timesteps 352000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1760/10000 episodes, total num timesteps 352200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1761/10000 episodes, total num timesteps 352400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1762/10000 episodes, total num timesteps 352600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1763/10000 episodes, total num timesteps 352800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1764/10000 episodes, total num timesteps 353000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1765/10000 episodes, total num timesteps 353200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1766/10000 episodes, total num timesteps 353400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1767/10000 episodes, total num timesteps 353600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1768/10000 episodes, total num timesteps 353800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1769/10000 episodes, total num timesteps 354000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1770/10000 episodes, total num timesteps 354200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1771/10000 episodes, total num timesteps 354400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1772/10000 episodes, total num timesteps 354600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1773/10000 episodes, total num timesteps 354800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1774/10000 episodes, total num timesteps 355000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1775/10000 episodes, total num timesteps 355200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.48942810357542654
team_policy eval average team episode rewards of agent0: 60.0
team_policy eval idv catch total num of agent0: 21
team_policy eval team catch total num: 24
team_policy eval average step individual rewards of agent1: 0.5059857909399323
team_policy eval average team episode rewards of agent1: 60.0
team_policy eval idv catch total num of agent1: 22
team_policy eval team catch total num: 24
team_policy eval average step individual rewards of agent2: 0.3360844671641356
team_policy eval average team episode rewards of agent2: 60.0
team_policy eval idv catch total num of agent2: 15
team_policy eval team catch total num: 24
team_policy eval average step individual rewards of agent3: 0.8962661576014814
team_policy eval average team episode rewards of agent3: 60.0
team_policy eval idv catch total num of agent3: 37
team_policy eval team catch total num: 24
team_policy eval average step individual rewards of agent4: 0.12956305088431988
team_policy eval average team episode rewards of agent4: 60.0
team_policy eval idv catch total num of agent4: 7
team_policy eval team catch total num: 24
idv_policy eval average step individual rewards of agent0: 0.5506574950959314
idv_policy eval average team episode rewards of agent0: 87.5
idv_policy eval idv catch total num of agent0: 24
idv_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent1: 0.6614600092832101
idv_policy eval average team episode rewards of agent1: 87.5
idv_policy eval idv catch total num of agent1: 28
idv_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent2: 0.6813742592525309
idv_policy eval average team episode rewards of agent2: 87.5
idv_policy eval idv catch total num of agent2: 29
idv_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent3: 0.846149342791852
idv_policy eval average team episode rewards of agent3: 87.5
idv_policy eval idv catch total num of agent3: 35
idv_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent4: 0.4819023604064776
idv_policy eval average team episode rewards of agent4: 87.5
idv_policy eval idv catch total num of agent4: 21
idv_policy eval team catch total num: 35

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1776/10000 episodes, total num timesteps 355400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1777/10000 episodes, total num timesteps 355600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1778/10000 episodes, total num timesteps 355800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1779/10000 episodes, total num timesteps 356000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1780/10000 episodes, total num timesteps 356200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1781/10000 episodes, total num timesteps 356400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1782/10000 episodes, total num timesteps 356600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1783/10000 episodes, total num timesteps 356800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1784/10000 episodes, total num timesteps 357000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1785/10000 episodes, total num timesteps 357200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1786/10000 episodes, total num timesteps 357400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1787/10000 episodes, total num timesteps 357600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1788/10000 episodes, total num timesteps 357800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1789/10000 episodes, total num timesteps 358000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1790/10000 episodes, total num timesteps 358200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1791/10000 episodes, total num timesteps 358400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1792/10000 episodes, total num timesteps 358600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1793/10000 episodes, total num timesteps 358800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1794/10000 episodes, total num timesteps 359000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1795/10000 episodes, total num timesteps 359200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1796/10000 episodes, total num timesteps 359400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1797/10000 episodes, total num timesteps 359600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1798/10000 episodes, total num timesteps 359800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1799/10000 episodes, total num timesteps 360000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1800/10000 episodes, total num timesteps 360200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.456670649520492
team_policy eval average team episode rewards of agent0: 75.0
team_policy eval idv catch total num of agent0: 20
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent1: 0.6918398912640226
team_policy eval average team episode rewards of agent1: 75.0
team_policy eval idv catch total num of agent1: 29
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent2: 0.4386251700808316
team_policy eval average team episode rewards of agent2: 75.0
team_policy eval idv catch total num of agent2: 19
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent3: 0.4516471047698466
team_policy eval average team episode rewards of agent3: 75.0
team_policy eval idv catch total num of agent3: 20
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent4: 0.7651145172345194
team_policy eval average team episode rewards of agent4: 75.0
team_policy eval idv catch total num of agent4: 32
team_policy eval team catch total num: 30
idv_policy eval average step individual rewards of agent0: 0.6155549634289047
idv_policy eval average team episode rewards of agent0: 92.5
idv_policy eval idv catch total num of agent0: 26
idv_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent1: 0.536200894135628
idv_policy eval average team episode rewards of agent1: 92.5
idv_policy eval idv catch total num of agent1: 23
idv_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent2: 0.9201037128345467
idv_policy eval average team episode rewards of agent2: 92.5
idv_policy eval idv catch total num of agent2: 38
idv_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent3: 1.0340491151989526
idv_policy eval average team episode rewards of agent3: 92.5
idv_policy eval idv catch total num of agent3: 43
idv_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent4: 0.7096502195950779
idv_policy eval average team episode rewards of agent4: 92.5
idv_policy eval idv catch total num of agent4: 30
idv_policy eval team catch total num: 37

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1801/10000 episodes, total num timesteps 360400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1802/10000 episodes, total num timesteps 360600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1803/10000 episodes, total num timesteps 360800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1804/10000 episodes, total num timesteps 361000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1805/10000 episodes, total num timesteps 361200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1806/10000 episodes, total num timesteps 361400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1807/10000 episodes, total num timesteps 361600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1808/10000 episodes, total num timesteps 361800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1809/10000 episodes, total num timesteps 362000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1810/10000 episodes, total num timesteps 362200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1811/10000 episodes, total num timesteps 362400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1812/10000 episodes, total num timesteps 362600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1813/10000 episodes, total num timesteps 362800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1814/10000 episodes, total num timesteps 363000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1815/10000 episodes, total num timesteps 363200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1816/10000 episodes, total num timesteps 363400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1817/10000 episodes, total num timesteps 363600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1818/10000 episodes, total num timesteps 363800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1819/10000 episodes, total num timesteps 364000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1820/10000 episodes, total num timesteps 364200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1821/10000 episodes, total num timesteps 364400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1822/10000 episodes, total num timesteps 364600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1823/10000 episodes, total num timesteps 364800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1824/10000 episodes, total num timesteps 365000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1825/10000 episodes, total num timesteps 365200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.7085755881987916
team_policy eval average team episode rewards of agent0: 122.5
team_policy eval idv catch total num of agent0: 30
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent1: 1.0682052645178646
team_policy eval average team episode rewards of agent1: 122.5
team_policy eval idv catch total num of agent1: 44
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent2: 0.7420424669933844
team_policy eval average team episode rewards of agent2: 122.5
team_policy eval idv catch total num of agent2: 31
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent3: 0.5051982281928294
team_policy eval average team episode rewards of agent3: 122.5
team_policy eval idv catch total num of agent3: 22
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent4: 1.3378897200168074
team_policy eval average team episode rewards of agent4: 122.5
team_policy eval idv catch total num of agent4: 55
team_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent0: 1.0189209158115855
idv_policy eval average team episode rewards of agent0: 140.0
idv_policy eval idv catch total num of agent0: 42
idv_policy eval team catch total num: 56
idv_policy eval average step individual rewards of agent1: 1.0855488560048405
idv_policy eval average team episode rewards of agent1: 140.0
idv_policy eval idv catch total num of agent1: 45
idv_policy eval team catch total num: 56
idv_policy eval average step individual rewards of agent2: 1.3271420234954108
idv_policy eval average team episode rewards of agent2: 140.0
idv_policy eval idv catch total num of agent2: 54
idv_policy eval team catch total num: 56
idv_policy eval average step individual rewards of agent3: 0.7164787635911682
idv_policy eval average team episode rewards of agent3: 140.0
idv_policy eval idv catch total num of agent3: 30
idv_policy eval team catch total num: 56
idv_policy eval average step individual rewards of agent4: 1.1121763435702028
idv_policy eval average team episode rewards of agent4: 140.0
idv_policy eval idv catch total num of agent4: 46
idv_policy eval team catch total num: 56

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1826/10000 episodes, total num timesteps 365400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1827/10000 episodes, total num timesteps 365600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1828/10000 episodes, total num timesteps 365800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1829/10000 episodes, total num timesteps 366000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1830/10000 episodes, total num timesteps 366200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1831/10000 episodes, total num timesteps 366400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1832/10000 episodes, total num timesteps 366600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1833/10000 episodes, total num timesteps 366800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1834/10000 episodes, total num timesteps 367000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1835/10000 episodes, total num timesteps 367200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1836/10000 episodes, total num timesteps 367400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1837/10000 episodes, total num timesteps 367600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1838/10000 episodes, total num timesteps 367800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1839/10000 episodes, total num timesteps 368000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1840/10000 episodes, total num timesteps 368200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1841/10000 episodes, total num timesteps 368400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1842/10000 episodes, total num timesteps 368600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1843/10000 episodes, total num timesteps 368800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1844/10000 episodes, total num timesteps 369000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1845/10000 episodes, total num timesteps 369200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1846/10000 episodes, total num timesteps 369400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1847/10000 episodes, total num timesteps 369600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1848/10000 episodes, total num timesteps 369800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1849/10000 episodes, total num timesteps 370000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1850/10000 episodes, total num timesteps 370200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.663115762041428
team_policy eval average team episode rewards of agent0: 110.0
team_policy eval idv catch total num of agent0: 28
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent1: 0.7788476134162498
team_policy eval average team episode rewards of agent1: 110.0
team_policy eval idv catch total num of agent1: 33
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent2: 0.5620271184627516
team_policy eval average team episode rewards of agent2: 110.0
team_policy eval idv catch total num of agent2: 24
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent3: 1.0093330444178847
team_policy eval average team episode rewards of agent3: 110.0
team_policy eval idv catch total num of agent3: 42
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent4: 0.8860685514070467
team_policy eval average team episode rewards of agent4: 110.0
team_policy eval idv catch total num of agent4: 37
team_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent0: 0.6164413097451191
idv_policy eval average team episode rewards of agent0: 82.5
idv_policy eval idv catch total num of agent0: 26
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent1: 0.5659956677599756
idv_policy eval average team episode rewards of agent1: 82.5
idv_policy eval idv catch total num of agent1: 24
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent2: 1.0903939774358467
idv_policy eval average team episode rewards of agent2: 82.5
idv_policy eval idv catch total num of agent2: 45
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent3: 0.6620424835891906
idv_policy eval average team episode rewards of agent3: 82.5
idv_policy eval idv catch total num of agent3: 28
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent4: 0.5099203135975995
idv_policy eval average team episode rewards of agent4: 82.5
idv_policy eval idv catch total num of agent4: 22
idv_policy eval team catch total num: 33

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1851/10000 episodes, total num timesteps 370400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1852/10000 episodes, total num timesteps 370600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1853/10000 episodes, total num timesteps 370800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1854/10000 episodes, total num timesteps 371000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1855/10000 episodes, total num timesteps 371200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1856/10000 episodes, total num timesteps 371400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1857/10000 episodes, total num timesteps 371600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1858/10000 episodes, total num timesteps 371800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1859/10000 episodes, total num timesteps 372000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1860/10000 episodes, total num timesteps 372200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1861/10000 episodes, total num timesteps 372400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1862/10000 episodes, total num timesteps 372600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1863/10000 episodes, total num timesteps 372800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1864/10000 episodes, total num timesteps 373000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1865/10000 episodes, total num timesteps 373200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1866/10000 episodes, total num timesteps 373400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1867/10000 episodes, total num timesteps 373600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1868/10000 episodes, total num timesteps 373800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1869/10000 episodes, total num timesteps 374000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1870/10000 episodes, total num timesteps 374200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1871/10000 episodes, total num timesteps 374400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1872/10000 episodes, total num timesteps 374600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1873/10000 episodes, total num timesteps 374800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1874/10000 episodes, total num timesteps 375000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1875/10000 episodes, total num timesteps 375200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.7899668173540259
team_policy eval average team episode rewards of agent0: 112.5
team_policy eval idv catch total num of agent0: 33
team_policy eval team catch total num: 45
team_policy eval average step individual rewards of agent1: 1.0942240671700836
team_policy eval average team episode rewards of agent1: 112.5
team_policy eval idv catch total num of agent1: 45
team_policy eval team catch total num: 45
team_policy eval average step individual rewards of agent2: 0.5909858717572556
team_policy eval average team episode rewards of agent2: 112.5
team_policy eval idv catch total num of agent2: 25
team_policy eval team catch total num: 45
team_policy eval average step individual rewards of agent3: 0.9144899606279822
team_policy eval average team episode rewards of agent3: 112.5
team_policy eval idv catch total num of agent3: 38
team_policy eval team catch total num: 45
team_policy eval average step individual rewards of agent4: 0.5665847979482347
team_policy eval average team episode rewards of agent4: 112.5
team_policy eval idv catch total num of agent4: 24
team_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent0: 0.6136171327195485
idv_policy eval average team episode rewards of agent0: 70.0
idv_policy eval idv catch total num of agent0: 26
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent1: 0.39337582838928925
idv_policy eval average team episode rewards of agent1: 70.0
idv_policy eval idv catch total num of agent1: 17
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent2: 0.6436016970915293
idv_policy eval average team episode rewards of agent2: 70.0
idv_policy eval idv catch total num of agent2: 27
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent3: 0.18587647821852948
idv_policy eval average team episode rewards of agent3: 70.0
idv_policy eval idv catch total num of agent3: 9
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent4: 0.8375979764746424
idv_policy eval average team episode rewards of agent4: 70.0
idv_policy eval idv catch total num of agent4: 35
idv_policy eval team catch total num: 28

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1876/10000 episodes, total num timesteps 375400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1877/10000 episodes, total num timesteps 375600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1878/10000 episodes, total num timesteps 375800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1879/10000 episodes, total num timesteps 376000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1880/10000 episodes, total num timesteps 376200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1881/10000 episodes, total num timesteps 376400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1882/10000 episodes, total num timesteps 376600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1883/10000 episodes, total num timesteps 376800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1884/10000 episodes, total num timesteps 377000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1885/10000 episodes, total num timesteps 377200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1886/10000 episodes, total num timesteps 377400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1887/10000 episodes, total num timesteps 377600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1888/10000 episodes, total num timesteps 377800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1889/10000 episodes, total num timesteps 378000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1890/10000 episodes, total num timesteps 378200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1891/10000 episodes, total num timesteps 378400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1892/10000 episodes, total num timesteps 378600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1893/10000 episodes, total num timesteps 378800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1894/10000 episodes, total num timesteps 379000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1895/10000 episodes, total num timesteps 379200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1896/10000 episodes, total num timesteps 379400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1897/10000 episodes, total num timesteps 379600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1898/10000 episodes, total num timesteps 379800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1899/10000 episodes, total num timesteps 380000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1900/10000 episodes, total num timesteps 380200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 1.14584084810304
team_policy eval average team episode rewards of agent0: 165.0
team_policy eval idv catch total num of agent0: 47
team_policy eval team catch total num: 66
team_policy eval average step individual rewards of agent1: 1.05952419064866
team_policy eval average team episode rewards of agent1: 165.0
team_policy eval idv catch total num of agent1: 44
team_policy eval team catch total num: 66
team_policy eval average step individual rewards of agent2: 1.299756163986105
team_policy eval average team episode rewards of agent2: 165.0
team_policy eval idv catch total num of agent2: 53
team_policy eval team catch total num: 66
team_policy eval average step individual rewards of agent3: 1.3406470824517993
team_policy eval average team episode rewards of agent3: 165.0
team_policy eval idv catch total num of agent3: 55
team_policy eval team catch total num: 66
team_policy eval average step individual rewards of agent4: 0.9903919328964225
team_policy eval average team episode rewards of agent4: 165.0
team_policy eval idv catch total num of agent4: 41
team_policy eval team catch total num: 66
idv_policy eval average step individual rewards of agent0: 0.4880275604062559
idv_policy eval average team episode rewards of agent0: 82.5
idv_policy eval idv catch total num of agent0: 21
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent1: 0.6081024173307324
idv_policy eval average team episode rewards of agent1: 82.5
idv_policy eval idv catch total num of agent1: 26
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent2: 0.6319915827054763
idv_policy eval average team episode rewards of agent2: 82.5
idv_policy eval idv catch total num of agent2: 27
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent3: 0.5422791467638087
idv_policy eval average team episode rewards of agent3: 82.5
idv_policy eval idv catch total num of agent3: 23
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent4: 0.7670213224288683
idv_policy eval average team episode rewards of agent4: 82.5
idv_policy eval idv catch total num of agent4: 32
idv_policy eval team catch total num: 33

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1901/10000 episodes, total num timesteps 380400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1902/10000 episodes, total num timesteps 380600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1903/10000 episodes, total num timesteps 380800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1904/10000 episodes, total num timesteps 381000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1905/10000 episodes, total num timesteps 381200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1906/10000 episodes, total num timesteps 381400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1907/10000 episodes, total num timesteps 381600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1908/10000 episodes, total num timesteps 381800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1909/10000 episodes, total num timesteps 382000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1910/10000 episodes, total num timesteps 382200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1911/10000 episodes, total num timesteps 382400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1912/10000 episodes, total num timesteps 382600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1913/10000 episodes, total num timesteps 382800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1914/10000 episodes, total num timesteps 383000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1915/10000 episodes, total num timesteps 383200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1916/10000 episodes, total num timesteps 383400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1917/10000 episodes, total num timesteps 383600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1918/10000 episodes, total num timesteps 383800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1919/10000 episodes, total num timesteps 384000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1920/10000 episodes, total num timesteps 384200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1921/10000 episodes, total num timesteps 384400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1922/10000 episodes, total num timesteps 384600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1923/10000 episodes, total num timesteps 384800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1924/10000 episodes, total num timesteps 385000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1925/10000 episodes, total num timesteps 385200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.8131660095714515
team_policy eval average team episode rewards of agent0: 122.5
team_policy eval idv catch total num of agent0: 34
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent1: 1.1918539201479807
team_policy eval average team episode rewards of agent1: 122.5
team_policy eval idv catch total num of agent1: 49
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent2: 0.945913477921957
team_policy eval average team episode rewards of agent2: 122.5
team_policy eval idv catch total num of agent2: 39
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent3: 0.5054249118944059
team_policy eval average team episode rewards of agent3: 122.5
team_policy eval idv catch total num of agent3: 22
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent4: 0.5604553591053998
team_policy eval average team episode rewards of agent4: 122.5
team_policy eval idv catch total num of agent4: 24
team_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent0: 0.9438081080209159
idv_policy eval average team episode rewards of agent0: 122.5
idv_policy eval idv catch total num of agent0: 39
idv_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent1: 1.1383004222896318
idv_policy eval average team episode rewards of agent1: 122.5
idv_policy eval idv catch total num of agent1: 47
idv_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent2: 0.7082146621516057
idv_policy eval average team episode rewards of agent2: 122.5
idv_policy eval idv catch total num of agent2: 30
idv_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent3: 0.6372903311110382
idv_policy eval average team episode rewards of agent3: 122.5
idv_policy eval idv catch total num of agent3: 27
idv_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent4: 0.7668278085159959
idv_policy eval average team episode rewards of agent4: 122.5
idv_policy eval idv catch total num of agent4: 32
idv_policy eval team catch total num: 49

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1926/10000 episodes, total num timesteps 385400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1927/10000 episodes, total num timesteps 385600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1928/10000 episodes, total num timesteps 385800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1929/10000 episodes, total num timesteps 386000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1930/10000 episodes, total num timesteps 386200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1931/10000 episodes, total num timesteps 386400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1932/10000 episodes, total num timesteps 386600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1933/10000 episodes, total num timesteps 386800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1934/10000 episodes, total num timesteps 387000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1935/10000 episodes, total num timesteps 387200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1936/10000 episodes, total num timesteps 387400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1937/10000 episodes, total num timesteps 387600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1938/10000 episodes, total num timesteps 387800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1939/10000 episodes, total num timesteps 388000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1940/10000 episodes, total num timesteps 388200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1941/10000 episodes, total num timesteps 388400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1942/10000 episodes, total num timesteps 388600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1943/10000 episodes, total num timesteps 388800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1944/10000 episodes, total num timesteps 389000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1945/10000 episodes, total num timesteps 389200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1946/10000 episodes, total num timesteps 389400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1947/10000 episodes, total num timesteps 389600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1948/10000 episodes, total num timesteps 389800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1949/10000 episodes, total num timesteps 390000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1950/10000 episodes, total num timesteps 390200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.728634628548563
team_policy eval average team episode rewards of agent0: 142.5
team_policy eval idv catch total num of agent0: 31
team_policy eval team catch total num: 57
team_policy eval average step individual rewards of agent1: 0.757328509197047
team_policy eval average team episode rewards of agent1: 142.5
team_policy eval idv catch total num of agent1: 32
team_policy eval team catch total num: 57
team_policy eval average step individual rewards of agent2: 0.9808126977285151
team_policy eval average team episode rewards of agent2: 142.5
team_policy eval idv catch total num of agent2: 41
team_policy eval team catch total num: 57
team_policy eval average step individual rewards of agent3: 1.1362431457206346
team_policy eval average team episode rewards of agent3: 142.5
team_policy eval idv catch total num of agent3: 47
team_policy eval team catch total num: 57
team_policy eval average step individual rewards of agent4: 1.081110108193061
team_policy eval average team episode rewards of agent4: 142.5
team_policy eval idv catch total num of agent4: 45
team_policy eval team catch total num: 57
idv_policy eval average step individual rewards of agent0: 0.7919275703310185
idv_policy eval average team episode rewards of agent0: 82.5
idv_policy eval idv catch total num of agent0: 33
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent1: 0.3576564159924823
idv_policy eval average team episode rewards of agent1: 82.5
idv_policy eval idv catch total num of agent1: 16
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent2: 0.3570732049833944
idv_policy eval average team episode rewards of agent2: 82.5
idv_policy eval idv catch total num of agent2: 16
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent3: 0.7344364555902968
idv_policy eval average team episode rewards of agent3: 82.5
idv_policy eval idv catch total num of agent3: 31
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent4: 0.7327957920692999
idv_policy eval average team episode rewards of agent4: 82.5
idv_policy eval idv catch total num of agent4: 31
idv_policy eval team catch total num: 33

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1951/10000 episodes, total num timesteps 390400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1952/10000 episodes, total num timesteps 390600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1953/10000 episodes, total num timesteps 390800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1954/10000 episodes, total num timesteps 391000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1955/10000 episodes, total num timesteps 391200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1956/10000 episodes, total num timesteps 391400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1957/10000 episodes, total num timesteps 391600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1958/10000 episodes, total num timesteps 391800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1959/10000 episodes, total num timesteps 392000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1960/10000 episodes, total num timesteps 392200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1961/10000 episodes, total num timesteps 392400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1962/10000 episodes, total num timesteps 392600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1963/10000 episodes, total num timesteps 392800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1964/10000 episodes, total num timesteps 393000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1965/10000 episodes, total num timesteps 393200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1966/10000 episodes, total num timesteps 393400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1967/10000 episodes, total num timesteps 393600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1968/10000 episodes, total num timesteps 393800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1969/10000 episodes, total num timesteps 394000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1970/10000 episodes, total num timesteps 394200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1971/10000 episodes, total num timesteps 394400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1972/10000 episodes, total num timesteps 394600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1973/10000 episodes, total num timesteps 394800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1974/10000 episodes, total num timesteps 395000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1975/10000 episodes, total num timesteps 395200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.30250972514529173
team_policy eval average team episode rewards of agent0: 65.0
team_policy eval idv catch total num of agent0: 14
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent1: 0.7897103020154698
team_policy eval average team episode rewards of agent1: 65.0
team_policy eval idv catch total num of agent1: 33
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent2: 0.32545930312976096
team_policy eval average team episode rewards of agent2: 65.0
team_policy eval idv catch total num of agent2: 15
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent3: 0.7604585995644162
team_policy eval average team episode rewards of agent3: 65.0
team_policy eval idv catch total num of agent3: 32
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent4: 0.5339285503404095
team_policy eval average team episode rewards of agent4: 65.0
team_policy eval idv catch total num of agent4: 23
team_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent0: 0.5571578947135637
idv_policy eval average team episode rewards of agent0: 70.0
idv_policy eval idv catch total num of agent0: 24
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent1: 0.46098469219832816
idv_policy eval average team episode rewards of agent1: 70.0
idv_policy eval idv catch total num of agent1: 20
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent2: 0.5333027575603526
idv_policy eval average team episode rewards of agent2: 70.0
idv_policy eval idv catch total num of agent2: 23
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent3: 0.7232445062861542
idv_policy eval average team episode rewards of agent3: 70.0
idv_policy eval idv catch total num of agent3: 31
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent4: 0.6369568948462342
idv_policy eval average team episode rewards of agent4: 70.0
idv_policy eval idv catch total num of agent4: 27
idv_policy eval team catch total num: 28

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1976/10000 episodes, total num timesteps 395400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1977/10000 episodes, total num timesteps 395600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1978/10000 episodes, total num timesteps 395800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1979/10000 episodes, total num timesteps 396000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1980/10000 episodes, total num timesteps 396200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1981/10000 episodes, total num timesteps 396400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1982/10000 episodes, total num timesteps 396600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1983/10000 episodes, total num timesteps 396800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1984/10000 episodes, total num timesteps 397000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1985/10000 episodes, total num timesteps 397200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1986/10000 episodes, total num timesteps 397400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1987/10000 episodes, total num timesteps 397600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1988/10000 episodes, total num timesteps 397800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1989/10000 episodes, total num timesteps 398000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1990/10000 episodes, total num timesteps 398200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1991/10000 episodes, total num timesteps 398400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1992/10000 episodes, total num timesteps 398600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1993/10000 episodes, total num timesteps 398800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1994/10000 episodes, total num timesteps 399000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1995/10000 episodes, total num timesteps 399200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1996/10000 episodes, total num timesteps 399400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1997/10000 episodes, total num timesteps 399600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1998/10000 episodes, total num timesteps 399800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 1999/10000 episodes, total num timesteps 400000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2000/10000 episodes, total num timesteps 400200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 1.0871391498991352
team_policy eval average team episode rewards of agent0: 100.0
team_policy eval idv catch total num of agent0: 45
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent1: 0.6584972018836374
team_policy eval average team episode rewards of agent1: 100.0
team_policy eval idv catch total num of agent1: 28
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent2: 0.5582725617699341
team_policy eval average team episode rewards of agent2: 100.0
team_policy eval idv catch total num of agent2: 24
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent3: 0.6560026941468496
team_policy eval average team episode rewards of agent3: 100.0
team_policy eval idv catch total num of agent3: 28
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent4: 0.5690868070930902
team_policy eval average team episode rewards of agent4: 100.0
team_policy eval idv catch total num of agent4: 25
team_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent0: 0.8293187483229003
idv_policy eval average team episode rewards of agent0: 117.5
idv_policy eval idv catch total num of agent0: 35
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent1: 0.9707717573653794
idv_policy eval average team episode rewards of agent1: 117.5
idv_policy eval idv catch total num of agent1: 40
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent2: 0.7408809317204765
idv_policy eval average team episode rewards of agent2: 117.5
idv_policy eval idv catch total num of agent2: 31
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent3: 0.9195750042375131
idv_policy eval average team episode rewards of agent3: 117.5
idv_policy eval idv catch total num of agent3: 38
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent4: 0.9616991397672043
idv_policy eval average team episode rewards of agent4: 117.5
idv_policy eval idv catch total num of agent4: 40
idv_policy eval team catch total num: 47

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2001/10000 episodes, total num timesteps 400400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2002/10000 episodes, total num timesteps 400600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2003/10000 episodes, total num timesteps 400800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2004/10000 episodes, total num timesteps 401000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2005/10000 episodes, total num timesteps 401200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2006/10000 episodes, total num timesteps 401400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2007/10000 episodes, total num timesteps 401600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2008/10000 episodes, total num timesteps 401800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2009/10000 episodes, total num timesteps 402000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2010/10000 episodes, total num timesteps 402200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2011/10000 episodes, total num timesteps 402400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2012/10000 episodes, total num timesteps 402600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2013/10000 episodes, total num timesteps 402800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2014/10000 episodes, total num timesteps 403000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2015/10000 episodes, total num timesteps 403200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2016/10000 episodes, total num timesteps 403400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2017/10000 episodes, total num timesteps 403600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2018/10000 episodes, total num timesteps 403800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2019/10000 episodes, total num timesteps 404000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2020/10000 episodes, total num timesteps 404200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2021/10000 episodes, total num timesteps 404400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2022/10000 episodes, total num timesteps 404600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2023/10000 episodes, total num timesteps 404800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2024/10000 episodes, total num timesteps 405000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2025/10000 episodes, total num timesteps 405200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.5848230908602888
team_policy eval average team episode rewards of agent0: 105.0
team_policy eval idv catch total num of agent0: 25
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent1: 0.6392679482494477
team_policy eval average team episode rewards of agent1: 105.0
team_policy eval idv catch total num of agent1: 27
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent2: 0.8879685042480026
team_policy eval average team episode rewards of agent2: 105.0
team_policy eval idv catch total num of agent2: 37
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent3: 0.7657320478564239
team_policy eval average team episode rewards of agent3: 105.0
team_policy eval idv catch total num of agent3: 32
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent4: 0.9114096939397933
team_policy eval average team episode rewards of agent4: 105.0
team_policy eval idv catch total num of agent4: 38
team_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent0: 0.6898346009671235
idv_policy eval average team episode rewards of agent0: 85.0
idv_policy eval idv catch total num of agent0: 29
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent1: 0.6580990861856963
idv_policy eval average team episode rewards of agent1: 85.0
idv_policy eval idv catch total num of agent1: 28
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent2: 0.7583452302799487
idv_policy eval average team episode rewards of agent2: 85.0
idv_policy eval idv catch total num of agent2: 32
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent3: 0.5019269162097291
idv_policy eval average team episode rewards of agent3: 85.0
idv_policy eval idv catch total num of agent3: 22
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent4: 0.7174982046983466
idv_policy eval average team episode rewards of agent4: 85.0
idv_policy eval idv catch total num of agent4: 30
idv_policy eval team catch total num: 34

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2026/10000 episodes, total num timesteps 405400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2027/10000 episodes, total num timesteps 405600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2028/10000 episodes, total num timesteps 405800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2029/10000 episodes, total num timesteps 406000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2030/10000 episodes, total num timesteps 406200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2031/10000 episodes, total num timesteps 406400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2032/10000 episodes, total num timesteps 406600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2033/10000 episodes, total num timesteps 406800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2034/10000 episodes, total num timesteps 407000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2035/10000 episodes, total num timesteps 407200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2036/10000 episodes, total num timesteps 407400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2037/10000 episodes, total num timesteps 407600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2038/10000 episodes, total num timesteps 407800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2039/10000 episodes, total num timesteps 408000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2040/10000 episodes, total num timesteps 408200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2041/10000 episodes, total num timesteps 408400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2042/10000 episodes, total num timesteps 408600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2043/10000 episodes, total num timesteps 408800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2044/10000 episodes, total num timesteps 409000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2045/10000 episodes, total num timesteps 409200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2046/10000 episodes, total num timesteps 409400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2047/10000 episodes, total num timesteps 409600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2048/10000 episodes, total num timesteps 409800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2049/10000 episodes, total num timesteps 410000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2050/10000 episodes, total num timesteps 410200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.7890856194569176
team_policy eval average team episode rewards of agent0: 95.0
team_policy eval idv catch total num of agent0: 33
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent1: 0.7627804062971097
team_policy eval average team episode rewards of agent1: 95.0
team_policy eval idv catch total num of agent1: 32
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent2: 1.0993383264711765
team_policy eval average team episode rewards of agent2: 95.0
team_policy eval idv catch total num of agent2: 45
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent3: 0.48905290892932185
team_policy eval average team episode rewards of agent3: 95.0
team_policy eval idv catch total num of agent3: 21
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent4: 0.6878957452181101
team_policy eval average team episode rewards of agent4: 95.0
team_policy eval idv catch total num of agent4: 29
team_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent0: 0.43598975859517247
idv_policy eval average team episode rewards of agent0: 97.5
idv_policy eval idv catch total num of agent0: 19
idv_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent1: 0.8933993415587739
idv_policy eval average team episode rewards of agent1: 97.5
idv_policy eval idv catch total num of agent1: 37
idv_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent2: 0.7939567928293003
idv_policy eval average team episode rewards of agent2: 97.5
idv_policy eval idv catch total num of agent2: 33
idv_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent3: 0.8681432064883122
idv_policy eval average team episode rewards of agent3: 97.5
idv_policy eval idv catch total num of agent3: 36
idv_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent4: 0.6682116952169129
idv_policy eval average team episode rewards of agent4: 97.5
idv_policy eval idv catch total num of agent4: 28
idv_policy eval team catch total num: 39

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2051/10000 episodes, total num timesteps 410400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2052/10000 episodes, total num timesteps 410600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2053/10000 episodes, total num timesteps 410800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2054/10000 episodes, total num timesteps 411000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2055/10000 episodes, total num timesteps 411200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2056/10000 episodes, total num timesteps 411400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2057/10000 episodes, total num timesteps 411600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2058/10000 episodes, total num timesteps 411800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2059/10000 episodes, total num timesteps 412000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2060/10000 episodes, total num timesteps 412200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2061/10000 episodes, total num timesteps 412400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2062/10000 episodes, total num timesteps 412600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2063/10000 episodes, total num timesteps 412800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2064/10000 episodes, total num timesteps 413000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2065/10000 episodes, total num timesteps 413200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2066/10000 episodes, total num timesteps 413400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2067/10000 episodes, total num timesteps 413600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2068/10000 episodes, total num timesteps 413800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2069/10000 episodes, total num timesteps 414000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2070/10000 episodes, total num timesteps 414200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2071/10000 episodes, total num timesteps 414400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2072/10000 episodes, total num timesteps 414600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2073/10000 episodes, total num timesteps 414800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2074/10000 episodes, total num timesteps 415000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2075/10000 episodes, total num timesteps 415200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.8899339107164173
team_policy eval average team episode rewards of agent0: 110.0
team_policy eval idv catch total num of agent0: 37
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent1: 0.816231191054797
team_policy eval average team episode rewards of agent1: 110.0
team_policy eval idv catch total num of agent1: 34
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent2: 1.0855331581438294
team_policy eval average team episode rewards of agent2: 110.0
team_policy eval idv catch total num of agent2: 45
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent3: 0.8916911176095437
team_policy eval average team episode rewards of agent3: 110.0
team_policy eval idv catch total num of agent3: 37
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent4: 0.9683673808892805
team_policy eval average team episode rewards of agent4: 110.0
team_policy eval idv catch total num of agent4: 40
team_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent0: 0.8595700107317079
idv_policy eval average team episode rewards of agent0: 117.5
idv_policy eval idv catch total num of agent0: 36
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent1: 1.16350040730842
idv_policy eval average team episode rewards of agent1: 117.5
idv_policy eval idv catch total num of agent1: 48
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent2: 0.6903933186050065
idv_policy eval average team episode rewards of agent2: 117.5
idv_policy eval idv catch total num of agent2: 29
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent3: 1.0221196259947705
idv_policy eval average team episode rewards of agent3: 117.5
idv_policy eval idv catch total num of agent3: 43
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent4: 0.5783301968298931
idv_policy eval average team episode rewards of agent4: 117.5
idv_policy eval idv catch total num of agent4: 25
idv_policy eval team catch total num: 47

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2076/10000 episodes, total num timesteps 415400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2077/10000 episodes, total num timesteps 415600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2078/10000 episodes, total num timesteps 415800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2079/10000 episodes, total num timesteps 416000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2080/10000 episodes, total num timesteps 416200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2081/10000 episodes, total num timesteps 416400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2082/10000 episodes, total num timesteps 416600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2083/10000 episodes, total num timesteps 416800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2084/10000 episodes, total num timesteps 417000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2085/10000 episodes, total num timesteps 417200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2086/10000 episodes, total num timesteps 417400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2087/10000 episodes, total num timesteps 417600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2088/10000 episodes, total num timesteps 417800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2089/10000 episodes, total num timesteps 418000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2090/10000 episodes, total num timesteps 418200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2091/10000 episodes, total num timesteps 418400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2092/10000 episodes, total num timesteps 418600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2093/10000 episodes, total num timesteps 418800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2094/10000 episodes, total num timesteps 419000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2095/10000 episodes, total num timesteps 419200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2096/10000 episodes, total num timesteps 419400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2097/10000 episodes, total num timesteps 419600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2098/10000 episodes, total num timesteps 419800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2099/10000 episodes, total num timesteps 420000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2100/10000 episodes, total num timesteps 420200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.5279493046822887
team_policy eval average team episode rewards of agent0: 70.0
team_policy eval idv catch total num of agent0: 23
team_policy eval team catch total num: 28
team_policy eval average step individual rewards of agent1: 0.555232328582521
team_policy eval average team episode rewards of agent1: 70.0
team_policy eval idv catch total num of agent1: 24
team_policy eval team catch total num: 28
team_policy eval average step individual rewards of agent2: 0.3750888554903194
team_policy eval average team episode rewards of agent2: 70.0
team_policy eval idv catch total num of agent2: 17
team_policy eval team catch total num: 28
team_policy eval average step individual rewards of agent3: 0.7657481361457947
team_policy eval average team episode rewards of agent3: 70.0
team_policy eval idv catch total num of agent3: 32
team_policy eval team catch total num: 28
team_policy eval average step individual rewards of agent4: 0.5846969332798887
team_policy eval average team episode rewards of agent4: 70.0
team_policy eval idv catch total num of agent4: 25
team_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent0: 1.0957010741075397
idv_policy eval average team episode rewards of agent0: 135.0
idv_policy eval idv catch total num of agent0: 45
idv_policy eval team catch total num: 54
idv_policy eval average step individual rewards of agent1: 1.546352028401767
idv_policy eval average team episode rewards of agent1: 135.0
idv_policy eval idv catch total num of agent1: 63
idv_policy eval team catch total num: 54
idv_policy eval average step individual rewards of agent2: 1.04060982135962
idv_policy eval average team episode rewards of agent2: 135.0
idv_policy eval idv catch total num of agent2: 43
idv_policy eval team catch total num: 54
idv_policy eval average step individual rewards of agent3: 0.8823451919020937
idv_policy eval average team episode rewards of agent3: 135.0
idv_policy eval idv catch total num of agent3: 37
idv_policy eval team catch total num: 54
idv_policy eval average step individual rewards of agent4: 0.639033368439911
idv_policy eval average team episode rewards of agent4: 135.0
idv_policy eval idv catch total num of agent4: 27
idv_policy eval team catch total num: 54

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2101/10000 episodes, total num timesteps 420400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2102/10000 episodes, total num timesteps 420600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2103/10000 episodes, total num timesteps 420800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2104/10000 episodes, total num timesteps 421000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2105/10000 episodes, total num timesteps 421200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2106/10000 episodes, total num timesteps 421400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2107/10000 episodes, total num timesteps 421600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2108/10000 episodes, total num timesteps 421800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2109/10000 episodes, total num timesteps 422000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2110/10000 episodes, total num timesteps 422200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2111/10000 episodes, total num timesteps 422400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2112/10000 episodes, total num timesteps 422600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2113/10000 episodes, total num timesteps 422800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2114/10000 episodes, total num timesteps 423000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2115/10000 episodes, total num timesteps 423200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2116/10000 episodes, total num timesteps 423400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2117/10000 episodes, total num timesteps 423600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2118/10000 episodes, total num timesteps 423800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2119/10000 episodes, total num timesteps 424000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2120/10000 episodes, total num timesteps 424200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2121/10000 episodes, total num timesteps 424400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2122/10000 episodes, total num timesteps 424600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2123/10000 episodes, total num timesteps 424800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2124/10000 episodes, total num timesteps 425000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2125/10000 episodes, total num timesteps 425200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 0.7910813942788174
team_policy eval average team episode rewards of agent0: 97.5
team_policy eval idv catch total num of agent0: 33
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent1: 0.9977202699787138
team_policy eval average team episode rewards of agent1: 97.5
team_policy eval idv catch total num of agent1: 41
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent2: 0.866722940510693
team_policy eval average team episode rewards of agent2: 97.5
team_policy eval idv catch total num of agent2: 36
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent3: 0.9202944748781187
team_policy eval average team episode rewards of agent3: 97.5
team_policy eval idv catch total num of agent3: 38
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent4: 0.5055668994437277
team_policy eval average team episode rewards of agent4: 97.5
team_policy eval idv catch total num of agent4: 22
team_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent0: 0.3696611483363083
idv_policy eval average team episode rewards of agent0: 67.5
idv_policy eval idv catch total num of agent0: 17
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent1: 0.4991286934651957
idv_policy eval average team episode rewards of agent1: 67.5
idv_policy eval idv catch total num of agent1: 22
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent2: 0.6561620758260713
idv_policy eval average team episode rewards of agent2: 67.5
idv_policy eval idv catch total num of agent2: 28
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent3: 0.8504325848547661
idv_policy eval average team episode rewards of agent3: 67.5
idv_policy eval idv catch total num of agent3: 36
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent4: 0.11211093904060021
idv_policy eval average team episode rewards of agent4: 67.5
idv_policy eval idv catch total num of agent4: 7
idv_policy eval team catch total num: 27

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2126/10000 episodes, total num timesteps 425400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2127/10000 episodes, total num timesteps 425600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2128/10000 episodes, total num timesteps 425800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2129/10000 episodes, total num timesteps 426000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2130/10000 episodes, total num timesteps 426200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2131/10000 episodes, total num timesteps 426400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2132/10000 episodes, total num timesteps 426600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2133/10000 episodes, total num timesteps 426800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2134/10000 episodes, total num timesteps 427000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2135/10000 episodes, total num timesteps 427200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2136/10000 episodes, total num timesteps 427400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2137/10000 episodes, total num timesteps 427600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2138/10000 episodes, total num timesteps 427800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2139/10000 episodes, total num timesteps 428000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2140/10000 episodes, total num timesteps 428200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2141/10000 episodes, total num timesteps 428400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2142/10000 episodes, total num timesteps 428600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2143/10000 episodes, total num timesteps 428800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2144/10000 episodes, total num timesteps 429000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2145/10000 episodes, total num timesteps 429200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2146/10000 episodes, total num timesteps 429400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2147/10000 episodes, total num timesteps 429600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2148/10000 episodes, total num timesteps 429800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2149/10000 episodes, total num timesteps 430000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2150/10000 episodes, total num timesteps 430200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.5508995593773365
team_policy eval average team episode rewards of agent0: 110.0
team_policy eval idv catch total num of agent0: 24
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent1: 0.7148746445459645
team_policy eval average team episode rewards of agent1: 110.0
team_policy eval idv catch total num of agent1: 30
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent2: 0.9145066680143062
team_policy eval average team episode rewards of agent2: 110.0
team_policy eval idv catch total num of agent2: 38
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent3: 0.688451375857548
team_policy eval average team episode rewards of agent3: 110.0
team_policy eval idv catch total num of agent3: 29
team_policy eval team catch total num: 44
team_policy eval average step individual rewards of agent4: 1.3001220104199294
team_policy eval average team episode rewards of agent4: 110.0
team_policy eval idv catch total num of agent4: 53
team_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent0: 0.9658268844690422
idv_policy eval average team episode rewards of agent0: 70.0
idv_policy eval idv catch total num of agent0: 40
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent1: 0.5342111623450758
idv_policy eval average team episode rewards of agent1: 70.0
idv_policy eval idv catch total num of agent1: 23
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent2: 0.43794213407159915
idv_policy eval average team episode rewards of agent2: 70.0
idv_policy eval idv catch total num of agent2: 19
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent3: 0.5368158332294909
idv_policy eval average team episode rewards of agent3: 70.0
idv_policy eval idv catch total num of agent3: 23
idv_policy eval team catch total num: 28
idv_policy eval average step individual rewards of agent4: 0.2866424966608561
idv_policy eval average team episode rewards of agent4: 70.0
idv_policy eval idv catch total num of agent4: 13
idv_policy eval team catch total num: 28

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2151/10000 episodes, total num timesteps 430400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2152/10000 episodes, total num timesteps 430600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2153/10000 episodes, total num timesteps 430800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2154/10000 episodes, total num timesteps 431000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2155/10000 episodes, total num timesteps 431200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2156/10000 episodes, total num timesteps 431400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2157/10000 episodes, total num timesteps 431600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2158/10000 episodes, total num timesteps 431800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2159/10000 episodes, total num timesteps 432000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2160/10000 episodes, total num timesteps 432200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2161/10000 episodes, total num timesteps 432400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2162/10000 episodes, total num timesteps 432600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2163/10000 episodes, total num timesteps 432800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2164/10000 episodes, total num timesteps 433000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2165/10000 episodes, total num timesteps 433200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2166/10000 episodes, total num timesteps 433400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2167/10000 episodes, total num timesteps 433600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2168/10000 episodes, total num timesteps 433800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2169/10000 episodes, total num timesteps 434000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2170/10000 episodes, total num timesteps 434200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2171/10000 episodes, total num timesteps 434400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2172/10000 episodes, total num timesteps 434600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2173/10000 episodes, total num timesteps 434800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2174/10000 episodes, total num timesteps 435000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2175/10000 episodes, total num timesteps 435200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.9397123478626345
team_policy eval average team episode rewards of agent0: 100.0
team_policy eval idv catch total num of agent0: 39
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent1: 0.6520848427192516
team_policy eval average team episode rewards of agent1: 100.0
team_policy eval idv catch total num of agent1: 28
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent2: 0.785067821847584
team_policy eval average team episode rewards of agent2: 100.0
team_policy eval idv catch total num of agent2: 33
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent3: 0.7515207076848065
team_policy eval average team episode rewards of agent3: 100.0
team_policy eval idv catch total num of agent3: 32
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent4: 0.4615898561765151
team_policy eval average team episode rewards of agent4: 100.0
team_policy eval idv catch total num of agent4: 20
team_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent0: 0.5383475711877495
idv_policy eval average team episode rewards of agent0: 90.0
idv_policy eval idv catch total num of agent0: 23
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent1: 0.5591435887878089
idv_policy eval average team episode rewards of agent1: 90.0
idv_policy eval idv catch total num of agent1: 24
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent2: 0.6639158376522232
idv_policy eval average team episode rewards of agent2: 90.0
idv_policy eval idv catch total num of agent2: 28
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent3: 0.6366132386967437
idv_policy eval average team episode rewards of agent3: 90.0
idv_policy eval idv catch total num of agent3: 27
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent4: 0.5654451557611059
idv_policy eval average team episode rewards of agent4: 90.0
idv_policy eval idv catch total num of agent4: 25
idv_policy eval team catch total num: 36

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2176/10000 episodes, total num timesteps 435400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2177/10000 episodes, total num timesteps 435600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2178/10000 episodes, total num timesteps 435800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2179/10000 episodes, total num timesteps 436000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2180/10000 episodes, total num timesteps 436200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2181/10000 episodes, total num timesteps 436400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2182/10000 episodes, total num timesteps 436600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2183/10000 episodes, total num timesteps 436800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2184/10000 episodes, total num timesteps 437000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2185/10000 episodes, total num timesteps 437200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2186/10000 episodes, total num timesteps 437400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2187/10000 episodes, total num timesteps 437600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2188/10000 episodes, total num timesteps 437800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2189/10000 episodes, total num timesteps 438000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2190/10000 episodes, total num timesteps 438200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2191/10000 episodes, total num timesteps 438400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2192/10000 episodes, total num timesteps 438600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2193/10000 episodes, total num timesteps 438800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2194/10000 episodes, total num timesteps 439000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2195/10000 episodes, total num timesteps 439200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2196/10000 episodes, total num timesteps 439400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2197/10000 episodes, total num timesteps 439600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2198/10000 episodes, total num timesteps 439800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2199/10000 episodes, total num timesteps 440000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2200/10000 episodes, total num timesteps 440200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.3901493045021831
team_policy eval average team episode rewards of agent0: 75.0
team_policy eval idv catch total num of agent0: 18
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent1: 0.7510579203933547
team_policy eval average team episode rewards of agent1: 75.0
team_policy eval idv catch total num of agent1: 32
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent2: 0.5294162410610044
team_policy eval average team episode rewards of agent2: 75.0
team_policy eval idv catch total num of agent2: 23
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent3: 0.3669329004032184
team_policy eval average team episode rewards of agent3: 75.0
team_policy eval idv catch total num of agent3: 17
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent4: 0.613653387763826
team_policy eval average team episode rewards of agent4: 75.0
team_policy eval idv catch total num of agent4: 26
team_policy eval team catch total num: 30
idv_policy eval average step individual rewards of agent0: 0.38950859367198265
idv_policy eval average team episode rewards of agent0: 105.0
idv_policy eval idv catch total num of agent0: 17
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent1: 1.2473785806640465
idv_policy eval average team episode rewards of agent1: 105.0
idv_policy eval idv catch total num of agent1: 51
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent2: 0.4047066017497833
idv_policy eval average team episode rewards of agent2: 105.0
idv_policy eval idv catch total num of agent2: 18
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent3: 0.8028099817914702
idv_policy eval average team episode rewards of agent3: 105.0
idv_policy eval idv catch total num of agent3: 34
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent4: 0.7768470241527197
idv_policy eval average team episode rewards of agent4: 105.0
idv_policy eval idv catch total num of agent4: 33
idv_policy eval team catch total num: 42

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2201/10000 episodes, total num timesteps 440400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2202/10000 episodes, total num timesteps 440600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2203/10000 episodes, total num timesteps 440800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2204/10000 episodes, total num timesteps 441000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2205/10000 episodes, total num timesteps 441200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2206/10000 episodes, total num timesteps 441400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2207/10000 episodes, total num timesteps 441600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2208/10000 episodes, total num timesteps 441800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2209/10000 episodes, total num timesteps 442000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2210/10000 episodes, total num timesteps 442200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2211/10000 episodes, total num timesteps 442400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2212/10000 episodes, total num timesteps 442600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2213/10000 episodes, total num timesteps 442800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2214/10000 episodes, total num timesteps 443000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2215/10000 episodes, total num timesteps 443200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2216/10000 episodes, total num timesteps 443400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2217/10000 episodes, total num timesteps 443600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2218/10000 episodes, total num timesteps 443800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2219/10000 episodes, total num timesteps 444000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2220/10000 episodes, total num timesteps 444200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2221/10000 episodes, total num timesteps 444400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2222/10000 episodes, total num timesteps 444600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2223/10000 episodes, total num timesteps 444800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2224/10000 episodes, total num timesteps 445000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2225/10000 episodes, total num timesteps 445200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.7389141306002742
team_policy eval average team episode rewards of agent0: 145.0
team_policy eval idv catch total num of agent0: 31
team_policy eval team catch total num: 58
team_policy eval average step individual rewards of agent1: 0.8619226015450846
team_policy eval average team episode rewards of agent1: 145.0
team_policy eval idv catch total num of agent1: 36
team_policy eval team catch total num: 58
team_policy eval average step individual rewards of agent2: 1.3754009740863706
team_policy eval average team episode rewards of agent2: 145.0
team_policy eval idv catch total num of agent2: 56
team_policy eval team catch total num: 58
team_policy eval average step individual rewards of agent3: 0.9452235858423806
team_policy eval average team episode rewards of agent3: 145.0
team_policy eval idv catch total num of agent3: 39
team_policy eval team catch total num: 58
team_policy eval average step individual rewards of agent4: 0.9676336261062497
team_policy eval average team episode rewards of agent4: 145.0
team_policy eval idv catch total num of agent4: 40
team_policy eval team catch total num: 58
idv_policy eval average step individual rewards of agent0: 0.5051390253322562
idv_policy eval average team episode rewards of agent0: 65.0
idv_policy eval idv catch total num of agent0: 22
idv_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent1: 0.3982645904525821
idv_policy eval average team episode rewards of agent1: 65.0
idv_policy eval idv catch total num of agent1: 18
idv_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent2: 0.6099836148854456
idv_policy eval average team episode rewards of agent2: 65.0
idv_policy eval idv catch total num of agent2: 26
idv_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent3: 0.38983154420690025
idv_policy eval average team episode rewards of agent3: 65.0
idv_policy eval idv catch total num of agent3: 18
idv_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent4: 0.3323466956482102
idv_policy eval average team episode rewards of agent4: 65.0
idv_policy eval idv catch total num of agent4: 15
idv_policy eval team catch total num: 26

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2226/10000 episodes, total num timesteps 445400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2227/10000 episodes, total num timesteps 445600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2228/10000 episodes, total num timesteps 445800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2229/10000 episodes, total num timesteps 446000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2230/10000 episodes, total num timesteps 446200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2231/10000 episodes, total num timesteps 446400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2232/10000 episodes, total num timesteps 446600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2233/10000 episodes, total num timesteps 446800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2234/10000 episodes, total num timesteps 447000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2235/10000 episodes, total num timesteps 447200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2236/10000 episodes, total num timesteps 447400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2237/10000 episodes, total num timesteps 447600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2238/10000 episodes, total num timesteps 447800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2239/10000 episodes, total num timesteps 448000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2240/10000 episodes, total num timesteps 448200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2241/10000 episodes, total num timesteps 448400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2242/10000 episodes, total num timesteps 448600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2243/10000 episodes, total num timesteps 448800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2244/10000 episodes, total num timesteps 449000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2245/10000 episodes, total num timesteps 449200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2246/10000 episodes, total num timesteps 449400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2247/10000 episodes, total num timesteps 449600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2248/10000 episodes, total num timesteps 449800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2249/10000 episodes, total num timesteps 450000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2250/10000 episodes, total num timesteps 450200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.7334602600643828
team_policy eval average team episode rewards of agent0: 120.0
team_policy eval idv catch total num of agent0: 31
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent1: 0.5631597203288146
team_policy eval average team episode rewards of agent1: 120.0
team_policy eval idv catch total num of agent1: 24
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent2: 1.1440307106273675
team_policy eval average team episode rewards of agent2: 120.0
team_policy eval idv catch total num of agent2: 47
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent3: 0.813986461507823
team_policy eval average team episode rewards of agent3: 120.0
team_policy eval idv catch total num of agent3: 34
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent4: 0.7375990589765021
team_policy eval average team episode rewards of agent4: 120.0
team_policy eval idv catch total num of agent4: 31
team_policy eval team catch total num: 48
idv_policy eval average step individual rewards of agent0: 0.9743709823592823
idv_policy eval average team episode rewards of agent0: 82.5
idv_policy eval idv catch total num of agent0: 40
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent1: 0.41080091781518385
idv_policy eval average team episode rewards of agent1: 82.5
idv_policy eval idv catch total num of agent1: 18
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent2: 0.8426247234430119
idv_policy eval average team episode rewards of agent2: 82.5
idv_policy eval idv catch total num of agent2: 35
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent3: 0.5613804874038582
idv_policy eval average team episode rewards of agent3: 82.5
idv_policy eval idv catch total num of agent3: 24
idv_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent4: 0.8920339822868661
idv_policy eval average team episode rewards of agent4: 82.5
idv_policy eval idv catch total num of agent4: 37
idv_policy eval team catch total num: 33

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2251/10000 episodes, total num timesteps 450400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2252/10000 episodes, total num timesteps 450600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2253/10000 episodes, total num timesteps 450800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2254/10000 episodes, total num timesteps 451000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2255/10000 episodes, total num timesteps 451200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2256/10000 episodes, total num timesteps 451400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2257/10000 episodes, total num timesteps 451600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2258/10000 episodes, total num timesteps 451800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2259/10000 episodes, total num timesteps 452000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2260/10000 episodes, total num timesteps 452200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2261/10000 episodes, total num timesteps 452400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2262/10000 episodes, total num timesteps 452600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2263/10000 episodes, total num timesteps 452800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2264/10000 episodes, total num timesteps 453000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2265/10000 episodes, total num timesteps 453200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2266/10000 episodes, total num timesteps 453400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2267/10000 episodes, total num timesteps 453600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2268/10000 episodes, total num timesteps 453800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2269/10000 episodes, total num timesteps 454000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2270/10000 episodes, total num timesteps 454200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2271/10000 episodes, total num timesteps 454400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2272/10000 episodes, total num timesteps 454600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2273/10000 episodes, total num timesteps 454800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2274/10000 episodes, total num timesteps 455000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2275/10000 episodes, total num timesteps 455200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.4526719554690866
team_policy eval average team episode rewards of agent0: 72.5
team_policy eval idv catch total num of agent0: 20
team_policy eval team catch total num: 29
team_policy eval average step individual rewards of agent1: 0.4860488131539982
team_policy eval average team episode rewards of agent1: 72.5
team_policy eval idv catch total num of agent1: 21
team_policy eval team catch total num: 29
team_policy eval average step individual rewards of agent2: 0.32810736023800563
team_policy eval average team episode rewards of agent2: 72.5
team_policy eval idv catch total num of agent2: 15
team_policy eval team catch total num: 29
team_policy eval average step individual rewards of agent3: 0.5603335781303121
team_policy eval average team episode rewards of agent3: 72.5
team_policy eval idv catch total num of agent3: 24
team_policy eval team catch total num: 29
team_policy eval average step individual rewards of agent4: 1.2175391183575428
team_policy eval average team episode rewards of agent4: 72.5
team_policy eval idv catch total num of agent4: 50
team_policy eval team catch total num: 29
idv_policy eval average step individual rewards of agent0: 0.8342622473069378
idv_policy eval average team episode rewards of agent0: 157.5
idv_policy eval idv catch total num of agent0: 35
idv_policy eval team catch total num: 63
idv_policy eval average step individual rewards of agent1: 1.5768816599692566
idv_policy eval average team episode rewards of agent1: 157.5
idv_policy eval idv catch total num of agent1: 64
idv_policy eval team catch total num: 63
idv_policy eval average step individual rewards of agent2: 1.0530578150964305
idv_policy eval average team episode rewards of agent2: 157.5
idv_policy eval idv catch total num of agent2: 43
idv_policy eval team catch total num: 63
idv_policy eval average step individual rewards of agent3: 1.1350151282687484
idv_policy eval average team episode rewards of agent3: 157.5
idv_policy eval idv catch total num of agent3: 47
idv_policy eval team catch total num: 63
idv_policy eval average step individual rewards of agent4: 0.8846892161374308
idv_policy eval average team episode rewards of agent4: 157.5
idv_policy eval idv catch total num of agent4: 37
idv_policy eval team catch total num: 63

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2276/10000 episodes, total num timesteps 455400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2277/10000 episodes, total num timesteps 455600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2278/10000 episodes, total num timesteps 455800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2279/10000 episodes, total num timesteps 456000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2280/10000 episodes, total num timesteps 456200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2281/10000 episodes, total num timesteps 456400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2282/10000 episodes, total num timesteps 456600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2283/10000 episodes, total num timesteps 456800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2284/10000 episodes, total num timesteps 457000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2285/10000 episodes, total num timesteps 457200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2286/10000 episodes, total num timesteps 457400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2287/10000 episodes, total num timesteps 457600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2288/10000 episodes, total num timesteps 457800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2289/10000 episodes, total num timesteps 458000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2290/10000 episodes, total num timesteps 458200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2291/10000 episodes, total num timesteps 458400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2292/10000 episodes, total num timesteps 458600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2293/10000 episodes, total num timesteps 458800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2294/10000 episodes, total num timesteps 459000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2295/10000 episodes, total num timesteps 459200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2296/10000 episodes, total num timesteps 459400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2297/10000 episodes, total num timesteps 459600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2298/10000 episodes, total num timesteps 459800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2299/10000 episodes, total num timesteps 460000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2300/10000 episodes, total num timesteps 460200/2000000, FPS 326.

team_policy eval average step individual rewards of agent0: 0.7710784325064464
team_policy eval average team episode rewards of agent0: 97.5
team_policy eval idv catch total num of agent0: 32
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent1: 0.6960342529360701
team_policy eval average team episode rewards of agent1: 97.5
team_policy eval idv catch total num of agent1: 29
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent2: 0.9598903230667131
team_policy eval average team episode rewards of agent2: 97.5
team_policy eval idv catch total num of agent2: 40
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent3: 0.761906440393662
team_policy eval average team episode rewards of agent3: 97.5
team_policy eval idv catch total num of agent3: 32
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent4: 0.566794556700231
team_policy eval average team episode rewards of agent4: 97.5
team_policy eval idv catch total num of agent4: 24
team_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent0: 0.5579825464847726
idv_policy eval average team episode rewards of agent0: 117.5
idv_policy eval idv catch total num of agent0: 24
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent1: 0.7139347044993535
idv_policy eval average team episode rewards of agent1: 117.5
idv_policy eval idv catch total num of agent1: 30
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent2: 0.9966501577677433
idv_policy eval average team episode rewards of agent2: 117.5
idv_policy eval idv catch total num of agent2: 41
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent3: 1.2208063619341314
idv_policy eval average team episode rewards of agent3: 117.5
idv_policy eval idv catch total num of agent3: 50
idv_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent4: 0.9392321213251286
idv_policy eval average team episode rewards of agent4: 117.5
idv_policy eval idv catch total num of agent4: 39
idv_policy eval team catch total num: 47

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2301/10000 episodes, total num timesteps 460400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2302/10000 episodes, total num timesteps 460600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2303/10000 episodes, total num timesteps 460800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2304/10000 episodes, total num timesteps 461000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2305/10000 episodes, total num timesteps 461200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2306/10000 episodes, total num timesteps 461400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2307/10000 episodes, total num timesteps 461600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2308/10000 episodes, total num timesteps 461800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2309/10000 episodes, total num timesteps 462000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2310/10000 episodes, total num timesteps 462200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2311/10000 episodes, total num timesteps 462400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2312/10000 episodes, total num timesteps 462600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2313/10000 episodes, total num timesteps 462800/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2314/10000 episodes, total num timesteps 463000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2315/10000 episodes, total num timesteps 463200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2316/10000 episodes, total num timesteps 463400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2317/10000 episodes, total num timesteps 463600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2318/10000 episodes, total num timesteps 463800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2319/10000 episodes, total num timesteps 464000/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2320/10000 episodes, total num timesteps 464200/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2321/10000 episodes, total num timesteps 464400/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2322/10000 episodes, total num timesteps 464600/2000000, FPS 326.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2323/10000 episodes, total num timesteps 464800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2324/10000 episodes, total num timesteps 465000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2325/10000 episodes, total num timesteps 465200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 0.9704219924112405
team_policy eval average team episode rewards of agent0: 107.5
team_policy eval idv catch total num of agent0: 40
team_policy eval team catch total num: 43
team_policy eval average step individual rewards of agent1: 0.8794037208737936
team_policy eval average team episode rewards of agent1: 107.5
team_policy eval idv catch total num of agent1: 37
team_policy eval team catch total num: 43
team_policy eval average step individual rewards of agent2: 0.6140198186155423
team_policy eval average team episode rewards of agent2: 107.5
team_policy eval idv catch total num of agent2: 26
team_policy eval team catch total num: 43
team_policy eval average step individual rewards of agent3: 0.5629618359868372
team_policy eval average team episode rewards of agent3: 107.5
team_policy eval idv catch total num of agent3: 24
team_policy eval team catch total num: 43
team_policy eval average step individual rewards of agent4: 0.8467560740661036
team_policy eval average team episode rewards of agent4: 107.5
team_policy eval idv catch total num of agent4: 35
team_policy eval team catch total num: 43
idv_policy eval average step individual rewards of agent0: 0.891733519695208
idv_policy eval average team episode rewards of agent0: 125.0
idv_policy eval idv catch total num of agent0: 37
idv_policy eval team catch total num: 50
idv_policy eval average step individual rewards of agent1: 0.6872512919289643
idv_policy eval average team episode rewards of agent1: 125.0
idv_policy eval idv catch total num of agent1: 29
idv_policy eval team catch total num: 50
idv_policy eval average step individual rewards of agent2: 0.8886006791468705
idv_policy eval average team episode rewards of agent2: 125.0
idv_policy eval idv catch total num of agent2: 37
idv_policy eval team catch total num: 50
idv_policy eval average step individual rewards of agent3: 1.0650140124540015
idv_policy eval average team episode rewards of agent3: 125.0
idv_policy eval idv catch total num of agent3: 44
idv_policy eval team catch total num: 50
idv_policy eval average step individual rewards of agent4: 0.7674186732800311
idv_policy eval average team episode rewards of agent4: 125.0
idv_policy eval idv catch total num of agent4: 32
idv_policy eval team catch total num: 50

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2326/10000 episodes, total num timesteps 465400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2327/10000 episodes, total num timesteps 465600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2328/10000 episodes, total num timesteps 465800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2329/10000 episodes, total num timesteps 466000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2330/10000 episodes, total num timesteps 466200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2331/10000 episodes, total num timesteps 466400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2332/10000 episodes, total num timesteps 466600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2333/10000 episodes, total num timesteps 466800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2334/10000 episodes, total num timesteps 467000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2335/10000 episodes, total num timesteps 467200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2336/10000 episodes, total num timesteps 467400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2337/10000 episodes, total num timesteps 467600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2338/10000 episodes, total num timesteps 467800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2339/10000 episodes, total num timesteps 468000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2340/10000 episodes, total num timesteps 468200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2341/10000 episodes, total num timesteps 468400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2342/10000 episodes, total num timesteps 468600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2343/10000 episodes, total num timesteps 468800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2344/10000 episodes, total num timesteps 469000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2345/10000 episodes, total num timesteps 469200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2346/10000 episodes, total num timesteps 469400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2347/10000 episodes, total num timesteps 469600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2348/10000 episodes, total num timesteps 469800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2349/10000 episodes, total num timesteps 470000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2350/10000 episodes, total num timesteps 470200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 0.8360743344549811
team_policy eval average team episode rewards of agent0: 92.5
team_policy eval idv catch total num of agent0: 35
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent1: 0.6567386634838738
team_policy eval average team episode rewards of agent1: 92.5
team_policy eval idv catch total num of agent1: 28
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent2: 0.8155003342428554
team_policy eval average team episode rewards of agent2: 92.5
team_policy eval idv catch total num of agent2: 34
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent3: 0.5623388521204599
team_policy eval average team episode rewards of agent3: 92.5
team_policy eval idv catch total num of agent3: 24
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent4: 0.8671108474968389
team_policy eval average team episode rewards of agent4: 92.5
team_policy eval idv catch total num of agent4: 36
team_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent0: 0.7897418876192813
idv_policy eval average team episode rewards of agent0: 75.0
idv_policy eval idv catch total num of agent0: 33
idv_policy eval team catch total num: 30
idv_policy eval average step individual rewards of agent1: 0.5769493930830238
idv_policy eval average team episode rewards of agent1: 75.0
idv_policy eval idv catch total num of agent1: 25
idv_policy eval team catch total num: 30
idv_policy eval average step individual rewards of agent2: 0.34952122056805024
idv_policy eval average team episode rewards of agent2: 75.0
idv_policy eval idv catch total num of agent2: 16
idv_policy eval team catch total num: 30
idv_policy eval average step individual rewards of agent3: 0.688795836384898
idv_policy eval average team episode rewards of agent3: 75.0
idv_policy eval idv catch total num of agent3: 29
idv_policy eval team catch total num: 30
idv_policy eval average step individual rewards of agent4: 0.5082427591320062
idv_policy eval average team episode rewards of agent4: 75.0
idv_policy eval idv catch total num of agent4: 22
idv_policy eval team catch total num: 30

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2351/10000 episodes, total num timesteps 470400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2352/10000 episodes, total num timesteps 470600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2353/10000 episodes, total num timesteps 470800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2354/10000 episodes, total num timesteps 471000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2355/10000 episodes, total num timesteps 471200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2356/10000 episodes, total num timesteps 471400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2357/10000 episodes, total num timesteps 471600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2358/10000 episodes, total num timesteps 471800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2359/10000 episodes, total num timesteps 472000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2360/10000 episodes, total num timesteps 472200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2361/10000 episodes, total num timesteps 472400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2362/10000 episodes, total num timesteps 472600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2363/10000 episodes, total num timesteps 472800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2364/10000 episodes, total num timesteps 473000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2365/10000 episodes, total num timesteps 473200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2366/10000 episodes, total num timesteps 473400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2367/10000 episodes, total num timesteps 473600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2368/10000 episodes, total num timesteps 473800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2369/10000 episodes, total num timesteps 474000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2370/10000 episodes, total num timesteps 474200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2371/10000 episodes, total num timesteps 474400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2372/10000 episodes, total num timesteps 474600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2373/10000 episodes, total num timesteps 474800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2374/10000 episodes, total num timesteps 475000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2375/10000 episodes, total num timesteps 475200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 0.46700271468055266
team_policy eval average team episode rewards of agent0: 95.0
team_policy eval idv catch total num of agent0: 20
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent1: 0.994571190985312
team_policy eval average team episode rewards of agent1: 95.0
team_policy eval idv catch total num of agent1: 41
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent2: 0.4368239364129644
team_policy eval average team episode rewards of agent2: 95.0
team_policy eval idv catch total num of agent2: 19
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent3: 1.0460161320998427
team_policy eval average team episode rewards of agent3: 95.0
team_policy eval idv catch total num of agent3: 43
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent4: 0.660642773695044
team_policy eval average team episode rewards of agent4: 95.0
team_policy eval idv catch total num of agent4: 28
team_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent0: 1.124838463930641
idv_policy eval average team episode rewards of agent0: 147.5
idv_policy eval idv catch total num of agent0: 46
idv_policy eval team catch total num: 59
idv_policy eval average step individual rewards of agent1: 0.7639804121575815
idv_policy eval average team episode rewards of agent1: 147.5
idv_policy eval idv catch total num of agent1: 32
idv_policy eval team catch total num: 59
idv_policy eval average step individual rewards of agent2: 1.0168430688764838
idv_policy eval average team episode rewards of agent2: 147.5
idv_policy eval idv catch total num of agent2: 42
idv_policy eval team catch total num: 59
idv_policy eval average step individual rewards of agent3: 1.116728897314878
idv_policy eval average team episode rewards of agent3: 147.5
idv_policy eval idv catch total num of agent3: 46
idv_policy eval team catch total num: 59
idv_policy eval average step individual rewards of agent4: 1.0742818481473622
idv_policy eval average team episode rewards of agent4: 147.5
idv_policy eval idv catch total num of agent4: 44
idv_policy eval team catch total num: 59

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2376/10000 episodes, total num timesteps 475400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2377/10000 episodes, total num timesteps 475600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2378/10000 episodes, total num timesteps 475800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2379/10000 episodes, total num timesteps 476000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2380/10000 episodes, total num timesteps 476200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2381/10000 episodes, total num timesteps 476400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2382/10000 episodes, total num timesteps 476600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2383/10000 episodes, total num timesteps 476800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2384/10000 episodes, total num timesteps 477000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2385/10000 episodes, total num timesteps 477200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2386/10000 episodes, total num timesteps 477400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2387/10000 episodes, total num timesteps 477600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2388/10000 episodes, total num timesteps 477800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2389/10000 episodes, total num timesteps 478000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2390/10000 episodes, total num timesteps 478200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2391/10000 episodes, total num timesteps 478400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2392/10000 episodes, total num timesteps 478600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2393/10000 episodes, total num timesteps 478800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2394/10000 episodes, total num timesteps 479000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2395/10000 episodes, total num timesteps 479200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2396/10000 episodes, total num timesteps 479400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2397/10000 episodes, total num timesteps 479600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2398/10000 episodes, total num timesteps 479800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2399/10000 episodes, total num timesteps 480000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2400/10000 episodes, total num timesteps 480200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 1.0148042133809818
team_policy eval average team episode rewards of agent0: 82.5
team_policy eval idv catch total num of agent0: 42
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent1: 0.5412120694692458
team_policy eval average team episode rewards of agent1: 82.5
team_policy eval idv catch total num of agent1: 23
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent2: 0.4596613116895547
team_policy eval average team episode rewards of agent2: 82.5
team_policy eval idv catch total num of agent2: 20
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent3: 0.7470094990392476
team_policy eval average team episode rewards of agent3: 82.5
team_policy eval idv catch total num of agent3: 31
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent4: 0.5647418954062179
team_policy eval average team episode rewards of agent4: 82.5
team_policy eval idv catch total num of agent4: 24
team_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent0: 0.2809846880942893
idv_policy eval average team episode rewards of agent0: 90.0
idv_policy eval idv catch total num of agent0: 13
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent1: 0.5833632651640981
idv_policy eval average team episode rewards of agent1: 90.0
idv_policy eval idv catch total num of agent1: 25
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent2: 0.6887479481417274
idv_policy eval average team episode rewards of agent2: 90.0
idv_policy eval idv catch total num of agent2: 29
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent3: 0.7943533169058781
idv_policy eval average team episode rewards of agent3: 90.0
idv_policy eval idv catch total num of agent3: 33
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent4: 0.7673806447476369
idv_policy eval average team episode rewards of agent4: 90.0
idv_policy eval idv catch total num of agent4: 32
idv_policy eval team catch total num: 36

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2401/10000 episodes, total num timesteps 480400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2402/10000 episodes, total num timesteps 480600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2403/10000 episodes, total num timesteps 480800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2404/10000 episodes, total num timesteps 481000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2405/10000 episodes, total num timesteps 481200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2406/10000 episodes, total num timesteps 481400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2407/10000 episodes, total num timesteps 481600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2408/10000 episodes, total num timesteps 481800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2409/10000 episodes, total num timesteps 482000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2410/10000 episodes, total num timesteps 482200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2411/10000 episodes, total num timesteps 482400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2412/10000 episodes, total num timesteps 482600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2413/10000 episodes, total num timesteps 482800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2414/10000 episodes, total num timesteps 483000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2415/10000 episodes, total num timesteps 483200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2416/10000 episodes, total num timesteps 483400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2417/10000 episodes, total num timesteps 483600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2418/10000 episodes, total num timesteps 483800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2419/10000 episodes, total num timesteps 484000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2420/10000 episodes, total num timesteps 484200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2421/10000 episodes, total num timesteps 484400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2422/10000 episodes, total num timesteps 484600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2423/10000 episodes, total num timesteps 484800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2424/10000 episodes, total num timesteps 485000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2425/10000 episodes, total num timesteps 485200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 0.7305530348472385
team_policy eval average team episode rewards of agent0: 105.0
team_policy eval idv catch total num of agent0: 31
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent1: 0.7594171120894121
team_policy eval average team episode rewards of agent1: 105.0
team_policy eval idv catch total num of agent1: 32
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent2: 0.9312641555588693
team_policy eval average team episode rewards of agent2: 105.0
team_policy eval idv catch total num of agent2: 39
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent3: 0.7361100423230641
team_policy eval average team episode rewards of agent3: 105.0
team_policy eval idv catch total num of agent3: 31
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent4: 0.663172926997886
team_policy eval average team episode rewards of agent4: 105.0
team_policy eval idv catch total num of agent4: 28
team_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent0: 0.412768332683292
idv_policy eval average team episode rewards of agent0: 95.0
idv_policy eval idv catch total num of agent0: 18
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent1: 0.9486371218192658
idv_policy eval average team episode rewards of agent1: 95.0
idv_policy eval idv catch total num of agent1: 39
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent2: 0.5555940791908912
idv_policy eval average team episode rewards of agent2: 95.0
idv_policy eval idv catch total num of agent2: 24
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent3: 0.7155148293403443
idv_policy eval average team episode rewards of agent3: 95.0
idv_policy eval idv catch total num of agent3: 30
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent4: 0.8722169758911786
idv_policy eval average team episode rewards of agent4: 95.0
idv_policy eval idv catch total num of agent4: 36
idv_policy eval team catch total num: 38

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2426/10000 episodes, total num timesteps 485400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2427/10000 episodes, total num timesteps 485600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2428/10000 episodes, total num timesteps 485800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2429/10000 episodes, total num timesteps 486000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2430/10000 episodes, total num timesteps 486200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2431/10000 episodes, total num timesteps 486400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2432/10000 episodes, total num timesteps 486600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2433/10000 episodes, total num timesteps 486800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2434/10000 episodes, total num timesteps 487000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2435/10000 episodes, total num timesteps 487200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2436/10000 episodes, total num timesteps 487400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2437/10000 episodes, total num timesteps 487600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2438/10000 episodes, total num timesteps 487800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2439/10000 episodes, total num timesteps 488000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2440/10000 episodes, total num timesteps 488200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2441/10000 episodes, total num timesteps 488400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2442/10000 episodes, total num timesteps 488600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2443/10000 episodes, total num timesteps 488800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2444/10000 episodes, total num timesteps 489000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2445/10000 episodes, total num timesteps 489200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2446/10000 episodes, total num timesteps 489400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2447/10000 episodes, total num timesteps 489600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2448/10000 episodes, total num timesteps 489800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2449/10000 episodes, total num timesteps 490000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2450/10000 episodes, total num timesteps 490200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 0.7313344848038744
team_policy eval average team episode rewards of agent0: 127.5
team_policy eval idv catch total num of agent0: 31
team_policy eval team catch total num: 51
team_policy eval average step individual rewards of agent1: 1.09891708724583
team_policy eval average team episode rewards of agent1: 127.5
team_policy eval idv catch total num of agent1: 45
team_policy eval team catch total num: 51
team_policy eval average step individual rewards of agent2: 1.0196392096808402
team_policy eval average team episode rewards of agent2: 127.5
team_policy eval idv catch total num of agent2: 42
team_policy eval team catch total num: 51
team_policy eval average step individual rewards of agent3: 0.8818794333778217
team_policy eval average team episode rewards of agent3: 127.5
team_policy eval idv catch total num of agent3: 37
team_policy eval team catch total num: 51
team_policy eval average step individual rewards of agent4: 0.6533060612897098
team_policy eval average team episode rewards of agent4: 127.5
team_policy eval idv catch total num of agent4: 28
team_policy eval team catch total num: 51
idv_policy eval average step individual rewards of agent0: 0.5132526267401439
idv_policy eval average team episode rewards of agent0: 80.0
idv_policy eval idv catch total num of agent0: 22
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent1: 0.6410435423542602
idv_policy eval average team episode rewards of agent1: 80.0
idv_policy eval idv catch total num of agent1: 27
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent2: 0.8167122864549476
idv_policy eval average team episode rewards of agent2: 80.0
idv_policy eval idv catch total num of agent2: 34
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent3: 0.9183125996864827
idv_policy eval average team episode rewards of agent3: 80.0
idv_policy eval idv catch total num of agent3: 38
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent4: 0.4496761160695706
idv_policy eval average team episode rewards of agent4: 80.0
idv_policy eval idv catch total num of agent4: 20
idv_policy eval team catch total num: 32

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2451/10000 episodes, total num timesteps 490400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2452/10000 episodes, total num timesteps 490600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2453/10000 episodes, total num timesteps 490800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2454/10000 episodes, total num timesteps 491000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2455/10000 episodes, total num timesteps 491200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2456/10000 episodes, total num timesteps 491400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2457/10000 episodes, total num timesteps 491600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2458/10000 episodes, total num timesteps 491800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2459/10000 episodes, total num timesteps 492000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2460/10000 episodes, total num timesteps 492200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2461/10000 episodes, total num timesteps 492400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2462/10000 episodes, total num timesteps 492600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2463/10000 episodes, total num timesteps 492800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2464/10000 episodes, total num timesteps 493000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2465/10000 episodes, total num timesteps 493200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2466/10000 episodes, total num timesteps 493400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2467/10000 episodes, total num timesteps 493600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2468/10000 episodes, total num timesteps 493800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2469/10000 episodes, total num timesteps 494000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2470/10000 episodes, total num timesteps 494200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2471/10000 episodes, total num timesteps 494400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2472/10000 episodes, total num timesteps 494600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2473/10000 episodes, total num timesteps 494800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2474/10000 episodes, total num timesteps 495000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2475/10000 episodes, total num timesteps 495200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 0.6631791695037899
team_policy eval average team episode rewards of agent0: 95.0
team_policy eval idv catch total num of agent0: 28
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent1: 0.8427762790562753
team_policy eval average team episode rewards of agent1: 95.0
team_policy eval idv catch total num of agent1: 35
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent2: 0.3576373160634415
team_policy eval average team episode rewards of agent2: 95.0
team_policy eval idv catch total num of agent2: 16
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent3: 1.1721173443507795
team_policy eval average team episode rewards of agent3: 95.0
team_policy eval idv catch total num of agent3: 48
team_policy eval team catch total num: 38
team_policy eval average step individual rewards of agent4: 0.7834047066781636
team_policy eval average team episode rewards of agent4: 95.0
team_policy eval idv catch total num of agent4: 33
team_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent0: 1.1232740524934874
idv_policy eval average team episode rewards of agent0: 110.0
idv_policy eval idv catch total num of agent0: 46
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent1: 0.9200627223152993
idv_policy eval average team episode rewards of agent1: 110.0
idv_policy eval idv catch total num of agent1: 38
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent2: 0.9632147263342139
idv_policy eval average team episode rewards of agent2: 110.0
idv_policy eval idv catch total num of agent2: 40
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent3: 0.7370285421572191
idv_policy eval average team episode rewards of agent3: 110.0
idv_policy eval idv catch total num of agent3: 31
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent4: 0.7696064853842647
idv_policy eval average team episode rewards of agent4: 110.0
idv_policy eval idv catch total num of agent4: 32
idv_policy eval team catch total num: 44

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2476/10000 episodes, total num timesteps 495400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2477/10000 episodes, total num timesteps 495600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2478/10000 episodes, total num timesteps 495800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2479/10000 episodes, total num timesteps 496000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2480/10000 episodes, total num timesteps 496200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2481/10000 episodes, total num timesteps 496400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2482/10000 episodes, total num timesteps 496600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2483/10000 episodes, total num timesteps 496800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2484/10000 episodes, total num timesteps 497000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2485/10000 episodes, total num timesteps 497200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2486/10000 episodes, total num timesteps 497400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2487/10000 episodes, total num timesteps 497600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2488/10000 episodes, total num timesteps 497800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2489/10000 episodes, total num timesteps 498000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2490/10000 episodes, total num timesteps 498200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2491/10000 episodes, total num timesteps 498400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2492/10000 episodes, total num timesteps 498600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2493/10000 episodes, total num timesteps 498800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2494/10000 episodes, total num timesteps 499000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2495/10000 episodes, total num timesteps 499200/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2496/10000 episodes, total num timesteps 499400/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2497/10000 episodes, total num timesteps 499600/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2498/10000 episodes, total num timesteps 499800/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2499/10000 episodes, total num timesteps 500000/2000000, FPS 325.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2500/10000 episodes, total num timesteps 500200/2000000, FPS 325.

team_policy eval average step individual rewards of agent0: 0.9400302607899633
team_policy eval average team episode rewards of agent0: 122.5
team_policy eval idv catch total num of agent0: 39
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent1: 1.1439047507475302
team_policy eval average team episode rewards of agent1: 122.5
team_policy eval idv catch total num of agent1: 47
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent2: 1.0183487826073616
team_policy eval average team episode rewards of agent2: 122.5
team_policy eval idv catch total num of agent2: 42
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent3: 1.1369694658145022
team_policy eval average team episode rewards of agent3: 122.5
team_policy eval idv catch total num of agent3: 47
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent4: 0.7342770741842787
team_policy eval average team episode rewards of agent4: 122.5
team_policy eval idv catch total num of agent4: 31
team_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent0: 0.4587592070729254
idv_policy eval average team episode rewards of agent0: 100.0
idv_policy eval idv catch total num of agent0: 20
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent1: 1.1188258230224417
idv_policy eval average team episode rewards of agent1: 100.0
idv_policy eval idv catch total num of agent1: 46
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent2: 0.7388638705303444
idv_policy eval average team episode rewards of agent2: 100.0
idv_policy eval idv catch total num of agent2: 31
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent3: 0.9159181675949154
idv_policy eval average team episode rewards of agent3: 100.0
idv_policy eval idv catch total num of agent3: 38
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent4: 0.4292029667586666
idv_policy eval average team episode rewards of agent4: 100.0
idv_policy eval idv catch total num of agent4: 19
idv_policy eval team catch total num: 40

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2501/10000 episodes, total num timesteps 500400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2502/10000 episodes, total num timesteps 500600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2503/10000 episodes, total num timesteps 500800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2504/10000 episodes, total num timesteps 501000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2505/10000 episodes, total num timesteps 501200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2506/10000 episodes, total num timesteps 501400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2507/10000 episodes, total num timesteps 501600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2508/10000 episodes, total num timesteps 501800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2509/10000 episodes, total num timesteps 502000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2510/10000 episodes, total num timesteps 502200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2511/10000 episodes, total num timesteps 502400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2512/10000 episodes, total num timesteps 502600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2513/10000 episodes, total num timesteps 502800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2514/10000 episodes, total num timesteps 503000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2515/10000 episodes, total num timesteps 503200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2516/10000 episodes, total num timesteps 503400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2517/10000 episodes, total num timesteps 503600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2518/10000 episodes, total num timesteps 503800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2519/10000 episodes, total num timesteps 504000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2520/10000 episodes, total num timesteps 504200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2521/10000 episodes, total num timesteps 504400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2522/10000 episodes, total num timesteps 504600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2523/10000 episodes, total num timesteps 504800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2524/10000 episodes, total num timesteps 505000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2525/10000 episodes, total num timesteps 505200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 1.1495442046349462
team_policy eval average team episode rewards of agent0: 117.5
team_policy eval idv catch total num of agent0: 47
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent1: 1.04341566525277
team_policy eval average team episode rewards of agent1: 117.5
team_policy eval idv catch total num of agent1: 43
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent2: 1.0645763880292016
team_policy eval average team episode rewards of agent2: 117.5
team_policy eval idv catch total num of agent2: 44
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent3: 0.5856283306988448
team_policy eval average team episode rewards of agent3: 117.5
team_policy eval idv catch total num of agent3: 25
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent4: 1.0095766267031563
team_policy eval average team episode rewards of agent4: 117.5
team_policy eval idv catch total num of agent4: 42
team_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent0: 1.126500345292076
idv_policy eval average team episode rewards of agent0: 160.0
idv_policy eval idv catch total num of agent0: 46
idv_policy eval team catch total num: 64
idv_policy eval average step individual rewards of agent1: 1.3201640989563195
idv_policy eval average team episode rewards of agent1: 160.0
idv_policy eval idv catch total num of agent1: 54
idv_policy eval team catch total num: 64
idv_policy eval average step individual rewards of agent2: 0.7534649635028612
idv_policy eval average team episode rewards of agent2: 160.0
idv_policy eval idv catch total num of agent2: 32
idv_policy eval team catch total num: 64
idv_policy eval average step individual rewards of agent3: 1.5788534998473387
idv_policy eval average team episode rewards of agent3: 160.0
idv_policy eval idv catch total num of agent3: 64
idv_policy eval team catch total num: 64
idv_policy eval average step individual rewards of agent4: 0.8952185944136343
idv_policy eval average team episode rewards of agent4: 160.0
idv_policy eval idv catch total num of agent4: 37
idv_policy eval team catch total num: 64

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2526/10000 episodes, total num timesteps 505400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2527/10000 episodes, total num timesteps 505600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2528/10000 episodes, total num timesteps 505800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2529/10000 episodes, total num timesteps 506000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2530/10000 episodes, total num timesteps 506200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2531/10000 episodes, total num timesteps 506400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2532/10000 episodes, total num timesteps 506600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2533/10000 episodes, total num timesteps 506800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2534/10000 episodes, total num timesteps 507000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2535/10000 episodes, total num timesteps 507200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2536/10000 episodes, total num timesteps 507400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2537/10000 episodes, total num timesteps 507600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2538/10000 episodes, total num timesteps 507800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2539/10000 episodes, total num timesteps 508000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2540/10000 episodes, total num timesteps 508200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2541/10000 episodes, total num timesteps 508400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2542/10000 episodes, total num timesteps 508600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2543/10000 episodes, total num timesteps 508800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2544/10000 episodes, total num timesteps 509000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2545/10000 episodes, total num timesteps 509200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2546/10000 episodes, total num timesteps 509400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2547/10000 episodes, total num timesteps 509600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2548/10000 episodes, total num timesteps 509800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2549/10000 episodes, total num timesteps 510000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2550/10000 episodes, total num timesteps 510200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 1.2434675584198562
team_policy eval average team episode rewards of agent0: 135.0
team_policy eval idv catch total num of agent0: 51
team_policy eval team catch total num: 54
team_policy eval average step individual rewards of agent1: 0.6097875359381224
team_policy eval average team episode rewards of agent1: 135.0
team_policy eval idv catch total num of agent1: 26
team_policy eval team catch total num: 54
team_policy eval average step individual rewards of agent2: 0.6403732766922016
team_policy eval average team episode rewards of agent2: 135.0
team_policy eval idv catch total num of agent2: 27
team_policy eval team catch total num: 54
team_policy eval average step individual rewards of agent3: 1.3198943695651177
team_policy eval average team episode rewards of agent3: 135.0
team_policy eval idv catch total num of agent3: 54
team_policy eval team catch total num: 54
team_policy eval average step individual rewards of agent4: 0.943759407912705
team_policy eval average team episode rewards of agent4: 135.0
team_policy eval idv catch total num of agent4: 39
team_policy eval team catch total num: 54
idv_policy eval average step individual rewards of agent0: 0.7115616166537113
idv_policy eval average team episode rewards of agent0: 105.0
idv_policy eval idv catch total num of agent0: 30
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent1: 0.7053327127374304
idv_policy eval average team episode rewards of agent1: 105.0
idv_policy eval idv catch total num of agent1: 30
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent2: 0.7611306529416428
idv_policy eval average team episode rewards of agent2: 105.0
idv_policy eval idv catch total num of agent2: 32
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent3: 0.8141530948830374
idv_policy eval average team episode rewards of agent3: 105.0
idv_policy eval idv catch total num of agent3: 34
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent4: 0.6069357350811633
idv_policy eval average team episode rewards of agent4: 105.0
idv_policy eval idv catch total num of agent4: 26
idv_policy eval team catch total num: 42

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2551/10000 episodes, total num timesteps 510400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2552/10000 episodes, total num timesteps 510600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2553/10000 episodes, total num timesteps 510800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2554/10000 episodes, total num timesteps 511000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2555/10000 episodes, total num timesteps 511200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2556/10000 episodes, total num timesteps 511400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2557/10000 episodes, total num timesteps 511600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2558/10000 episodes, total num timesteps 511800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2559/10000 episodes, total num timesteps 512000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2560/10000 episodes, total num timesteps 512200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2561/10000 episodes, total num timesteps 512400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2562/10000 episodes, total num timesteps 512600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2563/10000 episodes, total num timesteps 512800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2564/10000 episodes, total num timesteps 513000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2565/10000 episodes, total num timesteps 513200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2566/10000 episodes, total num timesteps 513400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2567/10000 episodes, total num timesteps 513600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2568/10000 episodes, total num timesteps 513800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2569/10000 episodes, total num timesteps 514000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2570/10000 episodes, total num timesteps 514200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2571/10000 episodes, total num timesteps 514400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2572/10000 episodes, total num timesteps 514600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2573/10000 episodes, total num timesteps 514800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2574/10000 episodes, total num timesteps 515000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2575/10000 episodes, total num timesteps 515200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.8706760786994883
team_policy eval average team episode rewards of agent0: 87.5
team_policy eval idv catch total num of agent0: 36
team_policy eval team catch total num: 35
team_policy eval average step individual rewards of agent1: 0.6646913418978673
team_policy eval average team episode rewards of agent1: 87.5
team_policy eval idv catch total num of agent1: 28
team_policy eval team catch total num: 35
team_policy eval average step individual rewards of agent2: 1.0964138279232918
team_policy eval average team episode rewards of agent2: 87.5
team_policy eval idv catch total num of agent2: 45
team_policy eval team catch total num: 35
team_policy eval average step individual rewards of agent3: 0.9183533913637296
team_policy eval average team episode rewards of agent3: 87.5
team_policy eval idv catch total num of agent3: 38
team_policy eval team catch total num: 35
team_policy eval average step individual rewards of agent4: 0.3361282810457091
team_policy eval average team episode rewards of agent4: 87.5
team_policy eval idv catch total num of agent4: 15
team_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent0: 0.6936642500511926
idv_policy eval average team episode rewards of agent0: 112.5
idv_policy eval idv catch total num of agent0: 29
idv_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent1: 0.894875932728382
idv_policy eval average team episode rewards of agent1: 112.5
idv_policy eval idv catch total num of agent1: 37
idv_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent2: 1.2766850094469853
idv_policy eval average team episode rewards of agent2: 112.5
idv_policy eval idv catch total num of agent2: 52
idv_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent3: 0.8135128998076806
idv_policy eval average team episode rewards of agent3: 112.5
idv_policy eval idv catch total num of agent3: 34
idv_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent4: 0.4848232889922032
idv_policy eval average team episode rewards of agent4: 112.5
idv_policy eval idv catch total num of agent4: 21
idv_policy eval team catch total num: 45

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2576/10000 episodes, total num timesteps 515400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2577/10000 episodes, total num timesteps 515600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2578/10000 episodes, total num timesteps 515800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2579/10000 episodes, total num timesteps 516000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2580/10000 episodes, total num timesteps 516200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2581/10000 episodes, total num timesteps 516400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2582/10000 episodes, total num timesteps 516600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2583/10000 episodes, total num timesteps 516800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2584/10000 episodes, total num timesteps 517000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2585/10000 episodes, total num timesteps 517200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2586/10000 episodes, total num timesteps 517400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2587/10000 episodes, total num timesteps 517600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2588/10000 episodes, total num timesteps 517800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2589/10000 episodes, total num timesteps 518000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2590/10000 episodes, total num timesteps 518200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2591/10000 episodes, total num timesteps 518400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2592/10000 episodes, total num timesteps 518600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2593/10000 episodes, total num timesteps 518800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2594/10000 episodes, total num timesteps 519000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2595/10000 episodes, total num timesteps 519200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2596/10000 episodes, total num timesteps 519400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2597/10000 episodes, total num timesteps 519600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2598/10000 episodes, total num timesteps 519800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2599/10000 episodes, total num timesteps 520000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2600/10000 episodes, total num timesteps 520200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 1.1226694767162337
team_policy eval average team episode rewards of agent0: 105.0
team_policy eval idv catch total num of agent0: 46
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent1: 0.4402442298412666
team_policy eval average team episode rewards of agent1: 105.0
team_policy eval idv catch total num of agent1: 20
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent2: 0.473448773502567
team_policy eval average team episode rewards of agent2: 105.0
team_policy eval idv catch total num of agent2: 21
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent3: 0.8129566007548823
team_policy eval average team episode rewards of agent3: 105.0
team_policy eval idv catch total num of agent3: 34
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent4: 0.8824617328818277
team_policy eval average team episode rewards of agent4: 105.0
team_policy eval idv catch total num of agent4: 37
team_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent0: 0.7593220984186828
idv_policy eval average team episode rewards of agent0: 110.0
idv_policy eval idv catch total num of agent0: 32
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent1: 0.8079364641069847
idv_policy eval average team episode rewards of agent1: 110.0
idv_policy eval idv catch total num of agent1: 34
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent2: 0.8152536877117216
idv_policy eval average team episode rewards of agent2: 110.0
idv_policy eval idv catch total num of agent2: 34
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent3: 0.7130718263554232
idv_policy eval average team episode rewards of agent3: 110.0
idv_policy eval idv catch total num of agent3: 30
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent4: 1.0494764371253467
idv_policy eval average team episode rewards of agent4: 110.0
idv_policy eval idv catch total num of agent4: 43
idv_policy eval team catch total num: 44

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2601/10000 episodes, total num timesteps 520400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2602/10000 episodes, total num timesteps 520600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2603/10000 episodes, total num timesteps 520800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2604/10000 episodes, total num timesteps 521000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2605/10000 episodes, total num timesteps 521200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2606/10000 episodes, total num timesteps 521400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2607/10000 episodes, total num timesteps 521600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2608/10000 episodes, total num timesteps 521800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2609/10000 episodes, total num timesteps 522000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2610/10000 episodes, total num timesteps 522200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2611/10000 episodes, total num timesteps 522400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2612/10000 episodes, total num timesteps 522600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2613/10000 episodes, total num timesteps 522800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2614/10000 episodes, total num timesteps 523000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2615/10000 episodes, total num timesteps 523200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2616/10000 episodes, total num timesteps 523400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2617/10000 episodes, total num timesteps 523600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2618/10000 episodes, total num timesteps 523800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2619/10000 episodes, total num timesteps 524000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2620/10000 episodes, total num timesteps 524200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2621/10000 episodes, total num timesteps 524400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2622/10000 episodes, total num timesteps 524600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2623/10000 episodes, total num timesteps 524800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2624/10000 episodes, total num timesteps 525000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2625/10000 episodes, total num timesteps 525200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.993993564977041
team_policy eval average team episode rewards of agent0: 102.5
team_policy eval idv catch total num of agent0: 41
team_policy eval team catch total num: 41
team_policy eval average step individual rewards of agent1: 0.968139339924279
team_policy eval average team episode rewards of agent1: 102.5
team_policy eval idv catch total num of agent1: 40
team_policy eval team catch total num: 41
team_policy eval average step individual rewards of agent2: 0.7714395547219537
team_policy eval average team episode rewards of agent2: 102.5
team_policy eval idv catch total num of agent2: 32
team_policy eval team catch total num: 41
team_policy eval average step individual rewards of agent3: 0.642529325495725
team_policy eval average team episode rewards of agent3: 102.5
team_policy eval idv catch total num of agent3: 27
team_policy eval team catch total num: 41
team_policy eval average step individual rewards of agent4: 0.5817980873826679
team_policy eval average team episode rewards of agent4: 102.5
team_policy eval idv catch total num of agent4: 25
team_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent0: 1.0826914190884542
idv_policy eval average team episode rewards of agent0: 95.0
idv_policy eval idv catch total num of agent0: 45
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent1: 0.8309576930930266
idv_policy eval average team episode rewards of agent1: 95.0
idv_policy eval idv catch total num of agent1: 35
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent2: 0.6577707881089748
idv_policy eval average team episode rewards of agent2: 95.0
idv_policy eval idv catch total num of agent2: 28
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent3: 0.3926052468572525
idv_policy eval average team episode rewards of agent3: 95.0
idv_policy eval idv catch total num of agent3: 18
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent4: 0.7142975055709545
idv_policy eval average team episode rewards of agent4: 95.0
idv_policy eval idv catch total num of agent4: 30
idv_policy eval team catch total num: 38

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2626/10000 episodes, total num timesteps 525400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2627/10000 episodes, total num timesteps 525600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2628/10000 episodes, total num timesteps 525800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2629/10000 episodes, total num timesteps 526000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2630/10000 episodes, total num timesteps 526200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2631/10000 episodes, total num timesteps 526400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2632/10000 episodes, total num timesteps 526600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2633/10000 episodes, total num timesteps 526800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2634/10000 episodes, total num timesteps 527000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2635/10000 episodes, total num timesteps 527200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2636/10000 episodes, total num timesteps 527400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2637/10000 episodes, total num timesteps 527600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2638/10000 episodes, total num timesteps 527800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2639/10000 episodes, total num timesteps 528000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2640/10000 episodes, total num timesteps 528200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2641/10000 episodes, total num timesteps 528400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2642/10000 episodes, total num timesteps 528600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2643/10000 episodes, total num timesteps 528800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2644/10000 episodes, total num timesteps 529000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2645/10000 episodes, total num timesteps 529200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2646/10000 episodes, total num timesteps 529400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2647/10000 episodes, total num timesteps 529600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2648/10000 episodes, total num timesteps 529800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2649/10000 episodes, total num timesteps 530000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2650/10000 episodes, total num timesteps 530200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 1.1191436880970462
team_policy eval average team episode rewards of agent0: 162.5
team_policy eval idv catch total num of agent0: 46
team_policy eval team catch total num: 65
team_policy eval average step individual rewards of agent1: 1.1494171773793993
team_policy eval average team episode rewards of agent1: 162.5
team_policy eval idv catch total num of agent1: 47
team_policy eval team catch total num: 65
team_policy eval average step individual rewards of agent2: 1.2983031546054145
team_policy eval average team episode rewards of agent2: 162.5
team_policy eval idv catch total num of agent2: 53
team_policy eval team catch total num: 65
team_policy eval average step individual rewards of agent3: 1.0734551686141716
team_policy eval average team episode rewards of agent3: 162.5
team_policy eval idv catch total num of agent3: 44
team_policy eval team catch total num: 65
team_policy eval average step individual rewards of agent4: 0.6616600785401664
team_policy eval average team episode rewards of agent4: 162.5
team_policy eval idv catch total num of agent4: 28
team_policy eval team catch total num: 65
idv_policy eval average step individual rewards of agent0: 0.3073482716529144
idv_policy eval average team episode rewards of agent0: 85.0
idv_policy eval idv catch total num of agent0: 14
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent1: 0.5802836706754867
idv_policy eval average team episode rewards of agent1: 85.0
idv_policy eval idv catch total num of agent1: 25
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent2: 0.5408207792649742
idv_policy eval average team episode rewards of agent2: 85.0
idv_policy eval idv catch total num of agent2: 23
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent3: 0.9110459352377148
idv_policy eval average team episode rewards of agent3: 85.0
idv_policy eval idv catch total num of agent3: 38
idv_policy eval team catch total num: 34
idv_policy eval average step individual rewards of agent4: 0.4252424980248645
idv_policy eval average team episode rewards of agent4: 85.0
idv_policy eval idv catch total num of agent4: 19
idv_policy eval team catch total num: 34

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2651/10000 episodes, total num timesteps 530400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2652/10000 episodes, total num timesteps 530600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2653/10000 episodes, total num timesteps 530800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2654/10000 episodes, total num timesteps 531000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2655/10000 episodes, total num timesteps 531200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2656/10000 episodes, total num timesteps 531400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2657/10000 episodes, total num timesteps 531600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2658/10000 episodes, total num timesteps 531800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2659/10000 episodes, total num timesteps 532000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2660/10000 episodes, total num timesteps 532200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2661/10000 episodes, total num timesteps 532400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2662/10000 episodes, total num timesteps 532600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2663/10000 episodes, total num timesteps 532800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2664/10000 episodes, total num timesteps 533000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2665/10000 episodes, total num timesteps 533200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2666/10000 episodes, total num timesteps 533400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2667/10000 episodes, total num timesteps 533600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2668/10000 episodes, total num timesteps 533800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2669/10000 episodes, total num timesteps 534000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2670/10000 episodes, total num timesteps 534200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2671/10000 episodes, total num timesteps 534400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2672/10000 episodes, total num timesteps 534600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2673/10000 episodes, total num timesteps 534800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2674/10000 episodes, total num timesteps 535000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2675/10000 episodes, total num timesteps 535200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.8153833341286071
team_policy eval average team episode rewards of agent0: 125.0
team_policy eval idv catch total num of agent0: 34
team_policy eval team catch total num: 50
team_policy eval average step individual rewards of agent1: 0.7136739931790567
team_policy eval average team episode rewards of agent1: 125.0
team_policy eval idv catch total num of agent1: 30
team_policy eval team catch total num: 50
team_policy eval average step individual rewards of agent2: 0.6801777127590786
team_policy eval average team episode rewards of agent2: 125.0
team_policy eval idv catch total num of agent2: 29
team_policy eval team catch total num: 50
team_policy eval average step individual rewards of agent3: 0.8654995914149092
team_policy eval average team episode rewards of agent3: 125.0
team_policy eval idv catch total num of agent3: 36
team_policy eval team catch total num: 50
team_policy eval average step individual rewards of agent4: 0.993384937236684
team_policy eval average team episode rewards of agent4: 125.0
team_policy eval idv catch total num of agent4: 41
team_policy eval team catch total num: 50
idv_policy eval average step individual rewards of agent0: 0.4407980465238877
idv_policy eval average team episode rewards of agent0: 95.0
idv_policy eval idv catch total num of agent0: 19
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent1: 0.6844998635033093
idv_policy eval average team episode rewards of agent1: 95.0
idv_policy eval idv catch total num of agent1: 29
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent2: 0.6182520919531945
idv_policy eval average team episode rewards of agent2: 95.0
idv_policy eval idv catch total num of agent2: 26
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent3: 0.5619710522679775
idv_policy eval average team episode rewards of agent3: 95.0
idv_policy eval idv catch total num of agent3: 24
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent4: 0.9904375764657126
idv_policy eval average team episode rewards of agent4: 95.0
idv_policy eval idv catch total num of agent4: 41
idv_policy eval team catch total num: 38

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2676/10000 episodes, total num timesteps 535400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2677/10000 episodes, total num timesteps 535600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2678/10000 episodes, total num timesteps 535800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2679/10000 episodes, total num timesteps 536000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2680/10000 episodes, total num timesteps 536200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2681/10000 episodes, total num timesteps 536400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2682/10000 episodes, total num timesteps 536600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2683/10000 episodes, total num timesteps 536800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2684/10000 episodes, total num timesteps 537000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2685/10000 episodes, total num timesteps 537200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2686/10000 episodes, total num timesteps 537400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2687/10000 episodes, total num timesteps 537600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2688/10000 episodes, total num timesteps 537800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2689/10000 episodes, total num timesteps 538000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2690/10000 episodes, total num timesteps 538200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2691/10000 episodes, total num timesteps 538400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2692/10000 episodes, total num timesteps 538600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2693/10000 episodes, total num timesteps 538800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2694/10000 episodes, total num timesteps 539000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2695/10000 episodes, total num timesteps 539200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2696/10000 episodes, total num timesteps 539400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2697/10000 episodes, total num timesteps 539600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2698/10000 episodes, total num timesteps 539800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2699/10000 episodes, total num timesteps 540000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2700/10000 episodes, total num timesteps 540200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.9661533084911865
team_policy eval average team episode rewards of agent0: 97.5
team_policy eval idv catch total num of agent0: 40
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent1: 0.6012215718764528
team_policy eval average team episode rewards of agent1: 97.5
team_policy eval idv catch total num of agent1: 26
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent2: 0.6339923319995323
team_policy eval average team episode rewards of agent2: 97.5
team_policy eval idv catch total num of agent2: 27
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent3: 1.369631013724335
team_policy eval average team episode rewards of agent3: 97.5
team_policy eval idv catch total num of agent3: 56
team_policy eval team catch total num: 39
team_policy eval average step individual rewards of agent4: 0.5030578021899966
team_policy eval average team episode rewards of agent4: 97.5
team_policy eval idv catch total num of agent4: 22
team_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent0: 0.6676003905622346
idv_policy eval average team episode rewards of agent0: 95.0
idv_policy eval idv catch total num of agent0: 28
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent1: 0.5845590448480875
idv_policy eval average team episode rewards of agent1: 95.0
idv_policy eval idv catch total num of agent1: 25
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent2: 0.962238773471823
idv_policy eval average team episode rewards of agent2: 95.0
idv_policy eval idv catch total num of agent2: 40
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent3: 0.4342193261148607
idv_policy eval average team episode rewards of agent3: 95.0
idv_policy eval idv catch total num of agent3: 19
idv_policy eval team catch total num: 38
idv_policy eval average step individual rewards of agent4: 1.043305143288523
idv_policy eval average team episode rewards of agent4: 95.0
idv_policy eval idv catch total num of agent4: 43
idv_policy eval team catch total num: 38

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2701/10000 episodes, total num timesteps 540400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2702/10000 episodes, total num timesteps 540600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2703/10000 episodes, total num timesteps 540800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2704/10000 episodes, total num timesteps 541000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2705/10000 episodes, total num timesteps 541200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2706/10000 episodes, total num timesteps 541400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2707/10000 episodes, total num timesteps 541600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2708/10000 episodes, total num timesteps 541800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2709/10000 episodes, total num timesteps 542000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2710/10000 episodes, total num timesteps 542200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2711/10000 episodes, total num timesteps 542400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2712/10000 episodes, total num timesteps 542600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2713/10000 episodes, total num timesteps 542800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2714/10000 episodes, total num timesteps 543000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2715/10000 episodes, total num timesteps 543200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2716/10000 episodes, total num timesteps 543400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2717/10000 episodes, total num timesteps 543600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2718/10000 episodes, total num timesteps 543800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2719/10000 episodes, total num timesteps 544000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2720/10000 episodes, total num timesteps 544200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2721/10000 episodes, total num timesteps 544400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2722/10000 episodes, total num timesteps 544600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2723/10000 episodes, total num timesteps 544800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2724/10000 episodes, total num timesteps 545000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2725/10000 episodes, total num timesteps 545200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.6391197447553122
team_policy eval average team episode rewards of agent0: 112.5
team_policy eval idv catch total num of agent0: 27
team_policy eval team catch total num: 45
team_policy eval average step individual rewards of agent1: 0.8395294038690173
team_policy eval average team episode rewards of agent1: 112.5
team_policy eval idv catch total num of agent1: 35
team_policy eval team catch total num: 45
team_policy eval average step individual rewards of agent2: 1.1997635668700788
team_policy eval average team episode rewards of agent2: 112.5
team_policy eval idv catch total num of agent2: 49
team_policy eval team catch total num: 45
team_policy eval average step individual rewards of agent3: 0.6257012771810814
team_policy eval average team episode rewards of agent3: 112.5
team_policy eval idv catch total num of agent3: 27
team_policy eval team catch total num: 45
team_policy eval average step individual rewards of agent4: 0.855876978270045
team_policy eval average team episode rewards of agent4: 112.5
team_policy eval idv catch total num of agent4: 36
team_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent0: 0.6265021954226215
idv_policy eval average team episode rewards of agent0: 102.5
idv_policy eval idv catch total num of agent0: 27
idv_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent1: 0.9686237558306928
idv_policy eval average team episode rewards of agent1: 102.5
idv_policy eval idv catch total num of agent1: 40
idv_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent2: 0.6098021299865448
idv_policy eval average team episode rewards of agent2: 102.5
idv_policy eval idv catch total num of agent2: 26
idv_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent3: 0.5710379434242581
idv_policy eval average team episode rewards of agent3: 102.5
idv_policy eval idv catch total num of agent3: 25
idv_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent4: 0.9382376728126474
idv_policy eval average team episode rewards of agent4: 102.5
idv_policy eval idv catch total num of agent4: 39
idv_policy eval team catch total num: 41

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2726/10000 episodes, total num timesteps 545400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2727/10000 episodes, total num timesteps 545600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2728/10000 episodes, total num timesteps 545800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2729/10000 episodes, total num timesteps 546000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2730/10000 episodes, total num timesteps 546200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2731/10000 episodes, total num timesteps 546400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2732/10000 episodes, total num timesteps 546600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2733/10000 episodes, total num timesteps 546800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2734/10000 episodes, total num timesteps 547000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2735/10000 episodes, total num timesteps 547200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2736/10000 episodes, total num timesteps 547400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2737/10000 episodes, total num timesteps 547600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2738/10000 episodes, total num timesteps 547800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2739/10000 episodes, total num timesteps 548000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2740/10000 episodes, total num timesteps 548200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2741/10000 episodes, total num timesteps 548400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2742/10000 episodes, total num timesteps 548600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2743/10000 episodes, total num timesteps 548800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2744/10000 episodes, total num timesteps 549000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2745/10000 episodes, total num timesteps 549200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2746/10000 episodes, total num timesteps 549400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2747/10000 episodes, total num timesteps 549600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2748/10000 episodes, total num timesteps 549800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2749/10000 episodes, total num timesteps 550000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2750/10000 episodes, total num timesteps 550200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.8731821990532797
team_policy eval average team episode rewards of agent0: 130.0
team_policy eval idv catch total num of agent0: 36
team_policy eval team catch total num: 52
team_policy eval average step individual rewards of agent1: 1.0416261986116908
team_policy eval average team episode rewards of agent1: 130.0
team_policy eval idv catch total num of agent1: 43
team_policy eval team catch total num: 52
team_policy eval average step individual rewards of agent2: 0.744817752716561
team_policy eval average team episode rewards of agent2: 130.0
team_policy eval idv catch total num of agent2: 31
team_policy eval team catch total num: 52
team_policy eval average step individual rewards of agent3: 0.8910964016196012
team_policy eval average team episode rewards of agent3: 130.0
team_policy eval idv catch total num of agent3: 37
team_policy eval team catch total num: 52
team_policy eval average step individual rewards of agent4: 1.2235582568674879
team_policy eval average team episode rewards of agent4: 130.0
team_policy eval idv catch total num of agent4: 50
team_policy eval team catch total num: 52
idv_policy eval average step individual rewards of agent0: 0.7348276780792365
idv_policy eval average team episode rewards of agent0: 132.5
idv_policy eval idv catch total num of agent0: 31
idv_policy eval team catch total num: 53
idv_policy eval average step individual rewards of agent1: 1.0456176807672206
idv_policy eval average team episode rewards of agent1: 132.5
idv_policy eval idv catch total num of agent1: 43
idv_policy eval team catch total num: 53
idv_policy eval average step individual rewards of agent2: 0.812493018233261
idv_policy eval average team episode rewards of agent2: 132.5
idv_policy eval idv catch total num of agent2: 34
idv_policy eval team catch total num: 53
idv_policy eval average step individual rewards of agent3: 0.5960207418142882
idv_policy eval average team episode rewards of agent3: 132.5
idv_policy eval idv catch total num of agent3: 26
idv_policy eval team catch total num: 53
idv_policy eval average step individual rewards of agent4: 1.198018435507806
idv_policy eval average team episode rewards of agent4: 132.5
idv_policy eval idv catch total num of agent4: 49
idv_policy eval team catch total num: 53

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2751/10000 episodes, total num timesteps 550400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2752/10000 episodes, total num timesteps 550600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2753/10000 episodes, total num timesteps 550800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2754/10000 episodes, total num timesteps 551000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2755/10000 episodes, total num timesteps 551200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2756/10000 episodes, total num timesteps 551400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2757/10000 episodes, total num timesteps 551600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2758/10000 episodes, total num timesteps 551800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2759/10000 episodes, total num timesteps 552000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2760/10000 episodes, total num timesteps 552200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2761/10000 episodes, total num timesteps 552400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2762/10000 episodes, total num timesteps 552600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2763/10000 episodes, total num timesteps 552800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2764/10000 episodes, total num timesteps 553000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2765/10000 episodes, total num timesteps 553200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2766/10000 episodes, total num timesteps 553400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2767/10000 episodes, total num timesteps 553600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2768/10000 episodes, total num timesteps 553800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2769/10000 episodes, total num timesteps 554000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2770/10000 episodes, total num timesteps 554200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2771/10000 episodes, total num timesteps 554400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2772/10000 episodes, total num timesteps 554600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2773/10000 episodes, total num timesteps 554800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2774/10000 episodes, total num timesteps 555000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2775/10000 episodes, total num timesteps 555200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.8880342927517918
team_policy eval average team episode rewards of agent0: 105.0
team_policy eval idv catch total num of agent0: 37
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent1: 0.6305085929945377
team_policy eval average team episode rewards of agent1: 105.0
team_policy eval idv catch total num of agent1: 27
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent2: 0.8306377010696457
team_policy eval average team episode rewards of agent2: 105.0
team_policy eval idv catch total num of agent2: 35
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent3: 0.679861052730432
team_policy eval average team episode rewards of agent3: 105.0
team_policy eval idv catch total num of agent3: 29
team_policy eval team catch total num: 42
team_policy eval average step individual rewards of agent4: 1.0420231931434505
team_policy eval average team episode rewards of agent4: 105.0
team_policy eval idv catch total num of agent4: 43
team_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent0: 0.9655095625797644
idv_policy eval average team episode rewards of agent0: 122.5
idv_policy eval idv catch total num of agent0: 40
idv_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent1: 0.58871883668643
idv_policy eval average team episode rewards of agent1: 122.5
idv_policy eval idv catch total num of agent1: 25
idv_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent2: 0.6367073719933758
idv_policy eval average team episode rewards of agent2: 122.5
idv_policy eval idv catch total num of agent2: 27
idv_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent3: 1.148736648848084
idv_policy eval average team episode rewards of agent3: 122.5
idv_policy eval idv catch total num of agent3: 47
idv_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent4: 0.9639759569351685
idv_policy eval average team episode rewards of agent4: 122.5
idv_policy eval idv catch total num of agent4: 40
idv_policy eval team catch total num: 49

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2776/10000 episodes, total num timesteps 555400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2777/10000 episodes, total num timesteps 555600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2778/10000 episodes, total num timesteps 555800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2779/10000 episodes, total num timesteps 556000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2780/10000 episodes, total num timesteps 556200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2781/10000 episodes, total num timesteps 556400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2782/10000 episodes, total num timesteps 556600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2783/10000 episodes, total num timesteps 556800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2784/10000 episodes, total num timesteps 557000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2785/10000 episodes, total num timesteps 557200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2786/10000 episodes, total num timesteps 557400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2787/10000 episodes, total num timesteps 557600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2788/10000 episodes, total num timesteps 557800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2789/10000 episodes, total num timesteps 558000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2790/10000 episodes, total num timesteps 558200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2791/10000 episodes, total num timesteps 558400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2792/10000 episodes, total num timesteps 558600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2793/10000 episodes, total num timesteps 558800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2794/10000 episodes, total num timesteps 559000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2795/10000 episodes, total num timesteps 559200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2796/10000 episodes, total num timesteps 559400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2797/10000 episodes, total num timesteps 559600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2798/10000 episodes, total num timesteps 559800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2799/10000 episodes, total num timesteps 560000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2800/10000 episodes, total num timesteps 560200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.7149057323144702
team_policy eval average team episode rewards of agent0: 122.5
team_policy eval idv catch total num of agent0: 30
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent1: 0.37442758652717617
team_policy eval average team episode rewards of agent1: 122.5
team_policy eval idv catch total num of agent1: 17
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent2: 1.065665367443321
team_policy eval average team episode rewards of agent2: 122.5
team_policy eval idv catch total num of agent2: 44
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent3: 0.6428304962509255
team_policy eval average team episode rewards of agent3: 122.5
team_policy eval idv catch total num of agent3: 27
team_policy eval team catch total num: 49
team_policy eval average step individual rewards of agent4: 1.1214539180504186
team_policy eval average team episode rewards of agent4: 122.5
team_policy eval idv catch total num of agent4: 46
team_policy eval team catch total num: 49
idv_policy eval average step individual rewards of agent0: 0.5354218993199302
idv_policy eval average team episode rewards of agent0: 77.5
idv_policy eval idv catch total num of agent0: 23
idv_policy eval team catch total num: 31
idv_policy eval average step individual rewards of agent1: 0.5007344272196445
idv_policy eval average team episode rewards of agent1: 77.5
idv_policy eval idv catch total num of agent1: 22
idv_policy eval team catch total num: 31
idv_policy eval average step individual rewards of agent2: 0.7266643267411907
idv_policy eval average team episode rewards of agent2: 77.5
idv_policy eval idv catch total num of agent2: 31
idv_policy eval team catch total num: 31
idv_policy eval average step individual rewards of agent3: 0.7850603470930939
idv_policy eval average team episode rewards of agent3: 77.5
idv_policy eval idv catch total num of agent3: 33
idv_policy eval team catch total num: 31
idv_policy eval average step individual rewards of agent4: 0.5598165716234748
idv_policy eval average team episode rewards of agent4: 77.5
idv_policy eval idv catch total num of agent4: 24
idv_policy eval team catch total num: 31

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2801/10000 episodes, total num timesteps 560400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2802/10000 episodes, total num timesteps 560600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2803/10000 episodes, total num timesteps 560800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2804/10000 episodes, total num timesteps 561000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2805/10000 episodes, total num timesteps 561200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2806/10000 episodes, total num timesteps 561400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2807/10000 episodes, total num timesteps 561600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2808/10000 episodes, total num timesteps 561800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2809/10000 episodes, total num timesteps 562000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2810/10000 episodes, total num timesteps 562200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2811/10000 episodes, total num timesteps 562400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2812/10000 episodes, total num timesteps 562600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2813/10000 episodes, total num timesteps 562800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2814/10000 episodes, total num timesteps 563000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2815/10000 episodes, total num timesteps 563200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2816/10000 episodes, total num timesteps 563400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2817/10000 episodes, total num timesteps 563600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2818/10000 episodes, total num timesteps 563800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2819/10000 episodes, total num timesteps 564000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2820/10000 episodes, total num timesteps 564200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2821/10000 episodes, total num timesteps 564400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2822/10000 episodes, total num timesteps 564600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2823/10000 episodes, total num timesteps 564800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2824/10000 episodes, total num timesteps 565000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2825/10000 episodes, total num timesteps 565200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.49827631073908135
team_policy eval average team episode rewards of agent0: 65.0
team_policy eval idv catch total num of agent0: 22
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent1: 0.9384665866254109
team_policy eval average team episode rewards of agent1: 65.0
team_policy eval idv catch total num of agent1: 39
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent2: 0.5154773270676304
team_policy eval average team episode rewards of agent2: 65.0
team_policy eval idv catch total num of agent2: 22
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent3: 0.3061054279325352
team_policy eval average team episode rewards of agent3: 65.0
team_policy eval idv catch total num of agent3: 14
team_policy eval team catch total num: 26
team_policy eval average step individual rewards of agent4: 0.5907625085215159
team_policy eval average team episode rewards of agent4: 65.0
team_policy eval idv catch total num of agent4: 25
team_policy eval team catch total num: 26
idv_policy eval average step individual rewards of agent0: 0.721405792974151
idv_policy eval average team episode rewards of agent0: 105.0
idv_policy eval idv catch total num of agent0: 30
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent1: 1.0674583558723638
idv_policy eval average team episode rewards of agent1: 105.0
idv_policy eval idv catch total num of agent1: 44
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent2: 0.989797332782139
idv_policy eval average team episode rewards of agent2: 105.0
idv_policy eval idv catch total num of agent2: 41
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent3: 0.8337704184165723
idv_policy eval average team episode rewards of agent3: 105.0
idv_policy eval idv catch total num of agent3: 35
idv_policy eval team catch total num: 42
idv_policy eval average step individual rewards of agent4: 0.5817841685693331
idv_policy eval average team episode rewards of agent4: 105.0
idv_policy eval idv catch total num of agent4: 25
idv_policy eval team catch total num: 42

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2826/10000 episodes, total num timesteps 565400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2827/10000 episodes, total num timesteps 565600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2828/10000 episodes, total num timesteps 565800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2829/10000 episodes, total num timesteps 566000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2830/10000 episodes, total num timesteps 566200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2831/10000 episodes, total num timesteps 566400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2832/10000 episodes, total num timesteps 566600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2833/10000 episodes, total num timesteps 566800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2834/10000 episodes, total num timesteps 567000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2835/10000 episodes, total num timesteps 567200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2836/10000 episodes, total num timesteps 567400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2837/10000 episodes, total num timesteps 567600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2838/10000 episodes, total num timesteps 567800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2839/10000 episodes, total num timesteps 568000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2840/10000 episodes, total num timesteps 568200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2841/10000 episodes, total num timesteps 568400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2842/10000 episodes, total num timesteps 568600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2843/10000 episodes, total num timesteps 568800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2844/10000 episodes, total num timesteps 569000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2845/10000 episodes, total num timesteps 569200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2846/10000 episodes, total num timesteps 569400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2847/10000 episodes, total num timesteps 569600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2848/10000 episodes, total num timesteps 569800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2849/10000 episodes, total num timesteps 570000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2850/10000 episodes, total num timesteps 570200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.9409418167819603
team_policy eval average team episode rewards of agent0: 100.0
team_policy eval idv catch total num of agent0: 39
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent1: 0.7392835389624222
team_policy eval average team episode rewards of agent1: 100.0
team_policy eval idv catch total num of agent1: 31
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent2: 1.0695647822128165
team_policy eval average team episode rewards of agent2: 100.0
team_policy eval idv catch total num of agent2: 44
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent3: 0.4887125903318348
team_policy eval average team episode rewards of agent3: 100.0
team_policy eval idv catch total num of agent3: 21
team_policy eval team catch total num: 40
team_policy eval average step individual rewards of agent4: 0.4920688679535873
team_policy eval average team episode rewards of agent4: 100.0
team_policy eval idv catch total num of agent4: 21
team_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent0: 0.6933131883373684
idv_policy eval average team episode rewards of agent0: 120.0
idv_policy eval idv catch total num of agent0: 29
idv_policy eval team catch total num: 48
idv_policy eval average step individual rewards of agent1: 0.5808794691277711
idv_policy eval average team episode rewards of agent1: 120.0
idv_policy eval idv catch total num of agent1: 25
idv_policy eval team catch total num: 48
idv_policy eval average step individual rewards of agent2: 0.7141109387757871
idv_policy eval average team episode rewards of agent2: 120.0
idv_policy eval idv catch total num of agent2: 30
idv_policy eval team catch total num: 48
idv_policy eval average step individual rewards of agent3: 0.9165931374134147
idv_policy eval average team episode rewards of agent3: 120.0
idv_policy eval idv catch total num of agent3: 38
idv_policy eval team catch total num: 48
idv_policy eval average step individual rewards of agent4: 1.3293422918332924
idv_policy eval average team episode rewards of agent4: 120.0
idv_policy eval idv catch total num of agent4: 54
idv_policy eval team catch total num: 48

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2851/10000 episodes, total num timesteps 570400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2852/10000 episodes, total num timesteps 570600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2853/10000 episodes, total num timesteps 570800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2854/10000 episodes, total num timesteps 571000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2855/10000 episodes, total num timesteps 571200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2856/10000 episodes, total num timesteps 571400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2857/10000 episodes, total num timesteps 571600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2858/10000 episodes, total num timesteps 571800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2859/10000 episodes, total num timesteps 572000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2860/10000 episodes, total num timesteps 572200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2861/10000 episodes, total num timesteps 572400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2862/10000 episodes, total num timesteps 572600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2863/10000 episodes, total num timesteps 572800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2864/10000 episodes, total num timesteps 573000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2865/10000 episodes, total num timesteps 573200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2866/10000 episodes, total num timesteps 573400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2867/10000 episodes, total num timesteps 573600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2868/10000 episodes, total num timesteps 573800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2869/10000 episodes, total num timesteps 574000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2870/10000 episodes, total num timesteps 574200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2871/10000 episodes, total num timesteps 574400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2872/10000 episodes, total num timesteps 574600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2873/10000 episodes, total num timesteps 574800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2874/10000 episodes, total num timesteps 575000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2875/10000 episodes, total num timesteps 575200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.8976030362796367
team_policy eval average team episode rewards of agent0: 92.5
team_policy eval idv catch total num of agent0: 37
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent1: 0.8153109716128916
team_policy eval average team episode rewards of agent1: 92.5
team_policy eval idv catch total num of agent1: 34
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent2: 0.5848218427548126
team_policy eval average team episode rewards of agent2: 92.5
team_policy eval idv catch total num of agent2: 25
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent3: 0.41569885970671755
team_policy eval average team episode rewards of agent3: 92.5
team_policy eval idv catch total num of agent3: 18
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent4: 0.5050471028639114
team_policy eval average team episode rewards of agent4: 92.5
team_policy eval idv catch total num of agent4: 22
team_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent0: 0.7910814539161205
idv_policy eval average team episode rewards of agent0: 67.5
idv_policy eval idv catch total num of agent0: 33
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent1: 0.6823030649482017
idv_policy eval average team episode rewards of agent1: 67.5
idv_policy eval idv catch total num of agent1: 29
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent2: 0.4997267807539284
idv_policy eval average team episode rewards of agent2: 67.5
idv_policy eval idv catch total num of agent2: 22
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent3: 0.908488880238852
idv_policy eval average team episode rewards of agent3: 67.5
idv_policy eval idv catch total num of agent3: 38
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent4: 0.5616665579527934
idv_policy eval average team episode rewards of agent4: 67.5
idv_policy eval idv catch total num of agent4: 24
idv_policy eval team catch total num: 27

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2876/10000 episodes, total num timesteps 575400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2877/10000 episodes, total num timesteps 575600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2878/10000 episodes, total num timesteps 575800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2879/10000 episodes, total num timesteps 576000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2880/10000 episodes, total num timesteps 576200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2881/10000 episodes, total num timesteps 576400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2882/10000 episodes, total num timesteps 576600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2883/10000 episodes, total num timesteps 576800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2884/10000 episodes, total num timesteps 577000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2885/10000 episodes, total num timesteps 577200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2886/10000 episodes, total num timesteps 577400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2887/10000 episodes, total num timesteps 577600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2888/10000 episodes, total num timesteps 577800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2889/10000 episodes, total num timesteps 578000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2890/10000 episodes, total num timesteps 578200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2891/10000 episodes, total num timesteps 578400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2892/10000 episodes, total num timesteps 578600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2893/10000 episodes, total num timesteps 578800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2894/10000 episodes, total num timesteps 579000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2895/10000 episodes, total num timesteps 579200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2896/10000 episodes, total num timesteps 579400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2897/10000 episodes, total num timesteps 579600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2898/10000 episodes, total num timesteps 579800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2899/10000 episodes, total num timesteps 580000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2900/10000 episodes, total num timesteps 580200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.8424822498126153
team_policy eval average team episode rewards of agent0: 117.5
team_policy eval idv catch total num of agent0: 35
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent1: 0.9464402673271118
team_policy eval average team episode rewards of agent1: 117.5
team_policy eval idv catch total num of agent1: 39
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent2: 1.1003235787599683
team_policy eval average team episode rewards of agent2: 117.5
team_policy eval idv catch total num of agent2: 45
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent3: 1.1143633669532824
team_policy eval average team episode rewards of agent3: 117.5
team_policy eval idv catch total num of agent3: 46
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent4: 0.43681650140051553
team_policy eval average team episode rewards of agent4: 117.5
team_policy eval idv catch total num of agent4: 19
team_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent0: 1.0118420177645522
idv_policy eval average team episode rewards of agent0: 142.5
idv_policy eval idv catch total num of agent0: 42
idv_policy eval team catch total num: 57
idv_policy eval average step individual rewards of agent1: 0.8465595487937304
idv_policy eval average team episode rewards of agent1: 142.5
idv_policy eval idv catch total num of agent1: 35
idv_policy eval team catch total num: 57
idv_policy eval average step individual rewards of agent2: 1.045405254926075
idv_policy eval average team episode rewards of agent2: 142.5
idv_policy eval idv catch total num of agent2: 43
idv_policy eval team catch total num: 57
idv_policy eval average step individual rewards of agent3: 1.0692180012632646
idv_policy eval average team episode rewards of agent3: 142.5
idv_policy eval idv catch total num of agent3: 44
idv_policy eval team catch total num: 57
idv_policy eval average step individual rewards of agent4: 1.3480616531150207
idv_policy eval average team episode rewards of agent4: 142.5
idv_policy eval idv catch total num of agent4: 55
idv_policy eval team catch total num: 57

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2901/10000 episodes, total num timesteps 580400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2902/10000 episodes, total num timesteps 580600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2903/10000 episodes, total num timesteps 580800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2904/10000 episodes, total num timesteps 581000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2905/10000 episodes, total num timesteps 581200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2906/10000 episodes, total num timesteps 581400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2907/10000 episodes, total num timesteps 581600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2908/10000 episodes, total num timesteps 581800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2909/10000 episodes, total num timesteps 582000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2910/10000 episodes, total num timesteps 582200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2911/10000 episodes, total num timesteps 582400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2912/10000 episodes, total num timesteps 582600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2913/10000 episodes, total num timesteps 582800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2914/10000 episodes, total num timesteps 583000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2915/10000 episodes, total num timesteps 583200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2916/10000 episodes, total num timesteps 583400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2917/10000 episodes, total num timesteps 583600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2918/10000 episodes, total num timesteps 583800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2919/10000 episodes, total num timesteps 584000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2920/10000 episodes, total num timesteps 584200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2921/10000 episodes, total num timesteps 584400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2922/10000 episodes, total num timesteps 584600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2923/10000 episodes, total num timesteps 584800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2924/10000 episodes, total num timesteps 585000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2925/10000 episodes, total num timesteps 585200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.8877403294051268
team_policy eval average team episode rewards of agent0: 140.0
team_policy eval idv catch total num of agent0: 37
team_policy eval team catch total num: 56
team_policy eval average step individual rewards of agent1: 0.9715081115695356
team_policy eval average team episode rewards of agent1: 140.0
team_policy eval idv catch total num of agent1: 40
team_policy eval team catch total num: 56
team_policy eval average step individual rewards of agent2: 0.9635179955380215
team_policy eval average team episode rewards of agent2: 140.0
team_policy eval idv catch total num of agent2: 40
team_policy eval team catch total num: 56
team_policy eval average step individual rewards of agent3: 1.4466012507434982
team_policy eval average team episode rewards of agent3: 140.0
team_policy eval idv catch total num of agent3: 59
team_policy eval team catch total num: 56
team_policy eval average step individual rewards of agent4: 1.0960591055207771
team_policy eval average team episode rewards of agent4: 140.0
team_policy eval idv catch total num of agent4: 45
team_policy eval team catch total num: 56
idv_policy eval average step individual rewards of agent0: 1.3954070675424355
idv_policy eval average team episode rewards of agent0: 112.5
idv_policy eval idv catch total num of agent0: 57
idv_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent1: 0.7110529918508307
idv_policy eval average team episode rewards of agent1: 112.5
idv_policy eval idv catch total num of agent1: 30
idv_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent2: 0.7879193366448893
idv_policy eval average team episode rewards of agent2: 112.5
idv_policy eval idv catch total num of agent2: 33
idv_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent3: 1.2247076367703449
idv_policy eval average team episode rewards of agent3: 112.5
idv_policy eval idv catch total num of agent3: 50
idv_policy eval team catch total num: 45
idv_policy eval average step individual rewards of agent4: 0.9658762604654814
idv_policy eval average team episode rewards of agent4: 112.5
idv_policy eval idv catch total num of agent4: 40
idv_policy eval team catch total num: 45

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2926/10000 episodes, total num timesteps 585400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2927/10000 episodes, total num timesteps 585600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2928/10000 episodes, total num timesteps 585800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2929/10000 episodes, total num timesteps 586000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2930/10000 episodes, total num timesteps 586200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2931/10000 episodes, total num timesteps 586400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2932/10000 episodes, total num timesteps 586600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2933/10000 episodes, total num timesteps 586800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2934/10000 episodes, total num timesteps 587000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2935/10000 episodes, total num timesteps 587200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2936/10000 episodes, total num timesteps 587400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2937/10000 episodes, total num timesteps 587600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2938/10000 episodes, total num timesteps 587800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2939/10000 episodes, total num timesteps 588000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2940/10000 episodes, total num timesteps 588200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2941/10000 episodes, total num timesteps 588400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2942/10000 episodes, total num timesteps 588600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2943/10000 episodes, total num timesteps 588800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2944/10000 episodes, total num timesteps 589000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2945/10000 episodes, total num timesteps 589200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2946/10000 episodes, total num timesteps 589400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2947/10000 episodes, total num timesteps 589600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2948/10000 episodes, total num timesteps 589800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2949/10000 episodes, total num timesteps 590000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2950/10000 episodes, total num timesteps 590200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 1.062536466028222
team_policy eval average team episode rewards of agent0: 120.0
team_policy eval idv catch total num of agent0: 44
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent1: 0.5955787500781702
team_policy eval average team episode rewards of agent1: 120.0
team_policy eval idv catch total num of agent1: 25
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent2: 0.43631967213623496
team_policy eval average team episode rewards of agent2: 120.0
team_policy eval idv catch total num of agent2: 19
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent3: 0.9945788784063703
team_policy eval average team episode rewards of agent3: 120.0
team_policy eval idv catch total num of agent3: 41
team_policy eval team catch total num: 48
team_policy eval average step individual rewards of agent4: 1.1963242260872424
team_policy eval average team episode rewards of agent4: 120.0
team_policy eval idv catch total num of agent4: 49
team_policy eval team catch total num: 48
idv_policy eval average step individual rewards of agent0: 0.539884086343283
idv_policy eval average team episode rewards of agent0: 67.5
idv_policy eval idv catch total num of agent0: 23
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent1: 0.40737286480109786
idv_policy eval average team episode rewards of agent1: 67.5
idv_policy eval idv catch total num of agent1: 18
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent2: 0.5651660649676445
idv_policy eval average team episode rewards of agent2: 67.5
idv_policy eval idv catch total num of agent2: 24
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent3: 0.3547363370205514
idv_policy eval average team episode rewards of agent3: 67.5
idv_policy eval idv catch total num of agent3: 16
idv_policy eval team catch total num: 27
idv_policy eval average step individual rewards of agent4: 0.7196804094349512
idv_policy eval average team episode rewards of agent4: 67.5
idv_policy eval idv catch total num of agent4: 30
idv_policy eval team catch total num: 27

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2951/10000 episodes, total num timesteps 590400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2952/10000 episodes, total num timesteps 590600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2953/10000 episodes, total num timesteps 590800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2954/10000 episodes, total num timesteps 591000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2955/10000 episodes, total num timesteps 591200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2956/10000 episodes, total num timesteps 591400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2957/10000 episodes, total num timesteps 591600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2958/10000 episodes, total num timesteps 591800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2959/10000 episodes, total num timesteps 592000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2960/10000 episodes, total num timesteps 592200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2961/10000 episodes, total num timesteps 592400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2962/10000 episodes, total num timesteps 592600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2963/10000 episodes, total num timesteps 592800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2964/10000 episodes, total num timesteps 593000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2965/10000 episodes, total num timesteps 593200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2966/10000 episodes, total num timesteps 593400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2967/10000 episodes, total num timesteps 593600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2968/10000 episodes, total num timesteps 593800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2969/10000 episodes, total num timesteps 594000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2970/10000 episodes, total num timesteps 594200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2971/10000 episodes, total num timesteps 594400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2972/10000 episodes, total num timesteps 594600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2973/10000 episodes, total num timesteps 594800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2974/10000 episodes, total num timesteps 595000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2975/10000 episodes, total num timesteps 595200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.8645075630607297
team_policy eval average team episode rewards of agent0: 82.5
team_policy eval idv catch total num of agent0: 36
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent1: 0.7050908038603741
team_policy eval average team episode rewards of agent1: 82.5
team_policy eval idv catch total num of agent1: 30
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent2: 0.6621529103575822
team_policy eval average team episode rewards of agent2: 82.5
team_policy eval idv catch total num of agent2: 28
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent3: 0.4115876157958048
team_policy eval average team episode rewards of agent3: 82.5
team_policy eval idv catch total num of agent3: 18
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent4: 0.6692521803682965
team_policy eval average team episode rewards of agent4: 82.5
team_policy eval idv catch total num of agent4: 28
team_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent0: 0.6362691703509236
idv_policy eval average team episode rewards of agent0: 110.0
idv_policy eval idv catch total num of agent0: 27
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent1: 0.9158386657716306
idv_policy eval average team episode rewards of agent1: 110.0
idv_policy eval idv catch total num of agent1: 38
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent2: 0.8975611666181268
idv_policy eval average team episode rewards of agent2: 110.0
idv_policy eval idv catch total num of agent2: 37
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent3: 0.761477273917927
idv_policy eval average team episode rewards of agent3: 110.0
idv_policy eval idv catch total num of agent3: 32
idv_policy eval team catch total num: 44
idv_policy eval average step individual rewards of agent4: 0.7031529136935026
idv_policy eval average team episode rewards of agent4: 110.0
idv_policy eval idv catch total num of agent4: 30
idv_policy eval team catch total num: 44

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2976/10000 episodes, total num timesteps 595400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2977/10000 episodes, total num timesteps 595600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2978/10000 episodes, total num timesteps 595800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2979/10000 episodes, total num timesteps 596000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2980/10000 episodes, total num timesteps 596200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2981/10000 episodes, total num timesteps 596400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2982/10000 episodes, total num timesteps 596600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2983/10000 episodes, total num timesteps 596800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2984/10000 episodes, total num timesteps 597000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2985/10000 episodes, total num timesteps 597200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2986/10000 episodes, total num timesteps 597400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2987/10000 episodes, total num timesteps 597600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2988/10000 episodes, total num timesteps 597800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2989/10000 episodes, total num timesteps 598000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2990/10000 episodes, total num timesteps 598200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2991/10000 episodes, total num timesteps 598400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2992/10000 episodes, total num timesteps 598600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2993/10000 episodes, total num timesteps 598800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2994/10000 episodes, total num timesteps 599000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2995/10000 episodes, total num timesteps 599200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2996/10000 episodes, total num timesteps 599400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2997/10000 episodes, total num timesteps 599600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2998/10000 episodes, total num timesteps 599800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 2999/10000 episodes, total num timesteps 600000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3000/10000 episodes, total num timesteps 600200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 1.0431868530475947
team_policy eval average team episode rewards of agent0: 117.5
team_policy eval idv catch total num of agent0: 43
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent1: 0.8078915824168673
team_policy eval average team episode rewards of agent1: 117.5
team_policy eval idv catch total num of agent1: 34
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent2: 0.7416993910075855
team_policy eval average team episode rewards of agent2: 117.5
team_policy eval idv catch total num of agent2: 31
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent3: 1.1468407781874734
team_policy eval average team episode rewards of agent3: 117.5
team_policy eval idv catch total num of agent3: 47
team_policy eval team catch total num: 47
team_policy eval average step individual rewards of agent4: 0.5794964740996665
team_policy eval average team episode rewards of agent4: 117.5
team_policy eval idv catch total num of agent4: 25
team_policy eval team catch total num: 47
idv_policy eval average step individual rewards of agent0: 0.5037671950631453
idv_policy eval average team episode rewards of agent0: 80.0
idv_policy eval idv catch total num of agent0: 22
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent1: 0.668676336705148
idv_policy eval average team episode rewards of agent1: 80.0
idv_policy eval idv catch total num of agent1: 28
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent2: 1.0283989268953717
idv_policy eval average team episode rewards of agent2: 80.0
idv_policy eval idv catch total num of agent2: 42
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent3: 0.47885812803175
idv_policy eval average team episode rewards of agent3: 80.0
idv_policy eval idv catch total num of agent3: 21
idv_policy eval team catch total num: 32
idv_policy eval average step individual rewards of agent4: 0.7390665338468
idv_policy eval average team episode rewards of agent4: 80.0
idv_policy eval idv catch total num of agent4: 31
idv_policy eval team catch total num: 32

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3001/10000 episodes, total num timesteps 600400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3002/10000 episodes, total num timesteps 600600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3003/10000 episodes, total num timesteps 600800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3004/10000 episodes, total num timesteps 601000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3005/10000 episodes, total num timesteps 601200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3006/10000 episodes, total num timesteps 601400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3007/10000 episodes, total num timesteps 601600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3008/10000 episodes, total num timesteps 601800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3009/10000 episodes, total num timesteps 602000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3010/10000 episodes, total num timesteps 602200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3011/10000 episodes, total num timesteps 602400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3012/10000 episodes, total num timesteps 602600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3013/10000 episodes, total num timesteps 602800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3014/10000 episodes, total num timesteps 603000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3015/10000 episodes, total num timesteps 603200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3016/10000 episodes, total num timesteps 603400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3017/10000 episodes, total num timesteps 603600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3018/10000 episodes, total num timesteps 603800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3019/10000 episodes, total num timesteps 604000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3020/10000 episodes, total num timesteps 604200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3021/10000 episodes, total num timesteps 604400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3022/10000 episodes, total num timesteps 604600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3023/10000 episodes, total num timesteps 604800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3024/10000 episodes, total num timesteps 605000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3025/10000 episodes, total num timesteps 605200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.5394011725763797
team_policy eval average team episode rewards of agent0: 82.5
team_policy eval idv catch total num of agent0: 23
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent1: 0.6996019073033013
team_policy eval average team episode rewards of agent1: 82.5
team_policy eval idv catch total num of agent1: 29
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent2: 0.5887522535385823
team_policy eval average team episode rewards of agent2: 82.5
team_policy eval idv catch total num of agent2: 25
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent3: 0.8130203150701848
team_policy eval average team episode rewards of agent3: 82.5
team_policy eval idv catch total num of agent3: 34
team_policy eval team catch total num: 33
team_policy eval average step individual rewards of agent4: 0.8896257531499284
team_policy eval average team episode rewards of agent4: 82.5
team_policy eval idv catch total num of agent4: 37
team_policy eval team catch total num: 33
idv_policy eval average step individual rewards of agent0: 1.0692071543020456
idv_policy eval average team episode rewards of agent0: 57.5
idv_policy eval idv catch total num of agent0: 44
idv_policy eval team catch total num: 23
idv_policy eval average step individual rewards of agent1: 0.1915021378774246
idv_policy eval average team episode rewards of agent1: 57.5
idv_policy eval idv catch total num of agent1: 10
idv_policy eval team catch total num: 23
idv_policy eval average step individual rewards of agent2: 0.44824810996912795
idv_policy eval average team episode rewards of agent2: 57.5
idv_policy eval idv catch total num of agent2: 20
idv_policy eval team catch total num: 23
idv_policy eval average step individual rewards of agent3: 0.6519715646416532
idv_policy eval average team episode rewards of agent3: 57.5
idv_policy eval idv catch total num of agent3: 28
idv_policy eval team catch total num: 23
idv_policy eval average step individual rewards of agent4: 0.4734883240201286
idv_policy eval average team episode rewards of agent4: 57.5
idv_policy eval idv catch total num of agent4: 21
idv_policy eval team catch total num: 23

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3026/10000 episodes, total num timesteps 605400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3027/10000 episodes, total num timesteps 605600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3028/10000 episodes, total num timesteps 605800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3029/10000 episodes, total num timesteps 606000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3030/10000 episodes, total num timesteps 606200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3031/10000 episodes, total num timesteps 606400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3032/10000 episodes, total num timesteps 606600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3033/10000 episodes, total num timesteps 606800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3034/10000 episodes, total num timesteps 607000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3035/10000 episodes, total num timesteps 607200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3036/10000 episodes, total num timesteps 607400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3037/10000 episodes, total num timesteps 607600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3038/10000 episodes, total num timesteps 607800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3039/10000 episodes, total num timesteps 608000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3040/10000 episodes, total num timesteps 608200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3041/10000 episodes, total num timesteps 608400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3042/10000 episodes, total num timesteps 608600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3043/10000 episodes, total num timesteps 608800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3044/10000 episodes, total num timesteps 609000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3045/10000 episodes, total num timesteps 609200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3046/10000 episodes, total num timesteps 609400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3047/10000 episodes, total num timesteps 609600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3048/10000 episodes, total num timesteps 609800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3049/10000 episodes, total num timesteps 610000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3050/10000 episodes, total num timesteps 610200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.7678085047650027
team_policy eval average team episode rewards of agent0: 132.5
team_policy eval idv catch total num of agent0: 32
team_policy eval team catch total num: 53
team_policy eval average step individual rewards of agent1: 1.0436377938909234
team_policy eval average team episode rewards of agent1: 132.5
team_policy eval idv catch total num of agent1: 43
team_policy eval team catch total num: 53
team_policy eval average step individual rewards of agent2: 1.1691696025236178
team_policy eval average team episode rewards of agent2: 132.5
team_policy eval idv catch total num of agent2: 48
team_policy eval team catch total num: 53
team_policy eval average step individual rewards of agent3: 0.917186779403142
team_policy eval average team episode rewards of agent3: 132.5
team_policy eval idv catch total num of agent3: 38
team_policy eval team catch total num: 53
team_policy eval average step individual rewards of agent4: 0.7137752154561141
team_policy eval average team episode rewards of agent4: 132.5
team_policy eval idv catch total num of agent4: 30
team_policy eval team catch total num: 53
idv_policy eval average step individual rewards of agent0: 0.3838917455547399
idv_policy eval average team episode rewards of agent0: 45.0
idv_policy eval idv catch total num of agent0: 17
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent1: 0.5664074773830811
idv_policy eval average team episode rewards of agent1: 45.0
idv_policy eval idv catch total num of agent1: 24
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent2: 0.3597445819374453
idv_policy eval average team episode rewards of agent2: 45.0
idv_policy eval idv catch total num of agent2: 16
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent3: 0.46040508161383437
idv_policy eval average team episode rewards of agent3: 45.0
idv_policy eval idv catch total num of agent3: 20
idv_policy eval team catch total num: 18
idv_policy eval average step individual rewards of agent4: 0.25687590848263403
idv_policy eval average team episode rewards of agent4: 45.0
idv_policy eval idv catch total num of agent4: 12
idv_policy eval team catch total num: 18

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3051/10000 episodes, total num timesteps 610400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3052/10000 episodes, total num timesteps 610600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3053/10000 episodes, total num timesteps 610800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3054/10000 episodes, total num timesteps 611000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3055/10000 episodes, total num timesteps 611200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3056/10000 episodes, total num timesteps 611400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3057/10000 episodes, total num timesteps 611600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3058/10000 episodes, total num timesteps 611800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3059/10000 episodes, total num timesteps 612000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3060/10000 episodes, total num timesteps 612200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3061/10000 episodes, total num timesteps 612400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3062/10000 episodes, total num timesteps 612600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3063/10000 episodes, total num timesteps 612800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3064/10000 episodes, total num timesteps 613000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3065/10000 episodes, total num timesteps 613200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3066/10000 episodes, total num timesteps 613400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3067/10000 episodes, total num timesteps 613600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3068/10000 episodes, total num timesteps 613800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3069/10000 episodes, total num timesteps 614000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3070/10000 episodes, total num timesteps 614200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3071/10000 episodes, total num timesteps 614400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3072/10000 episodes, total num timesteps 614600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3073/10000 episodes, total num timesteps 614800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3074/10000 episodes, total num timesteps 615000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3075/10000 episodes, total num timesteps 615200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.7651767981680199
team_policy eval average team episode rewards of agent0: 102.5
team_policy eval idv catch total num of agent0: 32
team_policy eval team catch total num: 41
team_policy eval average step individual rewards of agent1: 0.9744198878966748
team_policy eval average team episode rewards of agent1: 102.5
team_policy eval idv catch total num of agent1: 40
team_policy eval team catch total num: 41
team_policy eval average step individual rewards of agent2: 0.5709602493481004
team_policy eval average team episode rewards of agent2: 102.5
team_policy eval idv catch total num of agent2: 24
team_policy eval team catch total num: 41
team_policy eval average step individual rewards of agent3: 0.6956974439044505
team_policy eval average team episode rewards of agent3: 102.5
team_policy eval idv catch total num of agent3: 29
team_policy eval team catch total num: 41
team_policy eval average step individual rewards of agent4: 0.6870807552636886
team_policy eval average team episode rewards of agent4: 102.5
team_policy eval idv catch total num of agent4: 29
team_policy eval team catch total num: 41
idv_policy eval average step individual rewards of agent0: 0.5815570877163714
idv_policy eval average team episode rewards of agent0: 97.5
idv_policy eval idv catch total num of agent0: 25
idv_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent1: 0.6605354319688889
idv_policy eval average team episode rewards of agent1: 97.5
idv_policy eval idv catch total num of agent1: 28
idv_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent2: 0.7243526183500393
idv_policy eval average team episode rewards of agent2: 97.5
idv_policy eval idv catch total num of agent2: 31
idv_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent3: 0.6147346541968232
idv_policy eval average team episode rewards of agent3: 97.5
idv_policy eval idv catch total num of agent3: 26
idv_policy eval team catch total num: 39
idv_policy eval average step individual rewards of agent4: 0.8576206274474484
idv_policy eval average team episode rewards of agent4: 97.5
idv_policy eval idv catch total num of agent4: 36
idv_policy eval team catch total num: 39

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3076/10000 episodes, total num timesteps 615400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3077/10000 episodes, total num timesteps 615600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3078/10000 episodes, total num timesteps 615800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3079/10000 episodes, total num timesteps 616000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3080/10000 episodes, total num timesteps 616200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3081/10000 episodes, total num timesteps 616400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3082/10000 episodes, total num timesteps 616600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3083/10000 episodes, total num timesteps 616800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3084/10000 episodes, total num timesteps 617000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3085/10000 episodes, total num timesteps 617200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3086/10000 episodes, total num timesteps 617400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3087/10000 episodes, total num timesteps 617600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3088/10000 episodes, total num timesteps 617800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3089/10000 episodes, total num timesteps 618000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3090/10000 episodes, total num timesteps 618200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3091/10000 episodes, total num timesteps 618400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3092/10000 episodes, total num timesteps 618600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3093/10000 episodes, total num timesteps 618800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3094/10000 episodes, total num timesteps 619000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3095/10000 episodes, total num timesteps 619200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3096/10000 episodes, total num timesteps 619400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3097/10000 episodes, total num timesteps 619600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3098/10000 episodes, total num timesteps 619800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3099/10000 episodes, total num timesteps 620000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3100/10000 episodes, total num timesteps 620200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.6804998073945038
team_policy eval average team episode rewards of agent0: 87.5
team_policy eval idv catch total num of agent0: 29
team_policy eval team catch total num: 35
team_policy eval average step individual rewards of agent1: 0.6788105963772508
team_policy eval average team episode rewards of agent1: 87.5
team_policy eval idv catch total num of agent1: 29
team_policy eval team catch total num: 35
team_policy eval average step individual rewards of agent2: 0.8372771863078384
team_policy eval average team episode rewards of agent2: 87.5
team_policy eval idv catch total num of agent2: 35
team_policy eval team catch total num: 35
team_policy eval average step individual rewards of agent3: 0.5401746942743939
team_policy eval average team episode rewards of agent3: 87.5
team_policy eval idv catch total num of agent3: 23
team_policy eval team catch total num: 35
team_policy eval average step individual rewards of agent4: 0.5317569205774082
team_policy eval average team episode rewards of agent4: 87.5
team_policy eval idv catch total num of agent4: 23
team_policy eval team catch total num: 35
idv_policy eval average step individual rewards of agent0: 0.7655777501412819
idv_policy eval average team episode rewards of agent0: 127.5
idv_policy eval idv catch total num of agent0: 32
idv_policy eval team catch total num: 51
idv_policy eval average step individual rewards of agent1: 0.790022986342187
idv_policy eval average team episode rewards of agent1: 127.5
idv_policy eval idv catch total num of agent1: 33
idv_policy eval team catch total num: 51
idv_policy eval average step individual rewards of agent2: 1.222702877897033
idv_policy eval average team episode rewards of agent2: 127.5
idv_policy eval idv catch total num of agent2: 50
idv_policy eval team catch total num: 51
idv_policy eval average step individual rewards of agent3: 0.9620694979606432
idv_policy eval average team episode rewards of agent3: 127.5
idv_policy eval idv catch total num of agent3: 40
idv_policy eval team catch total num: 51
idv_policy eval average step individual rewards of agent4: 0.8134795988818658
idv_policy eval average team episode rewards of agent4: 127.5
idv_policy eval idv catch total num of agent4: 34
idv_policy eval team catch total num: 51

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3101/10000 episodes, total num timesteps 620400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3102/10000 episodes, total num timesteps 620600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3103/10000 episodes, total num timesteps 620800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3104/10000 episodes, total num timesteps 621000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3105/10000 episodes, total num timesteps 621200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3106/10000 episodes, total num timesteps 621400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3107/10000 episodes, total num timesteps 621600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3108/10000 episodes, total num timesteps 621800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3109/10000 episodes, total num timesteps 622000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3110/10000 episodes, total num timesteps 622200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3111/10000 episodes, total num timesteps 622400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3112/10000 episodes, total num timesteps 622600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3113/10000 episodes, total num timesteps 622800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3114/10000 episodes, total num timesteps 623000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3115/10000 episodes, total num timesteps 623200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3116/10000 episodes, total num timesteps 623400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3117/10000 episodes, total num timesteps 623600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3118/10000 episodes, total num timesteps 623800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3119/10000 episodes, total num timesteps 624000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3120/10000 episodes, total num timesteps 624200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3121/10000 episodes, total num timesteps 624400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3122/10000 episodes, total num timesteps 624600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3123/10000 episodes, total num timesteps 624800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3124/10000 episodes, total num timesteps 625000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3125/10000 episodes, total num timesteps 625200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.5235270447570792
team_policy eval average team episode rewards of agent0: 115.0
team_policy eval idv catch total num of agent0: 23
team_policy eval team catch total num: 46
team_policy eval average step individual rewards of agent1: 0.7725859292243021
team_policy eval average team episode rewards of agent1: 115.0
team_policy eval idv catch total num of agent1: 33
team_policy eval team catch total num: 46
team_policy eval average step individual rewards of agent2: 0.9836630012950078
team_policy eval average team episode rewards of agent2: 115.0
team_policy eval idv catch total num of agent2: 41
team_policy eval team catch total num: 46
team_policy eval average step individual rewards of agent3: 0.9687702508096467
team_policy eval average team episode rewards of agent3: 115.0
team_policy eval idv catch total num of agent3: 40
team_policy eval team catch total num: 46
team_policy eval average step individual rewards of agent4: 0.8569059415701026
team_policy eval average team episode rewards of agent4: 115.0
team_policy eval idv catch total num of agent4: 36
team_policy eval team catch total num: 46
idv_policy eval average step individual rewards of agent0: 0.9367751383343256
idv_policy eval average team episode rewards of agent0: 100.0
idv_policy eval idv catch total num of agent0: 39
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent1: 0.787495903765324
idv_policy eval average team episode rewards of agent1: 100.0
idv_policy eval idv catch total num of agent1: 33
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent2: 0.5657790330884713
idv_policy eval average team episode rewards of agent2: 100.0
idv_policy eval idv catch total num of agent2: 24
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent3: 0.534490308607496
idv_policy eval average team episode rewards of agent3: 100.0
idv_policy eval idv catch total num of agent3: 23
idv_policy eval team catch total num: 40
idv_policy eval average step individual rewards of agent4: 0.9780571958183971
idv_policy eval average team episode rewards of agent4: 100.0
idv_policy eval idv catch total num of agent4: 41
idv_policy eval team catch total num: 40

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3126/10000 episodes, total num timesteps 625400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3127/10000 episodes, total num timesteps 625600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3128/10000 episodes, total num timesteps 625800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3129/10000 episodes, total num timesteps 626000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3130/10000 episodes, total num timesteps 626200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3131/10000 episodes, total num timesteps 626400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3132/10000 episodes, total num timesteps 626600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3133/10000 episodes, total num timesteps 626800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3134/10000 episodes, total num timesteps 627000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3135/10000 episodes, total num timesteps 627200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3136/10000 episodes, total num timesteps 627400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3137/10000 episodes, total num timesteps 627600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3138/10000 episodes, total num timesteps 627800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3139/10000 episodes, total num timesteps 628000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3140/10000 episodes, total num timesteps 628200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3141/10000 episodes, total num timesteps 628400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3142/10000 episodes, total num timesteps 628600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3143/10000 episodes, total num timesteps 628800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3144/10000 episodes, total num timesteps 629000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3145/10000 episodes, total num timesteps 629200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3146/10000 episodes, total num timesteps 629400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3147/10000 episodes, total num timesteps 629600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3148/10000 episodes, total num timesteps 629800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3149/10000 episodes, total num timesteps 630000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3150/10000 episodes, total num timesteps 630200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.9212429708806326
team_policy eval average team episode rewards of agent0: 77.5
team_policy eval idv catch total num of agent0: 38
team_policy eval team catch total num: 31
team_policy eval average step individual rewards of agent1: 0.5034414384151679
team_policy eval average team episode rewards of agent1: 77.5
team_policy eval idv catch total num of agent1: 22
team_policy eval team catch total num: 31
team_policy eval average step individual rewards of agent2: 0.6365851766823593
team_policy eval average team episode rewards of agent2: 77.5
team_policy eval idv catch total num of agent2: 27
team_policy eval team catch total num: 31
team_policy eval average step individual rewards of agent3: 0.35706011895865913
team_policy eval average team episode rewards of agent3: 77.5
team_policy eval idv catch total num of agent3: 16
team_policy eval team catch total num: 31
team_policy eval average step individual rewards of agent4: 0.3542741999482314
team_policy eval average team episode rewards of agent4: 77.5
team_policy eval idv catch total num of agent4: 16
team_policy eval team catch total num: 31
idv_policy eval average step individual rewards of agent0: 0.5128642008897709
idv_policy eval average team episode rewards of agent0: 130.0
idv_policy eval idv catch total num of agent0: 22
idv_policy eval team catch total num: 52
idv_policy eval average step individual rewards of agent1: 1.0966785049638963
idv_policy eval average team episode rewards of agent1: 130.0
idv_policy eval idv catch total num of agent1: 45
idv_policy eval team catch total num: 52
idv_policy eval average step individual rewards of agent2: 0.8881574027158112
idv_policy eval average team episode rewards of agent2: 130.0
idv_policy eval idv catch total num of agent2: 37
idv_policy eval team catch total num: 52
idv_policy eval average step individual rewards of agent3: 0.7068572108271103
idv_policy eval average team episode rewards of agent3: 130.0
idv_policy eval idv catch total num of agent3: 30
idv_policy eval team catch total num: 52
idv_policy eval average step individual rewards of agent4: 0.9968807040302496
idv_policy eval average team episode rewards of agent4: 130.0
idv_policy eval idv catch total num of agent4: 41
idv_policy eval team catch total num: 52

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3151/10000 episodes, total num timesteps 630400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3152/10000 episodes, total num timesteps 630600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3153/10000 episodes, total num timesteps 630800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3154/10000 episodes, total num timesteps 631000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3155/10000 episodes, total num timesteps 631200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3156/10000 episodes, total num timesteps 631400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3157/10000 episodes, total num timesteps 631600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3158/10000 episodes, total num timesteps 631800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3159/10000 episodes, total num timesteps 632000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3160/10000 episodes, total num timesteps 632200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3161/10000 episodes, total num timesteps 632400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3162/10000 episodes, total num timesteps 632600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3163/10000 episodes, total num timesteps 632800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3164/10000 episodes, total num timesteps 633000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3165/10000 episodes, total num timesteps 633200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3166/10000 episodes, total num timesteps 633400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3167/10000 episodes, total num timesteps 633600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3168/10000 episodes, total num timesteps 633800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3169/10000 episodes, total num timesteps 634000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3170/10000 episodes, total num timesteps 634200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3171/10000 episodes, total num timesteps 634400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3172/10000 episodes, total num timesteps 634600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3173/10000 episodes, total num timesteps 634800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3174/10000 episodes, total num timesteps 635000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3175/10000 episodes, total num timesteps 635200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.5131514632156121
team_policy eval average team episode rewards of agent0: 92.5
team_policy eval idv catch total num of agent0: 22
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent1: 0.43361965341050024
team_policy eval average team episode rewards of agent1: 92.5
team_policy eval idv catch total num of agent1: 19
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent2: 0.7390027343813586
team_policy eval average team episode rewards of agent2: 92.5
team_policy eval idv catch total num of agent2: 31
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent3: 0.8579015317118105
team_policy eval average team episode rewards of agent3: 92.5
team_policy eval idv catch total num of agent3: 36
team_policy eval team catch total num: 37
team_policy eval average step individual rewards of agent4: 0.6770673427996767
team_policy eval average team episode rewards of agent4: 92.5
team_policy eval idv catch total num of agent4: 29
team_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent0: 0.6832970580414104
idv_policy eval average team episode rewards of agent0: 92.5
idv_policy eval idv catch total num of agent0: 29
idv_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent1: 1.0369336703286332
idv_policy eval average team episode rewards of agent1: 92.5
idv_policy eval idv catch total num of agent1: 43
idv_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent2: 0.5690116424423581
idv_policy eval average team episode rewards of agent2: 92.5
idv_policy eval idv catch total num of agent2: 24
idv_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent3: 0.6368455438737908
idv_policy eval average team episode rewards of agent3: 92.5
idv_policy eval idv catch total num of agent3: 27
idv_policy eval team catch total num: 37
idv_policy eval average step individual rewards of agent4: 0.8128655365721761
idv_policy eval average team episode rewards of agent4: 92.5
idv_policy eval idv catch total num of agent4: 34
idv_policy eval team catch total num: 37

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3176/10000 episodes, total num timesteps 635400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3177/10000 episodes, total num timesteps 635600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3178/10000 episodes, total num timesteps 635800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3179/10000 episodes, total num timesteps 636000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3180/10000 episodes, total num timesteps 636200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3181/10000 episodes, total num timesteps 636400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3182/10000 episodes, total num timesteps 636600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3183/10000 episodes, total num timesteps 636800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3184/10000 episodes, total num timesteps 637000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3185/10000 episodes, total num timesteps 637200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3186/10000 episodes, total num timesteps 637400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3187/10000 episodes, total num timesteps 637600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3188/10000 episodes, total num timesteps 637800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3189/10000 episodes, total num timesteps 638000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3190/10000 episodes, total num timesteps 638200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3191/10000 episodes, total num timesteps 638400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3192/10000 episodes, total num timesteps 638600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3193/10000 episodes, total num timesteps 638800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3194/10000 episodes, total num timesteps 639000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3195/10000 episodes, total num timesteps 639200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3196/10000 episodes, total num timesteps 639400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3197/10000 episodes, total num timesteps 639600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3198/10000 episodes, total num timesteps 639800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3199/10000 episodes, total num timesteps 640000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3200/10000 episodes, total num timesteps 640200/2000000, FPS 324.

team_policy eval average step individual rewards of agent0: 0.764461860532687
team_policy eval average team episode rewards of agent0: 75.0
team_policy eval idv catch total num of agent0: 32
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent1: 0.5833017397933857
team_policy eval average team episode rewards of agent1: 75.0
team_policy eval idv catch total num of agent1: 25
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent2: 0.5020890776562797
team_policy eval average team episode rewards of agent2: 75.0
team_policy eval idv catch total num of agent2: 22
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent3: 0.5381357801331432
team_policy eval average team episode rewards of agent3: 75.0
team_policy eval idv catch total num of agent3: 23
team_policy eval team catch total num: 30
team_policy eval average step individual rewards of agent4: 0.44936965511780513
team_policy eval average team episode rewards of agent4: 75.0
team_policy eval idv catch total num of agent4: 20
team_policy eval team catch total num: 30
idv_policy eval average step individual rewards of agent0: 0.562549473503894
idv_policy eval average team episode rewards of agent0: 90.0
idv_policy eval idv catch total num of agent0: 24
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent1: 0.7902115392884018
idv_policy eval average team episode rewards of agent1: 90.0
idv_policy eval idv catch total num of agent1: 33
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent2: 0.45786614834496525
idv_policy eval average team episode rewards of agent2: 90.0
idv_policy eval idv catch total num of agent2: 20
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent3: 1.0176073106192407
idv_policy eval average team episode rewards of agent3: 90.0
idv_policy eval idv catch total num of agent3: 42
idv_policy eval team catch total num: 36
idv_policy eval average step individual rewards of agent4: 0.6048727289369003
idv_policy eval average team episode rewards of agent4: 90.0
idv_policy eval idv catch total num of agent4: 26
idv_policy eval team catch total num: 36

 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3201/10000 episodes, total num timesteps 640400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3202/10000 episodes, total num timesteps 640600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3203/10000 episodes, total num timesteps 640800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3204/10000 episodes, total num timesteps 641000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3205/10000 episodes, total num timesteps 641200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3206/10000 episodes, total num timesteps 641400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3207/10000 episodes, total num timesteps 641600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3208/10000 episodes, total num timesteps 641800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3209/10000 episodes, total num timesteps 642000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3210/10000 episodes, total num timesteps 642200/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3211/10000 episodes, total num timesteps 642400/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3212/10000 episodes, total num timesteps 642600/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3213/10000 episodes, total num timesteps 642800/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3214/10000 episodes, total num timesteps 643000/2000000, FPS 324.


 Scenario simple_tag_tr Algo rmappotrsyn Exp exp_train_continue_tag_base_CMT_s2r2_v1 updates 3215/10000 episodes, total num timesteps 643200/2000000, FPS 324.

wandb: - 0.006 MB of 0.006 MB uploaded
wandb: \ 0.006 MB of 1.419 MB uploaded
wandb: | 1.419 MB of 1.419 MB uploaded
wandb: / 1.419 MB of 1.419 MB uploaded
wandb: 
wandb: Run history:
wandb:                                       Aa_idv_actor_loss █▁▁▁▁▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▆▆▆▆▇▆▆▇▇▇▇▇███
wandb:                                          Ab_policy_loss █▁▁▂▁▂▂▁▂▂▂▂▁▁▂▂▁▂▂▂▂▂▂▁▁▁▂▁▂▃▁▁▁▁▂▂▁▁▁▁
wandb:                                     Ac_idv_ppo_loss_abs ▆▆▁▂▂▃▅▅▂▆▆▃▅▂▇▇▇▅▇▆█▇▇▅▆▆▇▇██▇▆▅▇▇▇▆██▇
wandb:                                         Ad_idv_ppo_prop ▇▄▁▂▂▃▄▄▂▅▅▃▅▃▆▆▆▅▆▆▆▆▆▆▆▆▇▇▇▇▇▇▆▇▇▇▇███
wandb:                                                  Ae_eta █▅▅▄▅▅▄▅▄▄▆▄▅▄▆▅▄▄▄▄▅▅▄▁▅▄▆▄▄▆▅▄▅▅▅▅▅▃▄▄
wandb:                                    Af_noclip_proportion ▁██████████████▇█▇▇▇▇▇▇▅██▇▇▇▅▇█▇██▇█▆██
wandb:                                    Ag_update_proportion ██▇▂▄▁▄▆▄▆▄▅▄▅▇▅▇▆▇▅▇▆▇▆▇█▇▆█▇▇▇▇▇▇▇█▇▇▇
wandb:                                          Ah_update_loss ▆▁▁▇▅█▅▂▆▄▇▇▇▅▄▄▄▆▅▆▃▄▄▆▂▄▄▄▃▆▃▄▁▃▃▂▃▄▃▃
wandb:                                         Ai_idv_epsilon' ▁▁▁▁▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
wandb:                                            Aj_idv_sigma █▁▁▁▁▁▂▁▂▂▂▃▃▂▃▄▂▃▄▁▄▄▂▅▃▅▅▃▃▆▄▂▃▂▂▃▃▄▃▃
wandb:              Ak_idv_clip(sigma, 1-epislon', 1+epislon') ▂▂▂▂▂▁▂▂▃▃▂▃▃▂▄▄▃▄▅▂▅▄▃█▄▇▇▃▆█▃▃▆▃▃▆▆▇▆▆
wandb:                                Al_idv_noclip_proportion ▁▃▄▃▄▄▅▇▅▆▅▅▆▆▆▆▇▆▆▇▇▇▇▇▇▆▇█▇▇██████████
wandb:                       Am_idv_(sigma*A)update_proportion ▁▃▄▃▄▄▅▇▅▆▆▅▇▇▆▆▇▇▆█▇▇▇▇▇▆▇█▇▇▇██████▇██
wandb:                             An_idv_(sigma*A)update_loss ▁▇▇▇▆▆█▆▆▇▅▅▅▆▆▇▆▅▆▅▆▇▅▅▇▆▆▅▇▅▆▆▇▆▆▆▆▅▆▆
wandb:                                     Ao_idv_entropy_prop ▂▅█▇▇▆▅▅▇▄▄▆▄▆▃▃▃▄▃▃▃▃▃▃▃▃▂▂▂▂▂▂▃▂▂▂▂▁▁▁
wandb:                                         Ap_dist_entropy ▁███████████████████████████████████████
wandb:                                          Aq_idv_kl_prop ▁▁▁▁▁▁▁▁▂▁▂▂▂▂▂▃▂▃▃▃▄▄▄▄▄█▇▄▄▇▆▄▄▅▅▆▅▇▅▅
wandb:                                          Ar_idv_kl_coef ▁▁▁▁▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
wandb:                                          As_idv_kl_loss █▁▁▁▁▁▂▁▂▁▂▂▂▂▂▃▂▂▃▂▃▃▃▂▂▄▄▂▂▄▃▂▂▂▂▂▂▃▂▂
wandb:                                    At_idv_cross_entropy ▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb:                                           Au_value_loss ▁▁▁▃▁▃▂▁▂▃▂▁▂▂▂█▂▂▂▂▂▂▄▂▂▃▂▂▂▂▂▂▂▂▂▂▁▁▂▁
wandb:                                           Av_advantages ▃▃▄▆▅▄▄▂▄▂▅▅▅▅▅▆▆▄▅▃▅█▆▅▄▄▂▅▆▆▇▄▆▄▁▅▂▄▆▂
wandb:                                       Aw_idv_actor_norm █▅▃▄▃▂▃▁▂▂▂▂▃▂▂▃▁▂▃▂▂▃▂▃▂▃▃▂▃▄▃▂▂▂▂▃▂▃▂▂
wandb:                                      Ax_idv_critic_norm ▃▃▃█▃▇▅▂▄▅▄▃▄▃▄█▃▃▃▃▃▂▃▂▃▃▃▁▂▂▃▁▂▃▃▂▂▂▂▂
wandb:                                     Ba_idv_org_min_prop ▁▁▃▃▃▁▅▅▄▇▅▇▆▆█▅█▆▇▆█▇▇▇█▇▆▆█▆▇▇█▆▆▇▇▇▆█
wandb:                                     Bb_idv_org_max_prop ██▆▁▂▂▁▄▁▁▂▁▁▁▂▂▂▂▂▂▂▂▃▂▂▃▃▂▂▃▃▃▂▃▃▂▃▃▃▂
wandb:                                     Bc_idv_org_org_prop ▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb:                                     Bd_idv_new_min_prop ▁▆▇▃▄▄▄█▅▂▄▃▄▅▄▄▃▇▃▅▃▃▄▆▃▄▅▆▅▅▆▅▅▇▆▅▅▅▇▅
wandb:                                     Be_idv_new_max_prop ▁▂▃▃▄▄▅▆▅▆▆▆▇▇▇▆█▆▆█▇▇▇▇█▇▆█▇▇▇██████▇██
wandb:                                      Ta_team_actor_loss █▁▁▁▁▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▆▆▆▆▇▇▆▇▇▇▇████
wandb:                                     Tb_team_policy_loss ▄▄▄▅▄▅▅▄▄▄▄▅▄▄▃▅▃▅▅▄▅▆▅▃▄▁▄▅▆█▄▄▅▄▆▅▆▄▄▄
wandb:                                    Tc_team_ppo_loss_abs ▁▂▁▁▂▂▁▁▂▃▂▁▂▂▃▅▄▄▅▅▆▆▆▆▆▇▇▇██▇▇▆▇▇▇▇██▇
wandb:                                        Td_team_ppo_prop ▁▃▁▁▂▂▁▂▂▃▃▂▃▃▄▅▅▅▆▆▆▆▇▆▇▇▇▇█▇▇▇▇▇██████
wandb:                                        Te_team_epsilon^ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb:                                          Tf_team_sigma^ █▄▃▄▄▆▄▄▃▄▄▄▃▅▂▂▂▄▂▆▂▂▆▁▃▂▃▃▃▅▅▅▂▅▆▅▃▃▄▂
wandb:          Tg_team_clip(sigma^, 1-epislon^', 1+epislon^') ▁▆▆▆▆█▆▇▅▆▆▆▆▇▅▅▅▆▅▇▅▅▆▄▆▄▅▆▅▅▆▇▅▇▇▆▆▅▆▆
wandb:                               Th_team_noclip_proportion ▁███████▇█▇▆▇▇▇▅▇▆▆▇▆▅▆▆▇▄▄▆▆▄▆▆▇▇▆▆▇▅▆▆
wandb:                     Ti_team_(sigma^*A)update_proportion ▁███████▇█▇▇▇▇▇▆▇▆▆▇▇▆▆▆▆▄▅▇▆▅▆▇▇▇▇▆█▆▆▆
wandb:                           Tj_team_(sigma^*A)update_loss ▃▇▇▇▇▇▇▇█▆▇▇▇█▇▅█▆▅▃▅▄▆▇▇▇▄▇▃▁▃▇▆▇▅▄▆▇▅▇
wandb:                                    Tk_team_entropy_prop ▆▆██▇▇█▇▇▆▆▇▆▆▅▃▄▄▃▃▃▃▂▃▂▂▂▂▁▁▂▂▂▂▁▁▁▁▁▁
wandb:                                    Tl_team_dist_entropy ▁███████████████████████████████████████
wandb:                                         Tm_team_kl_prop █▁▁▁▁▂▁▁▂▁▂▂▂▂▂▂▁▂▂▂▂▂▂▂▂▃▂▂▂▂▂▂▂▂▂▂▁▂▂▂
wandb:                                         Tn_team_kl_coef ████▇▇▇▇▇▆▆▆▆▆▆▅▅▅▅▅▄▄▄▄▄▄▃▃▃▃▃▂▂▂▂▂▂▁▁▁
wandb:                                         To_team_kl_loss █▁▁▁▁▂▂▁▂▂▂▂▂▂▂▃▂▂▃▂▃▃▃▃▂▅▄▂▃▄▃▂▂▂▂▃▂▃▃▂
wandb:                                   Tp_team_cross_entropy ▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb:                                      Tq_team_value_loss ▁▁▁▁▁▂▁▁▂▂▁▁▁▂▂█▂▂▃▂▂▂▅▂▂▃▃▂▂▂▂▂▂▃▃▂▂▂▂▂
wandb:                                      Tr_team_advantages ▆▄▅▆▆▅▆▅▆▆▆▅▆▆▅▅▆▅▆▇▅▅▅▄▆▅▆▄▅▁▆▄▆█▄▄▆▇▆▃
wandb:                                      Ts_team_actor_norm █▂▂▂▂▂▂▁▂▂▂▂▃▂▂▂▂▂▂▂▂▃▃▃▂▃▃▂▃▄▃▂▂▂▂▃▂▃▂▂
wandb:                                     Tt_team_critic_norm ▂▁▁▄▁▄▃▂▃▄▃▃▃▃▄█▃▄▄▅▄▄▄▄▄▄▄▃▃▄▄▃▃▄▄▃▄▃▄▃
wandb:                     agent0/average_episode_team_rewards ▁▁▁▁▁▁▁▁▁▂▁▁▁▁▂▄▂▂▃▂▃▃▅▃▃▆▅▄▄▄▆▄▅▆▇▆▃▅█▄
wandb:                  agent0/average_step_individual_rewards ▁▁▂▁▃▂▂▂▂▄▃▂▂▂▃▄▃▃▅▄▄▅█▄▄▆▄▅▄▅▆▅▄▅▅█▄▆▆▄
wandb:     agent0/idv_policy_eval_average_episode_team_rewards ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:  agent0/idv_policy_eval_average_step_individual_rewards ▂▂▂▁▂▂▂▁▂▂▂▂▂▂▂▂▃▃▃▄▅▄▄▄▆▅▃▄▅▆▃▇▅▄▄▅█▅▄▅
wandb:              agent0/idv_policy_eval_idv_catch_total_num ▂▂▁▁▂▁▂▁▂▂▂▁▂▂▂▂▃▃▃▃▄▄▄▄▆▅▃▄▅▆▃▇▅▃▄▅█▄▄▅
wandb:             agent0/idv_policy_eval_team_catch_total_num ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:    agent0/team_policy_eval_average_episode_team_rewards ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb: agent0/team_policy_eval_average_step_individual_rewards ▁▁▁▁▂▂▂▄▂▂▂▂▃▃▄▂▃▄▆▄▃▆▄▆▆▅▆▇▄▇▆█▆▆▅▄▇▆▆▄
wandb:             agent0/team_policy_eval_idv_catch_total_num ▁▁▁▁▂▂▂▄▂▂▂▂▃▃▃▂▃▄▆▄▃▆▄▆▆▅▆▇▄▇▆█▆▆▅▄▇▆▆▄
wandb:            agent0/team_policy_eval_team_catch_total_num ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb:                     agent1/average_episode_team_rewards ▁▁▁▁▁▁▁▁▁▂▁▁▁▁▂▄▂▂▃▂▃▃▅▃▃▆▅▄▄▄▆▄▅▆▇▆▃▅█▄
wandb:                  agent1/average_step_individual_rewards ▁▁▁▃▁▂▂▂▃▃▂▂▃▂▃▄▂▃▄▅▄▄▃▄▄▆▇▄▄█▆▅▄▄▇▄▅▄▆▄
wandb:     agent1/idv_policy_eval_average_episode_team_rewards ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:  agent1/idv_policy_eval_average_step_individual_rewards ▂▁▂▁▂▁▂▂▂▂▂▂▂▂▂▂▂▂▃▄▄▄▄▃▆▄▄▄█▄▅▇▅▄▆▆▅▅▄▆
wandb:              agent1/idv_policy_eval_idv_catch_total_num ▂▁▁▁▂▁▂▁▂▁▂▂▁▁▂▂▂▁▂▄▄▄▄▃▆▄▃▄█▄▅▇▅▄▅▆▄▅▄▆
wandb:             agent1/idv_policy_eval_team_catch_total_num ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:    agent1/team_policy_eval_average_episode_team_rewards ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb: agent1/team_policy_eval_average_step_individual_rewards ▂▁▁▁▂▁▂▂▂▂▂▂▂▂▃▂▃▃▅▃▅▄▄▇█▅▇▅▄▆▆▇▅▅▆▇▇▅▇▄
wandb:             agent1/team_policy_eval_idv_catch_total_num ▂▁▁▁▂▁▁▁▂▂▂▂▂▂▃▂▃▃▅▃▅▄▄▇█▅▇▅▄▆▆▇▅▅▆▇▇▅▇▄
wandb:            agent1/team_policy_eval_team_catch_total_num ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb:                     agent2/average_episode_team_rewards ▁▁▁▁▁▁▁▁▁▂▁▁▁▁▂▄▂▂▃▂▃▃▅▃▃▆▅▄▄▄▆▄▅▆▇▆▃▅█▄
wandb:                  agent2/average_step_individual_rewards ▁▁▂▁▁▂▁▂▂▂▂▁▂▂▂▃▃▃▂▂▂▂▄▃▃▆▅▇▆▄▄▄▅█▄▅▅▄▆▆
wandb:     agent2/idv_policy_eval_average_episode_team_rewards ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:  agent2/idv_policy_eval_average_step_individual_rewards ▁▂▁▁▁▁▂▂▃▂▂▂▂▂▃▂▃▂▄▄▆▅▅▅▅▅▅▅▇▆▄▅█▅▅▇▆▆▅▄
wandb:              agent2/idv_policy_eval_idv_catch_total_num ▁▂▁▁▁▁▂▁▃▂▂▁▂▂▃▂▃▂▃▃▆▅▅▅▅▅▅▅▇▆▄▅█▅▅▇▅▆▅▄
wandb:             agent2/idv_policy_eval_team_catch_total_num ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:    agent2/team_policy_eval_average_episode_team_rewards ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb: agent2/team_policy_eval_average_step_individual_rewards ▂▁▁▁▂▂▂▂▂▃▂▂▂▃▃▃▃▅▅▄▄▅▃▅▇▆▆▆▃▅▇▇▇▅█▄▇▅▅▅
wandb:             agent2/team_policy_eval_idv_catch_total_num ▂▁▁▁▂▂▂▂▂▂▂▂▂▃▃▃▂▅▅▃▄▅▃▅▇▆▆▆▃▅▇▇▇▅█▄▇▅▄▅
wandb:            agent2/team_policy_eval_team_catch_total_num ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb:                     agent3/average_episode_team_rewards ▁▁▁▁▁▁▁▁▁▂▁▁▁▁▂▄▂▂▃▂▃▃▅▃▃▆▅▄▄▄▆▄▅▆▇▆▃▅█▄
wandb:                  agent3/average_step_individual_rewards ▁▁▁▁▂▁▂▂▂▂▃▂▂▂▃▂▂▂▅▄▃▃▅▄▄▅▄▃▃▄▅▅▇█▅▆▄▂▆▅
wandb:     agent3/idv_policy_eval_average_episode_team_rewards ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:  agent3/idv_policy_eval_average_step_individual_rewards ▂▂▁▁▂▁▂▁▂▂▂▂▂▂▃▂▃▂▂▃▃▄▅▂▄▄▅▄▆▆▄█▅▄▄▅▇▅▄▄
wandb:              agent3/idv_policy_eval_idv_catch_total_num ▂▁▁▁▂▁▁▁▂▂▂▁▁▁▂▂▂▂▂▂▃▃▅▂▄▃▅▄▆▆▄█▅▄▄▅▆▄▄▄
wandb:             agent3/idv_policy_eval_team_catch_total_num ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:    agent3/team_policy_eval_average_episode_team_rewards ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb: agent3/team_policy_eval_average_step_individual_rewards ▂▁▁▂▂▂▁▃▂▁▂▂▂▂▂▃▃▃▄▃▄▄▅▆▄▅▆▅▄▄▅▄▆▅▄▃█▃▅▅
wandb:             agent3/team_policy_eval_idv_catch_total_num ▁▁▁▁▂▂▁▃▂▁▁▁▂▂▂▂▃▃▄▃▄▄▅▅▄▅▅▅▄▄▅▄▅▅▄▃█▃▄▅
wandb:            agent3/team_policy_eval_team_catch_total_num ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb:                     agent4/average_episode_team_rewards ▁▁▁▁▁▁▁▁▁▂▁▁▁▁▂▄▂▂▃▂▃▃▅▃▃▆▅▄▄▄▆▄▅▆▇▆▃▅█▄
wandb:                  agent4/average_step_individual_rewards ▂▁▁▂▄▂▂▁▂▂▂▂▂▂▄▄▃▄▃▂▃▂▅▄▂▅▆▄▆▅▆▄▄▇█▅▆▇▆▅
wandb:     agent4/idv_policy_eval_average_episode_team_rewards ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:  agent4/idv_policy_eval_average_step_individual_rewards ▂▂▂▁▂▂▂▂▂▃▂▂▃▃▃▃▄▃▅▃▅▄▅▇▇▆▃▅▇▇▇▇▅██▅█▆▇▇
wandb:              agent4/idv_policy_eval_idv_catch_total_num ▁▂▂▁▂▁▁▁▂▃▂▁▂▃▃▂▃▃▅▃▅▄▅▇▆▆▂▅▇▆▇▇▅██▅█▆▇▇
wandb:             agent4/idv_policy_eval_team_catch_total_num ▁▁▁▁▂▁▁▁▂▂▂▁▂▂▂▂▃▂▃▃▅▄▅▄▆▅▄▅█▆▅█▆▅▅▆▆▆▅▅
wandb:    agent4/team_policy_eval_average_episode_team_rewards ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb: agent4/team_policy_eval_average_step_individual_rewards ▁▁▁▁▂▂▁▂▂▂▁▁▂▂▂▃▃▄▃▄▃▄▂▄▄▆▄▄█▆▅▇▃▇▆▅▇▅▅▅
wandb:             agent4/team_policy_eval_idv_catch_total_num ▂▁▁▁▂▂▁▂▂▂▁▁▂▂▂▃▃▄▃▄▃▄▂▄▄▆▄▄█▆▅▇▃▇▆▅▇▅▅▅
wandb:            agent4/team_policy_eval_team_catch_total_num ▁▁▁▁▁▁▁▃▂▂▂▁▂▁▃▃▃▄▅▄▄▅▄▇▇▆▆▆▅▆▆▇▅▇▇▄█▅▆▆
wandb: 
wandb: Run summary:
wandb:                                       Aa_idv_actor_loss -0.30177
wandb:                                          Ab_policy_loss 0.00193
wandb:                                     Ac_idv_ppo_loss_abs 0.80495
wandb:                                         Ad_idv_ppo_prop 0.71944
wandb:                                                  Ae_eta 0.99951
wandb:                                    Af_noclip_proportion 0.9992
wandb:                                    Ag_update_proportion 0.4587
wandb:                                          Ah_update_loss 0.21087
wandb:                                         Ai_idv_epsilon' 0.16075
wandb:                                            Aj_idv_sigma 1.01265
wandb:              Ak_idv_clip(sigma, 1-epislon', 1+epislon') 1.00854
wandb:                                Al_idv_noclip_proportion 0.92
wandb:                       Am_idv_(sigma*A)update_proportion 0.4975
wandb:                             An_idv_(sigma*A)update_loss -0.15497
wandb:                                     Ao_idv_entropy_prop 0.276
wandb:                                         Ap_dist_entropy 4.83785
wandb:                                          Aq_idv_kl_prop 0.00456
wandb:                                          Ar_idv_kl_coef 2.2505
wandb:                                          As_idv_kl_loss 0.00227
wandb:                                    At_idv_cross_entropy 0.0
wandb:                                           Au_value_loss 0.37115
wandb:                                           Av_advantages 0.0
wandb:                                       Aw_idv_actor_norm 0.32143
wandb:                                      Ax_idv_critic_norm 0.32491
wandb:                                     Ba_idv_org_min_prop 0.3971
wandb:                                     Bb_idv_org_max_prop 0.0616
wandb:                                     Bc_idv_org_org_prop 0.0
wandb:                                     Bd_idv_new_min_prop 0.1071
wandb:                                     Be_idv_new_max_prop 0.3904
wandb:                                      Ta_team_actor_loss -0.2961
wandb:                                     Tb_team_policy_loss 0.00202
wandb:                                    Tc_team_ppo_loss_abs 0.78167
wandb:                                        Td_team_ppo_prop 0.70986
wandb:                                        Te_team_epsilon^ 0.2
wandb:                                          Tf_team_sigma^ 0.99523
wandb:          Tg_team_clip(sigma^, 1-epislon^', 1+epislon^') 0.99391
wandb:                               Th_team_noclip_proportion 0.9548
wandb:                     Ti_team_(sigma^*A)update_proportion 0.9806
wandb:                           Tj_team_(sigma^*A)update_loss -0.01641
wandb:                                    Tk_team_entropy_prop 0.28044
wandb:                                    Tl_team_dist_entropy 4.83787
wandb:                                         Tm_team_kl_prop 0.00971
wandb:                                         Tn_team_kl_coef 4.7495
wandb:                                         To_team_kl_loss 0.00225
wandb:                                   Tp_team_cross_entropy 0.0
wandb:                                      Tq_team_value_loss 0.414
wandb:                                      Tr_team_advantages 0.0
wandb:                                      Ts_team_actor_norm 0.39924
wandb:                                     Tt_team_critic_norm 0.32464
wandb:                     agent0/average_episode_team_rewards 37.5
wandb:                  agent0/average_step_individual_rewards 0.32843
wandb:     agent0/idv_policy_eval_average_episode_team_rewards 90.0
wandb:  agent0/idv_policy_eval_average_step_individual_rewards 0.56255
wandb:              agent0/idv_policy_eval_idv_catch_total_num 24
wandb:             agent0/idv_policy_eval_team_catch_total_num 36
wandb:    agent0/team_policy_eval_average_episode_team_rewards 75.0
wandb: agent0/team_policy_eval_average_step_individual_rewards 0.76446
wandb:             agent0/team_policy_eval_idv_catch_total_num 32
wandb:            agent0/team_policy_eval_team_catch_total_num 30
wandb:                     agent1/average_episode_team_rewards 37.5
wandb:                  agent1/average_step_individual_rewards 0.55858
wandb:     agent1/idv_policy_eval_average_episode_team_rewards 90.0
wandb:  agent1/idv_policy_eval_average_step_individual_rewards 0.79021
wandb:              agent1/idv_policy_eval_idv_catch_total_num 33
wandb:             agent1/idv_policy_eval_team_catch_total_num 36
wandb:    agent1/team_policy_eval_average_episode_team_rewards 75.0
wandb: agent1/team_policy_eval_average_step_individual_rewards 0.5833
wandb:             agent1/team_policy_eval_idv_catch_total_num 25
wandb:            agent1/team_policy_eval_team_catch_total_num 30
wandb:                     agent2/average_episode_team_rewards 37.5
wandb:                  agent2/average_step_individual_rewards 0.4323
wandb:     agent2/idv_policy_eval_average_episode_team_rewards 90.0
wandb:  agent2/idv_policy_eval_average_step_individual_rewards 0.45787
wandb:              agent2/idv_policy_eval_idv_catch_total_num 20
wandb:             agent2/idv_policy_eval_team_catch_total_num 36
wandb:    agent2/team_policy_eval_average_episode_team_rewards 75.0
wandb: agent2/team_policy_eval_average_step_individual_rewards 0.50209
wandb:             agent2/team_policy_eval_idv_catch_total_num 22
wandb:            agent2/team_policy_eval_team_catch_total_num 30
wandb:                     agent3/average_episode_team_rewards 37.5
wandb:                  agent3/average_step_individual_rewards 0.35533
wandb:     agent3/idv_policy_eval_average_episode_team_rewards 90.0
wandb:  agent3/idv_policy_eval_average_step_individual_rewards 1.01761
wandb:              agent3/idv_policy_eval_idv_catch_total_num 42
wandb:             agent3/idv_policy_eval_team_catch_total_num 36
wandb:    agent3/team_policy_eval_average_episode_team_rewards 75.0
wandb: agent3/team_policy_eval_average_step_individual_rewards 0.53814
wandb:             agent3/team_policy_eval_idv_catch_total_num 23
wandb:            agent3/team_policy_eval_team_catch_total_num 30
wandb:                     agent4/average_episode_team_rewards 37.5
wandb:                  agent4/average_step_individual_rewards 0.48526
wandb:     agent4/idv_policy_eval_average_episode_team_rewards 90.0
wandb:  agent4/idv_policy_eval_average_step_individual_rewards 0.60487
wandb:              agent4/idv_policy_eval_idv_catch_total_num 26
wandb:             agent4/idv_policy_eval_team_catch_total_num 36
wandb:    agent4/team_policy_eval_average_episode_team_rewards 75.0
wandb: agent4/team_policy_eval_average_step_individual_rewards 0.44937
wandb:             agent4/team_policy_eval_idv_catch_total_num 20
wandb:            agent4/team_policy_eval_team_catch_total_num 30
wandb: 
wandb: 🚀 View run MPE_7 at: https://wandb.ai/804703098/Continue_Tag_Base_v1/runs/ipiauwxx
wandb: ⭐️ View project at: https://wandb.ai/804703098/Continue_Tag_Base_v1
wandb: Synced 6 W&B file(s), 0 media file(s), 0 artifact file(s) and 4 other file(s)
wandb: Find logs at: ./results/MPE/simple_tag_tr/rmappotrsyn/exp_train_continue_tag_base_CMT_s2r2_v1/wandb/run-20240508_193312-ipiauwxx/logs
Traceback (most recent call last):
  File "train/train_mpe_trsyn.py", line 244, in <module>
    main(sys.argv[1:])
  File "train/train_mpe_trsyn.py", line 229, in main
    runner.run()
  File "/home/user/zhangyang/PycharmProjects/Nips2024-ITPC-v2/Nips2024-ITPC-v2/onpolicy/runner/shared/mpe_runner_trsyn.py", line 64, in run
    obs, rewards, dones, infos = self.envs.step(actions_env)
  File "/home/user/zhangyang/PycharmProjects/Nips2024-ITPC-v2/Nips2024-ITPC-v2/onpolicy/envs/env_wrappers.py", line 106, in step
    self.step_async(actions)
  File "/home/user/zhangyang/PycharmProjects/Nips2024-ITPC-v2/Nips2024-ITPC-v2/onpolicy/envs/env_wrappers.py", line 261, in step_async
    remote.send(('step', action))
  File "/home/user/anaconda3/envs/zypy38/lib/python3.8/multiprocessing/connection.py", line 206, in send
    self._send_bytes(_ForkingPickler.dumps(obj))
  File "/home/user/anaconda3/envs/zypy38/lib/python3.8/multiprocessing/connection.py", line 411, in _send_bytes
    self._send(header + buf)
  File "/home/user/anaconda3/envs/zypy38/lib/python3.8/multiprocessing/connection.py", line 368, in _send
    n = write(self._handle, buf)
BrokenPipeError: [Errno 32] Broken pipe
