/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
=== specification ====================================================
+: rlrd.training:Training
epochs: 10
rounds: 50
steps: 2000
stats_window: 10000
seed: 0
tag: ''
Env:
   +: rlrd.envs:RandomDelayEnv
   seed_val: 0
   id: HalfCheetah-v4
   frame_skip: 0
   min_observation_delay: 0
   sup_observation_delay: 1
   min_action_delay: 0
   sup_action_delay: 1
   real_world_sampler: 5
   action_noise: 0.05
Test:
   +: rlrd.testing:Test
   workers: 1
   number: 1
   device: cpu
Agent:
   +: rlrd.dcac:Agent
   batchsize: 128
   memory_size: 1000000
   lr: 0.0003
   discount: 0.99
   target_update: 0.005
   reward_scale: 5.0
   entropy_scale: 1.0
   start_training: 10000
   device: cpu
   training_steps: 1.0
   loss_alpha: 0.2
   rtac: false
   Model:
      +: rlrd.dcac_models:Mlp
      hidden_units: 256
      num_critics: 2
      act_delay: true
      obs_delay: true
   OutputNorm:
      +: rlrd.nn:PopArt
      beta: 0.0003
      zero_debias: true
      start_pop: 8
__format_version__: '3'
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>

<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 1/10 ===== round 1/50 ======================================
100%|██████████| 2000/2000 [00:01<00:00, 1530.06it/s]
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                    2
episode_length                         1000.0
returns                           -274.905727
return_std                           8.993353
average_reward                      -0.274906
round_time             0 days 00:00:01.368312
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.962839
return_std_test                      2.766148
average_reward_test                 -0.008963
round_time_test        0 days 00:00:06.725990
round_time_total       0 days 00:00:08.368520 

=== epoch 1/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1534.33it/s]
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                    4
episode_length                         1000.0
returns                           -253.662738
return_std                          34.864795
average_reward                      -0.253663
round_time             0 days 00:00:01.762192
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.873886
return_std_test                      2.441655
average_reward_test                 -0.008874
round_time_test        0 days 00:00:06.774523
round_time_total       0 days 00:00:08.392788 

=== epoch 1/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1534.81it/s]
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                    6
episode_length                         1000.0
returns                           -238.945522
return_std                          46.331517
average_reward                      -0.238946
round_time             0 days 00:00:01.757147
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -6.798739
return_std_test                      4.953609
average_reward_test                 -0.006799
round_time_test        0 days 00:00:06.779682
round_time_total       0 days 00:00:08.354201 

=== epoch 1/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1524.50it/s]
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                    8
episode_length                         1000.0
returns                           -235.367653
return_std                          40.722644
average_reward                      -0.235368
round_time             0 days 00:00:01.769636
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.839454
return_std_test                      2.879052
average_reward_test                 -0.008839
round_time_test        0 days 00:00:06.762407
round_time_total       0 days 00:00:08.393782 

=== epoch 1/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1388.76it/s]
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -246.313559
return_std                           42.50598
average_reward                      -0.246314
round_time             0 days 00:00:01.907952
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.868969
return_std_test                      4.812919
average_reward_test                 -0.008869
round_time_test        0 days 00:00:06.814006
round_time_total       0 days 00:00:08.432116 

=== epoch 1/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 0/2000 [00:00<?, ?it/s]/<ANONYMIZED PATH>/rmst-rlrd/rlrd/nn.py:41: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
  assert b.storage().data_ptr() == a.storage().data_ptr()
  0%|          | 9/2000 [00:01<05:09,  6.44it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [04:29<00:00,  7.41it/s]
starting training
episodes                                   10
episode_length                         1000.0
returns                           -241.129988
return_std                          40.140513
average_reward                       -0.24113
round_time             0 days 00:04:30.367468
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.909486
return_std_test                      2.804463
average_reward_test                 -0.008909
round_time_test        0 days 00:00:06.901598
round_time_total       0 days 00:04:30.368560
loss_total                         151.033598
loss_critic                        205.291095
loss_actor                         -65.996404
memory_size                         10793.653 

=== epoch 1/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<04:59,  6.64it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [04:31<00:00,  7.37it/s]
episodes                                   10
episode_length                         1000.0
returns                           -246.426955
return_std                          45.716447
average_reward                      -0.246427
round_time             0 days 00:04:31.729942
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -55.126323
return_std_test                     19.100625
average_reward_test                 -0.055126
round_time_test        0 days 00:00:07.106228
round_time_total       0 days 00:04:31.731014
loss_total                         166.202183
loss_critic                        243.286007
loss_actor                        -142.133126
memory_size                         12757.653 

=== epoch 1/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<04:43,  7.02it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:11<00:00,  6.42it/s]
episodes                                   10
episode_length                         1000.0
returns                           -259.682777
return_std                          39.721989
average_reward                      -0.259683
round_time             0 days 00:05:12.029623
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -53.909659
return_std_test                      7.442057
average_reward_test                  -0.05391
round_time_test        0 days 00:00:06.935039
round_time_total       0 days 00:05:12.030724
loss_total                          226.61419
loss_critic                        333.921869
loss_actor                        -202.616545
memory_size                         14721.653 

=== epoch 1/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:28,  5.12it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:26<00:00,  6.13it/s]
episodes                                   10
episode_length                         1000.0
returns                           -269.362552
return_std                          37.341213
average_reward                      -0.269363
round_time             0 days 00:05:26.880510
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -22.277915
return_std_test                      8.108807
average_reward_test                 -0.022278
round_time_test        0 days 00:00:07.759801
round_time_total       0 days 00:05:26.881608
loss_total                         123.544214
loss_critic                        214.593458
loss_actor                        -240.652769
memory_size                         16685.653 

=== epoch 1/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:12,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:28<00:00,  6.09it/s]
episodes                                   10
episode_length                         1000.0
returns                           -262.118294
return_std                          38.577025
average_reward                      -0.262118
round_time             0 days 00:05:28.896980
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -36.194634
return_std_test                     14.339134
average_reward_test                 -0.036195
round_time_test        0 days 00:00:07.906569
round_time_total       0 days 00:05:28.898321
loss_total                         119.385574
loss_critic                        215.343855
loss_actor                        -264.447556
memory_size                         18649.653 

=== epoch 1/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.33it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.06it/s]
episodes                                   10
episode_length                         1000.0
returns                           -272.729981
return_std                          40.718058
average_reward                       -0.27273
round_time             0 days 00:05:30.440081
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -52.121486
return_std_test                     50.232881
average_reward_test                 -0.052121
round_time_test        0 days 00:00:07.821687
round_time_total       0 days 00:05:30.441379
loss_total                         107.770394
loss_critic                        204.176695
loss_actor                        -277.854816
memory_size                         20613.653 

=== epoch 1/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -275.769843
return_std                          31.838208
average_reward                       -0.27577
round_time             0 days 00:05:31.232906
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -37.774231
return_std_test                     49.771311
average_reward_test                 -0.037774
round_time_test        0 days 00:00:07.866128
round_time_total       0 days 00:05:31.234003
loss_total                         122.418729
loss_critic                        224.182074
loss_actor                        -284.634659
memory_size                         22577.653 

=== epoch 1/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:56,  5.58it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.04it/s]
episodes                                   10
episode_length                         1000.0
returns                           -275.183407
return_std                           31.10661
average_reward                      -0.275183
round_time             0 days 00:05:31.562744
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -36.558684
return_std_test                     21.852557
average_reward_test                 -0.036559
round_time_test        0 days 00:00:08.001889
round_time_total       0 days 00:05:31.564083
loss_total                         114.020287
loss_critic                        214.187745
loss_actor                        -286.649551
memory_size                         24541.653 

=== epoch 1/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:16,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.04it/s]
episodes                                   10
episode_length                         1000.0
returns                           -264.038601
return_std                          38.578355
average_reward                      -0.264039
round_time             0 days 00:05:31.493292
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -34.897669
return_std_test                     24.718517
average_reward_test                 -0.034898
round_time_test        0 days 00:00:08.009034
round_time_total       0 days 00:05:31.494611
loss_total                         111.494622
loss_critic                        210.953504
loss_actor                        -286.340914
memory_size                         26505.653 

=== epoch 1/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:16,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -250.547001
return_std                          48.049342
average_reward                      -0.250547
round_time             0 days 00:05:35.249024
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -56.548537
return_std_test                     17.481585
average_reward_test                 -0.056549
round_time_test        0 days 00:00:07.978406
round_time_total       0 days 00:05:35.250118
loss_total                         113.550853
loss_critic                        213.807259
loss_actor                        -287.474777
memory_size                         28469.653 

=== epoch 1/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:06,  5.42it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.04it/s]
episodes                                   10
episode_length                         1000.0
returns                           -236.847685
return_std                          41.298944
average_reward                      -0.236848
round_time             0 days 00:05:31.664354
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -42.588494
return_std_test                     21.073296
average_reward_test                 -0.042588
round_time_test        0 days 00:00:07.987594
round_time_total       0 days 00:05:31.665488
loss_total                         106.372074
loss_critic                        204.914851
loss_actor                        -287.799038
memory_size                         30433.653 

=== epoch 1/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:26,  5.15it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -229.789769
return_std                          36.006532
average_reward                       -0.22979
round_time             0 days 00:05:33.235971
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -68.875809
return_std_test                     20.877811
average_reward_test                 -0.068876
round_time_test        0 days 00:00:07.767374
round_time_total       0 days 00:05:33.237051
loss_total                         108.259512
loss_critic                        207.371019
loss_actor                        -288.186522
memory_size                         32397.653 

=== epoch 1/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:05,  5.44it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -224.982807
return_std                          28.646372
average_reward                      -0.224983
round_time             0 days 00:05:32.680789
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -74.551949
return_std_test                     27.223125
average_reward_test                 -0.074552
round_time_test        0 days 00:00:07.937055
round_time_total       0 days 00:05:32.682304
loss_total                          98.983869
loss_critic                        195.680553
loss_actor                        -287.802872
memory_size                         34361.653 

=== epoch 1/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:10,  5.38it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.03it/s]
episodes                                   10
episode_length                         1000.0
returns                           -227.546923
return_std                          28.026535
average_reward                      -0.227547
round_time             0 days 00:05:32.206809
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -30.092728
return_std_test                     19.191045
average_reward_test                 -0.030093
round_time_test        0 days 00:00:07.878086
round_time_total       0 days 00:05:32.208033
loss_total                          96.511728
loss_critic                        192.673431
loss_actor                        -288.135092
memory_size                         36325.653 

=== epoch 1/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:16,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -241.645829
return_std                          20.685346
average_reward                      -0.241646
round_time             0 days 00:05:33.708711
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -25.262395
return_std_test                     16.951381
average_reward_test                 -0.025262
round_time_test        0 days 00:00:07.916455
round_time_total       0 days 00:05:33.709976
loss_total                          92.487574
loss_critic                        187.699196
loss_actor                        -288.358917
memory_size                         38289.653 

=== epoch 1/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:35,  5.03it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -234.835862
return_std                          25.805613
average_reward                      -0.234836
round_time             0 days 00:05:34.537507
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -49.763662
return_std_test                     23.714281
average_reward_test                 -0.049764
round_time_test        0 days 00:00:08.030850
round_time_total       0 days 00:05:34.538647
loss_total                         102.130704
loss_critic                         200.08865
loss_actor                        -289.701089
memory_size                         40253.653 

=== epoch 1/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:16,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -241.037623
return_std                          35.316788
average_reward                      -0.241038
round_time             0 days 00:05:32.653974
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -25.367848
return_std_test                     20.864377
average_reward_test                 -0.025368
round_time_test        0 days 00:00:07.854862
round_time_total       0 days 00:05:32.655092
loss_total                         111.592678
loss_critic                        211.972134
loss_actor                        -289.925152
memory_size                         42217.653 

=== epoch 1/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:07,  5.42it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -242.747275
return_std                          37.116868
average_reward                      -0.242747
round_time             0 days 00:05:36.399611
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -24.919978
return_std_test                     26.527807
average_reward_test                  -0.02492
round_time_test        0 days 00:00:07.909481
round_time_total       0 days 00:05:36.401031
loss_total                         110.120839
loss_critic                        209.914507
loss_actor                        -289.053845
memory_size                         44181.653 

=== epoch 1/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:25,  5.16it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -250.721194
return_std                           39.40809
average_reward                      -0.250721
round_time             0 days 00:05:36.859305
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -26.710719
return_std_test                     17.866522
average_reward_test                 -0.026711
round_time_test        0 days 00:00:07.998796
round_time_total       0 days 00:05:36.860694
loss_total                         126.627946
loss_critic                        230.337523
loss_actor                        -288.210373
memory_size                         46145.653 

=== epoch 1/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:10,  5.38it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -242.114668
return_std                          46.541502
average_reward                      -0.242115
round_time             0 days 00:05:36.355814
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -41.001804
return_std_test                      11.64535
average_reward_test                 -0.041002
round_time_test        0 days 00:00:07.869270
round_time_total       0 days 00:05:36.357305
loss_total                         124.241659
loss_critic                        227.080276
loss_actor                        -287.112817
memory_size                         48109.653 

=== epoch 1/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:03,  5.48it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -245.952752
return_std                          46.759201
average_reward                      -0.245953
round_time             0 days 00:05:35.855710
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -37.347986
return_std_test                     21.674055
average_reward_test                 -0.037348
round_time_test        0 days 00:00:07.955962
round_time_total       0 days 00:05:35.857012
loss_total                         120.994068
loss_critic                        222.945736
loss_actor                        -286.812613
memory_size                         50073.653 

=== epoch 1/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:01,  5.51it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -241.975088
return_std                          40.477918
average_reward                      -0.241975
round_time             0 days 00:05:35.415721
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -15.550299
return_std_test                     26.995354
average_reward_test                  -0.01555
round_time_test        0 days 00:00:07.888684
round_time_total       0 days 00:05:35.417076
loss_total                         126.693478
loss_critic                        230.067457
loss_actor                        -286.802447
memory_size                         52037.653 

=== epoch 1/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.33it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -238.503967
return_std                          37.338555
average_reward                      -0.238504
round_time             0 days 00:05:34.921788
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -27.335114
return_std_test                     27.916475
average_reward_test                 -0.027335
round_time_test        0 days 00:00:07.979627
round_time_total       0 days 00:05:34.922978
loss_total                         142.430448
loss_critic                        249.634679
loss_actor                        -286.386484
memory_size                         54001.653 

=== epoch 1/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:05,  5.44it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -230.692362
return_std                          30.717728
average_reward                      -0.230692
round_time             0 days 00:05:37.873199
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -26.359133
return_std_test                     20.889119
average_reward_test                 -0.026359
round_time_test        0 days 00:00:07.913265
round_time_total       0 days 00:05:37.874478
loss_total                         141.381491
loss_critic                        248.197018
loss_actor                        -285.880625
memory_size                         55965.653 

=== epoch 1/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:15,  5.30it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -237.385928
return_std                          21.608051
average_reward                      -0.237386
round_time             0 days 00:05:35.200692
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -18.48703
return_std_test                      17.07461
average_reward_test                 -0.018487
round_time_test        0 days 00:00:07.830685
round_time_total       0 days 00:05:35.201781
loss_total                         134.272103
loss_critic                        239.168823
loss_actor                        -285.314788
memory_size                         57929.653 

=== epoch 1/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 7/2000 [00:01<07:24,  4.48it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -239.032931
return_std                          11.925464
average_reward                      -0.239033
round_time             0 days 00:05:38.989633
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -15.630697
return_std_test                     24.948105
average_reward_test                 -0.015631
round_time_test        0 days 00:00:07.997196
round_time_total       0 days 00:05:38.990728
loss_total                         134.455318
loss_critic                        239.302906
loss_actor                        -284.935044
memory_size                         59893.653 

=== epoch 1/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:53,  4.81it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -241.285358
return_std                          13.907419
average_reward                      -0.241285
round_time             0 days 00:05:37.224366
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -18.977399
return_std_test                     24.592411
average_reward_test                 -0.018977
round_time_test        0 days 00:00:07.877728
round_time_total       0 days 00:05:37.225861
loss_total                         142.576183
loss_critic                        249.470055
loss_actor                        -284.999315
memory_size                         61857.653 

=== epoch 1/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:37,  5.01it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -239.135564
return_std                          22.983127
average_reward                      -0.239136
round_time             0 days 00:05:36.609957
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        26.228472
return_std_test                     30.036062
average_reward_test                  0.026228
round_time_test        0 days 00:00:07.749182
round_time_total       0 days 00:05:36.611049
loss_total                         141.419005
loss_critic                        247.762164
loss_actor                        -283.953642
memory_size                         63821.653 

=== epoch 1/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:57,  5.57it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -241.622945
return_std                          40.262608
average_reward                      -0.241623
round_time             0 days 00:05:36.660996
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        35.602507
return_std_test                     21.419279
average_reward_test                  0.035603
round_time_test        0 days 00:00:08.166434
round_time_total       0 days 00:05:36.662451
loss_total                         132.921727
loss_critic                        236.993281
loss_actor                        -283.364493
memory_size                         65785.653 

=== epoch 1/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:24,  5.17it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -242.892827
return_std                          43.690395
average_reward                      -0.242893
round_time             0 days 00:05:36.838367
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -17.862226
return_std_test                      41.98861
average_reward_test                 -0.017862
round_time_test        0 days 00:00:07.885002
round_time_total       0 days 00:05:36.839451
loss_total                         134.228263
loss_critic                        238.611153
loss_actor                        -283.303305
memory_size                         67749.653 

=== epoch 1/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:02<08:20,  3.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -236.778292
return_std                          48.177201
average_reward                      -0.236778
round_time             0 days 00:05:40.338741
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -15.112043
return_std_test                     29.747223
average_reward_test                 -0.015112
round_time_test        0 days 00:00:07.966331
round_time_total       0 days 00:05:40.340003
loss_total                         130.152361
loss_critic                        233.740965
loss_actor                        -284.202065
memory_size                         69713.653 

=== epoch 1/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:26,  5.15it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -229.240298
return_std                          47.458752
average_reward                       -0.22924
round_time             0 days 00:05:38.858377
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -30.305768
return_std_test                     49.369128
average_reward_test                 -0.030306
round_time_test        0 days 00:00:07.998849
round_time_total       0 days 00:05:38.859466
loss_total                         133.662846
loss_critic                        238.372739
loss_actor                        -285.176735
memory_size                         71677.653 

=== epoch 1/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:19,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -230.133695
return_std                          44.043601
average_reward                      -0.230134
round_time             0 days 00:05:39.268122
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -40.187496
return_std_test                     26.384637
average_reward_test                 -0.040187
round_time_test        0 days 00:00:07.961004
round_time_total       0 days 00:05:39.269277
loss_total                         130.461716
loss_critic                        234.481857
loss_actor                        -285.618854
memory_size                         73641.653 

=== epoch 1/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:14,  5.31it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -228.503732
return_std                          35.650898
average_reward                      -0.228504
round_time             0 days 00:05:36.096064
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -42.335802
return_std_test                     19.089562
average_reward_test                 -0.042336
round_time_test        0 days 00:00:08.084815
round_time_total       0 days 00:05:36.097147
loss_total                         132.926151
loss_critic                        237.613666
loss_actor                        -285.823916
memory_size                         75605.653 

=== epoch 1/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:00,  4.74it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -217.577239
return_std                          30.777985
average_reward                      -0.217577
round_time             0 days 00:05:41.248946
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -22.934339
return_std_test                     26.513167
average_reward_test                 -0.022934
round_time_test        0 days 00:00:07.934875
round_time_total       0 days 00:05:41.250111
loss_total                         132.818686
loss_critic                        237.573034
loss_actor                        -286.198716
memory_size                         77569.653 

=== epoch 1/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:01,  5.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -226.421115
return_std                          32.771076
average_reward                      -0.226421
round_time             0 days 00:05:38.194974
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -43.721615
return_std_test                     14.906775
average_reward_test                 -0.043722
round_time_test        0 days 00:00:07.996532
round_time_total       0 days 00:05:38.196081
loss_total                         130.345594
loss_critic                        234.712482
loss_actor                        -287.121968
memory_size                         79533.653 

=== epoch 1/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.33it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -230.868564
return_std                          34.340579
average_reward                      -0.230869
round_time             0 days 00:05:37.700497
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -40.048786
return_std_test                     29.221741
average_reward_test                 -0.040049
round_time_test        0 days 00:00:07.938808
round_time_total       0 days 00:05:37.701995
loss_total                         128.724689
loss_critic                        232.879968
loss_actor                        -287.896434
memory_size                         81497.653 

=== epoch 1/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:25,  5.16it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -236.865379
return_std                           36.85213
average_reward                      -0.236865
round_time             0 days 00:05:38.761130
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -26.194593
return_std_test                     61.632504
average_reward_test                 -0.026195
round_time_test        0 days 00:00:07.783801
round_time_total       0 days 00:05:38.762420
loss_total                         125.523138
loss_critic                        229.019419
loss_actor                        -288.461997
memory_size                         83461.653 

=== epoch 1/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -228.514394
return_std                          34.689874
average_reward                      -0.228514
round_time             0 days 00:05:41.184710
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -23.201054
return_std_test                     11.569805
average_reward_test                 -0.023201
round_time_test        0 days 00:00:08.018351
round_time_total       0 days 00:05:41.185830
loss_total                         125.074155
loss_critic                        228.676833
loss_actor                        -289.336566
memory_size                         85425.653 

=== epoch 1/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:55,  5.59it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                            -239.45832
return_std                          32.192669
average_reward                      -0.239458
round_time             0 days 00:05:36.852020
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         24.43642
return_std_test                     35.909725
average_reward_test                  0.024436
round_time_test        0 days 00:00:08.017141
round_time_total       0 days 00:05:36.853117
loss_total                         126.197352
loss_critic                        230.266278
loss_actor                         -290.07836
memory_size                         87389.653 

=== epoch 1/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -241.396974
return_std                          27.914072
average_reward                      -0.241397
round_time             0 days 00:05:38.974195
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -64.741209
return_std_test                     36.921628
average_reward_test                 -0.064741
round_time_test        0 days 00:00:07.851540
round_time_total       0 days 00:05:38.975273
loss_total                         120.943832
loss_critic                        223.820854
loss_actor                        -290.564263
memory_size                         89353.653 

=== epoch 1/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -234.669096
return_std                          28.449732
average_reward                      -0.234669
round_time             0 days 00:05:38.222072
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.121672
return_std_test                      25.77295
average_reward_test                  0.006122
round_time_test        0 days 00:00:07.869391
round_time_total       0 days 00:05:38.223164
loss_total                          126.56644
loss_critic                        230.918238
loss_actor                        -290.840757
memory_size                         91317.653 

=== epoch 1/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:44,  4.93it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -218.204373
return_std                          30.803036
average_reward                      -0.218204
round_time             0 days 00:05:42.219153
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -43.188123
return_std_test                     34.598123
average_reward_test                 -0.043188
round_time_test        0 days 00:00:07.732519
round_time_total       0 days 00:05:42.220501
loss_total                         121.950198
loss_critic                        225.346068
loss_actor                        -291.633287
memory_size                         93281.653 

=== epoch 1/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:40,  4.97it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -224.675742
return_std                          29.556822
average_reward                      -0.224676
round_time             0 days 00:05:41.603688
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -41.643626
return_std_test                     25.133649
average_reward_test                 -0.041644
round_time_test        0 days 00:00:07.995289
round_time_total       0 days 00:05:41.604784
loss_total                         117.202943
loss_critic                        219.501174
loss_actor                        -291.989987
memory_size                         95245.653 

=== epoch 1/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:53,  4.82it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -223.821592
return_std                          28.493906
average_reward                      -0.223822
round_time             0 days 00:05:41.878449
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -24.408159
return_std_test                     22.296186
average_reward_test                 -0.024408
round_time_test        0 days 00:00:07.830710
round_time_total       0 days 00:05:41.879669
loss_total                         116.455619
loss_critic                        218.707741
loss_actor                        -292.552877
memory_size                         97209.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 2/10 ===== round 1/50 ======================================
  1%|          | 13/2000 [00:02<05:42,  5.80it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:20<00:00,  6.24it/s]
episodes                                    2
episode_length                         1000.0
returns                           -219.352744
return_std                           3.851586
average_reward                      -0.219353
round_time             0 days 00:05:20.654961
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -14.83082
return_std_test                     23.712341
average_reward_test                 -0.014831
round_time_test        0 days 00:00:07.848209
round_time_total       0 days 00:05:20.656368
loss_total                         117.884959
loss_critic                        220.622867
loss_actor                        -293.066677
memory_size                         99174.653 

=== epoch 2/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:17,  5.27it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:21<00:00,  6.21it/s]
episodes                                    4
episode_length                         1000.0
returns                           -216.926503
return_std                          25.392283
average_reward                      -0.216927
round_time             0 days 00:05:22.533434
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.059342
return_std_test                     24.744523
average_reward_test                  0.006059
round_time_test        0 days 00:00:08.010324
round_time_total       0 days 00:05:22.534529
loss_total                          115.00782
loss_critic                        217.269729
loss_actor                        -294.039824
memory_size                        101138.653 

=== epoch 2/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:07,  5.41it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:22<00:00,  6.21it/s]
episodes                                    6
episode_length                         1000.0
returns                           -213.681243
return_std                          30.687843
average_reward                      -0.213681
round_time             0 days 00:05:22.799598
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -26.524027
return_std_test                     22.979811
average_reward_test                 -0.026524
round_time_test        0 days 00:00:08.094299
round_time_total       0 days 00:05:22.800674
loss_total                         112.284058
loss_critic                        214.118398
loss_actor                        -295.053309
memory_size                        103102.653 

=== epoch 2/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:05,  5.45it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:23<00:00,  6.19it/s]
episodes                                    8
episode_length                         1000.0
returns                           -216.104679
return_std                          27.101658
average_reward                      -0.216105
round_time             0 days 00:05:23.806128
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.093087
return_std_test                     19.530677
average_reward_test                  0.001093
round_time_test        0 days 00:00:07.750244
round_time_total       0 days 00:05:23.807246
loss_total                          114.43216
loss_critic                        216.789479
loss_actor                        -294.997124
memory_size                        105066.653 

=== epoch 2/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:38,  5.00it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:25<00:00,  6.15it/s]
episodes                                   10
episode_length                         1000.0
returns                           -217.840015
return_std                          24.691187
average_reward                       -0.21784
round_time             0 days 00:05:25.909104
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         -2.00194
return_std_test                     36.062777
average_reward_test                 -0.002002
round_time_test        0 days 00:00:07.834565
round_time_total       0 days 00:05:25.910405
loss_total                         115.240077
loss_critic                        218.022847
loss_actor                         -295.89101
memory_size                        107030.653 

=== epoch 2/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:25<00:00,  6.14it/s]
episodes                                   10
episode_length                         1000.0
returns                           -208.454923
return_std                           37.32645
average_reward                      -0.208455
round_time             0 days 00:05:26.249235
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -16.629972
return_std_test                     19.743338
average_reward_test                  -0.01663
round_time_test        0 days 00:00:07.912982
round_time_total       0 days 00:05:26.250368
loss_total                         120.156289
loss_critic                        224.231291
loss_actor                        -296.143727
memory_size                        108994.653 

=== epoch 2/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:16,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.11it/s]
episodes                                   10
episode_length                         1000.0
returns                           -213.726906
return_std                          38.959838
average_reward                      -0.213727
round_time             0 days 00:05:27.801007
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -13.020324
return_std_test                     16.948244
average_reward_test                  -0.01302
round_time_test        0 days 00:00:08.097560
round_time_total       0 days 00:05:27.802482
loss_total                         125.425835
loss_critic                         230.88788
loss_actor                        -296.422352
memory_size                        110958.653 

=== epoch 2/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:45,  5.76it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.06it/s]
episodes                                   10
episode_length                         1000.0
returns                           -210.690702
return_std                           37.00208
average_reward                      -0.210691
round_time             0 days 00:05:30.613184
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -34.326917
return_std_test                     27.883348
average_reward_test                 -0.034327
round_time_test        0 days 00:00:07.970168
round_time_total       0 days 00:05:30.614298
loss_total                         135.283471
loss_critic                        243.421511
loss_actor                        -297.268697
memory_size                        112922.653 

=== epoch 2/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.33it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.10it/s]
episodes                                   10
episode_length                         1000.0
returns                           -214.565108
return_std                          39.071341
average_reward                      -0.214565
round_time             0 days 00:05:28.535092
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -29.912029
return_std_test                     25.408697
average_reward_test                 -0.029912
round_time_test        0 days 00:00:07.878908
round_time_total       0 days 00:05:28.536182
loss_total                         141.236392
loss_critic                        250.859348
loss_actor                        -297.255439
memory_size                        114886.653 

=== epoch 2/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:21,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -215.833897
return_std                          39.784321
average_reward                      -0.215834
round_time             0 days 00:05:30.213554
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -32.074265
return_std_test                     32.715958
average_reward_test                 -0.032074
round_time_test        0 days 00:00:07.893138
round_time_total       0 days 00:05:30.214652
loss_total                          136.33605
loss_critic                        244.723652
loss_actor                        -297.214362
memory_size                        116850.653 

=== epoch 2/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:16,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -227.287629
return_std                          25.506833
average_reward                      -0.227288
round_time             0 days 00:05:31.212748
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -24.313242
return_std_test                     28.658673
average_reward_test                 -0.024313
round_time_test        0 days 00:00:07.912841
round_time_total       0 days 00:05:31.213842
loss_total                         138.058074
loss_critic                        246.902393
loss_actor                        -297.319215
memory_size                        118814.653 

=== epoch 2/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:03,  5.48it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                            -229.46061
return_std                          22.996071
average_reward                      -0.229461
round_time             0 days 00:05:31.434517
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -20.945483
return_std_test                     17.734787
average_reward_test                 -0.020945
round_time_test        0 days 00:00:07.863022
round_time_total       0 days 00:05:31.435597
loss_total                         149.252597
loss_critic                        260.759128
loss_actor                        -296.773535
memory_size                        120778.653 

=== epoch 2/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 7/2000 [00:01<07:00,  4.74it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -228.701724
return_std                          28.691983
average_reward                      -0.228702
round_time             0 days 00:05:34.482652
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -5.106785
return_std_test                     20.096161
average_reward_test                 -0.005107
round_time_test        0 days 00:00:07.819667
round_time_total       0 days 00:05:34.483869
loss_total                         145.195769
loss_critic                        255.637861
loss_actor                        -296.572611
memory_size                        122742.653 

=== epoch 2/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:49,  4.86it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -219.645291
return_std                          29.822245
average_reward                      -0.219645
round_time             0 days 00:05:33.300619
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -7.101681
return_std_test                     27.881838
average_reward_test                 -0.007102
round_time_test        0 days 00:00:07.953413
round_time_total       0 days 00:05:33.301757
loss_total                         147.302858
loss_critic                        258.338049
loss_actor                        -296.837918
memory_size                        124706.653 

=== epoch 2/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:16,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                            -225.87175
return_std                          34.822354
average_reward                      -0.225872
round_time             0 days 00:05:30.928592
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -20.562493
return_std_test                     24.047684
average_reward_test                 -0.020562
round_time_test        0 days 00:00:08.134497
round_time_total       0 days 00:05:30.929678
loss_total                         151.222186
loss_critic                        263.389982
loss_actor                        -297.449007
memory_size                        126670.653 

=== epoch 2/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -227.975353
return_std                          35.320681
average_reward                      -0.227975
round_time             0 days 00:05:33.202690
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -23.230358
return_std_test                     17.395209
average_reward_test                  -0.02323
round_time_test        0 days 00:00:08.008685
round_time_total       0 days 00:05:33.204250
loss_total                          151.21358
loss_critic                        263.421219
loss_actor                        -297.616987
memory_size                        128634.653 

=== epoch 2/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:20,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -246.882981
return_std                          59.806017
average_reward                      -0.246883
round_time             0 days 00:05:34.119931
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -17.890824
return_std_test                     14.137138
average_reward_test                 -0.017891
round_time_test        0 days 00:00:07.769769
round_time_total       0 days 00:05:34.121337
loss_total                         167.351096
loss_critic                        283.563274
loss_actor                        -297.497626
memory_size                        130598.653 

=== epoch 2/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:40,  4.97it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -261.675824
return_std                          51.568371
average_reward                      -0.261676
round_time             0 days 00:05:37.335509
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -12.683386
return_std_test                     17.289205
average_reward_test                 -0.012683
round_time_test        0 days 00:00:08.140500
round_time_total       0 days 00:05:37.336588
loss_total                         180.085101
loss_critic                         299.14098
loss_actor                        -296.138431
memory_size                        132562.653 

=== epoch 2/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:19,  5.25it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -267.447247
return_std                          49.276142
average_reward                      -0.267447
round_time             0 days 00:05:35.806263
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -2.471254
return_std_test                     15.762178
average_reward_test                 -0.002471
round_time_test        0 days 00:00:08.083147
round_time_total       0 days 00:05:35.807454
loss_total                         183.400056
loss_critic                        303.020123
loss_actor                        -295.080224
memory_size                        134526.653 

=== epoch 2/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:04,  4.69it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -248.679988
return_std                           63.21416
average_reward                       -0.24868
round_time             0 days 00:05:35.372599
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -0.642271
return_std_test                     16.821491
average_reward_test                 -0.000642
round_time_test        0 days 00:00:07.775473
round_time_total       0 days 00:05:35.373919
loss_total                          183.70646
loss_critic                        303.296281
loss_actor                        -294.652839
memory_size                        136490.653 

=== epoch 2/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:41,  4.96it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                            -245.33273
return_std                          64.740552
average_reward                      -0.245333
round_time             0 days 00:05:34.628550
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -18.884411
return_std_test                     31.164038
average_reward_test                 -0.018884
round_time_test        0 days 00:00:08.009413
round_time_total       0 days 00:05:34.629825
loss_total                         185.977324
loss_critic                        306.182397
loss_actor                        -294.842983
memory_size                        138454.653 

=== epoch 2/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:21,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -221.624885
return_std                          40.678934
average_reward                      -0.221625
round_time             0 days 00:05:35.044274
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -11.66379
return_std_test                     25.959747
average_reward_test                 -0.011664
round_time_test        0 days 00:00:08.176590
round_time_total       0 days 00:05:35.045357
loss_total                         187.468325
loss_critic                        308.053428
loss_actor                        -294.872105
memory_size                        140418.653 

=== epoch 2/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:17,  5.27it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -205.615702
return_std                           34.06183
average_reward                      -0.205616
round_time             0 days 00:05:40.082273
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -10.95164
return_std_test                     38.932629
average_reward_test                 -0.010952
round_time_test        0 days 00:00:08.030422
round_time_total       0 days 00:05:40.083664
loss_total                         180.521288
loss_critic                        299.590863
loss_actor                        -295.757023
memory_size                        142382.653 

=== epoch 2/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.255795
return_std                          26.633215
average_reward                      -0.203256
round_time             0 days 00:05:36.824627
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.477469
return_std_test                     21.806722
average_reward_test                  0.005477
round_time_test        0 days 00:00:07.826158
round_time_total       0 days 00:05:36.825710
loss_total                         175.646394
loss_critic                        293.627612
loss_actor                        -296.278493
memory_size                        144346.653 

=== epoch 2/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:44,  4.93it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -207.745748
return_std                          22.194528
average_reward                      -0.207746
round_time             0 days 00:05:37.546880
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.382753
return_std_test                     20.221981
average_reward_test                 -0.008383
round_time_test        0 days 00:00:07.848121
round_time_total       0 days 00:05:37.547957
loss_total                         172.801459
loss_critic                        290.224048
loss_actor                         -296.88891
memory_size                        146310.653 

=== epoch 2/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:42,  4.95it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -207.344224
return_std                          20.111143
average_reward                      -0.207344
round_time             0 days 00:05:39.686532
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -17.192796
return_std_test                      24.42603
average_reward_test                 -0.017193
round_time_test        0 days 00:00:08.039454
round_time_total       0 days 00:05:39.687627
loss_total                         173.007349
loss_critic                        290.769624
loss_actor                        -298.041764
memory_size                        148274.653 

=== epoch 2/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:31,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                            -199.75869
return_std                          17.946263
average_reward                      -0.199759
round_time             0 days 00:05:38.101087
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.228146
return_std_test                     16.774051
average_reward_test                  0.005228
round_time_test        0 days 00:00:08.005285
round_time_total       0 days 00:05:38.102544
loss_total                         169.649517
loss_critic                        286.827406
loss_actor                        -299.062048
memory_size                        150238.653 

=== epoch 2/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.20it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -201.665755
return_std                           16.45901
average_reward                      -0.201666
round_time             0 days 00:05:36.559545
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -2.697142
return_std_test                     15.742068
average_reward_test                 -0.002697
round_time_test        0 days 00:00:07.888963
round_time_total       0 days 00:05:36.560635
loss_total                         169.716343
loss_critic                        287.149448
loss_actor                        -300.016089
memory_size                        152202.653 

=== epoch 2/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:08,  5.40it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.917639
return_std                          18.832775
average_reward                      -0.203918
round_time             0 days 00:05:36.464661
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.876704
return_std_test                     17.187906
average_reward_test                  0.004877
round_time_test        0 days 00:00:08.132949
round_time_total       0 days 00:05:36.465742
loss_total                         165.589281
loss_critic                        282.109201
loss_actor                        -300.490411
memory_size                        154166.653 

=== epoch 2/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:34,  5.05it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -214.898808
return_std                          22.698868
average_reward                      -0.214899
round_time             0 days 00:05:38.472136
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.686769
return_std_test                     10.826214
average_reward_test                  0.007687
round_time_test        0 days 00:00:07.933884
round_time_total       0 days 00:05:38.473464
loss_total                         165.532116
loss_critic                        282.192816
loss_actor                        -301.110697
memory_size                        156130.653 

=== epoch 2/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:52,  4.83it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -212.523407
return_std                          22.882488
average_reward                      -0.212523
round_time             0 days 00:05:37.071465
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.923179
return_std_test                     18.997295
average_reward_test                  0.008923
round_time_test        0 days 00:00:07.956272
round_time_total       0 days 00:05:37.072827
loss_total                         165.110235
loss_critic                        281.887006
loss_actor                        -301.996861
memory_size                        158094.653 

=== epoch 2/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:54,  4.81it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -216.160468
return_std                          20.565104
average_reward                       -0.21616
round_time             0 days 00:05:40.500900
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -15.870548
return_std_test                     22.682884
average_reward_test                 -0.015871
round_time_test        0 days 00:00:08.071456
round_time_total       0 days 00:05:40.502002
loss_total                         165.736036
loss_critic                        282.863185
loss_actor                        -302.772568
memory_size                        160058.653 

=== epoch 2/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:26,  5.16it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -221.149625
return_std                          17.404773
average_reward                       -0.22115
round_time             0 days 00:05:38.272507
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.734924
return_std_test                     15.472626
average_reward_test                 -0.008735
round_time_test        0 days 00:00:08.113345
round_time_total       0 days 00:05:38.273960
loss_total                           159.8485
loss_critic                        275.671657
loss_actor                         -303.44414
memory_size                        162022.653 

=== epoch 2/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:53,  5.63it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -215.514352
return_std                          20.190451
average_reward                      -0.215514
round_time             0 days 00:05:39.246602
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -9.560814
return_std_test                     28.226254
average_reward_test                 -0.009561
round_time_test        0 days 00:00:08.144708
round_time_total       0 days 00:05:39.247796
loss_total                         159.044912
loss_critic                        274.916507
loss_actor                        -304.441478
memory_size                        163986.653 

=== epoch 2/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:50,  4.86it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -206.967842
return_std                          14.829867
average_reward                      -0.206968
round_time             0 days 00:05:39.577461
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -13.598226
return_std_test                     27.270294
average_reward_test                 -0.013598
round_time_test        0 days 00:00:08.041512
round_time_total       0 days 00:05:39.578571
loss_total                         155.233827
loss_critic                         270.42937
loss_actor                        -305.548354
memory_size                        165950.653 

=== epoch 2/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:03,  5.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -197.979609
return_std                          23.572641
average_reward                       -0.19798
round_time             0 days 00:05:37.390893
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -6.812277
return_std_test                     21.449077
average_reward_test                 -0.006812
round_time_test        0 days 00:00:07.965467
round_time_total       0 days 00:05:37.391973
loss_total                         152.738112
loss_critic                        267.584397
loss_actor                        -306.647037
memory_size                        167914.653 

=== epoch 2/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:03,  5.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -195.245569
return_std                          22.860839
average_reward                      -0.195246
round_time             0 days 00:05:39.169474
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -3.386249
return_std_test                     23.615831
average_reward_test                 -0.003386
round_time_test        0 days 00:00:07.902431
round_time_total       0 days 00:05:39.170717
loss_total                         153.665094
loss_critic                        268.910818
loss_actor                        -307.317814
memory_size                        169878.653 

=== epoch 2/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:09,  5.38it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -193.807994
return_std                          24.860172
average_reward                      -0.193808
round_time             0 days 00:05:37.742246
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.521796
return_std_test                      15.37573
average_reward_test                  0.000522
round_time_test        0 days 00:00:08.136035
round_time_total       0 days 00:05:37.743350
loss_total                         152.029813
loss_critic                        266.990327
loss_actor                        -307.812253
memory_size                        171842.653 

=== epoch 2/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                             -191.8811
return_std                          24.783669
average_reward                      -0.191881
round_time             0 days 00:05:40.049742
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.104689
return_std_test                     18.137558
average_reward_test                  0.010105
round_time_test        0 days 00:00:07.933300
round_time_total       0 days 00:05:40.050848
loss_total                          149.48435
loss_critic                        263.960564
loss_actor                        -308.420515
memory_size                        173806.653 

=== epoch 2/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:53,  4.82it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                            -196.58308
return_std                          35.936233
average_reward                      -0.196583
round_time             0 days 00:05:39.848814
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -6.676292
return_std_test                     15.522265
average_reward_test                 -0.006676
round_time_test        0 days 00:00:08.307246
round_time_total       0 days 00:05:39.850398
loss_total                         149.161657
loss_critic                        263.757537
loss_actor                        -309.221875
memory_size                        175770.653 

=== epoch 2/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.987671
return_std                          31.076357
average_reward                      -0.203988
round_time             0 days 00:05:37.460732
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.725384
return_std_test                      7.298811
average_reward_test                  0.001725
round_time_test        0 days 00:00:07.915168
round_time_total       0 days 00:05:37.461958
loss_total                         146.289666
loss_critic                         260.32164
loss_actor                        -309.838242
memory_size                        177734.653 

=== epoch 2/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 6/2000 [00:01<10:34,  3.14it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -211.189621
return_std                          32.263465
average_reward                       -0.21119
round_time             0 days 00:05:41.487886
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.756144
return_std_test                     27.283915
average_reward_test                  0.004756
round_time_test        0 days 00:00:07.884512
round_time_total       0 days 00:05:41.489021
loss_total                         148.181227
loss_critic                        262.829691
loss_actor                        -310.412636
memory_size                        179698.653 

=== epoch 2/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:22,  5.20it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -213.184283
return_std                            30.8423
average_reward                      -0.213184
round_time             0 days 00:05:40.263846
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -11.317389
return_std_test                     19.549718
average_reward_test                 -0.011317
round_time_test        0 days 00:00:08.041415
round_time_total       0 days 00:05:40.265379
loss_total                         150.943825
loss_critic                        266.425355
loss_actor                        -310.982304
memory_size                        181662.653 

=== epoch 2/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:58,  5.55it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -217.104671
return_std                          28.427188
average_reward                      -0.217105
round_time             0 days 00:05:39.731726
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.928087
return_std_test                      8.504606
average_reward_test                  0.006928
round_time_test        0 days 00:00:08.087212
round_time_total       0 days 00:05:39.732854
loss_total                          147.70781
loss_critic                        262.513215
loss_actor                        -311.513822
memory_size                        183626.653 

=== epoch 2/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:12,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -205.909163
return_std                          25.778238
average_reward                      -0.205909
round_time             0 days 00:05:40.732464
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -9.652278
return_std_test                     26.739749
average_reward_test                 -0.009652
round_time_test        0 days 00:00:07.968754
round_time_total       0 days 00:05:40.733559
loss_total                         143.637838
loss_critic                        257.552863
loss_actor                        -312.022267
memory_size                        185590.653 

=== epoch 2/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:20,  5.23it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.230082
return_std                          29.289466
average_reward                       -0.20323
round_time             0 days 00:05:39.078961
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -7.437936
return_std_test                     28.951951
average_reward_test                 -0.007438
round_time_test        0 days 00:00:08.186815
round_time_total       0 days 00:05:39.080536
loss_total                         144.017702
loss_critic                        258.126097
loss_actor                        -312.415889
memory_size                        187554.653 

=== epoch 2/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:24,  5.18it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -202.149747
return_std                          28.807617
average_reward                       -0.20215
round_time             0 days 00:05:40.682694
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -11.218746
return_std_test                     29.334564
average_reward_test                 -0.011219
round_time_test        0 days 00:00:07.930448
round_time_total       0 days 00:05:40.683777
loss_total                         141.784584
loss_critic                        255.477904
loss_actor                        -312.988706
memory_size                        189518.653 

=== epoch 2/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:20,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -199.748793
return_std                          25.842528
average_reward                      -0.199749
round_time             0 days 00:05:37.593569
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.092452
return_std_test                     20.595117
average_reward_test                 -0.008092
round_time_test        0 days 00:00:08.023674
round_time_total       0 days 00:05:37.595029
loss_total                         140.020563
loss_critic                        253.430221
loss_actor                         -313.61808
memory_size                        191482.653 

=== epoch 2/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:41,  4.96it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -198.527882
return_std                          25.714125
average_reward                      -0.198528
round_time             0 days 00:05:42.694154
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -5.572588
return_std_test                     32.235268
average_reward_test                 -0.005573
round_time_test        0 days 00:00:07.761504
round_time_total       0 days 00:05:42.695254
loss_total                         139.034267
loss_critic                        252.234323
loss_actor                        -313.765968
memory_size                        193446.653 

=== epoch 2/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:48,  5.71it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -210.662699
return_std                          25.743102
average_reward                      -0.210663
round_time             0 days 00:05:39.105621
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -13.072868
return_std_test                     27.091154
average_reward_test                 -0.013073
round_time_test        0 days 00:00:07.967764
round_time_total       0 days 00:05:39.106704
loss_total                         137.302283
loss_critic                        250.206793
loss_actor                        -314.315767
memory_size                        195410.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 3/10 ===== round 1/50 ======================================
  1%|          | 13/2000 [00:02<05:26,  6.08it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:17<00:00,  6.30it/s]
episodes                                    2
episode_length                         1000.0
returns                           -220.797031
return_std                          15.243067
average_reward                      -0.220797
round_time             0 days 00:05:17.512035
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -23.307121
return_std_test                     34.397718
average_reward_test                 -0.023307
round_time_test        0 days 00:00:08.231659
round_time_total       0 days 00:05:17.513144
loss_total                         139.236403
loss_critic                        252.802105
loss_actor                        -315.026415
memory_size                        197375.653 

=== epoch 3/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:32,  5.07it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:22<00:00,  6.21it/s]
episodes                                    4
episode_length                         1000.0
returns                           -227.691506
return_std                          14.923886
average_reward                      -0.227692
round_time             0 days 00:05:22.551238
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -6.866114
return_std_test                      36.86081
average_reward_test                 -0.006866
round_time_test        0 days 00:00:07.949347
round_time_total       0 days 00:05:22.552337
loss_total                         139.456328
loss_critic                        253.225962
loss_actor                        -315.622213
memory_size                        199339.653 

=== epoch 3/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:51,  5.66it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:22<00:00,  6.20it/s]
episodes                                    6
episode_length                         1000.0
returns                           -211.066451
return_std                          27.549005
average_reward                      -0.211066
round_time             0 days 00:05:23.362350
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.623746
return_std_test                     10.151934
average_reward_test                  0.005624
round_time_test        0 days 00:00:08.181572
round_time_total       0 days 00:05:23.363470
loss_total                         140.544004
loss_critic                        254.627442
loss_actor                        -315.789758
memory_size                        201303.653 

=== epoch 3/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:33,  5.05it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:24<00:00,  6.16it/s]
episodes                                    8
episode_length                         1000.0
returns                           -204.930809
return_std                           26.12433
average_reward                      -0.204931
round_time             0 days 00:05:25.236490
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.581216
return_std_test                     21.662246
average_reward_test                  0.007581
round_time_test        0 days 00:00:07.710785
round_time_total       0 days 00:05:25.237893
loss_total                         138.936625
loss_critic                        252.700778
loss_actor                        -316.119995
memory_size                        203267.653 

=== epoch 3/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:10,  5.38it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:23<00:00,  6.18it/s]
episodes                                   10
episode_length                         1000.0
returns                           -211.789914
return_std                          28.127305
average_reward                       -0.21179
round_time             0 days 00:05:24.332552
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -4.998989
return_std_test                     25.501236
average_reward_test                 -0.004999
round_time_test        0 days 00:00:07.975901
round_time_total       0 days 00:05:24.333646
loss_total                         138.953884
loss_critic                        252.740243
loss_actor                        -316.191562
memory_size                        205231.653 

=== epoch 3/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:48,  5.70it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:25<00:00,  6.15it/s]
episodes                                   10
episode_length                         1000.0
returns                           -209.888935
return_std                          32.784769
average_reward                      -0.209889
round_time             0 days 00:05:25.697080
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         -8.77691
return_std_test                     21.765776
average_reward_test                 -0.008777
round_time_test        0 days 00:00:07.774373
round_time_total       0 days 00:05:25.698385
loss_total                         147.296213
loss_critic                        263.253665
loss_actor                        -316.533604
memory_size                        207195.653 

=== epoch 3/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:19,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -202.442038
return_std                          31.959833
average_reward                      -0.202442
round_time             0 days 00:05:30.072352
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -1.070602
return_std_test                     26.086938
average_reward_test                 -0.001071
round_time_test        0 days 00:00:07.877738
round_time_total       0 days 00:05:30.073452
loss_total                         151.431994
loss_critic                        268.349307
loss_actor                        -316.237271
memory_size                        209159.653 

=== epoch 3/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:49,  5.69it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.06it/s]
episodes                                   10
episode_length                         1000.0
returns                           -208.665151
return_std                          29.297603
average_reward                      -0.208665
round_time             0 days 00:05:30.385859
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.500982
return_std_test                     20.371711
average_reward_test                  0.002501
round_time_test        0 days 00:00:07.807806
round_time_total       0 days 00:05:30.387246
loss_total                         150.001164
loss_critic                        266.636847
loss_actor                         -316.54158
memory_size                        211123.653 

=== epoch 3/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:54,  5.61it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -213.786308
return_std                          27.316086
average_reward                      -0.213786
round_time             0 days 00:05:32.826337
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         -3.63773
return_std_test                     29.030785
average_reward_test                 -0.003638
round_time_test        0 days 00:00:08.017883
round_time_total       0 days 00:05:32.827438
loss_total                         150.609568
loss_critic                        267.438026
loss_actor                        -316.704275
memory_size                        213087.653 

=== epoch 3/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:14,  5.32it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -196.212988
return_std                          32.517339
average_reward                      -0.196213
round_time             0 days 00:05:32.631942
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -35.729121
return_std_test                     38.842664
average_reward_test                 -0.035729
round_time_test        0 days 00:00:07.889591
round_time_total       0 days 00:05:32.633248
loss_total                         152.086437
loss_critic                        269.437621
loss_actor                         -317.31831
memory_size                        215051.653 

=== epoch 3/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:20,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.06it/s]
episodes                                   10
episode_length                         1000.0
returns                           -196.408212
return_std                           26.73663
average_reward                      -0.196408
round_time             0 days 00:05:30.838258
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.639129
return_std_test                     10.412115
average_reward_test                  0.003639
round_time_test        0 days 00:00:07.975957
round_time_total       0 days 00:05:30.839742
loss_total                         153.612327
loss_critic                        271.471112
loss_actor                        -317.822824
memory_size                        217015.653 

=== epoch 3/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:58,  5.56it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -198.671767
return_std                          25.857886
average_reward                      -0.198672
round_time             0 days 00:05:30.215153
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -4.170411
return_std_test                     37.176795
average_reward_test                  -0.00417
round_time_test        0 days 00:00:07.794551
round_time_total       0 days 00:05:30.216494
loss_total                         150.106144
loss_critic                        267.093675
loss_actor                        -317.843988
memory_size                        218979.653 

=== epoch 3/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:47,  4.89it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                            -196.73265
return_std                          24.960967
average_reward                      -0.196733
round_time             0 days 00:05:34.828368
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.267707
return_std_test                     16.982759
average_reward_test                  0.002268
round_time_test        0 days 00:00:08.284508
round_time_total       0 days 00:05:34.829527
loss_total                          149.32474
loss_critic                         266.24443
loss_actor                        -318.354029
memory_size                        220943.653 

=== epoch 3/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:48,  4.87it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -209.254584
return_std                          40.385704
average_reward                      -0.209255
round_time             0 days 00:05:32.914316
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.457776
return_std_test                      9.588511
average_reward_test                  0.014458
round_time_test        0 days 00:00:07.913031
round_time_total       0 days 00:05:32.915900
loss_total                         147.956656
loss_critic                        264.686761
loss_actor                        -318.963774
memory_size                        222907.653 

=== epoch 3/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:16,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                            -213.44774
return_std                          34.576757
average_reward                      -0.213448
round_time             0 days 00:05:35.468436
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.810596
return_std_test                      8.635535
average_reward_test                  0.011811
round_time_test        0 days 00:00:08.243743
round_time_total       0 days 00:05:35.469654
loss_total                         147.385158
loss_critic                        264.096533
loss_actor                        -319.460356
memory_size                        224871.653 

=== epoch 3/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:51,  4.83it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                            -203.57323
return_std                          43.989105
average_reward                      -0.203573
round_time             0 days 00:05:34.915942
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          2.67896
return_std_test                      8.826711
average_reward_test                  0.002679
round_time_test        0 days 00:00:08.039241
round_time_total       0 days 00:05:34.917094
loss_total                         146.997509
loss_critic                         263.82959
loss_actor                        -320.330826
memory_size                        226835.653 

=== epoch 3/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:19,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -198.366706
return_std                          46.018359
average_reward                      -0.198367
round_time             0 days 00:05:35.700243
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.797657
return_std_test                     19.477958
average_reward_test                  0.001798
round_time_test        0 days 00:00:07.925885
round_time_total       0 days 00:05:35.701369
loss_total                         145.620523
loss_critic                        262.159448
loss_actor                        -320.535185
memory_size                        228799.653 

=== epoch 3/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:42,  4.94it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -194.918823
return_std                          47.322186
average_reward                      -0.194919
round_time             0 days 00:05:32.733554
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -4.189149
return_std_test                     33.717226
average_reward_test                 -0.004189
round_time_test        0 days 00:00:08.167150
round_time_total       0 days 00:05:32.734871
loss_total                         143.685798
loss_critic                        259.799631
loss_actor                        -320.769547
memory_size                        230763.653 

=== epoch 3/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:48,  5.71it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.416118
return_std                          26.613647
average_reward                      -0.173416
round_time             0 days 00:05:34.603996
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          5.85183
return_std_test                      16.74022
average_reward_test                  0.005852
round_time_test        0 days 00:00:07.972863
round_time_total       0 days 00:05:34.605332
loss_total                         147.763347
loss_critic                        265.068249
loss_actor                        -321.456273
memory_size                        232727.653 

=== epoch 3/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:31,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.425585
return_std                          29.180741
average_reward                      -0.179426
round_time             0 days 00:05:36.345221
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -16.918814
return_std_test                     53.156944
average_reward_test                 -0.016919
round_time_test        0 days 00:00:08.047266
round_time_total       0 days 00:05:36.346312
loss_total                         147.928952
loss_critic                        265.382774
loss_actor                        -321.886345
memory_size                        234691.653 

=== epoch 3/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:20,  5.23it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -190.864497
return_std                          26.023356
average_reward                      -0.190864
round_time             0 days 00:05:37.758730
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -7.851081
return_std_test                     41.390795
average_reward_test                 -0.007851
round_time_test        0 days 00:00:08.068580
round_time_total       0 days 00:05:37.759835
loss_total                         148.688187
loss_critic                        266.377849
loss_actor                        -322.070469
memory_size                        236655.653 

=== epoch 3/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:34,  5.05it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -200.303796
return_std                          27.193113
average_reward                      -0.200304
round_time             0 days 00:05:37.507204
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -10.230212
return_std_test                     36.052465
average_reward_test                  -0.01023
round_time_test        0 days 00:00:07.899909
round_time_total       0 days 00:05:37.508732
loss_total                         147.027528
loss_critic                        264.373679
loss_actor                        -322.357087
memory_size                        238619.653 

=== epoch 3/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:32,  5.08it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                            -203.35706
return_std                          24.830741
average_reward                      -0.203357
round_time             0 days 00:05:37.008272
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.647133
return_std_test                     18.598201
average_reward_test                  0.004647
round_time_test        0 days 00:00:07.915457
round_time_total       0 days 00:05:37.009475
loss_total                         145.177156
loss_critic                        262.216718
loss_actor                        -322.981099
memory_size                        240583.653 

=== epoch 3/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:29,  4.43it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -209.198066
return_std                          17.868156
average_reward                      -0.209198
round_time             0 days 00:05:38.279726
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.425925
return_std_test                     11.565629
average_reward_test                  0.002426
round_time_test        0 days 00:00:07.701837
round_time_total       0 days 00:05:38.280884
loss_total                         146.191688
loss_critic                        263.559799
loss_actor                        -323.280761
memory_size                        242547.653 

=== epoch 3/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.12it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -212.479359
return_std                          20.140887
average_reward                      -0.212479
round_time             0 days 00:05:38.116532
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -18.075312
return_std_test                     44.433782
average_reward_test                 -0.018075
round_time_test        0 days 00:00:07.927989
round_time_total       0 days 00:05:38.117864
loss_total                         140.841582
loss_critic                        256.958947
loss_actor                         -323.62789
memory_size                        244511.653 

=== epoch 3/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:18,  5.26it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.275483
return_std                          29.653856
average_reward                      -0.203275
round_time             0 days 00:05:37.018731
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.387534
return_std_test                      9.120354
average_reward_test                  0.014388
round_time_test        0 days 00:00:08.081559
round_time_total       0 days 00:05:37.020276
loss_total                         144.336095
loss_critic                        261.449709
loss_actor                        -324.118374
memory_size                        246475.653 

=== epoch 3/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:59,  4.75it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -200.524622
return_std                          27.120995
average_reward                      -0.200525
round_time             0 days 00:05:38.181467
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.414974
return_std_test                      15.94823
average_reward_test                  0.002415
round_time_test        0 days 00:00:08.071352
round_time_total       0 days 00:05:38.182559
loss_total                         143.893237
loss_critic                        261.064834
loss_actor                        -324.793162
memory_size                        248439.653 

=== epoch 3/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:22,  5.20it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -197.607234
return_std                          28.568243
average_reward                      -0.197607
round_time             0 days 00:05:39.180263
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        16.073728
return_std_test                      8.391563
average_reward_test                  0.016074
round_time_test        0 days 00:00:08.007431
round_time_total       0 days 00:05:39.181493
loss_total                         145.335189
loss_critic                        262.930097
loss_actor                        -325.044455
memory_size                        250403.653 

=== epoch 3/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:55,  5.59it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -191.189631
return_std                          32.591655
average_reward                       -0.19119
round_time             0 days 00:05:40.515014
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -11.605496
return_std_test                      45.33631
average_reward_test                 -0.011605
round_time_test        0 days 00:00:07.763336
round_time_total       0 days 00:05:40.516128
loss_total                         140.326458
loss_critic                        256.714409
loss_actor                        -325.225355
memory_size                        252367.653 

=== epoch 3/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:06,  5.43it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.710528
return_std                          28.494672
average_reward                      -0.187711
round_time             0 days 00:05:38.317893
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.402767
return_std_test                      6.536143
average_reward_test                  0.007403
round_time_test        0 days 00:00:08.172670
round_time_total       0 days 00:05:38.319247
loss_total                          142.04132
loss_critic                         258.96574
loss_actor                        -325.656372
memory_size                        254331.653 

=== epoch 3/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:10,  5.37it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                             -190.9405
return_std                          31.876273
average_reward                      -0.190941
round_time             0 days 00:05:36.784822
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.582999
return_std_test                     19.020795
average_reward_test                  0.002583
round_time_test        0 days 00:00:08.182673
round_time_total       0 days 00:05:36.785933
loss_total                         140.177062
loss_critic                        256.685945
loss_actor                         -325.85848
memory_size                        256295.653 

=== epoch 3/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:07,  4.66it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -182.402181
return_std                          29.959047
average_reward                      -0.182402
round_time             0 days 00:05:39.509266
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.658127
return_std_test                     14.800324
average_reward_test                  0.006658
round_time_test        0 days 00:00:07.853530
round_time_total       0 days 00:05:39.510653
loss_total                         139.095064
loss_critic                        255.354473
loss_actor                        -325.942582
memory_size                        258259.653 

=== epoch 3/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                            -180.24827
return_std                          29.511799
average_reward                      -0.180248
round_time             0 days 00:05:38.841201
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -2.501352
return_std_test                     41.116056
average_reward_test                 -0.002501
round_time_test        0 days 00:00:08.226073
round_time_total       0 days 00:05:38.842289
loss_total                          136.61422
loss_critic                        252.390011
loss_actor                        -326.488954
memory_size                        260223.653 

=== epoch 3/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:48,  5.71it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -193.555543
return_std                          32.627729
average_reward                      -0.193556
round_time             0 days 00:05:38.908181
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.220891
return_std_test                     14.413409
average_reward_test                  0.003221
round_time_test        0 days 00:00:07.924162
round_time_total       0 days 00:05:38.909558
loss_total                         140.917611
loss_critic                         257.84023
loss_actor                        -326.772871
memory_size                        262187.653 

=== epoch 3/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:28,  5.13it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                            -190.92257
return_std                           32.99647
average_reward                      -0.190923
round_time             0 days 00:05:40.351559
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.655538
return_std_test                     11.622489
average_reward_test                  0.008656
round_time_test        0 days 00:00:07.886438
round_time_total       0 days 00:05:40.352688
loss_total                         140.621702
loss_critic                        257.502817
loss_actor                        -326.902763
memory_size                        264151.653 

=== epoch 3/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.20it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -191.925345
return_std                          23.633446
average_reward                      -0.191925
round_time             0 days 00:05:40.608964
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -0.556007
return_std_test                     13.971863
average_reward_test                 -0.000556
round_time_test        0 days 00:00:08.097641
round_time_total       0 days 00:05:40.610066
loss_total                          143.51219
loss_critic                        261.182132
loss_actor                        -327.167587
memory_size                        266115.653 

=== epoch 3/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -201.078022
return_std                          23.017301
average_reward                      -0.201078
round_time             0 days 00:05:39.604768
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.714986
return_std_test                     11.834935
average_reward_test                  0.004715
round_time_test        0 days 00:00:07.901229
round_time_total       0 days 00:05:39.605854
loss_total                          141.26932
loss_critic                        258.441062
loss_actor                        -327.417657
memory_size                        268079.653 

=== epoch 3/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:06,  4.67it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -205.750602
return_std                          18.313874
average_reward                      -0.205751
round_time             0 days 00:05:38.616724
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.145136
return_std_test                     10.993102
average_reward_test                  0.011145
round_time_test        0 days 00:00:08.120363
round_time_total       0 days 00:05:38.617939
loss_total                         139.931398
loss_critic                        256.837395
loss_actor                        -327.692602
memory_size                        270043.653 

=== epoch 3/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:18,  5.25it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -201.584898
return_std                          15.394591
average_reward                      -0.201585
round_time             0 days 00:05:40.620320
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.724022
return_std_test                     10.904937
average_reward_test                  0.011724
round_time_test        0 days 00:00:07.879898
round_time_total       0 days 00:05:40.621418
loss_total                         134.337446
loss_critic                        250.010784
loss_actor                        -328.355914
memory_size                        272007.653 

=== epoch 3/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:53,  4.81it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                             -204.3138
return_std                          14.948512
average_reward                      -0.204314
round_time             0 days 00:05:40.053030
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.260208
return_std_test                     10.500812
average_reward_test                   0.00726
round_time_test        0 days 00:00:07.971169
round_time_total       0 days 00:05:40.054145
loss_total                         136.356801
loss_critic                        252.638492
loss_actor                        -328.769968
memory_size                        273971.653 

=== epoch 3/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:32,  5.07it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -198.265542
return_std                          21.948074
average_reward                      -0.198266
round_time             0 days 00:05:39.216008
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.530472
return_std_test                     10.825847
average_reward_test                   0.00453
round_time_test        0 days 00:00:07.902950
round_time_total       0 days 00:05:39.217098
loss_total                         134.370528
loss_critic                        250.259005
loss_actor                        -329.183389
memory_size                        275935.653 

=== epoch 3/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:24,  5.18it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -199.038667
return_std                          26.097169
average_reward                      -0.199039
round_time             0 days 00:05:37.829147
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -4.075335
return_std_test                     21.788019
average_reward_test                 -0.004075
round_time_test        0 days 00:00:07.909853
round_time_total       0 days 00:05:37.830266
loss_total                         137.074982
loss_critic                        253.710345
loss_actor                        -329.466479
memory_size                        277899.653 

=== epoch 3/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:26,  5.14it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                            -204.05765
return_std                          27.249218
average_reward                      -0.204058
round_time             0 days 00:05:42.598103
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.415461
return_std_test                     15.260962
average_reward_test                  0.003415
round_time_test        0 days 00:00:08.046818
round_time_total       0 days 00:05:42.599440
loss_total                         133.907308
loss_critic                        249.780618
loss_actor                         -329.58594
memory_size                        279863.653 

=== epoch 3/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:01,  5.51it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -204.054963
return_std                          26.111056
average_reward                      -0.204055
round_time             0 days 00:05:39.284989
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.944535
return_std_test                      8.815505
average_reward_test                  0.015945
round_time_test        0 days 00:00:07.701241
round_time_total       0 days 00:05:39.286092
loss_total                         133.011189
loss_critic                        248.732042
loss_actor                        -329.872235
memory_size                        281827.653 

=== epoch 3/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:38,  5.00it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -200.115331
return_std                          32.096192
average_reward                      -0.200115
round_time             0 days 00:05:40.844767
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.231568
return_std_test                      8.582174
average_reward_test                  0.005232
round_time_test        0 days 00:00:08.081373
round_time_total       0 days 00:05:40.846212
loss_total                         133.699856
loss_critic                        249.669942
loss_actor                          -330.1805
memory_size                        283791.653 

=== epoch 3/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:14,  4.58it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.877412
return_std                          30.193151
average_reward                      -0.203877
round_time             0 days 00:05:40.908094
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -6.471368
return_std_test                     27.399579
average_reward_test                 -0.006471
round_time_test        0 days 00:00:07.899860
round_time_total       0 days 00:05:40.909189
loss_total                         134.837433
loss_critic                         251.10698
loss_actor                        -330.240765
memory_size                        285755.653 

=== epoch 3/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:19,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.547208
return_std                          29.403803
average_reward                      -0.203547
round_time             0 days 00:05:40.090454
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.088245
return_std_test                     12.740159
average_reward_test                  0.014088
round_time_test        0 days 00:00:07.927355
round_time_total       0 days 00:05:40.091562
loss_total                         132.221725
loss_critic                        247.933719
loss_actor                        -330.626259
memory_size                        287719.653 

=== epoch 3/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:24,  5.18it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -198.545576
return_std                           28.09837
average_reward                      -0.198546
round_time             0 days 00:05:39.468684
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -1.210888
return_std_test                     20.705006
average_reward_test                 -0.001211
round_time_test        0 days 00:00:08.057028
round_time_total       0 days 00:05:39.469786
loss_total                         135.730987
loss_critic                        252.290664
loss_actor                        -330.507734
memory_size                        289683.653 

=== epoch 3/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:44,  4.92it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -196.991962
return_std                          27.611669
average_reward                      -0.196992
round_time             0 days 00:05:42.173702
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.146837
return_std_test                     14.219098
average_reward_test                  0.011147
round_time_test        0 days 00:00:07.985702
round_time_total       0 days 00:05:42.174805
loss_total                         134.996167
loss_critic                        251.496325
loss_actor                        -331.004475
memory_size                        291647.653 

=== epoch 3/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:20,  5.23it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.84it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                            -207.36315
return_std                          27.934634
average_reward                      -0.207363
round_time             0 days 00:05:42.989025
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.375669
return_std_test                     12.015066
average_reward_test                  0.007376
round_time_test        0 days 00:00:08.036082
round_time_total       0 days 00:05:42.990117
loss_total                         129.562289
loss_critic                         244.79949
loss_actor                        -331.386524
memory_size                        293611.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 4/10 ===== round 1/50 ======================================
  1%|          | 12/2000 [00:02<05:47,  5.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:20<00:00,  6.23it/s]
episodes                                    2
episode_length                         1000.0
returns                           -201.375797
return_std                           2.796179
average_reward                      -0.201376
round_time             0 days 00:05:21.014914
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.795423
return_std_test                      5.621079
average_reward_test                  0.004795
round_time_test        0 days 00:00:08.120872
round_time_total       0 days 00:05:21.016132
loss_total                         132.641063
loss_critic                        248.765825
loss_actor                        -331.857992
memory_size                        295576.653 

=== epoch 4/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:57,  5.57it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:24<00:00,  6.16it/s]
episodes                                    4
episode_length                         1000.0
returns                           -197.033098
return_std                          12.331245
average_reward                      -0.197033
round_time             0 days 00:05:25.002331
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.399267
return_std_test                     15.631526
average_reward_test                  0.013399
round_time_test        0 days 00:00:08.204486
round_time_total       0 days 00:05:25.003429
loss_total                          132.04197
loss_critic                        248.053862
loss_actor                        -332.005605
memory_size                        297540.653 

=== epoch 4/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:00,  5.52it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:24<00:00,  6.17it/s]
episodes                                    6
episode_length                         1000.0
returns                           -195.379392
return_std                          26.065162
average_reward                      -0.195379
round_time             0 days 00:05:24.941075
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.946101
return_std_test                     12.685099
average_reward_test                  0.005946
round_time_test        0 days 00:00:07.908909
round_time_total       0 days 00:05:24.942173
loss_total                         131.080786
loss_critic                        246.952535
loss_actor                        -332.406217
memory_size                        299504.653 

=== epoch 4/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:21,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:25<00:00,  6.14it/s]
episodes                                    8
episode_length                         1000.0
returns                           -200.323075
return_std                           24.26164
average_reward                      -0.200323
round_time             0 days 00:05:26.424221
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.667816
return_std_test                      9.037254
average_reward_test                  0.007668
round_time_test        0 days 00:00:08.129540
round_time_total       0 days 00:05:26.425299
loss_total                         131.535385
loss_critic                        247.594663
loss_actor                        -332.701738
memory_size                        301468.653 

=== epoch 4/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:10,  5.37it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:26<00:00,  6.12it/s]
episodes                                   10
episode_length                         1000.0
returns                             -203.6246
return_std                          33.692542
average_reward                      -0.203625
round_time             0 days 00:05:27.399299
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         10.86267
return_std_test                       6.85464
average_reward_test                  0.010863
round_time_test        0 days 00:00:07.842519
round_time_total       0 days 00:05:27.400415
loss_total                         135.571706
loss_critic                        252.645005
loss_actor                        -332.721498
memory_size                        303432.653 

=== epoch 4/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:56,  5.58it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:26<00:00,  6.12it/s]
episodes                                   10
episode_length                         1000.0
returns                           -200.932461
return_std                          34.749776
average_reward                      -0.200932
round_time             0 days 00:05:27.445791
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.910323
return_std_test                      7.273031
average_reward_test                   0.01191
round_time_test        0 days 00:00:07.729531
round_time_total       0 days 00:05:27.446917
loss_total                         136.437526
loss_critic                        253.663359
loss_actor                        -332.465817
memory_size                        305396.653 

=== epoch 4/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:05,  5.45it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:28<00:00,  6.08it/s]
episodes                                   10
episode_length                         1000.0
returns                           -198.557768
return_std                          40.066022
average_reward                      -0.198558
round_time             0 days 00:05:29.311402
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.170434
return_std_test                      6.849839
average_reward_test                   0.00917
round_time_test        0 days 00:00:07.949726
round_time_total       0 days 00:05:29.312562
loss_total                         137.850768
loss_critic                        255.395468
loss_actor                        -332.328044
memory_size                        307360.653 

=== epoch 4/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.12it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.03it/s]
episodes                                   10
episode_length                         1000.0
returns                           -194.792035
return_std                          38.347236
average_reward                      -0.194792
round_time             0 days 00:05:32.141959
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.364586
return_std_test                      6.347236
average_reward_test                  0.013365
round_time_test        0 days 00:00:07.910194
round_time_total       0 days 00:05:32.143437
loss_total                         136.858797
loss_critic                        254.105343
loss_actor                        -332.127396
memory_size                        309324.653 

=== epoch 4/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:57,  5.57it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -192.215758
return_std                          37.784021
average_reward                      -0.192216
round_time             0 days 00:05:31.373174
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.475379
return_std_test                     16.045525
average_reward_test                  0.006475
round_time_test        0 days 00:00:07.617424
round_time_total       0 days 00:05:31.374409
loss_total                         136.155164
loss_critic                        253.178311
loss_actor                        -331.937433
memory_size                        311288.653 

=== epoch 4/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:04,  5.46it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -189.533065
return_std                          27.182844
average_reward                      -0.189533
round_time             0 days 00:05:32.629637
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        17.334773
return_std_test                     11.573268
average_reward_test                  0.017335
round_time_test        0 days 00:00:08.275292
round_time_total       0 days 00:05:32.630744
loss_total                         136.810271
loss_critic                        254.002933
loss_actor                        -331.960387
memory_size                        313252.653 

=== epoch 4/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:03,  4.70it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.232419
return_std                          27.283341
average_reward                      -0.187232
round_time             0 days 00:05:32.616061
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         14.09033
return_std_test                      15.51291
average_reward_test                   0.01409
round_time_test        0 days 00:00:07.709914
round_time_total       0 days 00:05:32.617166
loss_total                          138.62725
loss_critic                        256.252879
loss_actor                        -331.875279
memory_size                        315216.653 

=== epoch 4/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:44,  5.79it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                            -191.22611
return_std                          19.379466
average_reward                      -0.191226
round_time             0 days 00:05:32.540298
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        20.446355
return_std_test                      9.930724
average_reward_test                  0.020446
round_time_test        0 days 00:00:07.905927
round_time_total       0 days 00:05:32.541540
loss_total                         132.522445
loss_critic                        248.647933
loss_actor                        -331.979515
memory_size                        317180.653 

=== epoch 4/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:51,  5.66it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -194.830164
return_std                          16.387808
average_reward                       -0.19483
round_time             0 days 00:05:35.043613
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.632711
return_std_test                     12.019064
average_reward_test                  0.001633
round_time_test        0 days 00:00:07.872916
round_time_total       0 days 00:05:35.044977
loss_total                         134.267996
loss_critic                         250.89425
loss_actor                        -332.237031
memory_size                        319144.653 

=== epoch 4/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:48,  4.88it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.954775
return_std                          16.712896
average_reward                      -0.188955
round_time             0 days 00:05:34.200003
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         11.93535
return_std_test                      4.760795
average_reward_test                  0.011935
round_time_test        0 days 00:00:07.900211
round_time_total       0 days 00:05:34.201229
loss_total                         134.765165
loss_critic                        251.672437
loss_actor                        -332.863929
memory_size                        321108.653 

=== epoch 4/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:15,  5.30it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.172639
return_std                           20.02198
average_reward                      -0.186173
round_time             0 days 00:05:33.308870
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.266541
return_std_test                     12.926945
average_reward_test                  0.009267
round_time_test        0 days 00:00:07.737326
round_time_total       0 days 00:05:33.310307
loss_total                         134.509225
loss_critic                         251.44697
loss_actor                        -333.241759
memory_size                        323072.653 

=== epoch 4/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:02,  5.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.894803
return_std                          24.123683
average_reward                      -0.184895
round_time             0 days 00:05:35.986492
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.587993
return_std_test                      4.160091
average_reward_test                  0.014588
round_time_test        0 days 00:00:07.838788
round_time_total       0 days 00:05:35.987577
loss_total                          136.33368
loss_critic                         253.74671
loss_actor                        -333.318449
memory_size                        325036.653 

=== epoch 4/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:10,  4.63it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.114032
return_std                          23.791578
average_reward                      -0.184114
round_time             0 days 00:05:35.157977
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.155815
return_std_test                      9.513633
average_reward_test                  0.011156
round_time_test        0 days 00:00:07.945356
round_time_total       0 days 00:05:35.159110
loss_total                         134.945811
loss_critic                        251.951077
loss_actor                        -333.075259
memory_size                        327000.653 

=== epoch 4/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:38,  5.00it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.487627
return_std                          23.072815
average_reward                      -0.179488
round_time             0 days 00:05:34.908022
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.700787
return_std_test                     14.489039
average_reward_test                  0.007701
round_time_test        0 days 00:00:07.945510
round_time_total       0 days 00:05:34.909116
loss_total                         131.169483
loss_critic                        247.321414
loss_actor                         -333.43825
memory_size                        328964.653 

=== epoch 4/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.33it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -181.598351
return_std                          23.423626
average_reward                      -0.181598
round_time             0 days 00:05:38.775845
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.344557
return_std_test                      17.30571
average_reward_test                  0.007345
round_time_test        0 days 00:00:07.959479
round_time_total       0 days 00:05:38.776961
loss_total                         133.410006
loss_critic                        250.239811
loss_actor                        -333.909218
memory_size                        330928.653 

=== epoch 4/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:08,  4.64it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -178.756101
return_std                          20.093203
average_reward                      -0.178756
round_time             0 days 00:05:35.575583
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.645558
return_std_test                      9.263211
average_reward_test                  0.003646
round_time_test        0 days 00:00:07.866604
round_time_total       0 days 00:05:35.576961
loss_total                         132.512619
loss_critic                        249.273398
loss_actor                        -334.530505
memory_size                        332892.653 

=== epoch 4/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:08,  5.41it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                            -184.07661
return_std                          16.548098
average_reward                      -0.184077
round_time             0 days 00:05:38.470708
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.724533
return_std_test                     10.273424
average_reward_test                  0.002725
round_time_test        0 days 00:00:07.793389
round_time_total       0 days 00:05:38.472052
loss_total                         133.340684
loss_critic                        250.344276
loss_actor                        -334.673693
memory_size                        334856.653 

=== epoch 4/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:02,  5.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.701514
return_std                          16.122612
average_reward                      -0.179702
round_time             0 days 00:05:39.351822
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.377521
return_std_test                      6.777452
average_reward_test                  0.012378
round_time_test        0 days 00:00:07.951787
round_time_total       0 days 00:05:39.352914
loss_total                         130.991036
loss_critic                        247.552124
loss_actor                        -335.253326
memory_size                        336820.653 

=== epoch 4/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:43,  4.94it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                            -185.81202
return_std                          16.504387
average_reward                      -0.185812
round_time             0 days 00:05:39.477614
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.864605
return_std_test                      9.362539
average_reward_test                  0.010865
round_time_test        0 days 00:00:08.021754
round_time_total       0 days 00:05:39.478810
loss_total                         130.999636
loss_critic                        247.678632
loss_actor                        -335.716355
memory_size                        338784.653 

=== epoch 4/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:25,  5.16it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -185.524718
return_std                          16.127853
average_reward                      -0.185525
round_time             0 days 00:05:36.724766
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                           8.3994
return_std_test                     10.752152
average_reward_test                  0.008399
round_time_test        0 days 00:00:07.979759
round_time_total       0 days 00:05:36.725848
loss_total                         130.694869
loss_critic                        247.246852
loss_actor                        -335.513067
memory_size                        340748.653 

=== epoch 4/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:46,  4.90it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -182.976875
return_std                          17.866204
average_reward                      -0.182977
round_time             0 days 00:05:37.839031
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.223525
return_std_test                     11.263548
average_reward_test                  0.013224
round_time_test        0 days 00:00:08.070996
round_time_total       0 days 00:05:37.840160
loss_total                         134.544917
loss_critic                        252.155292
loss_actor                        -335.896595
memory_size                        342712.653 

=== epoch 4/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:31,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -180.076251
return_std                          17.779557
average_reward                      -0.180076
round_time             0 days 00:05:37.325391
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                           4.4448
return_std_test                     12.679146
average_reward_test                  0.004445
round_time_test        0 days 00:00:08.099621
round_time_total       0 days 00:05:37.326473
loss_total                         129.046576
loss_critic                        245.384112
loss_actor                        -336.303578
memory_size                        344676.653 

=== epoch 4/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:15,  5.30it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                            -187.60461
return_std                          21.434609
average_reward                      -0.187605
round_time             0 days 00:05:38.678663
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.101781
return_std_test                      6.207944
average_reward_test                  0.011102
round_time_test        0 days 00:00:07.949041
round_time_total       0 days 00:05:38.679741
loss_total                         130.259809
loss_critic                        246.969399
loss_actor                        -336.578562
memory_size                        346640.653 

=== epoch 4/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:01,  5.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -185.357633
return_std                          26.718947
average_reward                      -0.185358
round_time             0 days 00:05:39.426090
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -3.116747
return_std_test                     13.941707
average_reward_test                 -0.003117
round_time_test        0 days 00:00:07.938490
round_time_total       0 days 00:05:39.427196
loss_total                         126.192508
loss_critic                        241.904457
loss_actor                        -336.655298
memory_size                        348604.653 

=== epoch 4/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:05,  5.44it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -189.375809
return_std                          29.357445
average_reward                      -0.189376
round_time             0 days 00:05:38.916693
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.181843
return_std_test                     10.513536
average_reward_test                  0.008182
round_time_test        0 days 00:00:07.833135
round_time_total       0 days 00:05:38.918053
loss_total                         126.717109
loss_critic                        242.654571
loss_actor                         -337.03275
memory_size                        350568.653 

=== epoch 4/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:56,  4.78it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -196.201815
return_std                          25.043772
average_reward                      -0.196202
round_time             0 days 00:05:40.458071
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.066452
return_std_test                      13.31636
average_reward_test                  0.001066
round_time_test        0 days 00:00:08.007633
round_time_total       0 days 00:05:40.459166
loss_total                          124.69803
loss_critic                        240.129923
loss_actor                        -337.029552
memory_size                        352532.653 

=== epoch 4/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:27,  5.14it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -194.214435
return_std                          27.230163
average_reward                      -0.194214
round_time             0 days 00:05:38.994549
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.893074
return_std_test                     10.064969
average_reward_test                  0.012893
round_time_test        0 days 00:00:08.109975
round_time_total       0 days 00:05:38.995853
loss_total                         127.852945
loss_critic                        244.036034
loss_actor                         -336.87942
memory_size                        354496.653 

=== epoch 4/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:42,  4.95it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -194.269847
return_std                          27.477115
average_reward                       -0.19427
round_time             0 days 00:05:38.926961
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.601514
return_std_test                      9.139476
average_reward_test                  0.009602
round_time_test        0 days 00:00:07.956599
round_time_total       0 days 00:05:38.928490
loss_total                         126.772053
loss_critic                        242.804406
loss_actor                        -337.357368
memory_size                        356460.653 

=== epoch 4/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:44,  4.92it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.457207
return_std                          26.484114
average_reward                      -0.203457
round_time             0 days 00:05:38.262189
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.015918
return_std_test                      9.329063
average_reward_test                  0.011016
round_time_test        0 days 00:00:07.995944
round_time_total       0 days 00:05:38.263297
loss_total                         124.929249
loss_critic                        240.556204
loss_actor                        -337.578581
memory_size                        358424.653 

=== epoch 4/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:47,  4.88it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.770907
return_std                          24.045442
average_reward                      -0.203771
round_time             0 days 00:05:41.916913
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.467528
return_std_test                     17.684908
average_reward_test                  0.005468
round_time_test        0 days 00:00:07.986225
round_time_total       0 days 00:05:41.918059
loss_total                         127.061248
loss_critic                        243.189075
loss_actor                        -337.450067
memory_size                        360388.653 

=== epoch 4/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:30,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.84it/s]
episodes                                   10
episode_length                         1000.0
returns                           -198.231483
return_std                          27.998033
average_reward                      -0.198231
round_time             0 days 00:05:43.075922
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.382473
return_std_test                      9.666929
average_reward_test                  0.012382
round_time_test        0 days 00:00:08.026967
round_time_total       0 days 00:05:43.077310
loss_total                         125.083878
loss_critic                        240.734818
loss_actor                        -337.519889
memory_size                        362352.653 

=== epoch 4/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:24,  5.17it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:53<00:00,  5.66it/s]
episodes                                   10
episode_length                         1000.0
returns                           -202.104846
return_std                          24.943154
average_reward                      -0.202105
round_time             0 days 00:05:54.055291
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.471644
return_std_test                     12.100186
average_reward_test                  0.008472
round_time_test        0 days 00:00:07.979688
round_time_total       0 days 00:05:54.056532
loss_total                          130.00961
loss_critic                        246.882969
loss_actor                        -337.483834
memory_size                        364316.653 

=== epoch 4/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:04,  5.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:58<00:00,  5.58it/s]
episodes                                   10
episode_length                         1000.0
returns                           -196.234956
return_std                          27.164732
average_reward                      -0.196235
round_time             0 days 00:05:58.811173
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         13.26483
return_std_test                      9.405189
average_reward_test                  0.013265
round_time_test        0 days 00:00:08.088167
round_time_total       0 days 00:05:58.812264
loss_total                         127.479679
loss_critic                        243.754808
loss_actor                        -337.620845
memory_size                        366280.653 

=== epoch 4/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:26,  5.16it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:54<00:00,  5.64it/s]
episodes                                   10
episode_length                         1000.0
returns                           -189.934333
return_std                          20.999332
average_reward                      -0.189934
round_time             0 days 00:05:54.925357
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -2.139807
return_std_test                     23.809046
average_reward_test                  -0.00214
round_time_test        0 days 00:00:08.558796
round_time_total       0 days 00:05:54.926484
loss_total                         128.197063
loss_critic                        244.775957
loss_actor                        -338.118523
memory_size                        368244.653 

=== epoch 4/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:31,  5.08it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -193.651834
return_std                          27.377319
average_reward                      -0.193652
round_time             0 days 00:05:42.640382
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.547106
return_std_test                     11.370662
average_reward_test                  0.002547
round_time_test        0 days 00:00:07.669338
round_time_total       0 days 00:05:42.641784
loss_total                         128.381833
loss_critic                        245.057106
loss_actor                        -338.319267
memory_size                        370208.653 

=== epoch 4/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:42,  4.94it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:44<00:00,  5.80it/s]
episodes                                   10
episode_length                         1000.0
returns                           -196.378779
return_std                          25.304536
average_reward                      -0.196379
round_time             0 days 00:05:45.146356
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.543906
return_std_test                      9.755889
average_reward_test                  0.012544
round_time_test        0 days 00:00:07.885675
round_time_total       0 days 00:05:45.147444
loss_total                         125.691757
loss_critic                        241.694051
loss_actor                        -338.317431
memory_size                        372172.653 

=== epoch 4/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:16,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -195.974042
return_std                          25.265638
average_reward                      -0.195974
round_time             0 days 00:05:39.783725
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.838733
return_std_test                      7.160794
average_reward_test                  0.014839
round_time_test        0 days 00:00:07.858330
round_time_total       0 days 00:05:39.785044
loss_total                         121.652763
loss_critic                        236.646099
loss_actor                        -338.320591
memory_size                        374136.653 

=== epoch 4/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:19,  5.25it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -199.225936
return_std                          21.706287
average_reward                      -0.199226
round_time             0 days 00:05:42.218096
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.527448
return_std_test                      9.208831
average_reward_test                  0.007527
round_time_test        0 days 00:00:07.958562
round_time_total       0 days 00:05:42.219204
loss_total                         126.592673
loss_critic                        242.769577
loss_actor                         -338.11495
memory_size                        376100.653 

=== epoch 4/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -192.917347
return_std                          23.324019
average_reward                      -0.192917
round_time             0 days 00:05:41.984879
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.981201
return_std_test                      7.030311
average_reward_test                  0.012981
round_time_test        0 days 00:00:08.073173
round_time_total       0 days 00:05:41.986040
loss_total                         124.836561
loss_critic                        240.542319
loss_actor                        -337.986481
memory_size                        378064.653 

=== epoch 4/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -181.342534
return_std                          17.175924
average_reward                      -0.181343
round_time             0 days 00:05:40.858391
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          4.53879
return_std_test                       9.54558
average_reward_test                  0.004539
round_time_test        0 days 00:00:07.859366
round_time_total       0 days 00:05:40.859501
loss_total                         125.517704
loss_critic                        241.547504
loss_actor                        -338.601506
memory_size                        380028.653 

=== epoch 4/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:28,  5.13it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.162006
return_std                          17.584776
average_reward                      -0.179162
round_time             0 days 00:05:40.904496
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.366946
return_std_test                      9.886175
average_reward_test                  0.011367
round_time_test        0 days 00:00:07.909881
round_time_total       0 days 00:05:40.905594
loss_total                         125.432126
loss_critic                         241.46975
loss_actor                        -338.718376
memory_size                        381992.653 

=== epoch 4/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:15,  5.31it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.84it/s]
episodes                                   10
episode_length                         1000.0
returns                           -181.734855
return_std                          18.782119
average_reward                      -0.181735
round_time             0 days 00:05:42.923815
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -1.086641
return_std_test                     16.601107
average_reward_test                 -0.001087
round_time_test        0 days 00:00:07.978186
round_time_total       0 days 00:05:42.925018
loss_total                         122.290294
loss_critic                         237.64166
loss_actor                         -339.11518
memory_size                        383956.653 

=== epoch 4/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:01,  4.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.144875
return_std                          28.811163
average_reward                      -0.188145
round_time             0 days 00:05:42.177562
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.261219
return_std_test                     10.243727
average_reward_test                  0.011261
round_time_test        0 days 00:00:08.159007
round_time_total       0 days 00:05:42.178973
loss_total                         121.468338
loss_critic                        236.659284
loss_actor                        -339.295455
memory_size                        385920.653 

=== epoch 4/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.84it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.720926
return_std                          31.618776
average_reward                      -0.186721
round_time             0 days 00:05:42.915387
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.795396
return_std_test                      9.861304
average_reward_test                  0.006795
round_time_test        0 days 00:00:07.816910
round_time_total       0 days 00:05:42.916672
loss_total                         122.589515
loss_critic                        238.156236
loss_actor                        -339.677382
memory_size                        387884.653 

=== epoch 4/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:17,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:43<00:00,  5.83it/s]
episodes                                   10
episode_length                         1000.0
returns                           -195.382063
return_std                          30.121291
average_reward                      -0.195382
round_time             0 days 00:05:43.640814
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.808761
return_std_test                     14.538025
average_reward_test                  0.007809
round_time_test        0 days 00:00:07.902575
round_time_total       0 days 00:05:43.642057
loss_total                         121.155644
loss_critic                        236.312832
loss_actor                        -339.473116
memory_size                        389848.653 

=== epoch 4/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:16,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.84it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -199.736588
return_std                          28.834595
average_reward                      -0.199737
round_time             0 days 00:05:43.209454
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          3.86136
return_std_test                     10.933461
average_reward_test                  0.003861
round_time_test        0 days 00:00:07.915014
round_time_total       0 days 00:05:43.210756
loss_total                           120.3432
loss_critic                         235.35156
loss_actor                        -339.690249
memory_size                        391812.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 5/10 ===== round 1/50 ======================================
  1%|          | 12/2000 [00:02<06:15,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:20<00:00,  6.24it/s]
episodes                                    2
episode_length                         1000.0
returns                           -185.800943
return_std                          32.560731
average_reward                      -0.185801
round_time             0 days 00:05:20.345470
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.687558
return_std_test                     19.718835
average_reward_test                  0.009688
round_time_test        0 days 00:00:08.093202
round_time_total       0 days 00:05:20.346604
loss_total                         122.030885
loss_critic                          237.5553
loss_actor                        -340.066784
memory_size                        393777.653 

=== epoch 5/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:21,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:22<00:00,  6.19it/s]
episodes                                    4
episode_length                         1000.0
returns                           -179.816477
return_std                          27.365314
average_reward                      -0.179816
round_time             0 days 00:05:23.533568
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.285027
return_std_test                       8.72693
average_reward_test                  0.009285
round_time_test        0 days 00:00:08.127914
round_time_total       0 days 00:05:23.534656
loss_total                         122.736552
loss_critic                        238.511163
loss_actor                        -340.361898
memory_size                        395741.653 

=== epoch 5/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:00,  5.52it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:26<00:00,  6.13it/s]
episodes                                    6
episode_length                         1000.0
returns                           -164.087761
return_std                          32.652745
average_reward                      -0.164088
round_time             0 days 00:05:26.951698
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.440518
return_std_test                      7.018734
average_reward_test                  0.009441
round_time_test        0 days 00:00:07.992409
round_time_total       0 days 00:05:26.952789
loss_total                         121.099475
loss_critic                         236.50537
loss_actor                        -340.524116
memory_size                        397705.653 

=== epoch 5/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:50,  4.85it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:25<00:00,  6.14it/s]
episodes                                    8
episode_length                         1000.0
returns                           -163.480789
return_std                            29.7093
average_reward                      -0.163481
round_time             0 days 00:05:26.311974
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.864635
return_std_test                      8.350552
average_reward_test                  0.010865
round_time_test        0 days 00:00:08.198885
round_time_total       0 days 00:05:26.313443
loss_total                         119.048434
loss_critic                        233.998975
loss_actor                        -340.753736
memory_size                        399669.653 

=== epoch 5/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:06,  5.43it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.10it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.029137
return_std                          32.160862
average_reward                      -0.172029
round_time             0 days 00:05:28.446972
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.003439
return_std_test                     11.952269
average_reward_test                  0.011003
round_time_test        0 days 00:00:07.933447
round_time_total       0 days 00:05:28.448296
loss_total                         121.000775
loss_critic                          236.4981
loss_actor                        -340.988531
memory_size                        401633.653 

=== epoch 5/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:40,  4.97it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.332822
return_std                          30.631402
average_reward                      -0.174333
round_time             0 days 00:05:29.968513
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.394706
return_std_test                      7.608526
average_reward_test                  0.015395
round_time_test        0 days 00:00:07.821444
round_time_total       0 days 00:05:29.969604
loss_total                         122.506922
loss_critic                        238.278868
loss_actor                        -340.580873
memory_size                        403597.653 

=== epoch 5/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:52,  4.82it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.178467
return_std                          30.636027
average_reward                      -0.170178
round_time             0 days 00:05:29.945714
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.329777
return_std_test                      7.582198
average_reward_test                   0.01533
round_time_test        0 days 00:00:07.889287
round_time_total       0 days 00:05:29.946818
loss_total                         121.709888
loss_critic                        237.281687
loss_actor                        -340.577316
memory_size                        405561.653 

=== epoch 5/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:50,  4.85it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.04it/s]
episodes                                   10
episode_length                         1000.0
returns                            -189.34779
return_std                          32.879642
average_reward                      -0.189348
round_time             0 days 00:05:31.847107
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         10.15532
return_std_test                     12.941673
average_reward_test                  0.010155
round_time_test        0 days 00:00:07.964397
round_time_total       0 days 00:05:31.848246
loss_total                         122.329456
loss_critic                        238.061462
loss_actor                        -340.598578
memory_size                        407525.653 

=== epoch 5/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:30,  5.10it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -197.250235
return_std                          28.863367
average_reward                       -0.19725
round_time             0 days 00:05:30.038608
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.746772
return_std_test                       8.12421
average_reward_test                  0.010747
round_time_test        0 days 00:00:07.944624
round_time_total       0 days 00:05:30.040083
loss_total                           121.2621
loss_critic                         236.78767
loss_actor                        -340.840189
memory_size                        409489.653 

=== epoch 5/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:49,  5.69it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -192.375054
return_std                          28.537296
average_reward                      -0.192375
round_time             0 days 00:05:35.833817
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.463831
return_std_test                     13.443362
average_reward_test                  0.005464
round_time_test        0 days 00:00:07.809170
round_time_total       0 days 00:05:35.834915
loss_total                         120.958839
loss_critic                        236.487376
loss_actor                        -341.155319
memory_size                        411453.653 

=== epoch 5/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:45,  4.91it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                            -185.49105
return_std                           30.08283
average_reward                      -0.185491
round_time             0 days 00:05:34.398454
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.554726
return_std_test                       8.86056
average_reward_test                  0.005555
round_time_test        0 days 00:00:07.932955
round_time_total       0 days 00:05:34.399954
loss_total                         122.845034
loss_critic                        238.848345
loss_actor                        -341.168219
memory_size                        413417.653 

=== epoch 5/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -193.912623
return_std                          28.028721
average_reward                      -0.193913
round_time             0 days 00:05:35.254185
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.616119
return_std_test                      9.529936
average_reward_test                  0.010616
round_time_test        0 days 00:00:08.064639
round_time_total       0 days 00:05:35.255288
loss_total                         118.408306
loss_critic                        233.330178
loss_actor                        -341.279191
memory_size                        415381.653 

=== epoch 5/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:57,  5.56it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.692638
return_std                          18.466503
average_reward                      -0.184693
round_time             0 days 00:05:36.558925
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.783722
return_std_test                     10.836858
average_reward_test                  0.011784
round_time_test        0 days 00:00:07.864201
round_time_total       0 days 00:05:36.560296
loss_total                         121.155399
loss_critic                        236.788995
loss_actor                        -341.378991
memory_size                        417345.653 

=== epoch 5/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:20,  4.52it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.233426
return_std                          16.601622
average_reward                      -0.179233
round_time             0 days 00:05:35.922272
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.411527
return_std_test                      9.619507
average_reward_test                  0.009412
round_time_test        0 days 00:00:08.242536
round_time_total       0 days 00:05:35.923485
loss_total                         119.416279
loss_critic                         234.68696
loss_actor                        -341.666453
memory_size                        419309.653 

=== epoch 5/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.772396
return_std                          34.841732
average_reward                      -0.184772
round_time             0 days 00:05:36.201459
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.823262
return_std_test                       7.10759
average_reward_test                  0.012823
round_time_test        0 days 00:00:08.002598
round_time_total       0 days 00:05:36.202548
loss_total                         123.524597
loss_critic                         239.70452
loss_actor                        -341.195103
memory_size                        421273.653 

=== epoch 5/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:24,  5.18it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.872409
return_std                          35.789764
average_reward                      -0.187872
round_time             0 days 00:05:37.694179
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.691593
return_std_test                      10.67155
average_reward_test                  0.010692
round_time_test        0 days 00:00:08.057348
round_time_total       0 days 00:05:37.695374
loss_total                         121.915295
loss_critic                        237.604806
loss_actor                        -340.842759
memory_size                        423237.653 

=== epoch 5/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:42,  4.95it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -191.269897
return_std                          35.158647
average_reward                       -0.19127
round_time             0 days 00:05:36.219615
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.675302
return_std_test                     15.994463
average_reward_test                  0.009675
round_time_test        0 days 00:00:08.009487
round_time_total       0 days 00:05:36.221036
loss_total                         124.871028
loss_critic                        241.283509
loss_actor                        -340.778907
memory_size                        425201.653 

=== epoch 5/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:00,  5.53it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -196.311241
return_std                          35.241431
average_reward                      -0.196311
round_time             0 days 00:05:38.019385
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.849003
return_std_test                      7.623194
average_reward_test                  0.007849
round_time_test        0 days 00:00:08.021748
round_time_total       0 days 00:05:38.020493
loss_total                         124.548148
loss_critic                        240.956876
loss_actor                        -341.086776
memory_size                        427165.653 

=== epoch 5/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -199.234923
return_std                           35.49548
average_reward                      -0.199235
round_time             0 days 00:05:37.016536
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         13.55066
return_std_test                      9.034272
average_reward_test                  0.013551
round_time_test        0 days 00:00:07.850711
round_time_total       0 days 00:05:37.017719
loss_total                         122.007991
loss_critic                        237.801062
loss_actor                          -341.1643
memory_size                        429129.653 

=== epoch 5/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:26,  5.15it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -197.311994
return_std                          22.974342
average_reward                      -0.197312
round_time             0 days 00:05:37.576257
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.502947
return_std_test                      8.384818
average_reward_test                  0.002503
round_time_test        0 days 00:00:07.984070
round_time_total       0 days 00:05:37.577337
loss_total                         122.904913
loss_critic                        238.850581
loss_actor                        -340.877767
memory_size                        431093.653 

=== epoch 5/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:53,  5.63it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -203.292135
return_std                          16.784451
average_reward                      -0.203292
round_time             0 days 00:05:39.519549
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          9.81426
return_std_test                      9.721655
average_reward_test                  0.009814
round_time_test        0 days 00:00:07.852908
round_time_total       0 days 00:05:39.520647
loss_total                         130.833056
loss_critic                        248.729702
loss_actor                        -340.753535
memory_size                        433057.653 

=== epoch 5/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                            -192.47731
return_std                          24.145601
average_reward                      -0.192477
round_time             0 days 00:05:40.452422
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.267491
return_std_test                      5.545837
average_reward_test                  0.008267
round_time_test        0 days 00:00:07.847872
round_time_total       0 days 00:05:40.453854
loss_total                         128.475635
loss_critic                        245.778937
loss_actor                         -340.73758
memory_size                        435021.653 

=== epoch 5/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:47,  4.26it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.655702
return_std                           24.52027
average_reward                      -0.188656
round_time             0 days 00:05:38.719270
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.599875
return_std_test                     20.805309
average_reward_test                    0.0006
round_time_test        0 days 00:00:08.039794
round_time_total       0 days 00:05:38.720492
loss_total                         125.669676
loss_critic                        242.369887
loss_actor                        -341.131176
memory_size                        436985.653 

=== epoch 5/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:26,  5.16it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.625687
return_std                          25.441957
average_reward                      -0.187626
round_time             0 days 00:05:38.183455
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.999781
return_std_test                     15.516326
average_reward_test                     0.009
round_time_test        0 days 00:00:07.833425
round_time_total       0 days 00:05:38.184858
loss_total                         126.218972
loss_critic                        243.180296
loss_actor                        -341.626331
memory_size                        438949.653 

=== epoch 5/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:01,  5.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.740282
return_std                          23.933312
average_reward                       -0.18374
round_time             0 days 00:05:38.836683
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.843192
return_std_test                     11.895881
average_reward_test                  0.013843
round_time_test        0 days 00:00:07.994069
round_time_total       0 days 00:05:38.837978
loss_total                         121.738543
loss_critic                        237.638565
loss_actor                        -341.861554
memory_size                        440913.653 

=== epoch 5/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:22,  5.20it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -177.917005
return_std                          26.161018
average_reward                      -0.177917
round_time             0 days 00:05:41.248881
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.371756
return_std_test                      7.334003
average_reward_test                  0.015372
round_time_test        0 days 00:00:07.949081
round_time_total       0 days 00:05:41.250322
loss_total                         120.708354
loss_critic                        236.435383
loss_actor                         -342.19977
memory_size                        442877.653 

=== epoch 5/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.595057
return_std                          23.870385
average_reward                      -0.184595
round_time             0 days 00:05:42.182365
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.899748
return_std_test                      6.635537
average_reward_test                    0.0129
round_time_test        0 days 00:00:07.886909
round_time_total       0 days 00:05:42.183460
loss_total                         119.414476
loss_critic                        234.793635
loss_actor                        -342.102168
memory_size                        444841.653 

=== epoch 5/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:32,  5.07it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.272879
return_std                          24.497065
average_reward                      -0.188273
round_time             0 days 00:05:38.638169
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.040689
return_std_test                     10.462714
average_reward_test                  0.007041
round_time_test        0 days 00:00:07.990423
round_time_total       0 days 00:05:38.639349
loss_total                         118.780559
loss_critic                        234.122262
loss_actor                        -342.586263
memory_size                        446805.653 

=== epoch 5/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:17,  5.27it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.877201
return_std                          20.965888
average_reward                      -0.188877
round_time             0 days 00:05:40.644797
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.211871
return_std_test                      7.678287
average_reward_test                  0.011212
round_time_test        0 days 00:00:07.941940
round_time_total       0 days 00:05:40.645888
loss_total                         119.485284
loss_critic                        235.038476
loss_actor                        -342.727492
memory_size                        448769.653 

=== epoch 5/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:25,  5.17it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                            -191.86016
return_std                          23.702556
average_reward                       -0.19186
round_time             0 days 00:05:41.224070
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.211829
return_std_test                     11.313404
average_reward_test                  0.006212
round_time_test        0 days 00:00:07.972576
round_time_total       0 days 00:05:41.225334
loss_total                         120.343594
loss_critic                        236.106944
loss_actor                        -342.709817
memory_size                        450733.653 

=== epoch 5/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:31,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -200.118425
return_std                          19.017164
average_reward                      -0.200118
round_time             0 days 00:05:37.936139
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.130104
return_std_test                      9.291546
average_reward_test                   0.00913
round_time_test        0 days 00:00:07.818402
round_time_total       0 days 00:05:37.937599
loss_total                         119.461287
loss_critic                        234.963124
loss_actor                        -342.546071
memory_size                        452697.653 

=== epoch 5/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:36,  5.02it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -205.401259
return_std                          30.960339
average_reward                      -0.205401
round_time             0 days 00:05:40.230378
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.458814
return_std_test                      13.27812
average_reward_test                  0.009459
round_time_test        0 days 00:00:07.996693
round_time_total       0 days 00:05:40.231455
loss_total                         122.995946
loss_critic                        239.411522
loss_actor                        -342.666368
memory_size                        454661.653 

=== epoch 5/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:16,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -204.825333
return_std                          30.549751
average_reward                      -0.204825
round_time             0 days 00:05:39.521122
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.008901
return_std_test                      8.505572
average_reward_test                  0.003009
round_time_test        0 days 00:00:08.015648
round_time_total       0 days 00:05:39.522457
loss_total                         119.408497
loss_critic                        234.923048
loss_actor                        -342.649716
memory_size                        456625.653 

=== epoch 5/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:10,  5.37it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -208.165418
return_std                           29.40484
average_reward                      -0.208165
round_time             0 days 00:05:37.880962
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.959185
return_std_test                      9.496414
average_reward_test                  0.008959
round_time_test        0 days 00:00:07.969588
round_time_total       0 days 00:05:37.882048
loss_total                         121.965056
loss_critic                        238.184414
loss_actor                        -342.912384
memory_size                        458589.653 

=== epoch 5/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:03,  5.48it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -209.864536
return_std                          25.798362
average_reward                      -0.209865
round_time             0 days 00:05:40.229614
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.754214
return_std_test                      6.004004
average_reward_test                  0.004754
round_time_test        0 days 00:00:08.106808
round_time_total       0 days 00:05:40.230718
loss_total                         121.360207
loss_critic                        237.476668
loss_actor                        -343.105644
memory_size                        460553.653 

=== epoch 5/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:55,  4.79it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -202.971142
return_std                          27.094707
average_reward                      -0.202971
round_time             0 days 00:05:39.298354
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.278335
return_std_test                      7.337089
average_reward_test                  0.008278
round_time_test        0 days 00:00:07.883020
round_time_total       0 days 00:05:39.299623
loss_total                         124.116641
loss_critic                        240.892379
loss_actor                        -342.986318
memory_size                        462517.653 

=== epoch 5/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:59,  4.75it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -201.623436
return_std                          11.228085
average_reward                      -0.201623
round_time             0 days 00:05:40.917145
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.090373
return_std_test                     12.402509
average_reward_test                   0.00509
round_time_test        0 days 00:00:08.082123
round_time_total       0 days 00:05:40.918236
loss_total                         120.192306
loss_critic                        235.991184
loss_actor                        -343.003215
memory_size                        464481.653 

=== epoch 5/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:17,  5.27it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -196.135085
return_std                          18.139623
average_reward                      -0.196135
round_time             0 days 00:05:39.971449
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.344642
return_std_test                      8.897765
average_reward_test                  0.005345
round_time_test        0 days 00:00:08.107527
round_time_total       0 days 00:05:39.972534
loss_total                         119.208867
loss_critic                        234.809678
loss_actor                        -343.194384
memory_size                        466445.653 

=== epoch 5/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -192.739847
return_std                          19.229969
average_reward                       -0.19274
round_time             0 days 00:05:38.850794
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         14.23985
return_std_test                      9.170157
average_reward_test                   0.01424
round_time_test        0 days 00:00:07.840256
round_time_total       0 days 00:05:38.851893
loss_total                         121.216025
loss_critic                        237.257349
loss_actor                        -342.949281
memory_size                        468409.653 

=== epoch 5/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:30,  5.10it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -190.430329
return_std                           18.01174
average_reward                       -0.19043
round_time             0 days 00:05:41.262440
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.236999
return_std_test                       5.92542
average_reward_test                  0.011237
round_time_test        0 days 00:00:07.998466
round_time_total       0 days 00:05:41.263546
loss_total                         119.652214
loss_critic                        235.371597
loss_actor                         -343.22533
memory_size                        470373.653 

=== epoch 5/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:01,  4.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -190.806618
return_std                          17.676433
average_reward                      -0.190807
round_time             0 days 00:05:39.640912
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.506991
return_std_test                     10.446806
average_reward_test                  0.008507
round_time_test        0 days 00:00:07.767873
round_time_total       0 days 00:05:39.641998
loss_total                          119.52739
loss_critic                          235.1812
loss_actor                        -343.087856
memory_size                        472337.653 

=== epoch 5/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:07,  5.42it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -185.174222
return_std                          20.188129
average_reward                      -0.185174
round_time             0 days 00:05:40.577221
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.361708
return_std_test                      6.558013
average_reward_test                  0.014362
round_time_test        0 days 00:00:07.921602
round_time_total       0 days 00:05:40.578422
loss_total                         119.236221
loss_critic                        234.772853
loss_actor                        -342.910316
memory_size                        474301.653 

=== epoch 5/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:43,  4.93it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.400142
return_std                          19.401363
average_reward                        -0.1844
round_time             0 days 00:05:39.492655
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.091993
return_std_test                     11.010101
average_reward_test                  0.005092
round_time_test        0 days 00:00:07.897038
round_time_total       0 days 00:05:39.493776
loss_total                         119.695507
loss_critic                        235.397832
loss_actor                        -343.113801
memory_size                        476265.653 

=== epoch 5/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:30,  4.42it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.218064
return_std                          20.357062
average_reward                      -0.179218
round_time             0 days 00:05:38.709434
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.848244
return_std_test                      5.098446
average_reward_test                  0.008848
round_time_test        0 days 00:00:08.042297
round_time_total       0 days 00:05:38.710507
loss_total                         120.951035
loss_critic                        236.943746
loss_actor                         -343.01982
memory_size                        478229.653 

=== epoch 5/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:55,  4.79it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -180.849682
return_std                          21.547552
average_reward                       -0.18085
round_time             0 days 00:05:41.061633
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.595437
return_std_test                      6.443824
average_reward_test                  0.009595
round_time_test        0 days 00:00:07.822295
round_time_total       0 days 00:05:41.063102
loss_total                         119.953046
loss_critic                        235.708598
loss_actor                        -343.069173
memory_size                        480193.653 

=== epoch 5/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:36,  5.02it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -180.507507
return_std                          21.132521
average_reward                      -0.180508
round_time             0 days 00:05:42.018018
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.482606
return_std_test                      8.216871
average_reward_test                  0.003483
round_time_test        0 days 00:00:08.037889
round_time_total       0 days 00:05:42.019167
loss_total                         117.593953
loss_critic                        232.811396
loss_actor                        -343.275828
memory_size                        482157.653 

=== epoch 5/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:27,  5.14it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -176.987825
return_std                          24.378706
average_reward                      -0.176988
round_time             0 days 00:05:41.833597
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          7.89244
return_std_test                      9.592253
average_reward_test                  0.007892
round_time_test        0 days 00:00:07.865738
round_time_total       0 days 00:05:41.834936
loss_total                         118.251614
loss_critic                        233.697509
loss_actor                        -343.531974
memory_size                        484121.653 

=== epoch 5/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:57,  4.77it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -182.278794
return_std                          24.477875
average_reward                      -0.182279
round_time             0 days 00:05:41.134079
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.705161
return_std_test                      4.806903
average_reward_test                  0.005705
round_time_test        0 days 00:00:07.932806
round_time_total       0 days 00:05:41.135172
loss_total                         117.673442
loss_critic                        233.009197
loss_actor                        -343.669585
memory_size                        486085.653 

=== epoch 5/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<12:31,  2.66it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.607311
return_std                          26.197475
average_reward                      -0.183607
round_time             0 days 00:05:40.479745
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.672439
return_std_test                     10.748091
average_reward_test                  0.007672
round_time_test        0 days 00:00:07.930807
round_time_total       0 days 00:05:40.481101
loss_total                         118.361938
loss_critic                        233.919618
loss_actor                        -343.868792
memory_size                        488049.653 

=== epoch 5/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:43,  4.94it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -188.322932
return_std                           30.68292
average_reward                      -0.188323
round_time             0 days 00:05:39.518702
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.434548
return_std_test                      8.289997
average_reward_test                  0.006435
round_time_test        0 days 00:00:07.937423
round_time_total       0 days 00:05:39.519907
loss_total                          120.01148
loss_critic                        235.947885
loss_actor                         -343.73415
memory_size                        490013.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 6/10 ===== round 1/50 ======================================
  1%|          | 13/2000 [00:02<06:16,  5.27it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:21<00:00,  6.22it/s]
episodes                                    2
episode_length                         1000.0
returns                           -195.982716
return_std                           6.163668
average_reward                      -0.195983
round_time             0 days 00:05:21.678822
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.549412
return_std_test                      8.642771
average_reward_test                  0.006549
round_time_test        0 days 00:00:07.938638
round_time_total       0 days 00:05:21.680286
loss_total                         117.983848
loss_critic                         233.39787
loss_actor                        -343.672248
memory_size                        491978.653 

=== epoch 6/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:04,  5.46it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:24<00:00,  6.17it/s]
episodes                                    4
episode_length                         1000.0
returns                            -173.22169
return_std                          27.742418
average_reward                      -0.173222
round_time             0 days 00:05:24.543724
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.850115
return_std_test                      4.631508
average_reward_test                   0.00285
round_time_test        0 days 00:00:07.853901
round_time_total       0 days 00:05:24.544822
loss_total                         119.102002
loss_critic                        234.815037
loss_actor                        -343.750146
memory_size                        493942.653 

=== epoch 6/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:22,  5.21it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:24<00:00,  6.15it/s]
episodes                                    6
episode_length                         1000.0
returns                           -174.161144
return_std                          23.898631
average_reward                      -0.174161
round_time             0 days 00:05:25.472523
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.024892
return_std_test                       4.62106
average_reward_test                  0.010025
round_time_test        0 days 00:00:08.102773
round_time_total       0 days 00:05:25.473799
loss_total                         119.734517
loss_critic                        235.642696
loss_actor                        -343.898204
memory_size                        495906.653 

=== epoch 6/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.11it/s]
episodes                                    8
episode_length                         1000.0
returns                            -181.58168
return_std                          24.691812
average_reward                      -0.181582
round_time             0 days 00:05:27.643775
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.937589
return_std_test                      9.974605
average_reward_test                  0.006938
round_time_test        0 days 00:00:08.037735
round_time_total       0 days 00:05:27.645217
loss_total                         115.812842
loss_critic                        230.848389
loss_actor                        -344.329356
memory_size                        497870.653 

=== epoch 6/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:17,  5.27it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.10it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.120859
return_std                          25.966321
average_reward                      -0.188121
round_time             0 days 00:05:28.558270
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.261382
return_std_test                      9.503959
average_reward_test                  0.011261
round_time_test        0 days 00:00:08.078627
round_time_total       0 days 00:05:28.559420
loss_total                         117.629953
loss_critic                        233.164068
loss_actor                        -344.506515
memory_size                        499834.653 

=== epoch 6/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:52,  5.64it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.06it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.900632
return_std                          27.880512
average_reward                      -0.188901
round_time             0 days 00:05:30.458686
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.937463
return_std_test                      7.652417
average_reward_test                  0.008937
round_time_test        0 days 00:00:08.159159
round_time_total       0 days 00:05:30.459799
loss_total                         117.313243
loss_critic                        232.777102
loss_actor                        -344.542201
memory_size                        501798.653 

=== epoch 6/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:57,  4.77it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -200.845603
return_std                          18.376077
average_reward                      -0.200846
round_time             0 days 00:05:31.129584
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.837936
return_std_test                      9.087631
average_reward_test                  0.010838
round_time_test        0 days 00:00:07.959433
round_time_total       0 days 00:05:31.130679
loss_total                         116.906676
loss_critic                        232.286179
loss_actor                        -344.611344
memory_size                        503762.653 

=== epoch 6/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.12it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -205.120525
return_std                          14.107197
average_reward                      -0.205121
round_time             0 days 00:05:29.847745
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         -1.35342
return_std_test                      22.66046
average_reward_test                 -0.001353
round_time_test        0 days 00:00:08.166108
round_time_total       0 days 00:05:29.849185
loss_total                          120.27527
loss_critic                        236.427964
loss_actor                        -344.335515
memory_size                        505726.653 

=== epoch 6/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:04,  4.70it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.03it/s]
episodes                                   10
episode_length                         1000.0
returns                           -209.244584
return_std                          17.645322
average_reward                      -0.209245
round_time             0 days 00:05:32.365415
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.601186
return_std_test                      7.377434
average_reward_test                  0.006601
round_time_test        0 days 00:00:08.079409
round_time_total       0 days 00:05:32.366906
loss_total                         121.429788
loss_critic                         237.84154
loss_actor                         -344.21723
memory_size                        507690.653 

=== epoch 6/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:43,  4.94it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -204.905764
return_std                          18.500417
average_reward                      -0.204906
round_time             0 days 00:05:34.207978
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.673465
return_std_test                       4.98172
average_reward_test                  0.007673
round_time_test        0 days 00:00:07.976896
round_time_total       0 days 00:05:34.209571
loss_total                         121.241893
loss_critic                        237.557341
loss_actor                         -344.01991
memory_size                        509654.653 

=== epoch 6/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:12,  5.35it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.03it/s]
episodes                                   10
episode_length                         1000.0
returns                            -202.32699
return_std                          17.354586
average_reward                      -0.202327
round_time             0 days 00:05:32.035212
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.699765
return_std_test                      7.248694
average_reward_test                    0.0107
round_time_test        0 days 00:00:08.315138
round_time_total       0 days 00:05:32.036308
loss_total                         116.801144
loss_critic                        232.115977
loss_actor                        -344.458197
memory_size                        511618.653 

=== epoch 6/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:06,  5.43it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.03it/s]
episodes                                   10
episode_length                         1000.0
returns                           -192.525564
return_std                          24.985291
average_reward                      -0.192526
round_time             0 days 00:05:32.494485
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.636002
return_std_test                     12.732379
average_reward_test                  0.007636
round_time_test        0 days 00:00:07.901347
round_time_total       0 days 00:05:32.495591
loss_total                         119.195707
loss_critic                        235.215366
loss_actor                        -344.882937
memory_size                        513582.653 

=== epoch 6/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:59,  5.54it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.105024
return_std                          25.445168
average_reward                      -0.188105
round_time             0 days 00:05:33.816320
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.935091
return_std_test                      6.551388
average_reward_test                  0.005935
round_time_test        0 days 00:00:08.065420
round_time_total       0 days 00:05:33.817402
loss_total                         119.330118
loss_critic                        235.411402
loss_actor                        -344.995029
memory_size                        515546.653 

=== epoch 6/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:10,  5.37it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.04it/s]
episodes                                   10
episode_length                         1000.0
returns                           -175.730226
return_std                          17.267522
average_reward                       -0.17573
round_time             0 days 00:05:31.773065
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.021149
return_std_test                     10.144768
average_reward_test                  0.010021
round_time_test        0 days 00:00:07.886097
round_time_total       0 days 00:05:31.774171
loss_total                         119.539209
loss_critic                        235.660583
loss_actor                        -344.946296
memory_size                        517510.653 

=== epoch 6/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:36,  5.01it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.322342
return_std                           15.68417
average_reward                      -0.174322
round_time             0 days 00:05:35.996286
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.066741
return_std_test                      6.760574
average_reward_test                  0.011067
round_time_test        0 days 00:00:07.889461
round_time_total       0 days 00:05:35.997506
loss_total                          115.91979
loss_critic                        231.135677
loss_actor                        -344.943767
memory_size                        519474.653 

=== epoch 6/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:41,  4.96it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.903489
return_std                          16.621483
average_reward                      -0.172903
round_time             0 days 00:05:35.458813
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          7.62539
return_std_test                      9.726404
average_reward_test                  0.007625
round_time_test        0 days 00:00:07.921808
round_time_total       0 days 00:05:35.459904
loss_total                         114.356955
loss_critic                        229.290587
loss_actor                        -345.377585
memory_size                        521438.653 

=== epoch 6/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:30,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.070709
return_std                          14.198704
average_reward                      -0.179071
round_time             0 days 00:05:34.696027
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.020584
return_std_test                      6.947221
average_reward_test                  0.008021
round_time_test        0 days 00:00:07.961587
round_time_total       0 days 00:05:34.697242
loss_total                         117.867708
loss_critic                        233.735335
loss_actor                         -345.60281
memory_size                        523402.653 

=== epoch 6/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:12,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.645396
return_std                          13.277228
average_reward                      -0.179645
round_time             0 days 00:05:34.858550
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.109383
return_std_test                       8.54822
average_reward_test                  0.002109
round_time_test        0 days 00:00:08.257855
round_time_total       0 days 00:05:34.859761
loss_total                         115.009392
loss_critic                        230.092511
loss_actor                        -345.323096
memory_size                        525366.653 

=== epoch 6/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:24,  5.17it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                            -184.32697
return_std                          10.279277
average_reward                      -0.184327
round_time             0 days 00:05:35.135327
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -0.722272
return_std_test                     15.340401
average_reward_test                 -0.000722
round_time_test        0 days 00:00:07.904186
round_time_total       0 days 00:05:35.136481
loss_total                         117.646471
loss_critic                        233.323422
loss_actor                        -345.061344
memory_size                        527330.653 

=== epoch 6/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:09,  4.64it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.139337
return_std                          20.644819
average_reward                      -0.187139
round_time             0 days 00:05:34.813738
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.495966
return_std_test                     12.804102
average_reward_test                  0.002496
round_time_test        0 days 00:00:07.866026
round_time_total       0 days 00:05:34.815108
loss_total                         113.275101
loss_critic                        227.826735
loss_actor                        -344.931443
memory_size                        529294.653 

=== epoch 6/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:34,  5.04it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.962604
return_std                          20.536319
average_reward                      -0.184963
round_time             0 days 00:05:37.522406
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.648116
return_std_test                      9.547602
average_reward_test                  0.005648
round_time_test        0 days 00:00:07.905824
round_time_total       0 days 00:05:37.523671
loss_total                         113.721908
loss_critic                        228.537133
loss_actor                        -345.538998
memory_size                        531258.653 

=== epoch 6/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:49,  4.86it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.610825
return_std                          21.021404
average_reward                      -0.184611
round_time             0 days 00:05:37.743344
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.454524
return_std_test                     11.070509
average_reward_test                  0.002455
round_time_test        0 days 00:00:07.836333
round_time_total       0 days 00:05:37.744428
loss_total                         113.975998
loss_critic                        228.991769
loss_actor                        -346.087094
memory_size                        533222.653 

=== epoch 6/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:12,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                            -189.52625
return_std                          22.793256
average_reward                      -0.189526
round_time             0 days 00:05:36.534288
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          6.48828
return_std_test                      8.443562
average_reward_test                  0.006488
round_time_test        0 days 00:00:07.878421
round_time_total       0 days 00:05:36.535379
loss_total                         113.144186
loss_critic                        227.936559
loss_actor                        -346.025313
memory_size                        535186.653 

=== epoch 6/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:44,  4.93it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -190.678852
return_std                          22.899129
average_reward                      -0.190679
round_time             0 days 00:05:36.892573
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.920431
return_std_test                      8.283742
average_reward_test                   0.01092
round_time_test        0 days 00:00:08.118167
round_time_total       0 days 00:05:36.894036
loss_total                         114.181839
loss_critic                        229.203266
loss_actor                        -345.903879
memory_size                        537150.653 

=== epoch 6/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:22,  5.21it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.740186
return_std                           15.73186
average_reward                       -0.18774
round_time             0 days 00:05:37.150591
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          4.34803
return_std_test                      8.223219
average_reward_test                  0.004348
round_time_test        0 days 00:00:07.979162
round_time_total       0 days 00:05:37.151700
loss_total                         114.116771
loss_critic                        229.061076
loss_actor                        -345.660457
memory_size                        539114.653 

=== epoch 6/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:36,  5.01it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                            -189.38063
return_std                          13.828186
average_reward                      -0.189381
round_time             0 days 00:05:38.795495
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.479375
return_std_test                      8.260364
average_reward_test                  0.006479
round_time_test        0 days 00:00:08.157458
round_time_total       0 days 00:05:38.796598
loss_total                         114.327235
loss_critic                         229.34608
loss_actor                        -345.748151
memory_size                        541078.653 

=== epoch 6/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:01,  5.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.855163
return_std                          13.332886
average_reward                      -0.186855
round_time             0 days 00:05:38.065482
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          4.21231
return_std_test                      6.847405
average_reward_test                  0.004212
round_time_test        0 days 00:00:08.014474
round_time_total       0 days 00:05:38.066591
loss_total                         114.750925
loss_critic                        229.928872
loss_actor                         -345.96087
memory_size                        543042.653 

=== epoch 6/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:30,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -178.791905
return_std                          15.576513
average_reward                      -0.178792
round_time             0 days 00:05:37.914431
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.637472
return_std_test                      9.355427
average_reward_test                  0.007637
round_time_test        0 days 00:00:08.340440
round_time_total       0 days 00:05:37.915539
loss_total                         115.060092
loss_critic                        230.370629
loss_actor                        -346.182062
memory_size                        545006.653 

=== epoch 6/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -178.937324
return_std                          20.171059
average_reward                      -0.178937
round_time             0 days 00:05:36.653943
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.650032
return_std_test                      8.622152
average_reward_test                   0.00465
round_time_test        0 days 00:00:07.798777
round_time_total       0 days 00:05:36.655033
loss_total                         113.510143
loss_critic                        228.441563
loss_actor                        -346.215544
memory_size                        546970.653 

=== epoch 6/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:41,  4.96it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.619268
return_std                          23.415715
average_reward                      -0.172619
round_time             0 days 00:05:36.725668
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.286896
return_std_test                     22.074113
average_reward_test                  0.003287
round_time_test        0 days 00:00:08.168927
round_time_total       0 days 00:05:36.726922
loss_total                         110.610573
loss_critic                        224.781931
loss_actor                        -346.074866
memory_size                        548934.653 

=== epoch 6/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:19,  5.25it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:43<00:00,  5.83it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.549297
return_std                          23.713239
average_reward                      -0.173549
round_time             0 days 00:05:43.583857
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         12.16644
return_std_test                      7.591368
average_reward_test                  0.012166
round_time_test        0 days 00:00:08.053427
round_time_total       0 days 00:05:43.585414
loss_total                         111.467448
loss_critic                         225.81737
loss_actor                        -345.932246
memory_size                        550898.653 

=== epoch 6/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:59,  5.54it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                            -172.98014
return_std                          24.182282
average_reward                       -0.17298
round_time             0 days 00:05:36.343432
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.138176
return_std_test                     13.096108
average_reward_test                  0.004138
round_time_test        0 days 00:00:07.951574
round_time_total       0 days 00:05:36.344524
loss_total                         113.717324
loss_critic                        228.686675
loss_actor                        -346.160085
memory_size                        552862.653 

=== epoch 6/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:18,  5.26it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.985648
return_std                          23.465358
average_reward                      -0.170986
round_time             0 days 00:05:40.782788
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.855361
return_std_test                      7.988664
average_reward_test                  0.006855
round_time_test        0 days 00:00:07.961904
round_time_total       0 days 00:05:40.783892
loss_total                         111.515217
loss_critic                         226.03251
loss_actor                        -346.553966
memory_size                        554826.653 

=== epoch 6/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:08,  5.41it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -165.900961
return_std                          17.068392
average_reward                      -0.165901
round_time             0 days 00:05:41.848360
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.495818
return_std_test                      7.471742
average_reward_test                  0.011496
round_time_test        0 days 00:00:08.075395
round_time_total       0 days 00:05:41.849831
loss_total                         107.728007
loss_critic                        221.396032
loss_actor                        -346.944099
memory_size                        556790.653 

=== epoch 6/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:14,  5.31it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -165.513404
return_std                          14.868696
average_reward                      -0.165513
round_time             0 days 00:05:39.742801
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        16.645863
return_std_test                      6.370268
average_reward_test                  0.016646
round_time_test        0 days 00:00:08.007726
round_time_total       0 days 00:05:39.744104
loss_total                         108.844919
loss_critic                        222.724232
loss_actor                         -346.67234
memory_size                        558754.653 

=== epoch 6/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:04,  5.46it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -164.213447
return_std                          16.413995
average_reward                      -0.164213
round_time             0 days 00:05:39.624179
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.253274
return_std_test                      8.779246
average_reward_test                  0.007253
round_time_test        0 days 00:00:07.920629
round_time_total       0 days 00:05:39.625272
loss_total                         109.712458
loss_critic                        223.841567
loss_actor                        -346.803981
memory_size                        560718.653 

=== epoch 6/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:30,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.278283
return_std                          19.850678
average_reward                      -0.166278
round_time             0 days 00:05:42.424938
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.406373
return_std_test                     11.113649
average_reward_test                  0.007406
round_time_test        0 days 00:00:07.877900
round_time_total       0 days 00:05:42.426025
loss_total                           109.6861
loss_critic                        223.827004
loss_actor                        -346.877519
memory_size                        562682.653 

=== epoch 6/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:19,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.830921
return_std                          28.095395
average_reward                      -0.174831
round_time             0 days 00:05:41.162209
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.433365
return_std_test                      7.478395
average_reward_test                  0.008433
round_time_test        0 days 00:00:07.946982
round_time_total       0 days 00:05:41.163308
loss_total                         111.371146
loss_critic                        225.929197
loss_actor                        -346.861064
memory_size                        564646.653 

=== epoch 6/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:37,  5.01it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -175.521361
return_std                          27.404333
average_reward                      -0.175521
round_time             0 days 00:05:41.703416
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          8.50906
return_std_test                       5.89885
average_reward_test                  0.008509
round_time_test        0 days 00:00:07.813007
round_time_total       0 days 00:05:41.704841
loss_total                          109.58211
loss_critic                        223.693172
loss_actor                        -346.862144
memory_size                        566610.653 

=== epoch 6/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:01,  4.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.509206
return_std                          25.295353
average_reward                      -0.183509
round_time             0 days 00:05:40.294094
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.991812
return_std_test                       6.66751
average_reward_test                  0.006992
round_time_test        0 days 00:00:07.994688
round_time_total       0 days 00:05:40.295496
loss_total                         110.310526
loss_critic                        224.585314
loss_actor                        -346.788631
memory_size                        568574.653 

=== epoch 6/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:49,  4.86it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -189.938417
return_std                          25.428094
average_reward                      -0.189938
round_time             0 days 00:05:38.672181
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.731501
return_std_test                      5.799643
average_reward_test                  0.007732
round_time_test        0 days 00:00:08.239720
round_time_total       0 days 00:05:38.673347
loss_total                          109.68872
loss_critic                        223.775178
loss_actor                        -346.657124
memory_size                        570538.653 

=== epoch 6/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:37,  5.01it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.021778
return_std                          29.330522
average_reward                      -0.183022
round_time             0 days 00:05:39.658524
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.177727
return_std_test                      7.384851
average_reward_test                  0.009178
round_time_test        0 days 00:00:07.941827
round_time_total       0 days 00:05:39.659621
loss_total                         109.050215
loss_critic                        223.042577
loss_actor                        -346.919242
memory_size                        572502.653 

=== epoch 6/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:26,  5.16it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.334955
return_std                          25.244465
average_reward                      -0.186335
round_time             0 days 00:05:40.950076
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.935254
return_std_test                     13.446097
average_reward_test                  0.000935
round_time_test        0 days 00:00:07.941410
round_time_total       0 days 00:05:40.951170
loss_total                         108.614126
loss_critic                        222.614036
loss_actor                        -347.385523
memory_size                        574466.653 

=== epoch 6/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.085874
return_std                          25.422929
average_reward                      -0.186086
round_time             0 days 00:05:40.303342
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.856878
return_std_test                      8.658934
average_reward_test                  0.005857
round_time_test        0 days 00:00:07.767985
round_time_total       0 days 00:05:40.304423
loss_total                         109.142299
loss_critic                        223.410287
loss_actor                        -347.929659
memory_size                        576430.653 

=== epoch 6/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:34,  5.04it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.490903
return_std                          25.566578
average_reward                      -0.187491
round_time             0 days 00:05:39.063424
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.462756
return_std_test                      7.979327
average_reward_test                  0.000463
round_time_test        0 days 00:00:08.072000
round_time_total       0 days 00:05:39.064524
loss_total                         107.693287
loss_critic                        221.641502
loss_actor                        -348.099581
memory_size                        578394.653 

=== epoch 6/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:10,  5.37it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                            -180.32789
return_std                          23.236422
average_reward                      -0.180328
round_time             0 days 00:05:39.935897
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.374064
return_std_test                      8.265805
average_reward_test                  0.004374
round_time_test        0 days 00:00:07.848182
round_time_total       0 days 00:05:39.936981
loss_total                         107.314848
loss_critic                        221.256125
loss_actor                        -348.450267
memory_size                        580358.653 

=== epoch 6/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:30,  5.10it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.139525
return_std                          26.491973
average_reward                       -0.18714
round_time             0 days 00:05:42.192077
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                           5.9702
return_std_test                      4.501199
average_reward_test                   0.00597
round_time_test        0 days 00:00:07.938101
round_time_total       0 days 00:05:42.193402
loss_total                         110.900589
loss_critic                        225.644501
loss_actor                        -348.075067
memory_size                        582322.653 

=== epoch 6/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:18,  5.26it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.196906
return_std                          23.997459
average_reward                      -0.183197
round_time             0 days 00:05:39.521950
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.983314
return_std_test                      5.344471
average_reward_test                  0.000983
round_time_test        0 days 00:00:07.848843
round_time_total       0 days 00:05:39.523074
loss_total                         106.872998
loss_critic                        220.617144
loss_actor                        -348.103595
memory_size                        584286.653 

=== epoch 6/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.849958
return_std                          23.657894
average_reward                       -0.18385
round_time             0 days 00:05:38.203804
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.369957
return_std_test                     10.330996
average_reward_test                   0.00337
round_time_test        0 days 00:00:07.956907
round_time_total       0 days 00:05:38.204889
loss_total                          106.92046
loss_critic                        220.596651
loss_actor                        -347.784313
memory_size                        586250.653 

=== epoch 6/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:38,  5.00it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -180.142914
return_std                           24.24976
average_reward                      -0.180143
round_time             0 days 00:05:40.176767
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.823943
return_std_test                      8.877322
average_reward_test                  0.015824
round_time_test        0 days 00:00:08.183336
round_time_total       0 days 00:05:40.178090
loss_total                         109.102353
loss_critic                        223.365305
loss_actor                        -347.949464
memory_size                        588214.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 7/10 ===== round 1/50 ======================================
  1%|          | 12/2000 [00:02<06:03,  5.46it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:22<00:00,  6.21it/s]
episodes                                    2
episode_length                         1000.0
returns                           -184.380885
return_std                          15.688571
average_reward                      -0.184381
round_time             0 days 00:05:22.041958
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.260861
return_std_test                      8.349307
average_reward_test                  0.008261
round_time_test        0 days 00:00:08.011323
round_time_total       0 days 00:05:22.043056
loss_total                         108.128455
loss_critic                        222.185508
loss_actor                        -348.099764
memory_size                        590179.653 

=== epoch 7/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:17,  5.27it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:23<00:00,  6.18it/s]
episodes                                    4
episode_length                         1000.0
returns                           -181.274027
return_std                          24.470706
average_reward                      -0.181274
round_time             0 days 00:05:24.183085
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.589473
return_std_test                      10.52511
average_reward_test                  0.009589
round_time_test        0 days 00:00:07.740603
round_time_total       0 days 00:05:24.184165
loss_total                         107.465786
loss_critic                        221.379452
loss_actor                        -348.188882
memory_size                        592143.653 

=== epoch 7/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:28,  5.13it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:25<00:00,  6.15it/s]
episodes                                    6
episode_length                         1000.0
returns                           -177.083836
return_std                          22.336884
average_reward                      -0.177084
round_time             0 days 00:05:26.008245
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.865628
return_std_test                       7.11735
average_reward_test                  0.006866
round_time_test        0 days 00:00:07.935660
round_time_total       0 days 00:05:26.009408
loss_total                         107.590083
loss_critic                        221.572424
loss_actor                        -348.339287
memory_size                        594107.653 

=== epoch 7/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:26,  5.15it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.11it/s]
episodes                                    8
episode_length                         1000.0
returns                           -175.261246
return_std                           23.66411
average_reward                      -0.175261
round_time             0 days 00:05:27.825974
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.767409
return_std_test                      8.672483
average_reward_test                  0.007767
round_time_test        0 days 00:00:07.906776
round_time_total       0 days 00:05:27.827063
loss_total                         105.892083
loss_critic                        219.492556
loss_actor                         -348.50982
memory_size                        596071.653 

=== epoch 7/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:06,  5.43it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:28<00:00,  6.08it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.506231
return_std                          27.256661
average_reward                      -0.168506
round_time             0 days 00:05:29.300767
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.678948
return_std_test                       7.91567
average_reward_test                  0.004679
round_time_test        0 days 00:00:07.832143
round_time_total       0 days 00:05:29.302106
loss_total                         112.820379
loss_critic                        228.149764
loss_actor                         -348.49717
memory_size                        598035.653 

=== epoch 7/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:10,  5.37it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.06it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.735582
return_std                          26.501385
average_reward                      -0.168736
round_time             0 days 00:05:30.543110
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.098097
return_std_test                     11.926935
average_reward_test                  0.009098
round_time_test        0 days 00:00:07.736990
round_time_total       0 days 00:05:30.544227
loss_total                         106.960635
loss_critic                        220.901435
loss_actor                        -348.802572
memory_size                        599999.653 

=== epoch 7/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:32,  5.06it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:28<00:00,  6.09it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.493325
return_std                          25.268753
average_reward                      -0.171493
round_time             0 days 00:05:28.782101
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.937603
return_std_test                      6.822386
average_reward_test                  0.007938
round_time_test        0 days 00:00:07.727346
round_time_total       0 days 00:05:28.783550
loss_total                         105.570014
loss_critic                         219.20849
loss_actor                        -348.983899
memory_size                        601963.653 

=== epoch 7/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:13,  5.33it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -176.854758
return_std                          26.288967
average_reward                      -0.176855
round_time             0 days 00:05:33.060421
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.588854
return_std_test                        7.0277
average_reward_test                  0.005589
round_time_test        0 days 00:00:08.154002
round_time_total       0 days 00:05:33.061516
loss_total                         103.297269
loss_critic                        216.387379
loss_actor                        -349.063179
memory_size                        603927.653 

=== epoch 7/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.239772
return_std                          28.998856
average_reward                       -0.17224
round_time             0 days 00:05:31.287714
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.676377
return_std_test                      7.272641
average_reward_test                  0.005676
round_time_test        0 days 00:00:08.055608
round_time_total       0 days 00:05:31.289066
loss_total                         103.956656
loss_critic                        217.248662
loss_actor                        -349.211372
memory_size                        605891.653 

=== epoch 7/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:48,  5.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -178.435107
return_std                          22.914835
average_reward                      -0.178435
round_time             0 days 00:05:33.958274
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.821163
return_std_test                      5.624209
average_reward_test                  0.004821
round_time_test        0 days 00:00:07.943427
round_time_total       0 days 00:05:33.959457
loss_total                         108.551707
loss_critic                        222.947037
loss_actor                         -349.02962
memory_size                        607855.653 

=== epoch 7/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:36,  5.03it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.03it/s]
episodes                                   10
episode_length                         1000.0
returns                            -177.04039
return_std                          23.012267
average_reward                       -0.17704
round_time             0 days 00:05:32.469984
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.704929
return_std_test                      5.416842
average_reward_test                  0.007705
round_time_test        0 days 00:00:07.935698
round_time_total       0 days 00:05:32.471073
loss_total                         105.938323
loss_critic                        219.758907
loss_actor                        -349.344023
memory_size                        609819.653 

=== epoch 7/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:00,  4.74it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.03it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.885416
return_std                          22.671767
average_reward                      -0.171885
round_time             0 days 00:05:32.368415
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.313708
return_std_test                      6.171998
average_reward_test                  0.015314
round_time_test        0 days 00:00:08.137088
round_time_total       0 days 00:05:32.369524
loss_total                         101.730375
loss_critic                        214.590345
loss_actor                        -349.709512
memory_size                        611783.653 

=== epoch 7/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -165.087744
return_std                          19.286578
average_reward                      -0.165088
round_time             0 days 00:05:34.955237
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          4.48485
return_std_test                      8.154092
average_reward_test                  0.004485
round_time_test        0 days 00:00:07.741894
round_time_total       0 days 00:05:34.956502
loss_total                         102.457099
loss_critic                         215.51021
loss_actor                        -349.755351
memory_size                        613747.653 

=== epoch 7/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:30,  4.42it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -176.778194
return_std                          19.433349
average_reward                      -0.176778
round_time             0 days 00:05:36.412748
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.527098
return_std_test                       8.07498
average_reward_test                  0.010527
round_time_test        0 days 00:00:07.905630
round_time_total       0 days 00:05:36.413859
loss_total                         102.831979
loss_critic                        216.015294
loss_actor                        -349.901289
memory_size                        615711.653 

=== epoch 7/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  1%|          | 11/2000 [00:01<06:03,  5.48it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.663187
return_std                           26.77504
average_reward                      -0.183663
round_time             0 days 00:05:35.249576
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.764084
return_std_test                      7.296736
average_reward_test                  0.004764
round_time_test        0 days 00:00:08.002012
round_time_total       0 days 00:05:35.250942
loss_total                         103.782895
loss_critic                        217.193024
loss_actor                        -349.857632
memory_size                        617675.653 

=== epoch 7/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.33it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -185.897916
return_std                          26.403133
average_reward                      -0.185898
round_time             0 days 00:05:36.295072
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.960253
return_std_test                      9.375846
average_reward_test                   0.00796
round_time_test        0 days 00:00:07.951801
round_time_total       0 days 00:05:36.296388
loss_total                          99.946569
loss_critic                         212.39014
loss_actor                        -349.827723
memory_size                        619639.653 

=== epoch 7/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:05,  5.45it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -184.224033
return_std                          26.514597
average_reward                      -0.184224
round_time             0 days 00:05:33.801651
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.180655
return_std_test                      7.449476
average_reward_test                  0.007181
round_time_test        0 days 00:00:07.877244
round_time_total       0 days 00:05:33.802754
loss_total                         102.673547
loss_critic                        215.825491
loss_actor                        -349.934237
memory_size                        621603.653 

=== epoch 7/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:53,  4.81it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -191.502494
return_std                          24.232622
average_reward                      -0.191502
round_time             0 days 00:05:35.426763
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.813867
return_std_test                      6.583215
average_reward_test                  0.004814
round_time_test        0 days 00:00:07.984765
round_time_total       0 days 00:05:35.427860
loss_total                         102.801282
loss_critic                        215.931102
loss_actor                        -349.718008
memory_size                        623567.653 

=== epoch 7/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:15,  5.30it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.423493
return_std                          22.999673
average_reward                      -0.186423
round_time             0 days 00:05:36.844494
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.260505
return_std_test                      5.986905
average_reward_test                  0.007261
round_time_test        0 days 00:00:07.910784
round_time_total       0 days 00:05:36.845601
loss_total                          100.30091
loss_critic                        212.818181
loss_actor                        -349.768183
memory_size                        625531.653 

=== epoch 7/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:36,  5.02it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -180.913278
return_std                          14.861348
average_reward                      -0.180913
round_time             0 days 00:05:38.297963
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.143572
return_std_test                       6.84196
average_reward_test                  0.008144
round_time_test        0 days 00:00:08.035117
round_time_total       0 days 00:05:38.299050
loss_total                         101.259052
loss_critic                        214.028474
loss_actor                        -349.818641
memory_size                        627495.653 

=== epoch 7/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:24,  5.18it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.997722
return_std                          19.106938
average_reward                      -0.183998
round_time             0 days 00:05:36.361054
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.688523
return_std_test                     12.050212
average_reward_test                  0.007689
round_time_test        0 days 00:00:07.852511
round_time_total       0 days 00:05:36.362152
loss_total                         104.777972
loss_critic                        218.429157
loss_actor                        -349.826773
memory_size                        629459.653 

=== epoch 7/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:14,  5.32it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -194.459981
return_std                          16.109743
average_reward                       -0.19446
round_time             0 days 00:05:37.149446
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.338695
return_std_test                      4.579949
average_reward_test                  0.009339
round_time_test        0 days 00:00:08.050329
round_time_total       0 days 00:05:37.150886
loss_total                         104.210473
loss_critic                        217.812958
loss_actor                        -350.199471
memory_size                        631423.653 

=== epoch 7/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:49,  4.86it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.841294
return_std                          19.652734
average_reward                      -0.187841
round_time             0 days 00:05:38.024053
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.230272
return_std_test                     10.690512
average_reward_test                   0.01123
round_time_test        0 days 00:00:07.935457
round_time_total       0 days 00:05:38.025228
loss_total                         101.690126
loss_critic                        214.658232
loss_actor                        -350.182305
memory_size                        633387.653 

=== epoch 7/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:30,  5.10it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -195.073044
return_std                          25.089232
average_reward                      -0.195073
round_time             0 days 00:05:38.700078
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.038829
return_std_test                      8.217983
average_reward_test                  0.004039
round_time_test        0 days 00:00:08.088288
round_time_total       0 days 00:05:38.701175
loss_total                         104.610199
loss_critic                        218.284021
loss_actor                        -350.085097
memory_size                        635351.653 

=== epoch 7/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -193.202535
return_std                          28.483626
average_reward                      -0.193203
round_time             0 days 00:05:37.266674
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.853751
return_std_test                      6.166324
average_reward_test                  0.008854
round_time_test        0 days 00:00:07.923136
round_time_total       0 days 00:05:37.267934
loss_total                         104.082728
loss_critic                        217.635803
loss_actor                        -350.129578
memory_size                        637315.653 

=== epoch 7/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -187.908838
return_std                          27.300027
average_reward                      -0.187909
round_time             0 days 00:05:39.007661
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.646481
return_std_test                      5.976025
average_reward_test                  0.006646
round_time_test        0 days 00:00:08.161202
round_time_total       0 days 00:05:39.009177
loss_total                         104.807238
loss_critic                          218.5017
loss_actor                        -349.970618
memory_size                        639279.653 

=== epoch 7/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:09,  5.39it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.981683
return_std                          25.282985
average_reward                      -0.179982
round_time             0 days 00:05:37.857235
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.460132
return_std_test                      10.78056
average_reward_test                   0.01046
round_time_test        0 days 00:00:08.227478
round_time_total       0 days 00:05:37.858348
loss_total                         105.226042
loss_critic                        219.015295
loss_actor                        -349.930979
memory_size                        641243.653 

=== epoch 7/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:27,  5.14it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                            -190.12767
return_std                          31.702315
average_reward                      -0.190128
round_time             0 days 00:05:39.463037
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.382851
return_std_test                      7.022434
average_reward_test                  0.014383
round_time_test        0 days 00:00:07.966287
round_time_total       0 days 00:05:39.464157
loss_total                         102.290085
loss_critic                        215.457151
loss_actor                        -350.378189
memory_size                        643207.653 

=== epoch 7/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:58,  4.76it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.745488
return_std                          29.072166
average_reward                      -0.186745
round_time             0 days 00:05:38.869851
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.027584
return_std_test                      5.659409
average_reward_test                  0.009028
round_time_test        0 days 00:00:07.945909
round_time_total       0 days 00:05:38.871099
loss_total                         103.878561
loss_critic                        217.511923
loss_actor                        -350.654894
memory_size                        645171.653 

=== epoch 7/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:01,  5.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.738016
return_std                          30.013821
average_reward                      -0.183738
round_time             0 days 00:05:36.972160
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.818547
return_std_test                      7.445019
average_reward_test                  0.004819
round_time_test        0 days 00:00:07.965910
round_time_total       0 days 00:05:36.973392
loss_total                         104.972383
loss_critic                        218.839096
loss_actor                         -350.49448
memory_size                        647135.653 

=== epoch 7/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.207566
return_std                          32.271649
average_reward                      -0.183208
round_time             0 days 00:05:37.575692
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                           5.7595
return_std_test                      5.990197
average_reward_test                  0.005759
round_time_test        0 days 00:00:07.843574
round_time_total       0 days 00:05:37.576822
loss_total                         103.725679
loss_critic                         217.28886
loss_actor                         -350.52705
memory_size                        649099.653 

=== epoch 7/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:44,  4.92it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.195926
return_std                          32.790336
average_reward                      -0.186196
round_time             0 days 00:05:39.314433
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.645488
return_std_test                      9.455924
average_reward_test                  0.012645
round_time_test        0 days 00:00:08.126122
round_time_total       0 days 00:05:39.315620
loss_total                         101.475197
loss_critic                        214.407935
loss_actor                        -350.255761
memory_size                        651063.653 

=== epoch 7/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:35,  5.03it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -185.417123
return_std                          28.360627
average_reward                      -0.185417
round_time             0 days 00:05:39.618529
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.073517
return_std_test                      7.809721
average_reward_test                  0.012074
round_time_test        0 days 00:00:07.814146
round_time_total       0 days 00:05:39.619998
loss_total                         106.509775
loss_critic                        220.666772
loss_actor                        -350.118223
memory_size                        653027.653 

=== epoch 7/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:09,  5.39it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -185.853562
return_std                          26.964391
average_reward                      -0.185854
round_time             0 days 00:05:39.935995
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.636028
return_std_test                      8.585712
average_reward_test                  0.007636
round_time_test        0 days 00:00:07.964098
round_time_total       0 days 00:05:39.937094
loss_total                          107.57581
loss_critic                        222.012896
loss_actor                        -350.172539
memory_size                        654991.653 

=== epoch 7/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -190.386063
return_std                          21.793311
average_reward                      -0.190386
round_time             0 days 00:05:38.970133
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.920758
return_std_test                     10.884282
average_reward_test                  0.000921
round_time_test        0 days 00:00:08.010260
round_time_total       0 days 00:05:38.971234
loss_total                         100.840455
loss_critic                        213.642636
loss_actor                        -350.368277
memory_size                        656955.653 

=== epoch 7/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:27,  5.14it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -195.584745
return_std                          17.419119
average_reward                      -0.195585
round_time             0 days 00:05:39.080604
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.428231
return_std_test                      7.316837
average_reward_test                  0.006428
round_time_test        0 days 00:00:07.966041
round_time_total       0 days 00:05:39.081861
loss_total                          102.38645
loss_critic                        215.651791
loss_actor                         -350.67492
memory_size                        658919.653 

=== epoch 7/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:18,  5.26it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -197.569338
return_std                          18.701599
average_reward                      -0.197569
round_time             0 days 00:05:39.601862
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.617157
return_std_test                      9.403216
average_reward_test                  0.008617
round_time_test        0 days 00:00:08.164375
round_time_total       0 days 00:05:39.603136
loss_total                          103.14043
loss_critic                        216.593285
loss_actor                        -350.670997
memory_size                        660883.653 

=== epoch 7/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -186.987155
return_std                          22.678766
average_reward                      -0.186987
round_time             0 days 00:05:41.350757
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.536159
return_std_test                      5.053324
average_reward_test                  0.003536
round_time_test        0 days 00:00:07.853061
round_time_total       0 days 00:05:41.351858
loss_total                         102.377904
loss_critic                        215.655001
loss_actor                        -350.730495
memory_size                        662847.653 

=== epoch 7/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:59,  5.54it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -182.965891
return_std                          20.717285
average_reward                      -0.182966
round_time             0 days 00:05:37.891563
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         12.70154
return_std_test                      3.393137
average_reward_test                  0.012702
round_time_test        0 days 00:00:07.768365
round_time_total       0 days 00:05:37.893011
loss_total                         105.617107
loss_critic                        219.666159
loss_actor                        -350.579106
memory_size                        664811.653 

=== epoch 7/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:34,  5.04it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -188.166796
return_std                          24.936799
average_reward                      -0.188167
round_time             0 days 00:05:41.410080
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.860694
return_std_test                      9.071817
average_reward_test                  0.009861
round_time_test        0 days 00:00:08.090067
round_time_total       0 days 00:05:41.411221
loss_total                         101.629924
loss_critic                        214.721081
loss_actor                        -350.734711
memory_size                        666775.653 

=== epoch 7/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:04,  5.46it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -180.354638
return_std                          27.024415
average_reward                      -0.180355
round_time             0 days 00:05:40.945328
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.622447
return_std_test                      6.897729
average_reward_test                  0.011622
round_time_test        0 days 00:00:08.142873
round_time_total       0 days 00:05:40.946431
loss_total                         101.548732
loss_critic                        214.677166
loss_actor                        -350.965011
memory_size                        668739.653 

=== epoch 7/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:34,  5.04it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.414092
return_std                          25.884007
average_reward                      -0.171414
round_time             0 days 00:05:40.597736
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.138448
return_std_test                      4.794802
average_reward_test                  0.009138
round_time_test        0 days 00:00:08.295693
round_time_total       0 days 00:05:40.599216
loss_total                         101.718356
loss_critic                        214.831399
loss_actor                        -350.733825
memory_size                        670703.653 

=== epoch 7/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:40,  4.97it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.513563
return_std                          24.516621
average_reward                      -0.172514
round_time             0 days 00:05:37.943025
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.368494
return_std_test                      11.05976
average_reward_test                  0.004368
round_time_test        0 days 00:00:08.060995
round_time_total       0 days 00:05:37.944309
loss_total                         104.118759
loss_critic                        217.907372
loss_actor                        -351.035703
memory_size                        672667.653 

=== epoch 7/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:56,  4.78it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.263425
return_std                          26.113963
average_reward                      -0.166263
round_time             0 days 00:05:39.648501
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.365286
return_std_test                      5.348133
average_reward_test                  0.006365
round_time_test        0 days 00:00:08.030777
round_time_total       0 days 00:05:39.649588
loss_total                         100.355105
loss_critic                        213.277563
loss_actor                        -351.334735
memory_size                        674631.653 

=== epoch 7/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:36,  5.03it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -154.361035
return_std                          14.860366
average_reward                      -0.154361
round_time             0 days 00:05:40.292962
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          9.29006
return_std_test                      6.249292
average_reward_test                   0.00929
round_time_test        0 days 00:00:07.966095
round_time_total       0 days 00:05:40.294097
loss_total                         103.304325
loss_critic                        216.970429
loss_actor                        -351.360097
memory_size                        676595.653 

=== epoch 7/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:28,  5.12it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                            -160.03909
return_std                          24.031466
average_reward                      -0.160039
round_time             0 days 00:05:41.032455
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.099917
return_std_test                      7.922576
average_reward_test                    0.0071
round_time_test        0 days 00:00:07.812805
round_time_total       0 days 00:05:41.033901
loss_total                         101.633397
loss_critic                        214.931616
loss_actor                        -351.559485
memory_size                        678559.653 

=== epoch 7/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:02,  5.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                             -164.9739
return_std                           23.67194
average_reward                      -0.164974
round_time             0 days 00:05:40.379074
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.111523
return_std_test                      8.301554
average_reward_test                  0.010112
round_time_test        0 days 00:00:07.978658
round_time_total       0 days 00:05:40.380349
loss_total                          99.644514
loss_critic                        212.452153
loss_actor                        -351.586047
memory_size                        680523.653 

=== epoch 7/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:14,  5.32it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -164.423821
return_std                          23.884262
average_reward                      -0.164424
round_time             0 days 00:05:39.978010
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.324661
return_std_test                      6.110412
average_reward_test                  0.005325
round_time_test        0 days 00:00:07.981890
round_time_total       0 days 00:05:39.979110
loss_total                         100.162571
loss_critic                        213.090091
loss_actor                        -351.547516
memory_size                        682487.653 

=== epoch 7/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:05,  4.68it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.484414
return_std                          22.186277
average_reward                      -0.168484
round_time             0 days 00:05:40.484843
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.153472
return_std_test                      6.719873
average_reward_test                  0.001153
round_time_test        0 days 00:00:07.821356
round_time_total       0 days 00:05:40.485955
loss_total                         100.510589
loss_critic                        213.542677
loss_actor                        -351.617767
memory_size                        684451.653 

=== epoch 7/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:04,  4.69it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:43<00:00,  5.82it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -174.735763
return_std                          18.452607
average_reward                      -0.174736
round_time             0 days 00:05:43.999196
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.359411
return_std_test                      7.909212
average_reward_test                  0.007359
round_time_test        0 days 00:00:07.847552
round_time_total       0 days 00:05:44.000433
loss_total                          99.654247
loss_critic                        212.557442
loss_actor                         -351.95854
memory_size                        686415.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 8/10 ===== round 1/50 ======================================
  1%|          | 12/2000 [00:02<06:18,  5.25it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:19<00:00,  6.25it/s]
episodes                                    2
episode_length                         1000.0
returns                           -173.357924
return_std                           1.011754
average_reward                      -0.173358
round_time             0 days 00:05:19.989581
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.589369
return_std_test                      7.027516
average_reward_test                  0.005589
round_time_test        0 days 00:00:07.854702
round_time_total       0 days 00:05:19.990835
loss_total                           99.03916
loss_critic                        211.758054
loss_actor                        -351.836423
memory_size                        688380.653 

=== epoch 8/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:10,  4.62it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:24<00:00,  6.17it/s]
episodes                                    4
episode_length                         1000.0
returns                           -177.882861
return_std                          10.224615
average_reward                      -0.177883
round_time             0 days 00:05:24.978382
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.029666
return_std_test                      6.891536
average_reward_test                   0.00703
round_time_test        0 days 00:00:08.096819
round_time_total       0 days 00:05:24.979494
loss_total                          97.588317
loss_critic                        209.888852
loss_actor                        -351.613829
memory_size                        690344.653 

=== epoch 8/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:17,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:24<00:00,  6.16it/s]
episodes                                    6
episode_length                         1000.0
returns                            -174.60172
return_std                          15.925164
average_reward                      -0.174602
round_time             0 days 00:05:25.140720
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.328007
return_std_test                      7.028547
average_reward_test                  0.009328
round_time_test        0 days 00:00:07.951599
round_time_total       0 days 00:05:25.141791
loss_total                          99.533069
loss_critic                        212.355694
loss_actor                        -351.757438
memory_size                        692308.653 

=== epoch 8/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:03,  5.48it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:26<00:00,  6.13it/s]
episodes                                    8
episode_length                         1000.0
returns                           -174.895244
return_std                          14.626289
average_reward                      -0.174895
round_time             0 days 00:05:26.767296
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.687245
return_std_test                     10.169449
average_reward_test                  0.010687
round_time_test        0 days 00:00:07.970986
round_time_total       0 days 00:05:26.768744
loss_total                          101.96781
loss_critic                        215.310826
loss_actor                         -351.40426
memory_size                        694272.653 

=== epoch 8/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:21,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:28<00:00,  6.09it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.320923
return_std                          18.676976
average_reward                      -0.171321
round_time             0 days 00:05:28.915329
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.023021
return_std_test                      8.945645
average_reward_test                  0.005023
round_time_test        0 days 00:00:08.150095
round_time_total       0 days 00:05:28.916428
loss_total                         101.824477
loss_critic                         215.13414
loss_actor                        -351.414183
memory_size                        696236.653 

=== epoch 8/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:53,  4.81it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.11it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.907675
return_std                          20.569908
average_reward                      -0.174908
round_time             0 days 00:05:28.133171
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.744343
return_std_test                      6.126594
average_reward_test                  0.012744
round_time_test        0 days 00:00:07.770343
round_time_total       0 days 00:05:28.134614
loss_total                         101.596692
loss_critic                        214.941355
loss_actor                        -351.781965
memory_size                        698200.653 

=== epoch 8/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:43,  5.79it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.10it/s]
episodes                                   10
episode_length                         1000.0
returns                            -173.07587
return_std                          19.450576
average_reward                      -0.173076
round_time             0 days 00:05:28.431352
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.606435
return_std_test                      5.197569
average_reward_test                  0.013606
round_time_test        0 days 00:00:07.997149
round_time_total       0 days 00:05:28.432540
loss_total                          98.694498
loss_critic                         211.37143
loss_actor                        -352.013236
memory_size                        700164.653 

=== epoch 8/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.519225
return_std                          19.973148
average_reward                      -0.171519
round_time             0 days 00:05:34.175792
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          9.08303
return_std_test                      7.266343
average_reward_test                  0.009083
round_time_test        0 days 00:00:07.937670
round_time_total       0 days 00:05:34.176897
loss_total                          97.533254
loss_critic                           210.006
loss_actor                        -352.357736
memory_size                        702128.653 

=== epoch 8/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:26,  5.15it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.942964
return_std                          19.648329
average_reward                      -0.171943
round_time             0 days 00:05:31.052758
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.029088
return_std_test                      7.489922
average_reward_test                  0.008029
round_time_test        0 days 00:00:08.030736
round_time_total       0 days 00:05:31.053840
loss_total                          97.019389
loss_critic                        209.454022
loss_actor                        -352.719153
memory_size                        704092.653 

=== epoch 8/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:54,  4.80it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.027945
return_std                          16.306241
average_reward                      -0.172028
round_time             0 days 00:05:33.768570
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.505787
return_std_test                      8.974795
average_reward_test                  0.013506
round_time_test        0 days 00:00:08.167882
round_time_total       0 days 00:05:33.769681
loss_total                         100.931429
loss_critic                        214.216634
loss_actor                        -352.209397
memory_size                        706056.653 

=== epoch 8/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:57,  5.57it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.459244
return_std                          15.123337
average_reward                      -0.168459
round_time             0 days 00:05:34.138555
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.625979
return_std_test                      9.069809
average_reward_test                  0.009626
round_time_test        0 days 00:00:07.992093
round_time_total       0 days 00:05:34.139667
loss_total                         102.509448
loss_critic                        216.104805
loss_actor                        -351.871988
memory_size                        708020.653 

=== epoch 8/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:12,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.572737
return_std                          15.881358
average_reward                      -0.169573
round_time             0 days 00:05:34.631194
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.579781
return_std_test                      6.660691
average_reward_test                   0.00758
round_time_test        0 days 00:00:07.965731
round_time_total       0 days 00:05:34.632576
loss_total                          97.327748
loss_critic                        209.613999
loss_actor                        -351.817263
memory_size                        709984.653 

=== epoch 8/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:03,  5.48it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -165.480315
return_std                           20.20089
average_reward                       -0.16548
round_time             0 days 00:05:35.313081
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          7.42747
return_std_test                      6.466412
average_reward_test                  0.007427
round_time_test        0 days 00:00:08.127916
round_time_total       0 days 00:05:35.314244
loss_total                         100.141821
loss_critic                        213.160672
loss_actor                        -351.933588
memory_size                        711948.653 

=== epoch 8/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:21,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.560816
return_std                          22.955301
average_reward                      -0.168561
round_time             0 days 00:05:36.506154
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.430601
return_std_test                       4.87115
average_reward_test                  0.012431
round_time_test        0 days 00:00:07.898216
round_time_total       0 days 00:05:36.507667
loss_total                          96.340596
loss_critic                        208.477693
loss_actor                        -352.207797
memory_size                        713912.653 

=== epoch 8/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:50,  4.85it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.411651
return_std                           23.70719
average_reward                      -0.174412
round_time             0 days 00:05:36.745212
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.177218
return_std_test                      6.536929
average_reward_test                  0.012177
round_time_test        0 days 00:00:08.165963
round_time_total       0 days 00:05:36.746594
loss_total                          98.864075
loss_critic                        211.654841
loss_actor                        -352.298996
memory_size                        715876.653 

=== epoch 8/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:04,  5.46it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.762763
return_std                          23.565595
average_reward                      -0.173763
round_time             0 days 00:05:35.836021
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.690579
return_std_test                      7.231623
average_reward_test                  0.013691
round_time_test        0 days 00:00:07.882366
round_time_total       0 days 00:05:35.837484
loss_total                          97.367215
loss_critic                        209.700254
loss_actor                        -351.964948
memory_size                        717840.653 

=== epoch 8/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:17,  5.27it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.612944
return_std                          26.541738
average_reward                      -0.166613
round_time             0 days 00:05:38.977378
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.177735
return_std_test                      6.015128
average_reward_test                  0.002178
round_time_test        0 days 00:00:07.830708
round_time_total       0 days 00:05:38.978484
loss_total                          94.370327
loss_critic                         206.03298
loss_actor                        -352.280292
memory_size                        719804.653 

=== epoch 8/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:45,  4.91it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.333166
return_std                          20.891375
average_reward                      -0.171333
round_time             0 days 00:05:37.009953
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.443976
return_std_test                      6.161326
average_reward_test                  0.006444
round_time_test        0 days 00:00:07.844802
round_time_total       0 days 00:05:37.011418
loss_total                          95.979473
loss_critic                        208.163076
loss_actor                        -352.754944
memory_size                        721768.653 

=== epoch 8/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:19,  5.25it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.686622
return_std                          18.039672
average_reward                      -0.166687
round_time             0 days 00:05:35.539358
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.825283
return_std_test                      4.068407
average_reward_test                  0.007825
round_time_test        0 days 00:00:08.007554
round_time_total       0 days 00:05:35.540874
loss_total                         100.623588
loss_critic                        213.950358
loss_actor                        -352.683501
memory_size                        723732.653 

=== epoch 8/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:15,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -164.927949
return_std                           15.88309
average_reward                      -0.164928
round_time             0 days 00:05:39.109357
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.435443
return_std_test                      6.567745
average_reward_test                  0.010435
round_time_test        0 days 00:00:07.941834
round_time_total       0 days 00:05:39.110455
loss_total                          99.806992
loss_critic                        212.941774
loss_actor                        -352.732145
memory_size                        725696.653 

=== epoch 8/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:11,  5.35it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.152597
return_std                          14.427729
average_reward                      -0.162153
round_time             0 days 00:05:37.698185
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.105345
return_std_test                      5.628552
average_reward_test                  0.007105
round_time_test        0 days 00:00:07.897220
round_time_total       0 days 00:05:37.699530
loss_total                          96.329379
loss_critic                        208.566763
loss_actor                        -352.620162
memory_size                        727660.653 

=== epoch 8/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.677783
return_std                          17.124455
average_reward                      -0.168678
round_time             0 days 00:05:35.417224
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         10.68044
return_std_test                       8.36851
average_reward_test                   0.01068
round_time_test        0 days 00:00:07.977764
round_time_total       0 days 00:05:35.418667
loss_total                          96.558253
loss_critic                        208.858672
loss_actor                         -352.64343
memory_size                        729624.653 

=== epoch 8/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:20,  5.23it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                            -162.83681
return_std                          24.312712
average_reward                      -0.162837
round_time             0 days 00:05:38.857826
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.856376
return_std_test                      7.963189
average_reward_test                  0.008856
round_time_test        0 days 00:00:08.291765
round_time_total       0 days 00:05:38.858928
loss_total                          95.977342
loss_critic                        208.091461
loss_actor                        -352.479142
memory_size                        731588.653 

=== epoch 8/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:12,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -164.521617
return_std                          24.783067
average_reward                      -0.164522
round_time             0 days 00:05:38.387088
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.531039
return_std_test                     10.341795
average_reward_test                  0.005531
round_time_test        0 days 00:00:08.282305
round_time_total       0 days 00:05:38.388194
loss_total                         100.200916
loss_critic                         213.43935
loss_actor                        -352.752828
memory_size                        733552.653 

=== epoch 8/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:19,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -160.571907
return_std                          30.622346
average_reward                      -0.160572
round_time             0 days 00:05:37.802504
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         14.42956
return_std_test                      7.758909
average_reward_test                   0.01443
round_time_test        0 days 00:00:08.140899
round_time_total       0 days 00:05:37.803935
loss_total                           94.97307
loss_critic                        206.871396
loss_actor                        -352.620241
memory_size                        735516.653 

=== epoch 8/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:07,  5.41it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.047894
return_std                          30.531762
average_reward                      -0.162048
round_time             0 days 00:05:39.430944
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          2.80305
return_std_test                      8.613236
average_reward_test                  0.002803
round_time_test        0 days 00:00:07.882804
round_time_total       0 days 00:05:39.432171
loss_total                          94.290596
loss_critic                        206.037056
loss_actor                        -352.695251
memory_size                        737480.653 

=== epoch 8/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:45,  4.91it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -158.535232
return_std                          27.758772
average_reward                      -0.158535
round_time             0 days 00:05:37.731103
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.465793
return_std_test                      4.320946
average_reward_test                  0.006466
round_time_test        0 days 00:00:07.745935
round_time_total       0 days 00:05:37.732427
loss_total                          95.325687
loss_critic                         207.44633
loss_actor                        -353.156891
memory_size                        739444.653 

=== epoch 8/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:38,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.135134
return_std                          24.567263
average_reward                      -0.169135
round_time             0 days 00:05:39.661750
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.679087
return_std_test                      4.844797
average_reward_test                  0.008679
round_time_test        0 days 00:00:08.017356
round_time_total       0 days 00:05:39.662832
loss_total                           98.59683
loss_critic                        211.541968
loss_actor                         -353.18373
memory_size                        741408.653 

=== epoch 8/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:11,  5.35it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -167.192423
return_std                          24.912122
average_reward                      -0.167192
round_time             0 days 00:05:37.510444
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.310687
return_std_test                      6.804939
average_reward_test                  0.007311
round_time_test        0 days 00:00:07.971192
round_time_total       0 days 00:05:37.511535
loss_total                          97.728638
loss_critic                        210.479507
loss_actor                        -353.274844
memory_size                        743372.653 

=== epoch 8/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:04,  5.46it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.222219
return_std                          17.675773
average_reward                      -0.168222
round_time             0 days 00:05:37.355133
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.206871
return_std_test                      9.213749
average_reward_test                  0.013207
round_time_test        0 days 00:00:08.012748
round_time_total       0 days 00:05:37.356374
loss_total                          94.928888
loss_critic                        206.983121
loss_actor                        -353.288054
memory_size                        745336.653 

=== epoch 8/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.336125
return_std                          19.301327
average_reward                      -0.169336
round_time             0 days 00:05:41.216917
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.636492
return_std_test                       6.35805
average_reward_test                  0.008636
round_time_test        0 days 00:00:07.973241
round_time_total       0 days 00:05:41.218401
loss_total                          96.139963
loss_critic                        208.460381
loss_actor                        -353.141719
memory_size                        747300.653 

=== epoch 8/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.316898
return_std                          18.498017
average_reward                      -0.168317
round_time             0 days 00:05:39.453675
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          5.69874
return_std_test                      8.724855
average_reward_test                  0.005699
round_time_test        0 days 00:00:08.136119
round_time_total       0 days 00:05:39.454925
loss_total                          92.549125
loss_critic                         203.96306
loss_actor                        -353.106625
memory_size                        749264.653 

=== epoch 8/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.350732
return_std                          18.743062
average_reward                      -0.168351
round_time             0 days 00:05:39.394816
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.700212
return_std_test                      9.681474
average_reward_test                    0.0067
round_time_test        0 days 00:00:07.935667
round_time_total       0 days 00:05:39.396106
loss_total                          93.716709
loss_critic                        205.493461
loss_actor                        -353.390306
memory_size                        751228.653 

=== epoch 8/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:46,  4.90it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.742266
return_std                          20.027047
average_reward                      -0.172742
round_time             0 days 00:05:39.283515
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.142308
return_std_test                       6.49911
average_reward_test                  0.010142
round_time_test        0 days 00:00:08.201672
round_time_total       0 days 00:05:39.284601
loss_total                          90.376528
loss_critic                        201.352921
loss_actor                        -353.529052
memory_size                        753192.653 

=== epoch 8/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -178.604037
return_std                          19.170541
average_reward                      -0.178604
round_time             0 days 00:05:40.220151
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.626112
return_std_test                     10.040643
average_reward_test                  0.014626
round_time_test        0 days 00:00:07.833775
round_time_total       0 days 00:05:40.221607
loss_total                          92.250929
loss_critic                        203.707011
loss_actor                        -353.573405
memory_size                        755156.653 

=== epoch 8/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:06,  5.43it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -177.961753
return_std                          17.752899
average_reward                      -0.177962
round_time             0 days 00:05:38.750865
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.158647
return_std_test                      7.783049
average_reward_test                  0.003159
round_time_test        0 days 00:00:07.949115
round_time_total       0 days 00:05:38.752054
loss_total                           95.32681
loss_critic                        207.566179
loss_actor                        -353.630671
memory_size                        757120.653 

=== epoch 8/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:13,  5.33it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -178.432687
return_std                          22.671321
average_reward                      -0.178433
round_time             0 days 00:05:39.632853
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.969622
return_std_test                      6.835789
average_reward_test                   0.00997
round_time_test        0 days 00:00:08.094206
round_time_total       0 days 00:05:39.634327
loss_total                          95.272382
loss_critic                        207.477712
loss_actor                        -353.548945
memory_size                        759084.653 

=== epoch 8/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:32,  5.07it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.022668
return_std                          26.676203
average_reward                      -0.169023
round_time             0 days 00:05:40.827604
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.875229
return_std_test                      6.999061
average_reward_test                  0.007875
round_time_test        0 days 00:00:07.896730
round_time_total       0 days 00:05:40.828698
loss_total                          92.687031
loss_critic                        204.323036
loss_actor                        -353.856995
memory_size                        761048.653 

=== epoch 8/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:52,  5.65it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -163.534592
return_std                          25.612938
average_reward                      -0.163535
round_time             0 days 00:05:37.651042
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.269167
return_std_test                      5.331084
average_reward_test                  0.004269
round_time_test        0 days 00:00:07.913591
round_time_total       0 days 00:05:37.652134
loss_total                          90.042297
loss_critic                        201.125096
loss_actor                        -354.288909
memory_size                        763012.653 

=== epoch 8/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:30,  5.10it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -159.036341
return_std                          21.035729
average_reward                      -0.159036
round_time             0 days 00:05:40.177702
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.731491
return_std_test                      9.532497
average_reward_test                  0.005731
round_time_test        0 days 00:00:07.999507
round_time_total       0 days 00:05:40.178798
loss_total                          94.022857
loss_critic                        206.123411
loss_actor                        -354.379368
memory_size                        764976.653 

=== epoch 8/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:07,  4.66it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                            -164.59819
return_std                           25.87085
average_reward                      -0.164598
round_time             0 days 00:05:39.405563
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.366136
return_std_test                      9.678738
average_reward_test                  0.010366
round_time_test        0 days 00:00:08.020759
round_time_total       0 days 00:05:39.406988
loss_total                          91.182984
loss_critic                        202.529937
loss_actor                        -354.204833
memory_size                        766940.653 

=== epoch 8/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:01,  4.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -165.471634
return_std                          20.586739
average_reward                      -0.165472
round_time             0 days 00:05:41.045434
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.871435
return_std_test                      8.194974
average_reward_test                  0.008871
round_time_test        0 days 00:00:07.825664
round_time_total       0 days 00:05:41.046530
loss_total                          92.520216
loss_critic                        204.242016
loss_actor                        -354.366989
memory_size                        768904.653 

=== epoch 8/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:01,  4.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:42<00:00,  5.84it/s]
episodes                                   10
episode_length                         1000.0
returns                           -164.276525
return_std                          22.246043
average_reward                      -0.164277
round_time             0 days 00:05:42.832884
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.609859
return_std_test                      7.010734
average_reward_test                   0.00961
round_time_test        0 days 00:00:07.987062
round_time_total       0 days 00:05:42.833983
loss_total                          93.498573
loss_critic                        205.496338
loss_actor                        -354.492495
memory_size                        770868.653 

=== epoch 8/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.481563
return_std                          22.025651
average_reward                      -0.162482
round_time             0 days 00:05:40.789606
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.375247
return_std_test                       5.40635
average_reward_test                  0.001375
round_time_test        0 days 00:00:07.950121
round_time_total       0 days 00:05:40.790848
loss_total                          94.181838
loss_critic                        206.300468
loss_actor                        -354.292692
memory_size                        772832.653 

=== epoch 8/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:37,  5.01it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -167.162129
return_std                          27.513217
average_reward                      -0.167162
round_time             0 days 00:05:39.187037
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.374986
return_std_test                      9.770642
average_reward_test                  0.011375
round_time_test        0 days 00:00:07.838848
round_time_total       0 days 00:05:39.188127
loss_total                          95.593447
loss_critic                        208.068288
loss_actor                        -354.305923
memory_size                        774796.653 

=== epoch 8/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:39,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -158.833064
return_std                          23.874306
average_reward                      -0.158833
round_time             0 days 00:05:42.549432
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.461886
return_std_test                      7.838797
average_reward_test                  0.008462
round_time_test        0 days 00:00:07.943013
round_time_total       0 days 00:05:42.550530
loss_total                          94.019775
loss_critic                        206.093962
loss_actor                        -354.276979
memory_size                        776760.653 

=== epoch 8/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:38,  5.00it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.542562
return_std                          24.982523
average_reward                      -0.162543
round_time             0 days 00:05:42.025954
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.903546
return_std_test                      6.861435
average_reward_test                  0.000904
round_time_test        0 days 00:00:07.972085
round_time_total       0 days 00:05:42.027046
loss_total                          94.543584
loss_critic                        206.726704
loss_actor                        -354.188903
memory_size                        778724.653 

=== epoch 8/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:47,  4.89it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.421546
return_std                          20.097919
average_reward                      -0.170422
round_time             0 days 00:05:40.894089
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.281367
return_std_test                      6.564466
average_reward_test                  0.006281
round_time_test        0 days 00:00:07.775992
round_time_total       0 days 00:05:40.895342
loss_total                          93.473454
loss_critic                        205.323364
loss_actor                        -353.926197
memory_size                        780688.653 

=== epoch 8/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:28,  5.13it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.605241
return_std                          17.302665
average_reward                      -0.173605
round_time             0 days 00:05:41.820438
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.871211
return_std_test                      5.681823
average_reward_test                  0.010871
round_time_test        0 days 00:00:07.684391
round_time_total       0 days 00:05:41.821584
loss_total                          90.021061
loss_critic                        201.099372
loss_actor                         -354.29219
memory_size                        782652.653 

=== epoch 8/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:38,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -170.685055
return_std                          13.167265
average_reward                      -0.170685
round_time             0 days 00:05:39.414568
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          5.17761
return_std_test                       5.98827
average_reward_test                  0.005178
round_time_test        0 days 00:00:07.871489
round_time_total       0 days 00:05:39.415653
loss_total                           91.74606
loss_critic                        203.363308
loss_actor                        -354.722942
memory_size                        784616.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 9/10 ===== round 1/50 ======================================
  1%|          | 12/2000 [00:02<06:10,  5.37it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:23<00:00,  6.19it/s]
episodes                                    2
episode_length                         1000.0
returns                            -161.07771
return_std                           9.032834
average_reward                      -0.161078
round_time             0 days 00:05:23.318373
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         12.11821
return_std_test                      6.239488
average_reward_test                  0.012118
round_time_test        0 days 00:00:07.934994
round_time_total       0 days 00:05:23.319488
loss_total                          91.675306
loss_critic                        203.279259
loss_actor                        -354.740511
memory_size                        786581.653 

=== epoch 9/10 ===== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:09,  5.38it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:25<00:00,  6.14it/s]
episodes                                    4
episode_length                         1000.0
returns                           -157.055359
return_std                          12.107462
average_reward                      -0.157055
round_time             0 days 00:05:26.133200
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.900178
return_std_test                      8.671596
average_reward_test                    0.0079
round_time_test        0 days 00:00:07.856482
round_time_total       0 days 00:05:26.134346
loss_total                           89.98052
loss_critic                        201.185311
loss_actor                        -354.838651
memory_size                        788545.653 

=== epoch 9/10 ===== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:40,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:25<00:00,  6.14it/s]
episodes                                    6
episode_length                         1000.0
returns                           -169.249472
return_std                          19.884033
average_reward                      -0.169249
round_time             0 days 00:05:26.511386
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.273982
return_std_test                      7.376315
average_reward_test                  0.007274
round_time_test        0 days 00:00:08.306426
round_time_total       0 days 00:05:26.512612
loss_total                          89.660214
loss_critic                        200.678512
loss_actor                        -354.412983
memory_size                        790509.653 

=== epoch 9/10 ===== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:59,  5.54it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.11it/s]
episodes                                    8
episode_length                         1000.0
returns                            -169.68201
return_std                          17.521993
average_reward                      -0.169682
round_time             0 days 00:05:27.659026
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.313096
return_std_test                      6.143647
average_reward_test                  0.012313
round_time_test        0 days 00:00:07.848243
round_time_total       0 days 00:05:27.660465
loss_total                          91.781993
loss_critic                        203.296196
loss_actor                        -354.274823
memory_size                        792473.653 

=== epoch 9/10 ===== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:04,  4.69it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:27<00:00,  6.11it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.430305
return_std                          18.319685
average_reward                       -0.17043
round_time             0 days 00:05:28.205824
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.177169
return_std_test                      6.644613
average_reward_test                  0.006177
round_time_test        0 days 00:00:07.935092
round_time_total       0 days 00:05:28.206944
loss_total                          91.483705
loss_critic                        202.950715
loss_actor                        -354.384343
memory_size                        794437.653 

=== epoch 9/10 ===== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:42,  4.95it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:31<00:00,  6.03it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.091301
return_std                          17.775136
average_reward                      -0.171091
round_time             0 days 00:05:32.442951
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.809288
return_std_test                      8.122625
average_reward_test                  0.010809
round_time_test        0 days 00:00:08.191998
round_time_total       0 days 00:05:32.444420
loss_total                          91.968758
loss_critic                        203.616519
loss_actor                         -354.62229
memory_size                        796401.653 

=== epoch 9/10 ===== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:25,  5.17it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.105738
return_std                          20.889647
average_reward                      -0.170106
round_time             0 days 00:05:30.102136
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         12.54113
return_std_test                     11.766267
average_reward_test                  0.012541
round_time_test        0 days 00:00:07.733433
round_time_total       0 days 00:05:30.103248
loss_total                          91.954167
loss_critic                        203.583397
loss_actor                        -354.562764
memory_size                        798365.653 

=== epoch 9/10 ===== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.19it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.617795
return_std                          22.299391
average_reward                      -0.170618
round_time             0 days 00:05:30.210204
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.872559
return_std_test                     11.148075
average_reward_test                  0.001873
round_time_test        0 days 00:00:07.970875
round_time_total       0 days 00:05:30.211508
loss_total                          91.475534
loss_critic                        203.025811
loss_actor                         -354.72558
memory_size                        800329.653 

=== epoch 9/10 ===== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:16,  5.29it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.242042
return_std                          22.159461
average_reward                      -0.170242
round_time             0 days 00:05:32.681945
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          8.32836
return_std_test                      9.098306
average_reward_test                  0.008328
round_time_test        0 days 00:00:07.926274
round_time_total       0 days 00:05:32.683379
loss_total                          91.407673
loss_critic                         202.94357
loss_actor                         -354.73592
memory_size                        802293.653 

=== epoch 9/10 ===== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:50,  5.68it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  5.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.863059
return_std                          20.036679
average_reward                      -0.169863
round_time             0 days 00:05:34.400555
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.552652
return_std_test                      6.682803
average_reward_test                  0.006553
round_time_test        0 days 00:00:08.154745
round_time_total       0 days 00:05:34.402106
loss_total                          89.533873
loss_critic                        200.704001
loss_actor                        -355.146644
memory_size                        804257.653 

=== epoch 9/10 ===== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:43,  4.94it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.501312
return_std                          20.486546
average_reward                      -0.169501
round_time             0 days 00:05:34.017463
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.375014
return_std_test                      9.652982
average_reward_test                  0.002375
round_time_test        0 days 00:00:08.076335
round_time_total       0 days 00:05:34.018810
loss_total                          91.137671
loss_critic                         202.74272
loss_actor                        -355.282532
memory_size                        806221.653 

=== epoch 9/10 ===== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:17,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.503404
return_std                          15.545575
average_reward                      -0.173503
round_time             0 days 00:05:36.370575
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.665297
return_std_test                      4.684413
average_reward_test                  0.011665
round_time_test        0 days 00:00:07.889739
round_time_total       0 days 00:05:36.371729
loss_total                           89.85116
loss_critic                        201.202466
loss_actor                         -355.55407
memory_size                        808185.653 

=== epoch 9/10 ===== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:20,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:33<00:00,  6.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.586718
return_std                          12.286518
average_reward                      -0.166587
round_time             0 days 00:05:33.874803
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.294143
return_std_test                       5.71223
average_reward_test                  0.004294
round_time_test        0 days 00:00:07.806914
round_time_total       0 days 00:05:33.875914
loss_total                          89.883319
loss_critic                        201.210186
loss_actor                        -355.424154
memory_size                        810149.653 

=== epoch 9/10 ===== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:34,  5.05it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.097309
return_std                           17.31175
average_reward                      -0.172097
round_time             0 days 00:05:35.894290
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.378524
return_std_test                       6.14718
average_reward_test                  0.008379
round_time_test        0 days 00:00:08.176796
round_time_total       0 days 00:05:35.895372
loss_total                           90.71771
loss_critic                         202.18078
loss_actor                        -355.134578
memory_size                        812113.653 

=== epoch 9/10 ===== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:49,  5.70it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.616849
return_std                          17.797924
average_reward                      -0.173617
round_time             0 days 00:05:36.056934
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.236091
return_std_test                      8.312925
average_reward_test                  0.008236
round_time_test        0 days 00:00:08.102107
round_time_total       0 days 00:05:36.058046
loss_total                          89.143413
loss_critic                        200.234795
loss_actor                        -355.222119
memory_size                        814077.653 

=== epoch 9/10 ===== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:13,  5.32it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                            -173.15158
return_std                          18.286105
average_reward                      -0.173152
round_time             0 days 00:05:35.265337
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.523444
return_std_test                       6.61956
average_reward_test                  0.006523
round_time_test        0 days 00:00:07.969573
round_time_total       0 days 00:05:35.266753
loss_total                          90.690535
loss_critic                        202.230546
loss_actor                        -355.469519
memory_size                        816041.653 

=== epoch 9/10 ===== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:54,  5.61it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -177.685846
return_std                          18.384082
average_reward                      -0.177686
round_time             0 days 00:05:35.706105
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.295346
return_std_test                      8.083069
average_reward_test                  0.007295
round_time_test        0 days 00:00:08.028824
round_time_total       0 days 00:05:35.707189
loss_total                           88.01624
loss_critic                        198.905722
loss_actor                        -355.541696
memory_size                        818005.653 

=== epoch 9/10 ===== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:20,  5.24it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.391726
return_std                          20.732565
average_reward                      -0.174392
round_time             0 days 00:05:36.393926
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.250564
return_std_test                      5.260718
average_reward_test                  0.006251
round_time_test        0 days 00:00:07.902997
round_time_total       0 days 00:05:36.395263
loss_total                          88.456724
loss_critic                        199.424562
loss_actor                        -355.414633
memory_size                        819969.653 

=== epoch 9/10 ===== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:21,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.289579
return_std                          18.239408
average_reward                       -0.17129
round_time             0 days 00:05:36.107326
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.800232
return_std_test                      5.228136
average_reward_test                    0.0098
round_time_test        0 days 00:00:07.955659
round_time_total       0 days 00:05:36.108565
loss_total                          89.477785
loss_critic                        200.735286
loss_actor                        -355.552224
memory_size                        821933.653 

=== epoch 9/10 ===== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:09,  5.39it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.854662
return_std                          17.597421
average_reward                      -0.169855
round_time             0 days 00:05:35.368012
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.957983
return_std_test                      7.245262
average_reward_test                  0.011958
round_time_test        0 days 00:00:07.748454
round_time_total       0 days 00:05:35.369108
loss_total                          89.578581
loss_critic                        200.799063
loss_actor                        -355.303354
memory_size                        823897.653 

=== epoch 9/10 ===== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:25,  5.16it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -167.999899
return_std                          18.248734
average_reward                         -0.168
round_time             0 days 00:05:39.479510
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.042818
return_std_test                      7.736554
average_reward_test                  0.009043
round_time_test        0 days 00:00:08.159910
round_time_total       0 days 00:05:39.480650
loss_total                          89.151223
loss_critic                        200.271113
loss_actor                        -355.328346
memory_size                        825861.653 

=== epoch 9/10 ===== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:08,  5.40it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.091966
return_std                          18.401953
average_reward                      -0.166092
round_time             0 days 00:05:36.897261
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.472573
return_std_test                      8.734856
average_reward_test                  0.004473
round_time_test        0 days 00:00:08.215174
round_time_total       0 days 00:05:36.898649
loss_total                          91.904538
loss_critic                         203.75792
loss_actor                        -355.508996
memory_size                        827825.653 

=== epoch 9/10 ===== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:26,  5.14it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -167.563395
return_std                          16.968197
average_reward                      -0.167563
round_time             0 days 00:05:35.277442
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.761202
return_std_test                      5.791813
average_reward_test                  0.007761
round_time_test        0 days 00:00:07.897154
round_time_total       0 days 00:05:35.278558
loss_total                          85.973495
loss_critic                        196.364714
loss_actor                        -355.591384
memory_size                        829789.653 

=== epoch 9/10 ===== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.415927
return_std                          15.967968
average_reward                      -0.162416
round_time             0 days 00:05:39.496216
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.431278
return_std_test                      6.639777
average_reward_test                  0.006431
round_time_test        0 days 00:00:07.953016
round_time_total       0 days 00:05:39.497305
loss_total                          88.961815
loss_critic                        200.039736
loss_actor                        -355.349872
memory_size                        831753.653 

=== epoch 9/10 ===== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:56,  4.78it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -161.422847
return_std                          16.713539
average_reward                      -0.161423
round_time             0 days 00:05:38.548730
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.262972
return_std_test                       6.66949
average_reward_test                  0.010263
round_time_test        0 days 00:00:08.051781
round_time_total       0 days 00:05:38.549837
loss_total                          90.345322
loss_critic                        201.789305
loss_actor                        -355.430615
memory_size                        833717.653 

=== epoch 9/10 ===== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:54,  5.62it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.567684
return_std                          16.499086
average_reward                      -0.162568
round_time             0 days 00:05:37.441831
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.062903
return_std_test                      3.946189
average_reward_test                  0.006063
round_time_test        0 days 00:00:08.104279
round_time_total       0 days 00:05:37.443130
loss_total                          88.875628
loss_critic                        200.024218
loss_actor                        -355.718738
memory_size                        835681.653 

=== epoch 9/10 ===== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:01,  5.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -161.593336
return_std                          12.294522
average_reward                      -0.161593
round_time             0 days 00:05:41.547307
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.485422
return_std_test                      7.842601
average_reward_test                  0.005485
round_time_test        0 days 00:00:08.176041
round_time_total       0 days 00:05:41.548578
loss_total                          89.038502
loss_critic                        200.278283
loss_actor                        -355.920627
memory_size                        837645.653 

=== epoch 9/10 ===== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:01,  4.73it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.326187
return_std                          17.187277
average_reward                      -0.170326
round_time             0 days 00:05:37.214139
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          3.24559
return_std_test                      8.804888
average_reward_test                  0.003246
round_time_test        0 days 00:00:07.783243
round_time_total       0 days 00:05:37.215550
loss_total                          87.331433
loss_critic                        198.132217
loss_actor                        -355.871708
memory_size                        839609.653 

=== epoch 9/10 ===== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:36,  5.02it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.95it/s]
episodes                                   10
episode_length                         1000.0
returns                           -176.045392
return_std                          16.354573
average_reward                      -0.176045
round_time             0 days 00:05:36.789550
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.396997
return_std_test                      7.969643
average_reward_test                  0.009397
round_time_test        0 days 00:00:08.114059
round_time_total       0 days 00:05:36.790631
loss_total                           89.14882
loss_critic                        200.441946
loss_actor                        -356.023689
memory_size                        841573.653 

=== epoch 9/10 ===== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:40,  4.97it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -176.956121
return_std                          14.633474
average_reward                      -0.176956
round_time             0 days 00:05:39.655562
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.035343
return_std_test                      5.989684
average_reward_test                  0.010035
round_time_test        0 days 00:00:08.007303
round_time_total       0 days 00:05:39.656729
loss_total                          87.382575
loss_critic                        198.205836
loss_actor                        -355.910474
memory_size                        843537.653 

=== epoch 9/10 ===== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:16,  5.28it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -185.891268
return_std                          12.822132
average_reward                      -0.185891
round_time             0 days 00:05:38.596576
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          9.64816
return_std_test                      7.618729
average_reward_test                  0.009648
round_time_test        0 days 00:00:07.834634
round_time_total       0 days 00:05:38.597674
loss_total                          86.981736
loss_critic                        197.771803
loss_actor                        -356.178537
memory_size                        845501.653 

=== epoch 9/10 ===== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:51,  5.66it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -185.351489
return_std                          15.389254
average_reward                      -0.185351
round_time             0 days 00:05:38.078745
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.051585
return_std_test                      8.213077
average_reward_test                  0.008052
round_time_test        0 days 00:00:08.007649
round_time_total       0 days 00:05:38.080155
loss_total                          87.426997
loss_critic                        198.369937
loss_actor                        -356.344771
memory_size                        847465.653 

=== epoch 9/10 ===== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:01,  4.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -183.483535
return_std                           14.78097
average_reward                      -0.183484
round_time             0 days 00:05:38.597113
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.025231
return_std_test                      4.808456
average_reward_test                  0.006025
round_time_test        0 days 00:00:07.930212
round_time_total       0 days 00:05:38.598527
loss_total                          87.037151
loss_critic                        197.921994
loss_actor                        -356.502225
memory_size                        849429.653 

=== epoch 9/10 ===== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -180.089261
return_std                          15.772786
average_reward                      -0.180089
round_time             0 days 00:05:38.948130
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.693575
return_std_test                      5.735483
average_reward_test                  0.002694
round_time_test        0 days 00:00:07.870201
round_time_total       0 days 00:05:38.949228
loss_total                          88.534941
loss_critic                        199.783658
loss_actor                        -356.459937
memory_size                        851393.653 

=== epoch 9/10 ===== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:12,  5.35it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -178.803548
return_std                          16.753254
average_reward                      -0.178804
round_time             0 days 00:05:40.059641
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.148521
return_std_test                      9.134869
average_reward_test                  0.006149
round_time_test        0 days 00:00:07.986944
round_time_total       0 days 00:05:40.060729
loss_total                          84.995041
loss_critic                        195.319861
loss_actor                        -356.304249
memory_size                        853357.653 

=== epoch 9/10 ===== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:33,  5.06it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.417053
return_std                          12.679028
average_reward                      -0.173417
round_time             0 days 00:05:38.760867
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.164264
return_std_test                      4.780061
average_reward_test                  0.006164
round_time_test        0 days 00:00:07.777891
round_time_total       0 days 00:05:38.761965
loss_total                          86.117005
loss_critic                        196.806171
loss_actor                        -356.639667
memory_size                        855321.653 

=== epoch 9/10 ===== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:33,  5.06it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -175.545208
return_std                           13.16964
average_reward                      -0.175545
round_time             0 days 00:05:40.565956
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.114869
return_std_test                      7.329566
average_reward_test                  0.009115
round_time_test        0 days 00:00:08.033725
round_time_total       0 days 00:05:40.567054
loss_total                          89.950556
loss_critic                        201.542031
loss_actor                        -356.415351
memory_size                        857285.653 

=== epoch 9/10 ===== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.445968
return_std                          11.271443
average_reward                      -0.173446
round_time             0 days 00:05:39.124872
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.968729
return_std_test                      6.851511
average_reward_test                  0.012969
round_time_test        0 days 00:00:07.827927
round_time_total       0 days 00:05:39.126399
loss_total                          87.765033
loss_critic                        198.876182
loss_actor                        -356.679569
memory_size                        859249.653 

=== epoch 9/10 ===== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:47,  4.89it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.049415
return_std                          11.398858
average_reward                      -0.173049
round_time             0 days 00:05:39.350461
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.852074
return_std_test                      6.085203
average_reward_test                  0.007852
round_time_test        0 days 00:00:08.009638
round_time_total       0 days 00:05:39.351622
loss_total                            90.6408
loss_critic                         202.47937
loss_actor                        -356.713485
memory_size                        861213.653 

=== epoch 9/10 ===== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:07,  5.41it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.012372
return_std                          14.953302
average_reward                      -0.171012
round_time             0 days 00:05:38.536010
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.920338
return_std_test                      8.421032
average_reward_test                   0.01092
round_time_test        0 days 00:00:08.050048
round_time_total       0 days 00:05:38.537456
loss_total                          86.762493
loss_critic                        197.638655
loss_actor                         -356.74216
memory_size                        863177.653 

=== epoch 9/10 ===== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:29,  5.11it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.031522
return_std                          17.972608
average_reward                      -0.166032
round_time             0 days 00:05:39.675763
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.100466
return_std_test                      5.418985
average_reward_test                    0.0101
round_time_test        0 days 00:00:08.175339
round_time_total       0 days 00:05:39.676854
loss_total                          87.410495
loss_critic                         198.46883
loss_actor                        -356.822851
memory_size                        865141.653 

=== epoch 9/10 ===== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:38,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -158.289114
return_std                          16.212316
average_reward                      -0.158289
round_time             0 days 00:05:38.939565
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          6.77724
return_std_test                      7.112801
average_reward_test                  0.006777
round_time_test        0 days 00:00:07.906164
round_time_total       0 days 00:05:38.940676
loss_total                          84.160708
loss_critic                        194.468722
loss_actor                         -357.07135
memory_size                        867105.653 

=== epoch 9/10 ===== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:55,  4.79it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -158.474598
return_std                          22.427948
average_reward                      -0.158475
round_time             0 days 00:05:39.615072
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.925104
return_std_test                      6.210656
average_reward_test                  0.009925
round_time_test        0 days 00:00:08.073072
round_time_total       0 days 00:05:39.616331
loss_total                          86.137619
loss_critic                        197.028397
loss_actor                        -357.425502
memory_size                        869069.653 

=== epoch 9/10 ===== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:21,  5.23it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -154.662254
return_std                          24.375425
average_reward                      -0.154662
round_time             0 days 00:05:38.859018
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.013416
return_std_test                      5.565369
average_reward_test                  0.013013
round_time_test        0 days 00:00:07.996619
round_time_total       0 days 00:05:38.860145
loss_total                           85.08805
loss_critic                         195.77622
loss_actor                        -357.664636
memory_size                        871033.653 

=== epoch 9/10 ===== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:54,  5.62it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -155.647944
return_std                          23.509822
average_reward                      -0.155648
round_time             0 days 00:05:41.414911
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.562116
return_std_test                      4.316082
average_reward_test                  0.009562
round_time_test        0 days 00:00:08.102857
round_time_total       0 days 00:05:41.416216
loss_total                          88.089759
loss_critic                        199.466337
loss_actor                        -357.416559
memory_size                        872997.653 

=== epoch 9/10 ===== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<07:01,  4.73it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -159.241945
return_std                          23.394165
average_reward                      -0.159242
round_time             0 days 00:05:40.418057
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.938405
return_std_test                      6.174884
average_reward_test                  0.005938
round_time_test        0 days 00:00:07.846604
round_time_total       0 days 00:05:40.419167
loss_total                          88.815591
loss_critic                        200.315169
loss_actor                        -357.182728
memory_size                        874961.653 

=== epoch 9/10 ===== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:28,  5.13it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -158.839317
return_std                          23.313422
average_reward                      -0.158839
round_time             0 days 00:05:37.749991
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.410151
return_std_test                      9.204832
average_reward_test                   0.01141
round_time_test        0 days 00:00:07.959202
round_time_total       0 days 00:05:37.751494
loss_total                          85.130334
loss_critic                        195.724755
loss_actor                        -357.247355
memory_size                        876925.653 

=== epoch 9/10 ===== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:11,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -154.214149
return_std                          21.245437
average_reward                      -0.154214
round_time             0 days 00:05:39.354155
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.821602
return_std_test                      3.785529
average_reward_test                  0.002822
round_time_test        0 days 00:00:07.840163
round_time_total       0 days 00:05:39.355249
loss_total                          87.219795
loss_critic                        198.347033
loss_actor                        -357.289163
memory_size                        878889.653 

=== epoch 9/10 ===== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:31,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -160.987626
return_std                          28.567237
average_reward                      -0.160988
round_time             0 days 00:05:38.943056
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.878237
return_std_test                      3.306596
average_reward_test                  0.005878
round_time_test        0 days 00:00:07.879572
round_time_total       0 days 00:05:38.944500
loss_total                          88.725694
loss_critic                        200.194774
loss_actor                        -357.150631
memory_size                        880853.653 

=== epoch 9/10 ===== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:28,  5.12it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                   10
episode_length                         1000.0
returns                           -157.893536
return_std                          29.311993
average_reward                      -0.157894
round_time             0 days 00:05:40.768476
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          7.67316
return_std_test                      2.543772
average_reward_test                  0.007673
round_time_test        0 days 00:00:07.870554
round_time_total       0 days 00:05:40.769934
loss_total                          85.256933
loss_critic                        195.797484
loss_actor                        -356.905278
memory_size                        882817.653 


<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 10/10 ==== round 1/50 ======================================
  1%|          | 13/2000 [00:02<06:10,  5.36it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:20<00:00,  6.24it/s]
episodes                                    2
episode_length                         1000.0
returns                           -166.455015
return_std                          27.034336
average_reward                      -0.166455
round_time             0 days 00:05:20.327053
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.318367
return_std_test                       7.77727
average_reward_test                  0.013318
round_time_test        0 days 00:00:08.041833
round_time_total       0 days 00:05:20.328163
loss_total                           85.69991
loss_critic                        196.395661
loss_actor                        -357.083098
memory_size                        884782.653 

=== epoch 10/10 ==== round 2/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:56,  5.59it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:23<00:00,  6.18it/s]
episodes                                    4
episode_length                         1000.0
returns                           -161.415892
return_std                          24.215362
average_reward                      -0.161416
round_time             0 days 00:05:24.214318
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.998621
return_std_test                      6.601495
average_reward_test                  0.013999
round_time_test        0 days 00:00:07.939683
round_time_total       0 days 00:05:24.215412
loss_total                          85.653117
loss_critic                        196.364729
loss_actor                        -357.193338
memory_size                        886746.653 

=== epoch 10/10 ==== round 3/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:53,  5.63it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:24<00:00,  6.17it/s]
episodes                                    6
episode_length                         1000.0
returns                           -171.157069
return_std                          28.257471
average_reward                      -0.171157
round_time             0 days 00:05:24.925550
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.788271
return_std_test                      8.997295
average_reward_test                  0.006788
round_time_test        0 days 00:00:07.843936
round_time_total       0 days 00:05:24.926941
loss_total                          85.301684
loss_critic                         196.11039
loss_actor                        -357.933148
memory_size                        888710.653 

=== epoch 10/10 ==== round 4/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:12,  5.34it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:28<00:00,  6.09it/s]
episodes                                    8
episode_length                         1000.0
returns                           -166.366794
return_std                          27.991208
average_reward                      -0.166367
round_time             0 days 00:05:29.134569
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.415288
return_std_test                      8.347246
average_reward_test                  0.009415
round_time_test        0 days 00:00:08.054542
round_time_total       0 days 00:05:29.135806
loss_total                          84.839805
loss_critic                        195.530972
loss_actor                        -357.924869
memory_size                        890674.653 

=== epoch 10/10 ==== round 5/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:51,  4.83it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:28<00:00,  6.09it/s]
episodes                                   10
episode_length                         1000.0
returns                            -174.55509
return_std                          31.488086
average_reward                      -0.174555
round_time             0 days 00:05:28.834841
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.405772
return_std_test                      6.000912
average_reward_test                  0.007406
round_time_test        0 days 00:00:07.990589
round_time_total       0 days 00:05:28.836196
loss_total                           88.22574
loss_critic                        199.772126
loss_actor                        -357.959814
memory_size                        892638.653 

=== epoch 10/10 ==== round 6/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:27,  5.14it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -176.414547
return_std                          29.926836
average_reward                      -0.176415
round_time             0 days 00:05:29.767307
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.716825
return_std_test                      7.273475
average_reward_test                  0.015717
round_time_test        0 days 00:00:08.066370
round_time_total       0 days 00:05:29.768773
loss_total                          85.181464
loss_critic                        195.950794
loss_actor                        -357.895861
memory_size                        894602.653 

=== epoch 10/10 ==== round 7/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:22,  5.21it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:29<00:00,  6.08it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.563473
return_std                          27.064026
average_reward                      -0.179563
round_time             0 days 00:05:29.642722
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.470735
return_std_test                      5.853733
average_reward_test                  0.011471
round_time_test        0 days 00:00:07.880474
round_time_total       0 days 00:05:29.644209
loss_total                          84.943401
loss_critic                        195.666941
loss_actor                        -357.950766
memory_size                        896566.653 

=== epoch 10/10 ==== round 8/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:31,  5.08it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:28<00:00,  6.08it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.079297
return_std                          27.356445
average_reward                      -0.173079
round_time             0 days 00:05:29.483536
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.897838
return_std_test                      9.226018
average_reward_test                  0.011898
round_time_test        0 days 00:00:07.953171
round_time_total       0 days 00:05:29.484751
loss_total                          85.503498
loss_critic                        196.369097
loss_actor                        -357.958902
memory_size                        898530.653 

=== epoch 10/10 ==== round 9/50 ======================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 6/2000 [00:02<16:45,  1.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -175.097397
return_std                          25.441337
average_reward                      -0.175097
round_time             0 days 00:05:35.017602
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.762077
return_std_test                      5.643811
average_reward_test                  0.007762
round_time_test        0 days 00:00:08.137410
round_time_total       0 days 00:05:35.018700
loss_total                           83.56943
loss_critic                        194.027111
loss_actor                        -358.261302
memory_size                        900494.653 

=== epoch 10/10 ==== round 10/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:21,  5.21it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:30<00:00,  6.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.022808
return_std                          17.188854
average_reward                      -0.168023
round_time             0 days 00:05:31.187643
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.373421
return_std_test                      5.913818
average_reward_test                  0.008373
round_time_test        0 days 00:00:07.770191
round_time_total       0 days 00:05:31.188749
loss_total                          83.968326
loss_critic                        194.526828
loss_actor                        -358.265691
memory_size                        902458.653 

=== epoch 10/10 ==== round 11/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:02,  5.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.026996
return_std                          16.024165
average_reward                      -0.169027
round_time             0 days 00:05:35.334466
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.465291
return_std_test                      5.557586
average_reward_test                  0.009465
round_time_test        0 days 00:00:07.954306
round_time_total       0 days 00:05:35.335555
loss_total                          83.539343
loss_critic                        194.035486
loss_actor                        -358.445232
memory_size                        904422.653 

=== epoch 10/10 ==== round 12/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:43,  4.94it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:32<00:00,  6.01it/s]
episodes                                   10
episode_length                         1000.0
returns                            -169.07478
return_std                          16.669937
average_reward                      -0.169075
round_time             0 days 00:05:33.438597
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.552718
return_std_test                      9.107439
average_reward_test                  0.010553
round_time_test        0 days 00:00:08.394542
round_time_total       0 days 00:05:33.440050
loss_total                          83.258804
loss_critic                        193.670775
loss_actor                        -358.389086
memory_size                        906386.653 

=== epoch 10/10 ==== round 13/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:53,  5.62it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.774628
return_std                          11.514255
average_reward                      -0.172775
round_time             0 days 00:05:35.233677
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          9.92005
return_std_test                       6.60841
average_reward_test                   0.00992
round_time_test        0 days 00:00:07.780854
round_time_total       0 days 00:05:35.234916
loss_total                          86.378362
loss_critic                        197.580319
loss_actor                        -358.429473
memory_size                        908350.653 

=== epoch 10/10 ==== round 14/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 8/2000 [00:01<06:50,  4.85it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.876717
return_std                          12.240984
average_reward                      -0.171877
round_time             0 days 00:05:35.099085
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.865325
return_std_test                      6.108075
average_reward_test                  0.007865
round_time_test        0 days 00:00:08.042800
round_time_total       0 days 00:05:35.100431
loss_total                          87.301018
loss_critic                        198.777148
loss_actor                        -358.603508
memory_size                        910314.653 

=== epoch 10/10 ==== round 15/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:48,  4.87it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.363742
return_std                          12.300723
average_reward                      -0.171364
round_time             0 days 00:05:35.746469
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.115984
return_std_test                     11.617074
average_reward_test                  0.009116
round_time_test        0 days 00:00:07.828884
round_time_total       0 days 00:05:35.747573
loss_total                          85.043232
loss_critic                        195.950871
loss_actor                        -358.587326
memory_size                        912278.653 

=== epoch 10/10 ==== round 16/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:56,  5.58it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.96it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.598473
return_std                          16.536235
average_reward                      -0.174598
round_time             0 days 00:05:35.924383
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.409291
return_std_test                       8.24576
average_reward_test                  0.007409
round_time_test        0 days 00:00:07.918165
round_time_total       0 days 00:05:35.925497
loss_total                          86.181829
loss_critic                         197.34675
loss_actor                        -358.477859
memory_size                        914242.653 

=== epoch 10/10 ==== round 17/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:11,  4.61it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.972097
return_std                          19.421291
average_reward                      -0.174972
round_time             0 days 00:05:35.289976
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.478566
return_std_test                       5.50132
average_reward_test                  0.009479
round_time_test        0 days 00:00:08.187155
round_time_total       0 days 00:05:35.291425
loss_total                          87.874734
loss_critic                        199.389639
loss_actor                        -358.184895
memory_size                        916206.653 

=== epoch 10/10 ==== round 18/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:36,  5.03it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.831215
return_std                          19.650553
average_reward                      -0.172831
round_time             0 days 00:05:38.585064
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.230583
return_std_test                      5.813042
average_reward_test                  0.009231
round_time_test        0 days 00:00:08.222546
round_time_total       0 days 00:05:38.586291
loss_total                          86.051531
loss_critic                        197.159623
loss_actor                        -358.380843
memory_size                        918170.653 

=== epoch 10/10 ==== round 19/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:46,  4.90it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.93it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.131241
return_std                          22.867923
average_reward                      -0.173131
round_time             0 days 00:05:37.935734
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.908371
return_std_test                      8.801682
average_reward_test                  0.012908
round_time_test        0 days 00:00:08.156022
round_time_total       0 days 00:05:37.936888
loss_total                          85.484141
loss_critic                        196.532279
loss_actor                        -358.708413
memory_size                        920134.653 

=== epoch 10/10 ==== round 20/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:43,  4.94it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -178.600471
return_std                          24.777427
average_reward                        -0.1786
round_time             0 days 00:05:38.237853
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         3.884579
return_std_test                     11.537448
average_reward_test                  0.003885
round_time_test        0 days 00:00:07.801703
round_time_total       0 days 00:05:38.238955
loss_total                          84.049891
loss_critic                        194.727002
loss_actor                        -358.658557
memory_size                        922098.653 

=== epoch 10/10 ==== round 21/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:57,  5.58it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.816531
return_std                          23.316567
average_reward                      -0.170817
round_time             0 days 00:05:37.516049
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.299244
return_std_test                       4.67654
average_reward_test                  0.009299
round_time_test        0 days 00:00:08.059271
round_time_total       0 days 00:05:37.517170
loss_total                          85.164889
loss_critic                        196.042889
loss_actor                        -358.347117
memory_size                        924062.653 

=== epoch 10/10 ==== round 22/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:14,  5.31it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:35<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.365081
return_std                          20.663787
average_reward                      -0.169365
round_time             0 days 00:05:35.700327
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.344242
return_std_test                      5.365656
average_reward_test                  0.007344
round_time_test        0 days 00:00:07.978138
round_time_total       0 days 00:05:35.701421
loss_total                          85.517651
loss_critic                        196.448828
loss_actor                        -358.207065
memory_size                        926026.653 

=== epoch 10/10 ==== round 23/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:04,  5.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -167.496219
return_std                          23.117665
average_reward                      -0.167496
round_time             0 days 00:05:37.011125
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.271485
return_std_test                      7.647851
average_reward_test                  0.007271
round_time_test        0 days 00:00:07.857098
round_time_total       0 days 00:05:37.012683
loss_total                          87.161026
loss_critic                        198.558784
loss_actor                        -358.430015
memory_size                        927990.653 

=== epoch 10/10 ==== round 24/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<05:54,  5.61it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.953339
return_std                          17.845555
average_reward                      -0.168953
round_time             0 days 00:05:39.693284
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.994312
return_std_test                      7.419692
average_reward_test                  0.005994
round_time_test        0 days 00:00:07.855195
round_time_total       0 days 00:05:39.694388
loss_total                          84.862784
loss_critic                        195.619803
loss_actor                        -358.165302
memory_size                        929954.653 

=== epoch 10/10 ==== round 25/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:48,  5.71it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -156.306047
return_std                          19.895509
average_reward                      -0.156306
round_time             0 days 00:05:38.561491
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.087106
return_std_test                      7.191324
average_reward_test                  0.008087
round_time_test        0 days 00:00:08.020998
round_time_total       0 days 00:05:38.562968
loss_total                          85.071376
loss_critic                        195.882245
loss_actor                        -358.172106
memory_size                        931918.653 

=== epoch 10/10 ==== round 26/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:41,  4.96it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:37<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -159.572235
return_std                          21.928466
average_reward                      -0.159572
round_time             0 days 00:05:38.185764
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.475917
return_std_test                      5.436878
average_reward_test                  0.008476
round_time_test        0 days 00:00:07.946164
round_time_total       0 days 00:05:38.186862
loss_total                           85.01052
loss_critic                        195.742496
loss_actor                        -357.917388
memory_size                        933882.653 

=== epoch 10/10 ==== round 27/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:59,  4.74it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -163.691631
return_std                          24.513995
average_reward                      -0.163692
round_time             0 days 00:05:39.934993
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.317549
return_std_test                      4.894549
average_reward_test                  0.013318
round_time_test        0 days 00:00:07.964634
round_time_total       0 days 00:05:39.936071
loss_total                          86.198878
loss_critic                        197.245041
loss_actor                        -357.985775
memory_size                        935846.653 

=== epoch 10/10 ==== round 28/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:38,  5.00it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.92it/s]
episodes                                   10
episode_length                         1000.0
returns                           -167.111241
return_std                          23.207895
average_reward                      -0.167111
round_time             0 days 00:05:38.637875
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.671079
return_std_test                      6.289893
average_reward_test                  0.006671
round_time_test        0 days 00:00:07.953047
round_time_total       0 days 00:05:38.639003
loss_total                          83.849758
loss_critic                        194.369155
loss_actor                        -358.227837
memory_size                        937810.653 

=== epoch 10/10 ==== round 29/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:14,  5.32it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:34<00:00,  5.97it/s]
episodes                                   10
episode_length                         1000.0
returns                           -165.859659
return_std                          23.809901
average_reward                       -0.16586
round_time             0 days 00:05:35.535972
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          7.29555
return_std_test                      4.967941
average_reward_test                  0.007296
round_time_test        0 days 00:00:07.867763
round_time_total       0 days 00:05:35.537134
loss_total                          80.847906
loss_critic                        190.727332
loss_actor                        -358.669801
memory_size                        939774.653 

=== epoch 10/10 ==== round 30/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:03,  5.48it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.86it/s]
episodes                                   10
episode_length                         1000.0
returns                           -176.135315
return_std                          13.300315
average_reward                      -0.176135
round_time             0 days 00:05:41.920809
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.837008
return_std_test                      7.617291
average_reward_test                  0.011837
round_time_test        0 days 00:00:08.066900
round_time_total       0 days 00:05:41.922009
loss_total                          83.448021
loss_critic                        194.052675
loss_actor                        -358.970605
memory_size                        941738.653 

=== epoch 10/10 ==== round 31/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:08,  5.40it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                            -167.96562
return_std                          21.159431
average_reward                      -0.167966
round_time             0 days 00:05:39.464431
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.969488
return_std_test                      5.617748
average_reward_test                  0.007969
round_time_test        0 days 00:00:07.937957
round_time_total       0 days 00:05:39.465932
loss_total                          84.576909
loss_critic                        195.424468
loss_actor                        -358.813334
memory_size                        943702.653 

=== epoch 10/10 ==== round 32/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:20,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                            -165.88046
return_std                          22.597941
average_reward                       -0.16588
round_time             0 days 00:05:38.818037
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.595029
return_std_test                      5.886078
average_reward_test                  0.010595
round_time_test        0 days 00:00:07.871781
round_time_total       0 days 00:05:38.819542
loss_total                          84.127382
loss_critic                        194.835999
loss_actor                        -358.707095
memory_size                        945666.653 

=== epoch 10/10 ==== round 33/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:54,  4.80it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -164.442691
return_std                          22.917387
average_reward                      -0.164443
round_time             0 days 00:05:38.814651
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.615117
return_std_test                      3.408443
average_reward_test                  0.008615
round_time_test        0 days 00:00:07.893241
round_time_total       0 days 00:05:38.815753
loss_total                          85.464242
loss_critic                        196.488531
loss_actor                        -358.632921
memory_size                        947630.653 

=== epoch 10/10 ==== round 34/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:28,  5.13it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -160.533303
return_std                          24.488303
average_reward                      -0.160533
round_time             0 days 00:05:39.169800
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.368882
return_std_test                      8.175685
average_reward_test                  0.013369
round_time_test        0 days 00:00:07.834052
round_time_total       0 days 00:05:39.170903
loss_total                          82.174872
loss_critic                        192.378549
loss_actor                         -358.63984
memory_size                        949594.653 

=== epoch 10/10 ==== round 35/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:31,  5.09it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -158.666348
return_std                          23.545981
average_reward                      -0.158666
round_time             0 days 00:05:39.606819
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.542464
return_std_test                       9.61718
average_reward_test                  0.009542
round_time_test        0 days 00:00:07.959726
round_time_total       0 days 00:05:39.607910
loss_total                          85.260507
loss_critic                        196.281403
loss_actor                        -358.823087
memory_size                        951558.653 

=== epoch 10/10 ==== round 36/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:39,  4.99it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:36<00:00,  5.94it/s]
episodes                                   10
episode_length                         1000.0
returns                           -163.569398
return_std                          22.440953
average_reward                      -0.163569
round_time             0 days 00:05:37.203747
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.803986
return_std_test                        5.8672
average_reward_test                  0.005804
round_time_test        0 days 00:00:07.880663
round_time_total       0 days 00:05:37.204821
loss_total                          81.540013
loss_critic                        191.672398
loss_actor                        -358.989534
memory_size                        953522.653 

=== epoch 10/10 ==== round 37/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:52,  5.64it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.129157
return_std                          23.035318
average_reward                      -0.166129
round_time             0 days 00:05:39.639650
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         11.56948
return_std_test                      5.671033
average_reward_test                  0.011569
round_time_test        0 days 00:00:07.914446
round_time_total       0 days 00:05:39.641007
loss_total                          83.609218
loss_critic                        194.282772
loss_actor                        -359.085003
memory_size                        955486.653 

=== epoch 10/10 ==== round 38/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:51,  4.84it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                           -167.730628
return_std                           22.20848
average_reward                      -0.167731
round_time             0 days 00:05:42.404499
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         9.529851
return_std_test                     10.563723
average_reward_test                   0.00953
round_time_test        0 days 00:00:07.936248
round_time_total       0 days 00:05:42.405604
loss_total                          82.822389
loss_critic                        193.231377
loss_actor                        -358.813568
memory_size                        957450.653 

=== epoch 10/10 ==== round 39/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:08,  5.40it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.91it/s]
episodes                                   10
episode_length                         1000.0
returns                           -174.496748
return_std                          18.114965
average_reward                      -0.174497
round_time             0 days 00:05:38.893091
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.736962
return_std_test                      4.664653
average_reward_test                  0.012737
round_time_test        0 days 00:00:07.905161
round_time_total       0 days 00:05:38.894575
loss_total                          83.067178
loss_critic                        193.583777
loss_actor                        -358.999222
memory_size                        959414.653 

=== epoch 10/10 ==== round 40/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:23,  5.20it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:38<00:00,  5.90it/s]
episodes                                   10
episode_length                         1000.0
returns                           -177.382489
return_std                          18.502944
average_reward                      -0.177382
round_time             0 days 00:05:39.330137
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.199709
return_std_test                      5.905734
average_reward_test                    0.0132
round_time_test        0 days 00:00:07.870762
round_time_total       0 days 00:05:39.331243
loss_total                          81.787922
loss_critic                        192.025434
loss_actor                        -359.162134
memory_size                        961378.653 

=== epoch 10/10 ==== round 41/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:02,  5.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -175.759131
return_std                          17.595084
average_reward                      -0.175759
round_time             0 days 00:05:40.733212
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.292758
return_std_test                      8.091472
average_reward_test                  0.011293
round_time_test        0 days 00:00:08.048757
round_time_total       0 days 00:05:40.734318
loss_total                          82.911988
loss_critic                        193.448939
loss_actor                        -359.235825
memory_size                        963342.653 

=== epoch 10/10 ==== round 42/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:24,  5.18it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.286437
return_std                          16.864964
average_reward                      -0.172286
round_time             0 days 00:05:40.488930
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.654399
return_std_test                      8.316563
average_reward_test                  0.012654
round_time_test        0 days 00:00:08.027551
round_time_total       0 days 00:05:40.490025
loss_total                          83.690452
loss_critic                        194.376409
loss_actor                        -359.053383
memory_size                        965306.653 

=== epoch 10/10 ==== round 43/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:24,  5.18it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.664901
return_std                          17.363167
average_reward                      -0.172665
round_time             0 days 00:05:40.188269
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.935688
return_std_test                      4.846074
average_reward_test                  0.007936
round_time_test        0 days 00:00:07.772873
round_time_total       0 days 00:05:40.189665
loss_total                          82.514577
loss_critic                         192.91277
loss_actor                        -359.078201
memory_size                        967270.653 

=== epoch 10/10 ==== round 44/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<07:08,  4.64it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.612255
return_std                          19.173258
average_reward                      -0.173612
round_time             0 days 00:05:41.196707
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.112955
return_std_test                      6.064145
average_reward_test                  0.010113
round_time_test        0 days 00:00:07.897487
round_time_total       0 days 00:05:41.197844
loss_total                          81.275057
loss_critic                        191.361409
loss_actor                        -359.070358
memory_size                        969234.653 

=== epoch 10/10 ==== round 45/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:19,  5.25it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.782019
return_std                          17.343504
average_reward                      -0.168782
round_time             0 days 00:05:39.903340
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.737928
return_std_test                      9.195781
average_reward_test                  0.014738
round_time_test        0 days 00:00:07.805463
round_time_total       0 days 00:05:39.904441
loss_total                          78.782115
loss_critic                        188.274918
loss_actor                        -359.189101
memory_size                        971198.653 

=== epoch 10/10 ==== round 46/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<06:10,  5.37it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:40<00:00,  5.87it/s]
episodes                                   10
episode_length                         1000.0
returns                           -171.060984
return_std                          16.877089
average_reward                      -0.171061
round_time             0 days 00:05:40.991573
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.507573
return_std_test                      6.245176
average_reward_test                  0.011508
round_time_test        0 days 00:00:07.758347
round_time_total       0 days 00:05:40.992847
loss_total                          82.966009
loss_critic                        193.560115
loss_actor                        -359.410422
memory_size                        973162.653 

=== epoch 10/10 ==== round 47/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:21,  5.22it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.89it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.461629
return_std                          14.927032
average_reward                      -0.168462
round_time             0 days 00:05:39.834282
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.089129
return_std_test                      7.521523
average_reward_test                  0.011089
round_time_test        0 days 00:00:08.227547
round_time_total       0 days 00:05:39.835377
loss_total                          84.425636
loss_critic                        195.390894
loss_actor                        -359.435404
memory_size                        975126.653 

=== epoch 10/10 ==== round 48/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 10/2000 [00:01<05:36,  5.92it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:39<00:00,  5.88it/s]
episodes                                   10
episode_length                         1000.0
returns                           -166.070763
return_std                          17.145854
average_reward                      -0.166071
round_time             0 days 00:05:40.504469
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.399721
return_std_test                       7.98477
average_reward_test                    0.0124
round_time_test        0 days 00:00:08.105228
round_time_total       0 days 00:05:40.505856
loss_total                          85.763856
loss_critic                          197.0437
loss_actor                        -359.355527
memory_size                        977090.653 

=== epoch 10/10 ==== round 49/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:09,  5.38it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:41<00:00,  5.85it/s]
episodes                                   10
episode_length                         1000.0
returns                            -162.20422
return_std                           13.17613
average_reward                      -0.162204
round_time             0 days 00:05:42.519527
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.715895
return_std_test                      6.937938
average_reward_test                  0.015716
round_time_test        0 days 00:00:07.959626
round_time_total       0 days 00:05:42.520618
loss_total                          83.582999
loss_critic                        194.281584
loss_actor                        -359.211347
memory_size                        979054.653 

=== epoch 10/10 ==== round 50/50 =====================================
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 9/2000 [00:01<06:26,  5.15it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [05:43<00:00,  5.83it/s]
<MM1_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
episodes                                   10
episode_length                         1000.0
returns                           -163.152623
return_std                          13.223575
average_reward                      -0.163153
round_time             0 days 00:05:43.880717
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.130913
return_std_test                      5.724419
average_reward_test                  0.011131
round_time_test        0 days 00:00:08.067327
round_time_total       0 days 00:05:43.881820
loss_total                          88.078767
loss_critic                        199.860022
loss_actor                        -359.046259
memory_size                        981018.653 


