/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/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DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date.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DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date.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: 3
   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'
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>

<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 1/10 ===== round 1/50 ======================================
100%|██████████| 2000/2000 [00:01<00:00, 1529.22it/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DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date.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(
episodes                                    2
episode_length                         1000.0
returns                           -293.723314
return_std                          39.776671
average_reward                      -0.293723
round_time             0 days 00:00:01.318545
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         -8.65247
return_std_test                       2.10934
average_reward_test                 -0.008652
round_time_test        0 days 00:00:06.787120
round_time_total       0 days 00:00:08.373927 

=== epoch 1/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1525.52it/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(
episodes                                    4
episode_length                         1000.0
returns                           -281.697932
return_std                          31.180482
average_reward                      -0.281698
round_time             0 days 00:00:01.778383
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -10.715652
return_std_test                      4.339736
average_reward_test                 -0.010716
round_time_test        0 days 00:00:06.723982
round_time_total       0 days 00:00:08.328021 

=== epoch 1/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1520.89it/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(
episodes                                    6
episode_length                         1000.0
returns                           -280.022417
return_std                          35.373122
average_reward                      -0.280022
round_time             0 days 00:00:01.787577
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -10.194872
return_std_test                      4.028472
average_reward_test                 -0.010195
round_time_test        0 days 00:00:06.764748
round_time_total       0 days 00:00:08.329069 

=== epoch 1/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1535.90it/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(
episodes                                    8
episode_length                         1000.0
returns                           -281.434182
return_std                          36.984416
average_reward                      -0.281434
round_time             0 days 00:00:01.759671
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.681681
return_std_test                      3.061821
average_reward_test                 -0.008682
round_time_test        0 days 00:00:06.789433
round_time_total       0 days 00:00:08.388512 

=== epoch 1/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1533.18it/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(
episodes                                   10
episode_length                         1000.0
returns                           -281.514872
return_std                           33.55372
average_reward                      -0.281515
round_time             0 days 00:00:01.765400
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.614505
return_std_test                      3.007009
average_reward_test                 -0.008615
round_time_test        0 days 00:00:06.710633
round_time_total       0 days 00:00:08.309639 

=== epoch 1/10 ===== round 6/50 ======================================
<GE123_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%|          | 5/2000 [00:01<09:04,  3.67it/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 [09:22<00:00,  3.55it/s]
starting training
episodes                                   10
episode_length                         1000.0
returns                           -278.367508
return_std                           34.08864
average_reward                      -0.278368
round_time             0 days 00:09:23.460324
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.203907
return_std_test                      4.411527
average_reward_test                 -0.008204
round_time_test        0 days 00:00:06.927815
round_time_total       0 days 00:09:23.461415
loss_total                         300.044553
loss_critic                        389.903277
loss_actor                         -59.390374
memory_size                         10701.825 

=== epoch 1/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:05,  3.00it/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 [10:03<00:00,  3.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            -291.07962
return_std                          40.019763
average_reward                       -0.29108
round_time             0 days 00:10:04.358605
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -33.248227
return_std_test                     10.458841
average_reward_test                 -0.033248
round_time_test        0 days 00:00:07.561169
round_time_total       0 days 00:10:04.359701
loss_total                         231.907895
loss_critic                         319.63631
loss_actor                        -119.005785
memory_size                         12649.825 

=== epoch 1/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:16,  2.95it/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 [10:14<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                           -288.968951
return_std                          36.646746
average_reward                      -0.288969
round_time             0 days 00:10:15.356881
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -49.644747
return_std_test                     84.625855
average_reward_test                 -0.049645
round_time_test        0 days 00:00:07.676626
round_time_total       0 days 00:10:15.358066
loss_total                         177.334348
loss_critic                        263.949724
loss_actor                        -169.127168
memory_size                         14597.825 

=== epoch 1/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:43,  3.10it/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 [10:14<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            -282.12452
return_std                          35.440093
average_reward                      -0.282125
round_time             0 days 00:10:15.272534
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -22.99259
return_std_test                     26.510768
average_reward_test                 -0.022993
round_time_test        0 days 00:00:07.692418
round_time_total       0 days 00:10:15.273798
loss_total                         220.288217
loss_critic                         327.37616
loss_actor                         -208.06357
memory_size                         16545.825 

=== epoch 1/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:45,  3.09it/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 [10:15<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                           -271.075334
return_std                          41.496821
average_reward                      -0.271075
round_time             0 days 00:10:16.011446
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -77.148541
return_std_test                     47.011304
average_reward_test                 -0.077149
round_time_test        0 days 00:00:07.619471
round_time_total       0 days 00:10:16.012584
loss_total                         163.732288
loss_critic                        262.125786
loss_actor                        -229.841712
memory_size                         18493.825 

=== epoch 1/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:52,  3.06it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                           -260.551031
return_std                          41.652359
average_reward                      -0.260551
round_time             0 days 00:10:18.357669
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -18.184238
return_std_test                     28.911554
average_reward_test                 -0.018184
round_time_test        0 days 00:00:07.536381
round_time_total       0 days 00:10:18.358768
loss_total                         146.655466
loss_critic                        243.486939
loss_actor                        -240.670432
memory_size                         20441.825 

=== epoch 1/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:52,  2.80it/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 [10:18<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                           -231.810722
return_std                            29.9512
average_reward                      -0.231811
round_time             0 days 00:10:18.613597
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        19.533222
return_std_test                     46.437991
average_reward_test                  0.019533
round_time_test        0 days 00:00:07.851677
round_time_total       0 days 00:10:18.614721
loss_total                         175.480103
loss_critic                        281.278369
loss_actor                        -247.712976
memory_size                         22389.825 

=== epoch 1/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:45,  3.09it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -229.278878
return_std                          27.805501
average_reward                      -0.229279
round_time             0 days 00:10:19.235924
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        48.929095
return_std_test                      77.20356
average_reward_test                  0.048929
round_time_test        0 days 00:00:07.733909
round_time_total       0 days 00:10:19.237017
loss_total                         132.990873
loss_critic                        228.459072
loss_actor                        -248.881934
memory_size                         24337.825 

=== epoch 1/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:41,  3.11it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -220.948588
return_std                          38.067051
average_reward                      -0.220949
round_time             0 days 00:10:20.945190
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.520738
return_std_test                     59.693401
average_reward_test                  0.006521
round_time_test        0 days 00:00:07.406903
round_time_total       0 days 00:10:20.946398
loss_total                         131.596625
loss_critic                         227.12068
loss_actor                        -250.499605
memory_size                         26285.825 

=== epoch 1/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:52,  3.06it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -217.017909
return_std                          38.338062
average_reward                      -0.217018
round_time             0 days 00:10:22.345724
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        38.113846
return_std_test                     38.996738
average_reward_test                  0.038114
round_time_test        0 days 00:00:07.600283
round_time_total       0 days 00:10:22.346825
loss_total                         141.434708
loss_critic                         239.69191
loss_actor                        -251.594109
memory_size                         28233.825 

=== epoch 1/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:07,  2.99it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -206.766246
return_std                          44.174613
average_reward                      -0.206766
round_time             0 days 00:10:21.013908
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -17.542812
return_std_test                     28.151372
average_reward_test                 -0.017543
round_time_test        0 days 00:00:07.608744
round_time_total       0 days 00:10:21.015221
loss_total                         133.560904
loss_critic                        229.637647
loss_actor                         -250.74608
memory_size                         30181.825 

=== epoch 1/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:53,  3.05it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -216.528483
return_std                           43.95346
average_reward                      -0.216528
round_time             0 days 00:10:20.840013
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        75.121357
return_std_test                     42.177171
average_reward_test                  0.075121
round_time_test        0 days 00:00:07.614733
round_time_total       0 days 00:10:20.841203
loss_total                         134.590544
loss_critic                        230.497285
loss_actor                        -249.036428
memory_size                         32129.825 

=== epoch 1/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:47,  3.08it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -201.865044
return_std                          40.796721
average_reward                      -0.201865
round_time             0 days 00:10:21.602703
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        72.253364
return_std_test                     78.632026
average_reward_test                  0.072253
round_time_test        0 days 00:00:07.776466
round_time_total       0 days 00:10:21.603785
loss_total                         141.793279
loss_critic                        239.349649
loss_actor                        -248.432209
memory_size                         34077.825 

=== epoch 1/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:42,  2.84it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -204.567987
return_std                          30.926847
average_reward                      -0.204568
round_time             0 days 00:10:24.323634
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       121.457899
return_std_test                     73.541814
average_reward_test                  0.121458
round_time_test        0 days 00:00:07.556702
round_time_total       0 days 00:10:24.324855
loss_total                         132.850308
loss_critic                         228.11215
loss_actor                        -248.197066
memory_size                         36025.825 

=== epoch 1/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:18,  2.94it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -205.504317
return_std                           33.37821
average_reward                      -0.205504
round_time             0 days 00:10:21.201421
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         11.47144
return_std_test                     29.582513
average_reward_test                  0.011471
round_time_test        0 days 00:00:07.697434
round_time_total       0 days 00:10:21.202563
loss_total                         137.887254
loss_critic                        234.670947
loss_actor                        -249.247522
memory_size                         37973.825 

=== epoch 1/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:25,  3.19it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -209.127973
return_std                          34.504202
average_reward                      -0.209128
round_time             0 days 00:10:21.962190
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        55.013547
return_std_test                     67.349628
average_reward_test                  0.055014
round_time_test        0 days 00:00:07.534799
round_time_total       0 days 00:10:21.963476
loss_total                         142.955878
loss_critic                          241.1682
loss_actor                        -249.893418
memory_size                         39921.825 

=== epoch 1/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:50,  3.07it/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 [10:20<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -205.191279
return_std                          33.159913
average_reward                      -0.205191
round_time             0 days 00:10:20.591386
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -47.788093
return_std_test                     15.079075
average_reward_test                 -0.047788
round_time_test        0 days 00:00:07.640512
round_time_total       0 days 00:10:20.592616
loss_total                         138.333625
loss_critic                        235.637061
loss_actor                        -250.880126
memory_size                         41869.825 

=== epoch 1/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:34,  3.15it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -204.64526
return_std                          36.202255
average_reward                      -0.204645
round_time             0 days 00:10:23.544709
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -2.183703
return_std_test                     25.881011
average_reward_test                 -0.002184
round_time_test        0 days 00:00:07.758868
round_time_total       0 days 00:10:23.545971
loss_total                         141.423781
loss_critic                        239.873354
loss_actor                        -252.374521
memory_size                         43817.825 

=== epoch 1/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:02,  3.01it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -207.989563
return_std                          56.653666
average_reward                       -0.20799
round_time             0 days 00:10:23.163568
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        44.500479
return_std_test                     29.360704
average_reward_test                    0.0445
round_time_test        0 days 00:00:07.606837
round_time_total       0 days 00:10:23.164704
loss_total                         152.494636
loss_critic                        253.992932
loss_actor                        -253.498555
memory_size                         45765.825 

=== epoch 1/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:46,  3.09it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -214.856125
return_std                          60.326673
average_reward                      -0.214856
round_time             0 days 00:10:24.808665
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.491174
return_std_test                     22.674512
average_reward_test                  0.010491
round_time_test        0 days 00:00:07.575100
round_time_total       0 days 00:10:24.809822
loss_total                         175.544947
loss_critic                        282.651381
loss_actor                        -252.880803
memory_size                         47713.825 

=== epoch 1/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:08,  2.99it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -217.210783
return_std                          54.508345
average_reward                      -0.217211
round_time             0 days 00:10:22.416213
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -3.243142
return_std_test                     18.722826
average_reward_test                 -0.003243
round_time_test        0 days 00:00:07.845930
round_time_total       0 days 00:10:22.417661
loss_total                          173.92203
loss_critic                        280.238205
loss_actor                        -251.342682
memory_size                         49661.825 

=== epoch 1/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:06,  2.99it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -228.742339
return_std                          58.821144
average_reward                      -0.228742
round_time             0 days 00:10:23.563440
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        43.815079
return_std_test                     18.850216
average_reward_test                  0.043815
round_time_test        0 days 00:00:07.519989
round_time_total       0 days 00:10:23.564575
loss_total                         210.707115
loss_critic                        326.348526
loss_actor                        -251.858544
memory_size                         51609.825 

=== epoch 1/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:09,  2.98it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -238.357546
return_std                          51.673359
average_reward                      -0.238358
round_time             0 days 00:10:23.168519
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        19.846326
return_std_test                      40.90897
average_reward_test                  0.019846
round_time_test        0 days 00:00:07.815977
round_time_total       0 days 00:10:23.169979
loss_total                          184.79205
loss_critic                        294.409264
loss_actor                        -253.676815
memory_size                         53557.825 

=== epoch 1/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<11:31,  2.89it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -228.049472
return_std                          36.490714
average_reward                      -0.228049
round_time             0 days 00:10:22.882421
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -41.027252
return_std_test                     24.500535
average_reward_test                 -0.041027
round_time_test        0 days 00:00:07.820335
round_time_total       0 days 00:10:22.883765
loss_total                         170.625555
loss_critic                        276.549898
loss_actor                        -253.071827
memory_size                         55505.825 

=== epoch 1/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:59,  2.77it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -214.214651
return_std                          35.601212
average_reward                      -0.214215
round_time             0 days 00:10:24.481738
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -19.905192
return_std_test                     20.394494
average_reward_test                 -0.019905
round_time_test        0 days 00:00:07.589832
round_time_total       0 days 00:10:24.483088
loss_total                         171.079358
loss_critic                        277.416639
loss_actor                        -254.269777
memory_size                         57453.825 

=== epoch 1/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:03,  3.01it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -230.121674
return_std                          46.250814
average_reward                      -0.230122
round_time             0 days 00:10:22.817926
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.259562
return_std_test                     21.302485
average_reward_test                   0.01526
round_time_test        0 days 00:00:07.630578
round_time_total       0 days 00:10:22.819039
loss_total                         182.740077
loss_critic                        292.150487
loss_actor                        -254.901574
memory_size                         59401.825 

=== epoch 1/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:30,  2.89it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -220.217887
return_std                          41.834476
average_reward                      -0.220218
round_time             0 days 00:10:25.547104
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        53.445105
return_std_test                     34.528423
average_reward_test                  0.053445
round_time_test        0 days 00:00:07.695446
round_time_total       0 days 00:10:25.548261
loss_total                         180.662428
loss_critic                        289.515633
loss_actor                        -254.750403
memory_size                         61349.825 

=== epoch 1/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:56,  3.04it/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 [10:27<00:00,  3.19it/s]
episodes                                   10
episode_length                         1000.0
returns                           -230.176304
return_std                           47.57973
average_reward                      -0.230176
round_time             0 days 00:10:27.744208
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        32.932626
return_std_test                     27.189593
average_reward_test                  0.032933
round_time_test        0 days 00:00:07.567254
round_time_total       0 days 00:10:27.745331
loss_total                         186.773989
loss_critic                        297.244924
loss_actor                        -255.109761
memory_size                         63297.825 

=== epoch 1/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:25,  2.91it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -226.699711
return_std                           50.93854
average_reward                        -0.2267
round_time             0 days 00:10:24.975100
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.758919
return_std_test                     29.718747
average_reward_test                  0.010759
round_time_test        0 days 00:00:07.693510
round_time_total       0 days 00:10:24.976224
loss_total                         184.795236
loss_critic                        294.761947
loss_actor                         -255.07162
memory_size                         65245.825 

=== epoch 1/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -228.262546
return_std                          49.355492
average_reward                      -0.228263
round_time             0 days 00:10:25.333478
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        29.292265
return_std_test                     20.977648
average_reward_test                  0.029292
round_time_test        0 days 00:00:07.782185
round_time_total       0 days 00:10:25.334672
loss_total                         185.814634
loss_critic                        295.910844
loss_actor                        -254.570222
memory_size                         67193.825 

=== epoch 1/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:52,  3.06it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -210.780478
return_std                          43.117912
average_reward                       -0.21078
round_time             0 days 00:10:23.981571
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -21.530386
return_std_test                     21.515332
average_reward_test                  -0.02153
round_time_test        0 days 00:00:07.752677
round_time_total       0 days 00:10:23.982672
loss_total                         183.485701
loss_critic                        293.032064
loss_actor                        -254.699762
memory_size                         69141.825 

=== epoch 1/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:38,  3.12it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -192.112711
return_std                          56.003984
average_reward                      -0.192113
round_time             0 days 00:10:26.584949
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -9.988837
return_std_test                      39.14864
average_reward_test                 -0.009989
round_time_test        0 days 00:00:07.614762
round_time_total       0 days 00:10:26.586041
loss_total                         189.891475
loss_critic                        301.091496
loss_actor                        -254.908626
memory_size                         71089.825 

=== epoch 1/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:38,  2.86it/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 [10:28<00:00,  3.18it/s]
episodes                                   10
episode_length                         1000.0
returns                           -165.366949
return_std                          41.182375
average_reward                      -0.165367
round_time             0 days 00:10:28.772053
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -10.265772
return_std_test                     16.076162
average_reward_test                 -0.010266
round_time_test        0 days 00:00:07.667165
round_time_total       0 days 00:10:28.773145
loss_total                         191.570934
loss_critic                        303.221085
loss_actor                        -255.029682
memory_size                         73037.825 

=== epoch 1/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -156.525527
return_std                          47.213514
average_reward                      -0.156526
round_time             0 days 00:10:26.219112
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -33.138641
return_std_test                     15.853633
average_reward_test                 -0.033139
round_time_test        0 days 00:00:07.719369
round_time_total       0 days 00:10:26.220304
loss_total                         191.330783
loss_critic                        303.134513
loss_actor                         -255.88415
memory_size                         74985.825 

=== epoch 1/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:30,  2.89it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -146.805633
return_std                          50.248306
average_reward                      -0.146806
round_time             0 days 00:10:24.377568
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -14.830158
return_std_test                     16.203539
average_reward_test                  -0.01483
round_time_test        0 days 00:00:07.701800
round_time_total       0 days 00:10:24.378653
loss_total                          203.64386
loss_critic                         318.54776
loss_actor                        -255.971757
memory_size                         76933.825 

=== epoch 1/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:46,  2.82it/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 [10:27<00:00,  3.19it/s]
episodes                                   10
episode_length                         1000.0
returns                           -142.887517
return_std                          43.949402
average_reward                      -0.142888
round_time             0 days 00:10:28.019272
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.177249
return_std_test                       9.97052
average_reward_test                  0.000177
round_time_test        0 days 00:00:07.783627
round_time_total       0 days 00:10:28.020354
loss_total                         219.232247
loss_critic                        338.078547
loss_actor                        -256.152971
memory_size                         78881.825 

=== epoch 1/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:23,  3.20it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -155.753528
return_std                           41.92553
average_reward                      -0.155754
round_time             0 days 00:10:24.049886
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -67.364482
return_std_test                      9.678208
average_reward_test                 -0.067364
round_time_test        0 days 00:00:07.742729
round_time_total       0 days 00:10:24.050963
loss_total                         211.353065
loss_critic                        328.430537
loss_actor                        -256.956842
memory_size                         80829.825 

=== epoch 1/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:41,  2.84it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -161.393448
return_std                          40.703838
average_reward                      -0.161393
round_time             0 days 00:10:26.236871
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -7.440099
return_std_test                      21.32602
average_reward_test                  -0.00744
round_time_test        0 days 00:00:07.524667
round_time_total       0 days 00:10:26.238104
loss_total                         211.767859
loss_critic                        329.357457
loss_actor                        -258.590548
memory_size                         82777.825 

=== epoch 1/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:26,  2.91it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -168.842115
return_std                          32.394317
average_reward                      -0.168842
round_time             0 days 00:10:24.207352
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.796037
return_std_test                     44.262244
average_reward_test                  0.000796
round_time_test        0 days 00:00:07.724752
round_time_total       0 days 00:10:24.208895
loss_total                          212.34007
loss_critic                        330.457252
loss_actor                        -260.128679
memory_size                         84725.825 

=== epoch 1/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<12:22,  2.69it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -169.371007
return_std                          24.223052
average_reward                      -0.169371
round_time             0 days 00:10:23.609364
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -26.223063
return_std_test                     23.529797
average_reward_test                 -0.026223
round_time_test        0 days 00:00:07.833521
round_time_total       0 days 00:10:23.610478
loss_total                         208.404903
loss_critic                        325.839149
loss_actor                        -261.332099
memory_size                         86673.825 

=== epoch 1/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:58,  3.03it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.559678
return_std                          24.950605
average_reward                       -0.16256
round_time             0 days 00:10:24.612934
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -9.435665
return_std_test                     16.522884
average_reward_test                 -0.009436
round_time_test        0 days 00:00:07.573596
round_time_total       0 days 00:10:24.614008
loss_total                         219.446223
loss_critic                        339.661306
loss_actor                        -261.414131
memory_size                         88621.825 

=== epoch 1/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:41,  3.11it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -150.628224
return_std                          21.533622
average_reward                      -0.150628
round_time             0 days 00:10:24.553715
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        21.144613
return_std_test                     27.557764
average_reward_test                  0.021145
round_time_test        0 days 00:00:07.581296
round_time_total       0 days 00:10:24.554806
loss_total                         214.330411
loss_critic                        333.515145
loss_actor                        -262.408544
memory_size                         90569.825 

=== epoch 1/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:51,  3.06it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -150.328443
return_std                           42.56004
average_reward                      -0.150328
round_time             0 days 00:10:22.531972
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        25.592175
return_std_test                     29.268045
average_reward_test                  0.025592
round_time_test        0 days 00:00:07.612844
round_time_total       0 days 00:10:22.533066
loss_total                         215.242519
loss_critic                        334.954352
loss_actor                        -263.604828
memory_size                         92517.825 

=== epoch 1/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:46,  3.08it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -156.531387
return_std                          46.192362
average_reward                      -0.156531
round_time             0 days 00:10:24.745966
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        14.551066
return_std_test                     18.515399
average_reward_test                  0.014551
round_time_test        0 days 00:00:07.565468
round_time_total       0 days 00:10:24.747066
loss_total                         215.730571
loss_critic                        335.793096
loss_actor                        -264.519551
memory_size                         94465.825 

=== epoch 1/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:33,  3.15it/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 [10:22<00:00,  3.21it/s]
<GE123_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                           -157.189074
return_std                          48.806714
average_reward                      -0.157189
round_time             0 days 00:10:23.374417
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.634088
return_std_test                     25.211916
average_reward_test                  0.010634
round_time_test        0 days 00:00:07.735584
round_time_total       0 days 00:10:23.375822
loss_total                         211.979106
loss_critic                        331.400224
loss_actor                        -265.705383
memory_size                         96413.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 2/10 ===== round 1/50 ======================================
  0%|          | 7/2000 [00:02<10:19,  3.22it/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 [10:09<00:00,  3.28it/s]
episodes                                    2
episode_length                         1000.0
returns                            -159.48606
return_std                           2.954057
average_reward                      -0.159486
round_time             0 days 00:10:10.030914
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -0.522972
return_std_test                     21.694171
average_reward_test                 -0.000523
round_time_test        0 days 00:00:07.579822
round_time_total       0 days 00:10:10.032058
loss_total                         214.675263
loss_critic                         335.01035
loss_actor                          -266.6651
memory_size                         98362.825 

=== epoch 2/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:25,  3.19it/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 [10:13<00:00,  3.26it/s]
episodes                                    4
episode_length                         1000.0
returns                           -155.328894
return_std                          22.181856
average_reward                      -0.155329
round_time             0 days 00:10:13.884995
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        16.355673
return_std_test                     48.547813
average_reward_test                  0.016356
round_time_test        0 days 00:00:07.664942
round_time_total       0 days 00:10:13.886127
loss_total                         215.714668
loss_critic                        336.517063
loss_actor                         -267.49493
memory_size                        100310.825 

=== epoch 2/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:51,  3.06it/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 [10:13<00:00,  3.26it/s]
episodes                                    6
episode_length                         1000.0
returns                           -153.225852
return_std                          18.528537
average_reward                      -0.153226
round_time             0 days 00:10:13.834611
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.703892
return_std_test                     15.680351
average_reward_test                  0.015704
round_time_test        0 days 00:00:07.780354
round_time_total       0 days 00:10:13.835731
loss_total                         213.148761
loss_critic                        333.584582
loss_actor                        -268.594542
memory_size                        102258.825 

=== epoch 2/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:44,  3.10it/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 [10:14<00:00,  3.25it/s]
episodes                                    8
episode_length                         1000.0
returns                           -152.894843
return_std                           29.66529
average_reward                      -0.152895
round_time             0 days 00:10:15.009070
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        36.926189
return_std_test                     25.730055
average_reward_test                  0.036926
round_time_test        0 days 00:00:07.625323
round_time_total       0 days 00:10:15.010321
loss_total                         215.775086
loss_critic                        337.112039
loss_actor                        -269.572743
memory_size                        104206.825 

=== epoch 2/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:07,  2.99it/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 [10:12<00:00,  3.26it/s]
episodes                                   10
episode_length                         1000.0
returns                           -142.085257
return_std                          34.794836
average_reward                      -0.142085
round_time             0 days 00:10:13.159594
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.657337
return_std_test                     14.111262
average_reward_test                  0.006657
round_time_test        0 days 00:00:07.548622
round_time_total       0 days 00:10:13.161243
loss_total                         220.255095
loss_critic                        343.068383
loss_actor                         -270.99808
memory_size                        106154.825 

=== epoch 2/10 ===== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:43,  2.83it/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 [10:16<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                           -142.529797
return_std                          35.007906
average_reward                       -0.14253
round_time             0 days 00:10:16.633047
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        33.963047
return_std_test                     13.948651
average_reward_test                  0.033963
round_time_test        0 days 00:00:07.906742
round_time_total       0 days 00:10:16.634157
loss_total                         222.179004
loss_critic                        345.714528
loss_actor                        -271.963114
memory_size                        108102.825 

=== epoch 2/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:58,  3.03it/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 [10:13<00:00,  3.26it/s]
episodes                                   10
episode_length                         1000.0
returns                           -149.500659
return_std                          37.234401
average_reward                      -0.149501
round_time             0 days 00:10:13.832268
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        23.677258
return_std_test                     21.358509
average_reward_test                  0.023677
round_time_test        0 days 00:00:07.741936
round_time_total       0 days 00:10:13.833654
loss_total                         215.685335
loss_critic                        337.849678
loss_actor                        -272.972054
memory_size                        110050.825 

=== epoch 2/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:48,  3.08it/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 [10:16<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                           -153.771647
return_std                          39.076652
average_reward                      -0.153772
round_time             0 days 00:10:16.553791
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.811434
return_std_test                     13.676645
average_reward_test                  0.005811
round_time_test        0 days 00:00:07.727819
round_time_total       0 days 00:10:16.555173
loss_total                         213.513822
loss_critic                        335.476204
loss_actor                        -274.335726
memory_size                        111998.825 

=== epoch 2/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:12,  2.97it/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 [10:15<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            -163.72317
return_std                          37.839939
average_reward                      -0.163723
round_time             0 days 00:10:16.350370
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        47.608498
return_std_test                     22.704375
average_reward_test                  0.047608
round_time_test        0 days 00:00:07.580624
round_time_total       0 days 00:10:16.351459
loss_total                         211.503355
loss_critic                        333.337084
loss_actor                        -275.831584
memory_size                        113946.825 

=== epoch 2/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:30,  3.16it/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 [10:16<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                           -172.187664
return_std                          29.074065
average_reward                      -0.172188
round_time             0 days 00:10:17.118966
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        27.578251
return_std_test                     18.250667
average_reward_test                  0.027578
round_time_test        0 days 00:00:07.759426
round_time_total       0 days 00:10:17.120092
loss_total                         211.825138
loss_critic                        334.112094
loss_actor                        -277.322707
memory_size                        115894.825 

=== epoch 2/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:54,  3.05it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -173.690559
return_std                          30.507024
average_reward                      -0.173691
round_time             0 days 00:10:20.932872
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.310264
return_std_test                     18.729311
average_reward_test                   0.00631
round_time_test        0 days 00:00:07.646051
round_time_total       0 days 00:10:20.934058
loss_total                         211.691928
loss_critic                        334.196453
loss_actor                        -278.326189
memory_size                        117842.825 

=== epoch 2/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:42,  3.11it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -157.497319
return_std                          50.955643
average_reward                      -0.157497
round_time             0 days 00:10:22.255542
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        20.687525
return_std_test                     26.403671
average_reward_test                  0.020688
round_time_test        0 days 00:00:07.513050
round_time_total       0 days 00:10:22.256776
loss_total                         209.061834
loss_critic                        331.241417
loss_actor                        -279.656513
memory_size                        119790.825 

=== epoch 2/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:13,  2.96it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -150.767314
return_std                           52.89146
average_reward                      -0.150767
round_time             0 days 00:10:19.797411
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        17.109499
return_std_test                     18.825427
average_reward_test                  0.017109
round_time_test        0 days 00:00:07.860343
round_time_total       0 days 00:10:19.798892
loss_total                         211.522045
loss_critic                        334.589497
loss_actor                         -280.74778
memory_size                        121738.825 

=== epoch 2/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:21,  3.21it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -138.331538
return_std                          46.041496
average_reward                      -0.138332
round_time             0 days 00:10:19.050685
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.359287
return_std_test                     12.621029
average_reward_test                  0.004359
round_time_test        0 days 00:00:07.727842
round_time_total       0 days 00:10:19.051785
loss_total                         207.777577
loss_critic                        330.137493
loss_actor                        -281.662108
memory_size                        123686.825 

=== epoch 2/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:39,  2.85it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -138.343642
return_std                          43.107023
average_reward                      -0.138344
round_time             0 days 00:10:20.034441
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        27.441384
return_std_test                     21.669446
average_reward_test                  0.027441
round_time_test        0 days 00:00:07.799031
round_time_total       0 days 00:10:20.035552
loss_total                         208.715551
loss_critic                        331.601512
loss_actor                        -282.828309
memory_size                        125634.825 

=== epoch 2/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:36,  2.86it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -133.879598
return_std                          41.636767
average_reward                       -0.13388
round_time             0 days 00:10:19.339867
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          1.08176
return_std_test                     11.741854
average_reward_test                  0.001082
round_time_test        0 days 00:00:07.588161
round_time_total       0 days 00:10:19.341322
loss_total                         204.955514
loss_critic                        327.350113
loss_actor                        -284.622899
memory_size                        127582.825 

=== epoch 2/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:40,  2.85it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -137.174121
return_std                          23.455701
average_reward                      -0.137174
round_time             0 days 00:10:21.418039
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        27.673357
return_std_test                     33.294663
average_reward_test                  0.027673
round_time_test        0 days 00:00:07.612440
round_time_total       0 days 00:10:21.419135
loss_total                         208.572951
loss_critic                        332.289404
loss_actor                        -286.292874
memory_size                        129530.825 

=== epoch 2/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:23,  2.92it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -142.030894
return_std                          21.083774
average_reward                      -0.142031
round_time             0 days 00:10:21.514604
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        31.181856
return_std_test                     17.529599
average_reward_test                  0.031182
round_time_test        0 days 00:00:07.668855
round_time_total       0 days 00:10:21.515703
loss_total                         203.883653
loss_critic                        326.796203
loss_actor                        -287.766566
memory_size                        131478.825 

=== epoch 2/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:02,  3.01it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -142.102019
return_std                          29.510706
average_reward                      -0.142102
round_time             0 days 00:10:23.263890
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        40.300456
return_std_test                     30.550805
average_reward_test                    0.0403
round_time_test        0 days 00:00:07.657326
round_time_total       0 days 00:10:23.265167
loss_total                         198.022186
loss_critic                        319.951573
loss_actor                        -289.695379
memory_size                        133426.825 

=== epoch 2/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:29,  2.89it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -132.385234
return_std                          36.977583
average_reward                      -0.132385
round_time             0 days 00:10:20.308219
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        26.821981
return_std_test                     19.238254
average_reward_test                  0.026822
round_time_test        0 days 00:00:07.550458
round_time_total       0 days 00:10:20.309619
loss_total                         199.689114
loss_critic                        322.322344
loss_actor                        -290.843822
memory_size                        135374.825 

=== epoch 2/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:22,  2.92it/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 [10:18<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                           -130.471458
return_std                          38.030467
average_reward                      -0.130471
round_time             0 days 00:10:18.523574
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        19.199848
return_std_test                     16.055204
average_reward_test                    0.0192
round_time_test        0 days 00:00:07.576621
round_time_total       0 days 00:10:18.524674
loss_total                         197.891064
loss_critic                        320.435006
loss_actor                        -292.284723
memory_size                        137322.825 

=== epoch 2/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:35,  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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -133.328758
return_std                          37.738121
average_reward                      -0.133329
round_time             0 days 00:10:21.560633
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         15.25457
return_std_test                      8.927823
average_reward_test                  0.015255
round_time_test        0 days 00:00:07.647306
round_time_total       0 days 00:10:21.561811
loss_total                         197.230828
loss_critic                        319.942289
loss_actor                         -293.61503
memory_size                        139270.825 

=== epoch 2/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:30,  3.16it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -128.524344
return_std                          36.946032
average_reward                      -0.128524
round_time             0 days 00:10:20.099833
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.086454
return_std_test                      14.02558
average_reward_test                  0.005086
round_time_test        0 days 00:00:07.462601
round_time_total       0 days 00:10:20.101211
loss_total                         194.096211
loss_critic                         316.27649
loss_actor                        -294.624919
memory_size                        141218.825 

=== epoch 2/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:31,  2.89it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -134.459624
return_std                          34.890368
average_reward                       -0.13446
round_time             0 days 00:10:20.528277
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -2.287914
return_std_test                      12.80496
average_reward_test                 -0.002288
round_time_test        0 days 00:00:07.765773
round_time_total       0 days 00:10:20.529406
loss_total                         191.987056
loss_critic                        313.981948
loss_actor                         -295.99253
memory_size                        143166.825 

=== epoch 2/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:47,  3.08it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -134.183252
return_std                          44.173354
average_reward                      -0.134183
round_time             0 days 00:10:21.665191
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.056412
return_std_test                      10.32486
average_reward_test                  0.002056
round_time_test        0 days 00:00:07.702658
round_time_total       0 days 00:10:21.666305
loss_total                         191.552743
loss_critic                        313.785671
loss_actor                        -297.378984
memory_size                        145114.825 

=== epoch 2/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:12,  2.96it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -133.872811
return_std                          45.361769
average_reward                      -0.133873
round_time             0 days 00:10:21.075215
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -10.282649
return_std_test                      7.208439
average_reward_test                 -0.010283
round_time_test        0 days 00:00:07.728247
round_time_total       0 days 00:10:21.076500
loss_total                         208.591825
loss_critic                        335.481925
loss_actor                        -298.968595
memory_size                        147062.825 

=== epoch 2/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:43,  2.84it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -137.097371
return_std                           49.82042
average_reward                      -0.137097
round_time             0 days 00:10:21.292665
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          3.98271
return_std_test                     11.641821
average_reward_test                  0.003983
round_time_test        0 days 00:00:07.491684
round_time_total       0 days 00:10:21.293966
loss_total                         204.455149
loss_critic                        330.696166
loss_actor                        -300.508936
memory_size                        149010.825 

=== epoch 2/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:41,  3.11it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -142.474482
return_std                          49.152658
average_reward                      -0.142474
round_time             0 days 00:10:23.644656
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        23.315741
return_std_test                       14.4072
average_reward_test                  0.023316
round_time_test        0 days 00:00:07.643315
round_time_total       0 days 00:10:23.645749
loss_total                         208.288798
loss_critic                        335.923449
loss_actor                        -302.249825
memory_size                        150958.825 

=== epoch 2/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:25,  2.91it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -126.822465
return_std                          51.536225
average_reward                      -0.126822
round_time             0 days 00:10:23.295316
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -5.049264
return_std_test                     14.340899
average_reward_test                 -0.005049
round_time_test        0 days 00:00:07.649421
round_time_total       0 days 00:10:23.296728
loss_total                         201.861432
loss_critic                        328.305542
loss_actor                        -303.915028
memory_size                        152906.825 

=== epoch 2/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:34,  2.87it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -133.400413
return_std                          39.724631
average_reward                        -0.1334
round_time             0 days 00:10:24.078435
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        10.321929
return_std_test                     10.902156
average_reward_test                  0.010322
round_time_test        0 days 00:00:07.751223
round_time_total       0 days 00:10:24.079514
loss_total                         196.995136
loss_critic                        322.688384
loss_actor                        -305.777873
memory_size                        154854.825 

=== epoch 2/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:40,  3.12it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -134.932089
return_std                          39.207143
average_reward                      -0.134932
round_time             0 days 00:10:23.152467
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -3.458826
return_std_test                     15.186439
average_reward_test                 -0.003459
round_time_test        0 days 00:00:07.600528
round_time_total       0 days 00:10:23.153565
loss_total                         193.236575
loss_critic                        318.365403
loss_actor                        -307.278756
memory_size                        156802.825 

=== epoch 2/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:43,  2.83it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -129.670336
return_std                          34.426556
average_reward                       -0.12967
round_time             0 days 00:10:23.707929
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.789709
return_std_test                     21.374862
average_reward_test                   0.00179
round_time_test        0 days 00:00:07.901775
round_time_total       0 days 00:10:23.709090
loss_total                         191.547195
loss_critic                        316.679673
loss_actor                        -308.982735
memory_size                        158750.825 

=== epoch 2/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:35,  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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -125.039681
return_std                          31.447442
average_reward                       -0.12504
round_time             0 days 00:10:23.001967
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          9.89389
return_std_test                     12.472323
average_reward_test                  0.009894
round_time_test        0 days 00:00:07.755529
round_time_total       0 days 00:10:23.003064
loss_total                         186.814707
loss_critic                        311.103759
loss_actor                         -310.34152
memory_size                        160698.825 

=== epoch 2/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:42,  3.11it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -139.158104
return_std                          27.100852
average_reward                      -0.139158
round_time             0 days 00:10:24.036656
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.961834
return_std_test                     11.657653
average_reward_test                  0.002962
round_time_test        0 days 00:00:07.617331
round_time_total       0 days 00:10:24.037756
loss_total                         187.937317
loss_critic                        312.915909
loss_actor                        -311.977064
memory_size                        162646.825 

=== epoch 2/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:10,  2.98it/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 [10:22<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -140.780686
return_std                          25.776096
average_reward                      -0.140781
round_time             0 days 00:10:22.597825
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.626593
return_std_test                     19.469311
average_reward_test                  0.002627
round_time_test        0 days 00:00:07.471693
round_time_total       0 days 00:10:22.599121
loss_total                         187.077654
loss_critic                         312.12802
loss_actor                        -313.123823
memory_size                        164594.825 

=== epoch 2/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:33,  2.88it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            -137.01813
return_std                          24.160248
average_reward                      -0.137018
round_time             0 days 00:10:19.075661
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -6.194232
return_std_test                     13.742688
average_reward_test                 -0.006194
round_time_test        0 days 00:00:07.727017
round_time_total       0 days 00:10:19.076757
loss_total                          188.68244
loss_critic                        314.425141
loss_actor                        -314.288376
memory_size                        166542.825 

=== epoch 2/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:08,  2.99it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -138.762954
return_std                          24.193707
average_reward                      -0.138763
round_time             0 days 00:10:20.325956
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        18.044919
return_std_test                     10.028067
average_reward_test                  0.018045
round_time_test        0 days 00:00:07.637083
round_time_total       0 days 00:10:20.327092
loss_total                         183.933361
loss_critic                        308.838714
loss_actor                        -315.688067
memory_size                        168490.825 

=== epoch 2/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:51,  3.06it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -134.887401
return_std                          24.258073
average_reward                      -0.134887
round_time             0 days 00:10:22.600251
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -4.647665
return_std_test                     10.930649
average_reward_test                 -0.004648
round_time_test        0 days 00:00:07.684948
round_time_total       0 days 00:10:22.601356
loss_total                         181.844867
loss_critic                         306.54666
loss_actor                        -316.962319
memory_size                        170438.825 

=== epoch 2/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:00,  3.02it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -121.382829
return_std                          24.026294
average_reward                      -0.121383
round_time             0 days 00:10:22.039940
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          4.43666
return_std_test                      7.415981
average_reward_test                  0.004437
round_time_test        0 days 00:00:07.580117
round_time_total       0 days 00:10:22.041025
loss_total                         181.570746
loss_critic                        306.485529
loss_actor                          -318.0884
memory_size                        172386.825 

=== epoch 2/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:25,  2.91it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -121.321422
return_std                          24.283504
average_reward                      -0.121321
round_time             0 days 00:10:23.538127
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        12.986533
return_std_test                     20.319508
average_reward_test                  0.012987
round_time_test        0 days 00:00:07.567898
round_time_total       0 days 00:10:23.539224
loss_total                         179.590103
loss_critic                        304.249346
loss_actor                        -319.046883
memory_size                        174334.825 

=== epoch 2/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:57,  3.03it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -111.359841
return_std                          26.799965
average_reward                       -0.11136
round_time             0 days 00:10:22.846315
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         11.43639
return_std_test                     15.875643
average_reward_test                  0.011436
round_time_test        0 days 00:00:07.674073
round_time_total       0 days 00:10:22.847406
loss_total                          175.32939
loss_critic                        299.295061
loss_actor                        -320.533303
memory_size                        176282.825 

=== epoch 2/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:39,  3.12it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -115.779559
return_std                          32.328736
average_reward                       -0.11578
round_time             0 days 00:10:22.031182
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.464597
return_std_test                      12.58352
average_reward_test                  0.006465
round_time_test        0 days 00:00:07.638629
round_time_total       0 days 00:10:22.032364
loss_total                         176.525612
loss_critic                        301.124026
loss_actor                        -321.868055
memory_size                        178230.825 

=== epoch 2/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:28,  2.90it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -116.51755
return_std                          32.599679
average_reward                      -0.116518
round_time             0 days 00:10:24.299723
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.924748
return_std_test                     17.524865
average_reward_test                  0.011925
round_time_test        0 days 00:00:07.799453
round_time_total       0 days 00:10:24.300865
loss_total                         176.710642
loss_critic                        301.655413
loss_actor                        -323.068455
memory_size                        180178.825 

=== epoch 2/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:55,  3.04it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -126.662856
return_std                          31.858581
average_reward                      -0.126663
round_time             0 days 00:10:23.491858
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.115583
return_std_test                      8.150553
average_reward_test                  0.008116
round_time_test        0 days 00:00:07.674366
round_time_total       0 days 00:10:23.492949
loss_total                         172.431305
loss_critic                        296.668728
loss_actor                        -324.518398
memory_size                        182126.825 

=== epoch 2/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:14,  2.96it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -123.934653
return_std                          32.335777
average_reward                      -0.123935
round_time             0 days 00:10:23.671245
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         26.85258
return_std_test                       8.03621
average_reward_test                  0.026853
round_time_test        0 days 00:00:07.807073
round_time_total       0 days 00:10:23.672784
loss_total                         170.611845
loss_critic                        294.674088
loss_actor                        -325.637137
memory_size                        184074.825 

=== epoch 2/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:41,  3.11it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -130.078342
return_std                          28.085512
average_reward                      -0.130078
round_time             0 days 00:10:23.339324
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -8.732793
return_std_test                      8.344308
average_reward_test                 -0.008733
round_time_test        0 days 00:00:07.682351
round_time_total       0 days 00:10:23.340518
loss_total                         173.782379
loss_critic                         298.80886
loss_actor                        -326.323557
memory_size                        186022.825 

=== epoch 2/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:43,  3.10it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                           -115.095049
return_std                          27.929951
average_reward                      -0.115095
round_time             0 days 00:10:25.055756
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        15.825818
return_std_test                      18.63788
average_reward_test                  0.015826
round_time_test        0 days 00:00:07.862974
round_time_total       0 days 00:10:25.056842
loss_total                          173.75834
loss_critic                        298.924892
loss_actor                         -326.90788
memory_size                        187970.825 

=== epoch 2/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:16,  2.95it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -116.827753
return_std                          34.368011
average_reward                      -0.116828
round_time             0 days 00:10:21.833335
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        23.432877
return_std_test                      8.779056
average_reward_test                  0.023433
round_time_test        0 days 00:00:07.640373
round_time_total       0 days 00:10:21.834443
loss_total                         172.765743
loss_critic                        297.959676
loss_actor                        -328.009999
memory_size                        189918.825 

=== epoch 2/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:00,  3.02it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -112.48012
return_std                          31.775341
average_reward                       -0.11248
round_time             0 days 00:10:22.504146
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         0.635398
return_std_test                      9.939107
average_reward_test                  0.000635
round_time_test        0 days 00:00:07.709352
round_time_total       0 days 00:10:22.505460
loss_total                         171.200057
loss_critic                        296.299383
loss_actor                        -329.197258
memory_size                        191866.825 

=== epoch 2/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:40,  2.85it/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 [10:24<00:00,  3.20it/s]
<GE123_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                           -120.751346
return_std                          36.641908
average_reward                      -0.120751
round_time             0 days 00:10:25.009923
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        11.335333
return_std_test                     19.542968
average_reward_test                  0.011335
round_time_test        0 days 00:00:07.744282
round_time_total       0 days 00:10:25.011050
loss_total                         172.671389
loss_critic                        298.377532
loss_actor                        -330.153192
memory_size                        193814.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 3/10 ===== round 1/50 ======================================
  0%|          | 6/2000 [00:01<10:28,  3.17it/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 [10:10<00:00,  3.27it/s]
episodes                                    2
episode_length                         1000.0
returns                           -137.689734
return_std                          12.117719
average_reward                       -0.13769
round_time             0 days 00:10:11.034110
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        37.091138
return_std_test                     15.401567
average_reward_test                  0.037091
round_time_test        0 days 00:00:07.715769
round_time_total       0 days 00:10:11.035436
loss_total                         172.064375
loss_critic                         297.89182
loss_actor                        -331.245413
memory_size                        195763.825 

=== epoch 3/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:22,  3.20it/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 [10:15<00:00,  3.25it/s]
episodes                                    4
episode_length                         1000.0
returns                           -135.930527
return_std                           9.687465
average_reward                      -0.135931
round_time             0 days 00:10:15.823484
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        18.253658
return_std_test                      7.501736
average_reward_test                  0.018254
round_time_test        0 days 00:00:07.706491
round_time_total       0 days 00:10:15.824813
loss_total                          171.76619
loss_critic                        297.694003
loss_actor                        -331.945078
memory_size                        197711.825 

=== epoch 3/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:02,  3.01it/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 [10:29<00:00,  3.18it/s]
episodes                                    6
episode_length                         1000.0
returns                           -137.356363
return_std                          22.359199
average_reward                      -0.137356
round_time             0 days 00:10:30.259181
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -0.468442
return_std_test                     19.662141
average_reward_test                 -0.000468
round_time_test        0 days 00:00:07.905861
round_time_total       0 days 00:10:30.260451
loss_total                         172.954055
loss_critic                        299.336542
loss_actor                        -332.575905
memory_size                        199659.825 

=== epoch 3/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:55,  3.04it/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 [10:42<00:00,  3.11it/s]
episodes                                    8
episode_length                         1000.0
returns                           -126.491813
return_std                          27.903902
average_reward                      -0.126492
round_time             0 days 00:10:42.756382
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         7.869604
return_std_test                     14.798902
average_reward_test                   0.00787
round_time_test        0 days 00:00:07.660639
round_time_total       0 days 00:10:42.757494
loss_total                          175.19437
loss_critic                        302.188154
loss_actor                        -332.780777
memory_size                        201607.825 

=== epoch 3/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:57,  3.03it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -120.775715
return_std                           27.46698
average_reward                      -0.120776
round_time             0 days 00:10:18.881556
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        21.414132
return_std_test                     10.552014
average_reward_test                  0.021414
round_time_test        0 days 00:00:07.685806
round_time_total       0 days 00:10:18.882659
loss_total                         175.695322
loss_critic                        302.949091
loss_actor                        -333.319764
memory_size                        203555.825 

=== epoch 3/10 ===== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:38,  3.12it/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 [10:15<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                           -117.226857
return_std                          25.609537
average_reward                      -0.117227
round_time             0 days 00:10:15.821759
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        13.870055
return_std_test                      7.165467
average_reward_test                   0.01387
round_time_test        0 days 00:00:07.618949
round_time_total       0 days 00:10:15.823158
loss_total                         173.716752
loss_critic                        300.588512
loss_actor                        -333.770297
memory_size                        205503.825 

=== epoch 3/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:26,  3.18it/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 [10:14<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                           -113.182228
return_std                          25.936669
average_reward                      -0.113182
round_time             0 days 00:10:15.053399
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.604076
return_std_test                     10.511004
average_reward_test                  0.006604
round_time_test        0 days 00:00:07.899895
round_time_total       0 days 00:10:15.054905
loss_total                         170.787667
loss_critic                        297.156579
loss_actor                        -334.687994
memory_size                        207451.825 

=== epoch 3/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:30,  2.89it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -108.407333
return_std                          16.659199
average_reward                      -0.108407
round_time             0 days 00:10:19.410853
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -4.865507
return_std_test                       5.31873
average_reward_test                 -0.004866
round_time_test        0 days 00:00:07.756769
round_time_total       0 days 00:10:19.411957
loss_total                         170.246884
loss_critic                        296.783685
loss_actor                        -335.900329
memory_size                        209399.825 

=== epoch 3/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:50,  3.07it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -107.425407
return_std                          17.818461
average_reward                      -0.107425
round_time             0 days 00:10:20.256887
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         1.736537
return_std_test                     10.080831
average_reward_test                  0.001737
round_time_test        0 days 00:00:07.724815
round_time_total       0 days 00:10:20.258194
loss_total                         170.330814
loss_critic                        297.195047
loss_actor                        -337.126131
memory_size                        211347.825 

=== epoch 3/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:41,  3.11it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                           -109.145606
return_std                          17.284039
average_reward                      -0.109146
round_time             0 days 00:10:17.677521
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         2.850282
return_std_test                     13.505139
average_reward_test                   0.00285
round_time_test        0 days 00:00:07.600673
round_time_total       0 days 00:10:17.678639
loss_total                         169.426091
loss_critic                        296.268098
loss_actor                         -337.94195
memory_size                        213295.825 

=== epoch 3/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:12,  2.96it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                           -110.447544
return_std                          18.258482
average_reward                      -0.110448
round_time             0 days 00:10:18.367649
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        21.778361
return_std_test                     17.559298
average_reward_test                  0.021778
round_time_test        0 days 00:00:07.788676
round_time_total       0 days 00:10:18.368848
loss_total                         170.947187
loss_critic                         298.41476
loss_actor                        -338.923118
memory_size                        215243.825 

=== epoch 3/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:57,  3.03it/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 [10:20<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -107.347581
return_std                          15.980961
average_reward                      -0.107348
round_time             0 days 00:10:20.749710
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.598623
return_std_test                     18.270823
average_reward_test                  0.005599
round_time_test        0 days 00:00:07.617128
round_time_total       0 days 00:10:20.750814
loss_total                         175.631593
loss_critic                         304.45434
loss_actor                        -339.659407
memory_size                        217191.825 

=== epoch 3/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<12:02,  2.76it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                           -102.586966
return_std                          18.529233
average_reward                      -0.102587
round_time             0 days 00:10:19.499102
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.079812
return_std_test                      7.426112
average_reward_test                   0.00508
round_time_test        0 days 00:00:07.784380
round_time_total       0 days 00:10:19.500550
loss_total                          174.07074
loss_critic                        302.744857
loss_actor                         -340.62574
memory_size                        219139.825 

=== epoch 3/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:03,  3.01it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                           -100.628113
return_std                          19.884249
average_reward                      -0.100628
round_time             0 days 00:10:21.409567
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         5.863488
return_std_test                     16.617202
average_reward_test                  0.005863
round_time_test        0 days 00:00:07.689057
round_time_total       0 days 00:10:21.410702
loss_total                         170.649648
loss_critic                        298.531548
loss_actor                        -340.877963
memory_size                        221087.825 

=== epoch 3/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:19,  3.22it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                           -102.881684
return_std                          21.234685
average_reward                      -0.102882
round_time             0 days 00:10:18.575874
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        49.698837
return_std_test                     19.748316
average_reward_test                  0.049699
round_time_test        0 days 00:00:07.776393
round_time_total       0 days 00:10:18.577009
loss_total                         168.795469
loss_critic                         296.39769
loss_actor                        -341.613426
memory_size                        223035.825 

=== epoch 3/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:44,  3.09it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                             -92.09613
return_std                          23.755266
average_reward                      -0.092096
round_time             0 days 00:10:24.914045
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         8.402545
return_std_test                      11.04134
average_reward_test                  0.008403
round_time_test        0 days 00:00:07.768472
round_time_total       0 days 00:10:24.915152
loss_total                         174.409074
loss_critic                        303.570028
loss_actor                        -342.234754
memory_size                        224983.825 

=== epoch 3/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:04,  3.00it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -91.148741
return_std                          27.283119
average_reward                      -0.091149
round_time             0 days 00:10:22.267995
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        29.125652
return_std_test                     10.531787
average_reward_test                  0.029126
round_time_test        0 days 00:00:07.672123
round_time_total       0 days 00:10:22.269073
loss_total                         175.145511
loss_critic                        304.681463
loss_actor                        -342.998307
memory_size                        226931.825 

=== epoch 3/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:28,  3.18it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -90.763154
return_std                          26.172245
average_reward                      -0.090763
round_time             0 days 00:10:20.654562
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        34.198891
return_std_test                     13.173259
average_reward_test                  0.034199
round_time_test        0 days 00:00:07.213516
round_time_total       0 days 00:10:20.655678
loss_total                         170.021824
loss_critic                        298.576587
loss_actor                        -344.197238
memory_size                        228879.825 

=== epoch 3/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<12:01,  2.76it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             -95.78415
return_std                          25.355678
average_reward                      -0.095784
round_time             0 days 00:10:23.735904
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        19.049686
return_std_test                     11.095405
average_reward_test                   0.01905
round_time_test        0 days 00:00:07.722477
round_time_total       0 days 00:10:23.736984
loss_total                         172.424204
loss_critic                        301.786005
loss_actor                        -345.023006
memory_size                        230827.825 

=== epoch 3/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:52,  2.80it/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 [10:26<00:00,  3.19it/s]
episodes                                   10
episode_length                         1000.0
returns                            -94.985227
return_std                          25.442641
average_reward                      -0.094985
round_time             0 days 00:10:26.550263
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        84.978692
return_std_test                     25.845979
average_reward_test                  0.084979
round_time_test        0 days 00:00:07.701796
round_time_total       0 days 00:10:26.551752
loss_total                         176.299863
loss_critic                        306.851407
loss_actor                        -345.906322
memory_size                        232775.825 

=== epoch 3/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:47,  3.08it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                           -100.278461
return_std                          19.264571
average_reward                      -0.100278
round_time             0 days 00:10:23.878185
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         57.39622
return_std_test                     24.744252
average_reward_test                  0.057396
round_time_test        0 days 00:00:07.595631
round_time_total       0 days 00:10:23.879296
loss_total                         171.760289
loss_critic                        301.384328
loss_actor                        -346.735875
memory_size                        234723.825 

=== epoch 3/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:26,  3.18it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -98.772225
return_std                          14.531603
average_reward                      -0.098772
round_time             0 days 00:10:22.499653
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         35.90868
return_std_test                       25.5183
average_reward_test                  0.035909
round_time_test        0 days 00:00:07.672248
round_time_total       0 days 00:10:22.500754
loss_total                         168.152327
loss_critic                        297.032171
loss_actor                        -347.367059
memory_size                        236671.825 

=== epoch 3/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:25,  3.19it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -98.399546
return_std                          19.547721
average_reward                        -0.0984
round_time             0 days 00:10:23.061695
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       107.560015
return_std_test                     36.009369
average_reward_test                   0.10756
round_time_test        0 days 00:00:07.686325
round_time_total       0 days 00:10:23.062786
loss_total                         169.504354
loss_critic                         298.96433
loss_actor                        -348.335563
memory_size                        238619.825 

=== epoch 3/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:15,  2.95it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -90.620699
return_std                          25.643077
average_reward                      -0.090621
round_time             0 days 00:10:21.945242
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        50.863443
return_std_test                     18.397101
average_reward_test                  0.050863
round_time_test        0 days 00:00:07.677587
round_time_total       0 days 00:10:21.946763
loss_total                         171.175759
loss_critic                        301.254463
loss_actor                        -349.139065
memory_size                        240567.825 

=== epoch 3/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:16,  2.95it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            -78.073675
return_std                          26.188209
average_reward                      -0.078074
round_time             0 days 00:10:25.457284
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        69.450909
return_std_test                     28.282792
average_reward_test                  0.069451
round_time_test        0 days 00:00:07.786552
round_time_total       0 days 00:10:25.458582
loss_total                          166.27415
loss_critic                        295.241928
loss_actor                        -349.596977
memory_size                        242515.825 

=== epoch 3/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:44,  3.10it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -73.068304
return_std                          25.616037
average_reward                      -0.073068
round_time             0 days 00:10:20.892945
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       158.571821
return_std_test                     35.375833
average_reward_test                  0.158572
round_time_test        0 days 00:00:07.537719
round_time_total       0 days 00:10:20.894308
loss_total                         165.700561
loss_critic                        294.735017
loss_actor                        -350.437273
memory_size                        244463.825 

=== epoch 3/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:55,  3.04it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -68.672485
return_std                          26.552332
average_reward                      -0.068672
round_time             0 days 00:10:24.039580
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       113.355729
return_std_test                     29.817884
average_reward_test                  0.113356
round_time_test        0 days 00:00:07.550343
round_time_total       0 days 00:10:24.040719
loss_total                         168.134162
loss_critic                        297.947681
loss_actor                        -351.119925
memory_size                        246411.825 

=== epoch 3/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:04,  3.00it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -64.299763
return_std                          19.842645
average_reward                        -0.0643
round_time             0 days 00:10:23.338129
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       138.788882
return_std_test                     47.574216
average_reward_test                  0.138789
round_time_test        0 days 00:00:07.649633
round_time_total       0 days 00:10:23.339445
loss_total                         169.736559
loss_critic                        300.261519
loss_actor                        -352.363292
memory_size                        248359.825 

=== epoch 3/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:20,  3.21it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             -66.54393
return_std                          17.023226
average_reward                      -0.066544
round_time             0 days 00:10:24.574439
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       100.616127
return_std_test                      26.99277
average_reward_test                  0.100616
round_time_test        0 days 00:00:07.633484
round_time_total       0 days 00:10:24.575581
loss_total                         169.472152
loss_critic                        300.050936
loss_actor                        -352.842994
memory_size                        250307.825 

=== epoch 3/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:37,  2.86it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             -70.10856
return_std                           14.48458
average_reward                      -0.070109
round_time             0 days 00:10:22.826446
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       121.866906
return_std_test                     40.551728
average_reward_test                  0.121867
round_time_test        0 days 00:00:07.633982
round_time_total       0 days 00:10:22.827661
loss_total                         168.512261
loss_critic                        299.111195
loss_actor                        -353.883486
memory_size                        252255.825 

=== epoch 3/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:30,  2.89it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -69.909609
return_std                          12.277425
average_reward                       -0.06991
round_time             0 days 00:10:21.217419
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       225.450394
return_std_test                     54.881442
average_reward_test                   0.22545
round_time_test        0 days 00:00:07.588251
round_time_total       0 days 00:10:21.218543
loss_total                         169.534493
loss_critic                        300.649119
loss_actor                        -354.924023
memory_size                        254203.825 

=== epoch 3/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:37,  2.86it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            -67.807865
return_std                          14.690313
average_reward                      -0.067808
round_time             0 days 00:10:26.307580
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       246.976754
return_std_test                     74.202471
average_reward_test                  0.246977
round_time_test        0 days 00:00:07.683292
round_time_total       0 days 00:10:26.308866
loss_total                         170.123391
loss_critic                        301.536137
loss_actor                        -355.527606
memory_size                        256151.825 

=== epoch 3/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:30,  2.89it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -60.239244
return_std                          31.776057
average_reward                      -0.060239
round_time             0 days 00:10:21.901598
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       212.505533
return_std_test                     34.659886
average_reward_test                  0.212506
round_time_test        0 days 00:00:07.554171
round_time_total       0 days 00:10:21.902676
loss_total                          167.80548
loss_critic                        298.805765
loss_actor                        -356.195671
memory_size                        258099.825 

=== epoch 3/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:10,  2.98it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -61.674512
return_std                          32.748427
average_reward                      -0.061675
round_time             0 days 00:10:23.113270
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       178.350494
return_std_test                      50.58881
average_reward_test                   0.17835
round_time_test        0 days 00:00:07.583332
round_time_total       0 days 00:10:23.114466
loss_total                         169.791761
loss_critic                        301.431215
loss_actor                        -356.766067
memory_size                        260047.825 

=== epoch 3/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:36,  2.87it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            -61.937005
return_std                          33.079562
average_reward                      -0.061937
round_time             0 days 00:10:25.784233
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       262.542402
return_std_test                     60.628459
average_reward_test                  0.262542
round_time_test        0 days 00:00:07.851551
round_time_total       0 days 00:10:25.785336
loss_total                         168.930135
loss_critic                        300.517186
loss_actor                        -357.418082
memory_size                        261995.825 

=== epoch 3/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:36,  3.13it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -65.457777
return_std                          34.872782
average_reward                      -0.065458
round_time             0 days 00:10:23.407008
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       252.279773
return_std_test                     79.742403
average_reward_test                   0.25228
round_time_test        0 days 00:00:07.662803
round_time_total       0 days 00:10:23.408129
loss_total                         169.549537
loss_critic                        301.555835
loss_actor                        -358.475667
memory_size                        263943.825 

=== epoch 3/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:06,  2.99it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -60.778961
return_std                          37.581735
average_reward                      -0.060779
round_time             0 days 00:10:24.313973
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       312.595859
return_std_test                     65.515042
average_reward_test                  0.312596
round_time_test        0 days 00:00:07.636407
round_time_total       0 days 00:10:24.315074
loss_total                         167.337962
loss_critic                        298.942833
loss_actor                        -359.081531
memory_size                        265891.825 

=== epoch 3/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:59,  3.03it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -58.787283
return_std                          33.408303
average_reward                      -0.058787
round_time             0 days 00:10:24.354507
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        410.06031
return_std_test                     50.852243
average_reward_test                   0.41006
round_time_test        0 days 00:00:07.539462
round_time_total       0 days 00:10:24.356064
loss_total                         166.301113
loss_critic                         297.84182
loss_actor                        -359.861728
memory_size                        267839.825 

=== epoch 3/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:06,  2.99it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -51.852557
return_std                          31.075809
average_reward                      -0.051853
round_time             0 days 00:10:24.095210
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       401.317461
return_std_test                     96.655996
average_reward_test                  0.401317
round_time_test        0 days 00:00:07.544073
round_time_total       0 days 00:10:24.096468
loss_total                         164.079362
loss_critic                        295.302201
loss_actor                        -360.812003
memory_size                        269787.825 

=== epoch 3/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:28,  2.90it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -44.141578
return_std                          29.974743
average_reward                      -0.044142
round_time             0 days 00:10:21.841294
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       296.434575
return_std_test                     56.240902
average_reward_test                  0.296435
round_time_test        0 days 00:00:07.737663
round_time_total       0 days 00:10:21.842381
loss_total                         166.930552
loss_critic                        299.026877
loss_actor                         -361.45476
memory_size                        271735.825 

=== epoch 3/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<11:24,  2.92it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -26.191282
return_std                          22.995179
average_reward                      -0.026191
round_time             0 days 00:10:24.020806
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       247.160382
return_std_test                     71.437399
average_reward_test                   0.24716
round_time_test        0 days 00:00:07.722289
round_time_total       0 days 00:10:24.022009
loss_total                         165.094236
loss_critic                         296.89278
loss_actor                        -362.099948
memory_size                        273683.825 

=== epoch 3/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:45,  2.83it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -30.391322
return_std                           32.55776
average_reward                      -0.030391
round_time             0 days 00:10:23.813311
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       413.437196
return_std_test                     68.194751
average_reward_test                  0.413437
round_time_test        0 days 00:00:07.446467
round_time_total       0 days 00:10:23.814561
loss_total                         166.963366
loss_critic                        299.281591
loss_actor                        -362.309543
memory_size                        275631.825 

=== epoch 3/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:09,  2.98it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            -29.666298
return_std                          31.313329
average_reward                      -0.029666
round_time             0 days 00:10:25.931739
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       424.106334
return_std_test                     76.378689
average_reward_test                  0.424106
round_time_test        0 days 00:00:07.521416
round_time_total       0 days 00:10:25.932879
loss_total                         169.968496
loss_critic                        303.170895
loss_actor                         -362.84111
memory_size                        277579.825 

=== epoch 3/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:01,  3.02it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            -18.979535
return_std                          31.960168
average_reward                       -0.01898
round_time             0 days 00:10:25.878270
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       439.279941
return_std_test                     51.110126
average_reward_test                   0.43928
round_time_test        0 days 00:00:07.741754
round_time_total       0 days 00:10:25.879435
loss_total                           168.8905
loss_critic                        302.112785
loss_actor                        -363.998648
memory_size                        279527.825 

=== epoch 3/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:31,  2.88it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            -15.921287
return_std                          33.528433
average_reward                      -0.015921
round_time             0 days 00:10:21.696405
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       548.202931
return_std_test                     95.481486
average_reward_test                  0.548203
round_time_test        0 days 00:00:07.470543
round_time_total       0 days 00:10:21.697515
loss_total                           168.1547
loss_critic                        301.386877
loss_actor                        -364.774019
memory_size                        281475.825 

=== epoch 3/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:14,  2.96it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            -24.712161
return_std                          34.309441
average_reward                      -0.024712
round_time             0 days 00:10:24.721341
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       477.499205
return_std_test                     75.900197
average_reward_test                  0.477499
round_time_test        0 days 00:00:07.574469
round_time_total       0 days 00:10:24.722467
loss_total                         169.033714
loss_critic                         302.75701
loss_actor                        -365.859482
memory_size                        283423.825 

=== epoch 3/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:38,  2.86it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            -18.851933
return_std                          25.281474
average_reward                      -0.018852
round_time             0 days 00:10:23.921484
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       479.840404
return_std_test                     82.885018
average_reward_test                   0.47984
round_time_test        0 days 00:00:07.761177
round_time_total       0 days 00:10:23.922699
loss_total                         169.340752
loss_critic                        303.468919
loss_actor                        -367.171926
memory_size                        285371.825 

=== epoch 3/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:00,  3.02it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            -15.971432
return_std                          38.098577
average_reward                      -0.015971
round_time             0 days 00:10:25.911778
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       566.349097
return_std_test                     78.770945
average_reward_test                  0.566349
round_time_test        0 days 00:00:07.568929
round_time_total       0 days 00:10:25.912884
loss_total                         169.860006
loss_critic                        304.307479
loss_actor                        -367.929896
memory_size                        287319.825 

=== epoch 3/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:46,  3.09it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            -11.723413
return_std                          41.204457
average_reward                      -0.011723
round_time             0 days 00:10:26.227414
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       530.585166
return_std_test                     59.850881
average_reward_test                  0.530585
round_time_test        0 days 00:00:07.709420
round_time_total       0 days 00:10:26.228504
loss_total                           171.2116
loss_critic                        306.085543
loss_actor                        -368.284183
memory_size                        289267.825 

=== epoch 3/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:49,  3.07it/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 [10:25<00:00,  3.20it/s]
<GE123_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                            -11.944814
return_std                          39.433873
average_reward                      -0.011945
round_time             0 days 00:10:25.624903
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       552.740864
return_std_test                     89.028744
average_reward_test                  0.552741
round_time_test        0 days 00:00:07.579249
round_time_total       0 days 00:10:25.626188
loss_total                         172.352365
loss_critic                        307.707455
loss_actor                        -369.068006
memory_size                        291215.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 4/10 ===== round 1/50 ======================================
  0%|          | 7/2000 [00:02<10:32,  3.15it/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 [10:09<00:00,  3.28it/s]
episodes                                    2
episode_length                         1000.0
returns                            -15.555052
return_std                          25.835819
average_reward                      -0.015555
round_time             0 days 00:10:09.413349
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       505.747121
return_std_test                      52.96475
average_reward_test                  0.505747
round_time_test        0 days 00:00:07.438623
round_time_total       0 days 00:10:09.414587
loss_total                         168.930488
loss_critic                        303.728641
loss_actor                        -370.262136
memory_size                        293164.825 

=== epoch 4/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:51,  3.06it/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 [10:14<00:00,  3.26it/s]
episodes                                    4
episode_length                         1000.0
returns                            -14.320383
return_std                           22.83497
average_reward                       -0.01432
round_time             0 days 00:10:14.895569
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       557.024793
return_std_test                      66.87183
average_reward_test                  0.557025
round_time_test        0 days 00:00:07.750148
round_time_total       0 days 00:10:14.896645
loss_total                         170.780201
loss_critic                        306.280441
loss_actor                        -371.220771
memory_size                        295112.825 

=== epoch 4/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:32,  2.88it/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 [10:15<00:00,  3.25it/s]
episodes                                    6
episode_length                         1000.0
returns                            -15.314607
return_std                           25.92561
average_reward                      -0.015315
round_time             0 days 00:10:16.379569
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       541.096938
return_std_test                     70.099761
average_reward_test                  0.541097
round_time_test        0 days 00:00:07.554137
round_time_total       0 days 00:10:16.380661
loss_total                          181.67631
loss_critic                        320.026361
loss_actor                        -371.723903
memory_size                        297060.825 

=== epoch 4/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:38,  3.12it/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 [10:19<00:00,  3.23it/s]
episodes                                    8
episode_length                         1000.0
returns                            -17.321826
return_std                          23.841075
average_reward                      -0.017322
round_time             0 days 00:10:19.854973
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       459.859417
return_std_test                     69.704712
average_reward_test                  0.459859
round_time_test        0 days 00:00:07.613920
round_time_total       0 days 00:10:19.856257
loss_total                         177.790819
loss_critic                        315.311436
loss_actor                        -372.291663
memory_size                        299008.825 

=== epoch 4/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:01,  3.01it/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 [10:14<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            -13.162914
return_std                          23.433057
average_reward                      -0.013163
round_time             0 days 00:10:15.252789
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       586.723522
return_std_test                     61.235744
average_reward_test                  0.586724
round_time_test        0 days 00:00:07.560959
round_time_total       0 days 00:10:15.254053
loss_total                         176.815812
loss_critic                        314.253088
loss_actor                        -372.933303
memory_size                        300956.825 

=== epoch 4/10 ===== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<12:03,  2.76it/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 [10:15<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            -17.726165
return_std                          24.666761
average_reward                      -0.017726
round_time             0 days 00:10:16.509721
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       616.197905
return_std_test                     76.596771
average_reward_test                  0.616198
round_time_test        0 days 00:00:07.609453
round_time_total       0 days 00:10:16.510997
loss_total                         181.821859
loss_critic                        320.570674
loss_actor                        -373.173413
memory_size                        302904.825 

=== epoch 4/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:18,  2.94it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            -14.337651
return_std                          25.471863
average_reward                      -0.014338
round_time             0 days 00:10:18.453374
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       592.357031
return_std_test                     69.728561
average_reward_test                  0.592357
round_time_test        0 days 00:00:07.407157
round_time_total       0 days 00:10:18.454492
loss_total                         173.154254
loss_critic                        309.862179
loss_actor                        -373.677461
memory_size                        304852.825 

=== epoch 4/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:49,  3.07it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            -22.050154
return_std                          29.601992
average_reward                       -0.02205
round_time             0 days 00:10:17.712898
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       575.175334
return_std_test                     64.626782
average_reward_test                  0.575175
round_time_test        0 days 00:00:07.511578
round_time_total       0 days 00:10:17.714194
loss_total                         180.070847
loss_critic                        318.657298
loss_actor                        -374.274969
memory_size                        306800.825 

=== epoch 4/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:43,  2.83it/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 [10:18<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            -13.192571
return_std                          34.101365
average_reward                      -0.013193
round_time             0 days 00:10:18.712097
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       603.378312
return_std_test                     57.854375
average_reward_test                  0.603378
round_time_test        0 days 00:00:07.353784
round_time_total       0 days 00:10:18.713417
loss_total                         184.005091
loss_critic                        323.730011
loss_actor                        -374.894602
memory_size                        308748.825 

=== epoch 4/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:31,  3.16it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            -13.516228
return_std                          33.668057
average_reward                      -0.013516
round_time             0 days 00:10:20.158986
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       566.425879
return_std_test                      60.98962
average_reward_test                  0.566426
round_time_test        0 days 00:00:07.555068
round_time_total       0 days 00:10:20.160122
loss_total                         181.162212
loss_critic                        320.342564
loss_actor                        -375.559206
memory_size                        310696.825 

=== epoch 4/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:41,  3.11it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                              2.227537
return_std                          39.407971
average_reward                       0.002228
round_time             0 days 00:10:19.406359
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       529.531771
return_std_test                     67.174413
average_reward_test                  0.529532
round_time_test        0 days 00:00:07.678261
round_time_total       0 days 00:10:19.407463
loss_total                         179.814749
loss_critic                        318.831992
loss_actor                        -376.254238
memory_size                        312644.825 

=== epoch 4/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:36,  3.13it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                              5.812475
return_std                          39.732408
average_reward                       0.005812
round_time             0 days 00:10:22.336388
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       568.257452
return_std_test                     70.713233
average_reward_test                  0.568257
round_time_test        0 days 00:00:07.589961
round_time_total       0 days 00:10:22.337742
loss_total                         178.986236
loss_critic                        318.002646
loss_actor                        -377.079416
memory_size                        314592.825 

=== epoch 4/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:17,  2.95it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                             13.381446
return_std                            27.6873
average_reward                       0.013381
round_time             0 days 00:10:20.795632
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       470.646997
return_std_test                     85.817467
average_reward_test                  0.470647
round_time_test        0 days 00:00:07.647060
round_time_total       0 days 00:10:20.796743
loss_total                          185.79464
loss_critic                        326.677256
loss_actor                        -377.735836
memory_size                        316540.825 

=== epoch 4/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<11:26,  2.91it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                             21.456782
return_std                          35.527308
average_reward                       0.021457
round_time             0 days 00:10:20.807074
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       589.006127
return_std_test                     63.860832
average_reward_test                  0.589006
round_time_test        0 days 00:00:07.513743
round_time_total       0 days 00:10:20.808327
loss_total                         183.021365
loss_critic                        323.463768
loss_actor                         -378.74826
memory_size                        318488.825 

=== epoch 4/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:18,  2.94it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             20.529453
return_std                          37.113958
average_reward                       0.020529
round_time             0 days 00:10:23.345861
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       603.045764
return_std_test                     93.315047
average_reward_test                  0.603046
round_time_test        0 days 00:00:07.521633
round_time_total       0 days 00:10:23.346967
loss_total                         180.482302
loss_critic                        320.438238
loss_actor                        -379.341456
memory_size                        320436.825 

=== epoch 4/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:25,  3.19it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                             18.070099
return_std                          47.337205
average_reward                        0.01807
round_time             0 days 00:10:22.196919
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       564.815582
return_std_test                     69.577003
average_reward_test                  0.564816
round_time_test        0 days 00:00:07.571738
round_time_total       0 days 00:10:22.198221
loss_total                         184.144855
loss_critic                        325.183286
loss_actor                        -380.008881
memory_size                        322384.825 

=== epoch 4/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:27,  3.18it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                             32.716085
return_std                          58.063256
average_reward                       0.032716
round_time             0 days 00:10:22.112345
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       586.670114
return_std_test                     69.142869
average_reward_test                   0.58667
round_time_test        0 days 00:00:07.525837
round_time_total       0 days 00:10:22.113472
loss_total                         181.526488
loss_critic                        321.993541
loss_actor                        -380.341736
memory_size                        324332.825 

=== epoch 4/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:58,  3.03it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             42.535441
return_std                          52.320132
average_reward                       0.042535
round_time             0 days 00:10:23.210435
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       561.859341
return_std_test                     89.491159
average_reward_test                  0.561859
round_time_test        0 days 00:00:07.445190
round_time_total       0 days 00:10:23.211525
loss_total                         181.502001
loss_critic                        322.231535
loss_actor                        -381.416148
memory_size                        326280.825 

=== epoch 4/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:45,  3.09it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             44.489213
return_std                          53.225277
average_reward                       0.044489
round_time             0 days 00:10:23.697021
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       597.590414
return_std_test                     88.007941
average_reward_test                   0.59759
round_time_test        0 days 00:00:07.723875
round_time_total       0 days 00:10:23.698249
loss_total                         181.917407
loss_critic                        323.037301
loss_actor                         -382.56218
memory_size                        328228.825 

=== epoch 4/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<12:01,  2.77it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                             64.902351
return_std                          52.698732
average_reward                       0.064902
round_time             0 days 00:10:25.549215
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       597.589374
return_std_test                     57.393544
average_reward_test                  0.597589
round_time_test        0 days 00:00:07.612713
round_time_total       0 days 00:10:25.550325
loss_total                         181.473241
loss_critic                        322.694391
loss_actor                         -383.41137
memory_size                        330176.825 

=== epoch 4/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:51,  3.06it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             72.692896
return_std                          35.210961
average_reward                       0.072693
round_time             0 days 00:10:23.633405
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        553.88765
return_std_test                     59.557929
average_reward_test                  0.553888
round_time_test        0 days 00:00:07.464772
round_time_total       0 days 00:10:23.634510
loss_total                         184.876245
loss_critic                        327.180915
loss_actor                        -384.342445
memory_size                        332124.825 

=== epoch 4/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:55,  3.04it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                             83.369631
return_std                          50.147381
average_reward                        0.08337
round_time             0 days 00:10:22.083106
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        660.11986
return_std_test                     56.293078
average_reward_test                   0.66012
round_time_test        0 days 00:00:07.595425
round_time_total       0 days 00:10:22.084316
loss_total                         185.508643
loss_critic                        328.145674
loss_actor                        -385.039494
memory_size                        334072.825 

=== epoch 4/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:20,  2.93it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            107.087078
return_std                          48.001231
average_reward                       0.107087
round_time             0 days 00:10:25.389932
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       595.859875
return_std_test                     60.760115
average_reward_test                   0.59586
round_time_test        0 days 00:00:07.413798
round_time_total       0 days 00:10:25.391044
loss_total                         188.817744
loss_critic                        332.537485
loss_actor                        -386.061232
memory_size                        336020.825 

=== epoch 4/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:04,  3.00it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                             99.592602
return_std                          55.486171
average_reward                       0.099593
round_time             0 days 00:10:22.035160
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       638.100371
return_std_test                     57.804303
average_reward_test                    0.6381
round_time_test        0 days 00:00:07.514963
round_time_total       0 days 00:10:22.036246
loss_total                         192.447419
loss_critic                        337.287576
loss_actor                        -386.913224
memory_size                        337968.825 

=== epoch 4/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            104.947856
return_std                          55.772628
average_reward                       0.104948
round_time             0 days 00:10:21.480931
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       605.753035
return_std_test                     62.262969
average_reward_test                  0.605753
round_time_test        0 days 00:00:06.986851
round_time_total       0 days 00:10:21.482063
loss_total                         189.753559
loss_critic                        334.135614
loss_actor                        -387.774674
memory_size                        339916.825 

=== epoch 4/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:04,  3.00it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            102.930484
return_std                          58.699847
average_reward                        0.10293
round_time             0 days 00:10:26.032462
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       551.893215
return_std_test                     73.050425
average_reward_test                  0.551893
round_time_test        0 days 00:00:07.661874
round_time_total       0 days 00:10:26.033998
loss_total                         195.154624
loss_critic                        341.157874
loss_actor                        -388.858391
memory_size                        341864.825 

=== epoch 4/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:54,  3.05it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             99.331867
return_std                          51.619356
average_reward                       0.099332
round_time             0 days 00:10:24.145539
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       549.026566
return_std_test                      68.59389
average_reward_test                  0.549027
round_time_test        0 days 00:00:07.606898
round_time_total       0 days 00:10:24.146639
loss_total                         195.539002
loss_critic                        341.964394
loss_actor                        -390.162581
memory_size                        343812.825 

=== epoch 4/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:50,  3.06it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                             99.703387
return_std                          51.911863
average_reward                       0.099703
round_time             0 days 00:10:25.109936
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       583.355245
return_std_test                     55.468349
average_reward_test                  0.583355
round_time_test        0 days 00:00:07.484555
round_time_total       0 days 00:10:25.111389
loss_total                         195.979972
loss_critic                        342.846473
loss_actor                        -391.486044
memory_size                        345760.825 

=== epoch 4/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:40,  3.11it/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 [10:24<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            126.538406
return_std                          43.222668
average_reward                       0.126538
round_time             0 days 00:10:24.524244
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        587.68518
return_std_test                      67.77333
average_reward_test                  0.587685
round_time_test        0 days 00:00:07.538195
round_time_total       0 days 00:10:24.525388
loss_total                         197.847514
loss_critic                          345.4597
loss_actor                        -392.601242
memory_size                        347708.825 

=== epoch 4/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:05,  3.00it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            118.887775
return_std                          45.579677
average_reward                       0.118888
round_time             0 days 00:10:20.317455
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       554.172983
return_std_test                     50.083268
average_reward_test                  0.554173
round_time_test        0 days 00:00:07.532845
round_time_total       0 days 00:10:20.318550
loss_total                         198.320385
loss_critic                        346.243278
loss_actor                        -393.371198
memory_size                        349656.825 

=== epoch 4/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:08,  2.99it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            134.661183
return_std                          37.722352
average_reward                       0.134661
round_time             0 days 00:10:21.643988
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       632.232899
return_std_test                      61.32951
average_reward_test                  0.632233
round_time_test        0 days 00:00:07.611563
round_time_total       0 days 00:10:21.645263
loss_total                          196.29537
loss_critic                        344.101962
loss_actor                        -394.931013
memory_size                        351604.825 

=== epoch 4/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:48,  3.08it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            134.970917
return_std                          41.209605
average_reward                       0.134971
round_time             0 days 00:10:22.149594
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       584.693318
return_std_test                     54.938582
average_reward_test                  0.584693
round_time_test        0 days 00:00:07.462476
round_time_total       0 days 00:10:22.150690
loss_total                         200.507042
loss_critic                        349.619271
loss_actor                         -395.94189
memory_size                        353552.825 

=== epoch 4/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:44,  2.83it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            136.789383
return_std                          43.228176
average_reward                       0.136789
round_time             0 days 00:10:20.794602
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        662.16594
return_std_test                     93.427339
average_reward_test                  0.662166
round_time_test        0 days 00:00:07.389714
round_time_total       0 days 00:10:20.795680
loss_total                          199.78878
loss_critic                        348.971474
loss_actor                        -396.942009
memory_size                        355500.825 

=== epoch 4/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:08,  2.99it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            123.173525
return_std                          53.695779
average_reward                       0.123174
round_time             0 days 00:10:24.089329
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       594.673808
return_std_test                     58.281261
average_reward_test                  0.594674
round_time_test        0 days 00:00:07.604614
round_time_total       0 days 00:10:24.090440
loss_total                          199.88232
loss_critic                        349.282082
loss_actor                        -397.716738
memory_size                        357448.825 

=== epoch 4/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:56,  3.04it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            129.322007
return_std                          49.478209
average_reward                       0.129322
round_time             0 days 00:10:25.080445
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       676.858884
return_std_test                     68.874347
average_reward_test                  0.676859
round_time_test        0 days 00:00:07.652265
round_time_total       0 days 00:10:25.081604
loss_total                         199.061114
loss_critic                        348.522176
loss_actor                        -398.783147
memory_size                        359396.825 

=== epoch 4/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:48,  2.82it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            128.182235
return_std                          45.981217
average_reward                       0.128182
round_time             0 days 00:10:24.748017
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       642.946557
return_std_test                     52.174036
average_reward_test                  0.642947
round_time_test        0 days 00:00:07.598923
round_time_total       0 days 00:10:24.749263
loss_total                         202.761681
loss_critic                        353.201326
loss_actor                        -398.996914
memory_size                        361344.825 

=== epoch 4/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:21,  2.93it/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 [10:22<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            136.335519
return_std                          47.276031
average_reward                       0.136336
round_time             0 days 00:10:22.623549
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       641.750174
return_std_test                    104.924712
average_reward_test                   0.64175
round_time_test        0 days 00:00:07.658703
round_time_total       0 days 00:10:22.624756
loss_total                         203.277805
loss_critic                        354.005935
loss_actor                        -399.634728
memory_size                        363292.825 

=== epoch 4/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<12:04,  2.75it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            128.739036
return_std                          45.491438
average_reward                       0.128739
round_time             0 days 00:10:23.144040
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       705.733824
return_std_test                     47.179818
average_reward_test                  0.705734
round_time_test        0 days 00:00:07.450531
round_time_total       0 days 00:10:23.145139
loss_total                          204.86774
loss_critic                        356.201675
loss_actor                        -400.468011
memory_size                        365240.825 

=== epoch 4/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:41,  3.11it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            139.129126
return_std                           28.84018
average_reward                       0.139129
round_time             0 days 00:10:24.687747
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       643.505862
return_std_test                     66.121908
average_reward_test                  0.643506
round_time_test        0 days 00:00:07.513304
round_time_total       0 days 00:10:24.689049
loss_total                         205.641611
loss_critic                        357.372821
loss_actor                        -401.283241
memory_size                        367188.825 

=== epoch 4/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:16,  2.95it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            141.852329
return_std                          30.030622
average_reward                       0.141852
round_time             0 days 00:10:24.949663
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       622.886534
return_std_test                     85.438216
average_reward_test                  0.622887
round_time_test        0 days 00:00:07.554145
round_time_total       0 days 00:10:24.950772
loss_total                         203.437586
loss_critic                        354.832373
loss_actor                        -402.141575
memory_size                        369136.825 

=== epoch 4/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:45,  3.09it/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 [10:20<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            141.837241
return_std                          35.898572
average_reward                       0.141837
round_time             0 days 00:10:20.653095
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       574.948548
return_std_test                     75.799303
average_reward_test                  0.574949
round_time_test        0 days 00:00:07.662114
round_time_total       0 days 00:10:20.654198
loss_total                         206.137409
loss_critic                        358.459679
loss_actor                         -403.15169
memory_size                        371084.825 

=== epoch 4/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:15,  2.95it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            127.009447
return_std                          39.380314
average_reward                       0.127009
round_time             0 days 00:10:25.148206
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        617.16454
return_std_test                     50.425183
average_reward_test                  0.617165
round_time_test        0 days 00:00:07.603724
round_time_total       0 days 00:10:25.149291
loss_total                         207.482184
loss_critic                        360.261316
loss_actor                        -403.634358
memory_size                        373032.825 

=== epoch 4/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:39,  3.12it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            132.887235
return_std                           44.34159
average_reward                       0.132887
round_time             0 days 00:10:22.131537
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       665.600235
return_std_test                     58.166565
average_reward_test                    0.6656
round_time_test        0 days 00:00:07.559804
round_time_total       0 days 00:10:22.132666
loss_total                         204.355671
loss_critic                          356.4671
loss_actor                         -404.09006
memory_size                        374980.825 

=== epoch 4/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:57,  3.03it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                              131.9757
return_std                          43.605082
average_reward                       0.131976
round_time             0 days 00:10:24.334513
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       608.219649
return_std_test                     60.532646
average_reward_test                   0.60822
round_time_test        0 days 00:00:07.455755
round_time_total       0 days 00:10:24.335707
loss_total                         207.614702
loss_critic                        360.797886
loss_actor                        -405.118049
memory_size                        376928.825 

=== epoch 4/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:51,  3.06it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            140.888336
return_std                          45.275194
average_reward                       0.140888
round_time             0 days 00:10:23.883432
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       644.393885
return_std_test                     67.490397
average_reward_test                  0.644394
round_time_test        0 days 00:00:07.546131
round_time_total       0 days 00:10:23.884534
loss_total                         208.452857
loss_critic                        362.101166
loss_actor                        -406.140389
memory_size                        378876.825 

=== epoch 4/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:56,  3.04it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            157.150015
return_std                          46.815146
average_reward                        0.15715
round_time             0 days 00:10:25.572115
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       670.354974
return_std_test                     49.071731
average_reward_test                  0.670355
round_time_test        0 days 00:00:07.551567
round_time_total       0 days 00:10:25.573222
loss_total                         208.495473
loss_critic                        362.474458
loss_actor                         -407.42048
memory_size                        380824.825 

=== epoch 4/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:47,  3.08it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            155.462139
return_std                          45.370745
average_reward                       0.155462
round_time             0 days 00:10:23.423005
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       629.230112
return_std_test                     61.771632
average_reward_test                   0.62923
round_time_test        0 days 00:00:07.692194
round_time_total       0 days 00:10:23.424103
loss_total                         211.694296
loss_critic                        366.738218
loss_actor                        -408.481405
memory_size                        382772.825 

=== epoch 4/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:07,  2.99it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            146.592214
return_std                          49.148768
average_reward                       0.146592
round_time             0 days 00:10:26.229695
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       654.245888
return_std_test                     55.114907
average_reward_test                  0.654246
round_time_test        0 days 00:00:07.485140
round_time_total       0 days 00:10:26.230858
loss_total                         216.089566
loss_critic                        372.481769
loss_actor                        -409.479263
memory_size                        384720.825 

=== epoch 4/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:27,  2.90it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            153.844205
return_std                          51.789028
average_reward                       0.153844
round_time             0 days 00:10:25.100338
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       684.598686
return_std_test                      67.16268
average_reward_test                  0.684599
round_time_test        0 days 00:00:07.609403
round_time_total       0 days 00:10:25.101584
loss_total                           218.6496
loss_critic                        375.863833
loss_actor                        -410.207347
memory_size                        386668.825 

=== epoch 4/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:05,  3.00it/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 [10:22<00:00,  3.21it/s]
<GE123_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                            160.974673
return_std                          58.281451
average_reward                       0.160975
round_time             0 days 00:10:22.852900
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       633.048397
return_std_test                    107.759471
average_reward_test                  0.633048
round_time_test        0 days 00:00:07.482567
round_time_total       0 days 00:10:22.853979
loss_total                         217.728615
loss_critic                        375.064791
loss_actor                        -411.616105
memory_size                        388616.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 5/10 ===== round 1/50 ======================================
  0%|          | 6/2000 [00:01<10:29,  3.17it/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 [10:11<00:00,  3.27it/s]
episodes                                    2
episode_length                         1000.0
returns                            211.500945
return_std                          19.276993
average_reward                       0.211501
round_time             0 days 00:10:11.335387
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       638.629433
return_std_test                    115.223081
average_reward_test                  0.638629
round_time_test        0 days 00:00:07.540485
round_time_total       0 days 00:10:11.336719
loss_total                         219.978909
loss_critic                        378.098788
loss_actor                         -412.50062
memory_size                        390565.825 

=== epoch 5/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:35,  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 [10:14<00:00,  3.25it/s]
episodes                                    4
episode_length                         1000.0
returns                            190.962075
return_std                          26.583771
average_reward                       0.190962
round_time             0 days 00:10:14.945464
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       676.339992
return_std_test                     76.650301
average_reward_test                   0.67634
round_time_test        0 days 00:00:07.536579
round_time_total       0 days 00:10:14.946550
loss_total                         213.852851
loss_critic                        370.635976
loss_actor                        -413.279663
memory_size                        392513.825 

=== epoch 5/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:08,  2.98it/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 [10:14<00:00,  3.25it/s]
episodes                                    6
episode_length                         1000.0
returns                            183.242981
return_std                          25.603501
average_reward                       0.183243
round_time             0 days 00:10:15.439808
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       664.275495
return_std_test                     93.525944
average_reward_test                  0.664275
round_time_test        0 days 00:00:07.747238
round_time_total       0 days 00:10:15.441114
loss_total                         219.839896
loss_critic                        378.250562
loss_actor                        -413.802782
memory_size                        394461.825 

=== epoch 5/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:48,  3.08it/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 [10:19<00:00,  3.23it/s]
episodes                                    8
episode_length                         1000.0
returns                            183.748302
return_std                          33.049944
average_reward                       0.183748
round_time             0 days 00:10:19.659957
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       716.300379
return_std_test                     98.279478
average_reward_test                    0.7163
round_time_test        0 days 00:00:07.675618
round_time_total       0 days 00:10:19.661229
loss_total                         217.701931
loss_critic                        375.666985
loss_actor                          -414.1583
memory_size                        396409.825 

=== epoch 5/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:08,  2.99it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            176.811947
return_std                          32.774005
average_reward                       0.176812
round_time             0 days 00:10:17.924972
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        661.78482
return_std_test                      50.46409
average_reward_test                  0.661785
round_time_test        0 days 00:00:07.559411
round_time_total       0 days 00:10:17.926067
loss_total                         225.312533
loss_critic                        385.309483
loss_actor                        -414.675281
memory_size                        398357.825 

=== epoch 5/10 ===== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:43,  3.10it/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 [10:18<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            181.214671
return_std                          37.241725
average_reward                       0.181215
round_time             0 days 00:10:18.999091
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       693.097213
return_std_test                     64.627464
average_reward_test                  0.693097
round_time_test        0 days 00:00:07.529839
round_time_total       0 days 00:10:19.000175
loss_total                         222.025494
loss_critic                        381.387379
loss_actor                        -415.422058
memory_size                        400305.825 

=== epoch 5/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:09,  2.98it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            196.750695
return_std                          45.008929
average_reward                       0.196751
round_time             0 days 00:10:18.502441
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       631.297955
return_std_test                     68.379799
average_reward_test                  0.631298
round_time_test        0 days 00:00:07.579017
round_time_total       0 days 00:10:18.503534
loss_total                         224.617144
loss_critic                        384.838643
loss_actor                        -416.268868
memory_size                        402253.825 

=== epoch 5/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:19,  2.93it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            209.868145
return_std                          44.117421
average_reward                       0.209868
round_time             0 days 00:10:20.026387
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       684.114172
return_std_test                     75.575806
average_reward_test                  0.684114
round_time_test        0 days 00:00:07.627610
round_time_total       0 days 00:10:20.027556
loss_total                         225.148139
loss_critic                        385.849398
loss_actor                        -417.656914
memory_size                        404201.825 

=== epoch 5/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:51,  3.06it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            189.458714
return_std                          64.359573
average_reward                       0.189459
round_time             0 days 00:10:20.884337
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       735.800934
return_std_test                     54.605778
average_reward_test                  0.735801
round_time_test        0 days 00:00:07.677086
round_time_total       0 days 00:10:20.885472
loss_total                         229.351435
loss_critic                        391.206697
loss_actor                        -418.069629
memory_size                        406149.825 

=== epoch 5/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:00,  3.02it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            200.757276
return_std                          63.464094
average_reward                       0.200757
round_time             0 days 00:10:18.292397
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       665.022979
return_std_test                     89.356947
average_reward_test                  0.665023
round_time_test        0 days 00:00:07.543411
round_time_total       0 days 00:10:18.293497
loss_total                         226.969885
loss_critic                        388.406716
loss_actor                        -418.777449
memory_size                        408097.825 

=== epoch 5/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:36,  3.13it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            191.912426
return_std                          62.235362
average_reward                       0.191912
round_time             0 days 00:10:21.537608
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       689.530962
return_std_test                     58.888772
average_reward_test                  0.689531
round_time_test        0 days 00:00:07.647104
round_time_total       0 days 00:10:21.538704
loss_total                          230.17555
loss_critic                        392.761131
loss_actor                        -420.166788
memory_size                        410045.825 

=== epoch 5/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:38,  3.12it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            167.936967
return_std                          65.784453
average_reward                       0.167937
round_time             0 days 00:10:22.355289
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       705.850188
return_std_test                     83.224065
average_reward_test                   0.70585
round_time_test        0 days 00:00:07.471343
round_time_total       0 days 00:10:22.356423
loss_total                         233.834903
loss_critic                         397.52606
loss_actor                        -420.929737
memory_size                        411993.825 

=== epoch 5/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:40,  3.12it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            154.813126
return_std                          63.724421
average_reward                       0.154813
round_time             0 days 00:10:19.893367
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       673.034444
return_std_test                    101.318596
average_reward_test                  0.673034
round_time_test        0 days 00:00:07.592037
round_time_total       0 days 00:10:19.894492
loss_total                         235.938884
loss_critic                        400.315022
loss_actor                        -421.565686
memory_size                        413941.825 

=== epoch 5/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:43,  3.10it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            175.733212
return_std                          55.395686
average_reward                       0.175733
round_time             0 days 00:10:22.065604
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       684.697419
return_std_test                     35.758174
average_reward_test                  0.684697
round_time_test        0 days 00:00:07.481245
round_time_total       0 days 00:10:22.066704
loss_total                          235.99276
loss_critic                         400.49438
loss_actor                        -422.013733
memory_size                        415889.825 

=== epoch 5/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:16,  2.95it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            182.850055
return_std                           58.39999
average_reward                        0.18285
round_time             0 days 00:10:23.207405
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       676.866085
return_std_test                     52.182594
average_reward_test                  0.676866
round_time_test        0 days 00:00:07.595597
round_time_total       0 days 00:10:23.208549
loss_total                         233.636836
loss_critic                        397.680721
loss_actor                        -422.538718
memory_size                        417837.825 

=== epoch 5/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:13,  2.96it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            183.173294
return_std                          64.802175
average_reward                       0.183173
round_time             0 days 00:10:20.549368
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       696.363446
return_std_test                     66.787449
average_reward_test                  0.696363
round_time_test        0 days 00:00:07.447815
round_time_total       0 days 00:10:20.550457
loss_total                         234.988274
loss_critic                        399.563994
loss_actor                        -423.314622
memory_size                        419785.825 

=== epoch 5/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:43,  3.10it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            217.977396
return_std                          71.567642
average_reward                       0.217977
round_time             0 days 00:10:22.729312
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       669.342037
return_std_test                     45.870554
average_reward_test                  0.669342
round_time_test        0 days 00:00:07.510335
round_time_total       0 days 00:10:22.730563
loss_total                         237.474527
loss_critic                        402.774616
loss_actor                        -423.725841
memory_size                        421733.825 

=== epoch 5/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:38,  3.12it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            234.847296
return_std                          63.061155
average_reward                       0.234847
round_time             0 days 00:10:21.056616
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       652.147969
return_std_test                     70.703451
average_reward_test                  0.652148
round_time_test        0 days 00:00:07.534648
round_time_total       0 days 00:10:21.057907
loss_total                         235.182571
loss_critic                         400.08954
loss_actor                         -424.44532
memory_size                        423681.825 

=== epoch 5/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:18,  2.94it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            247.532068
return_std                          56.353773
average_reward                       0.247532
round_time             0 days 00:10:20.097359
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       673.972245
return_std_test                     48.546069
average_reward_test                  0.673972
round_time_test        0 days 00:00:07.596202
round_time_total       0 days 00:10:20.098624
loss_total                         236.278001
loss_critic                         401.55951
loss_actor                        -424.848053
memory_size                        425629.825 

=== epoch 5/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:15,  2.95it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            244.197482
return_std                          63.270076
average_reward                       0.244197
round_time             0 days 00:10:22.960410
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       665.983848
return_std_test                     73.696267
average_reward_test                  0.665984
round_time_test        0 days 00:00:07.683121
round_time_total       0 days 00:10:22.961801
loss_total                         236.817076
loss_critic                        402.328761
loss_actor                        -425.229681
memory_size                        427577.825 

=== epoch 5/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:04,  3.00it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            241.022697
return_std                          59.139025
average_reward                       0.241023
round_time             0 days 00:10:22.475091
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       678.682707
return_std_test                     54.584422
average_reward_test                  0.678683
round_time_test        0 days 00:00:07.595807
round_time_total       0 days 00:10:22.476299
loss_total                         236.929932
loss_critic                        402.714019
loss_actor                        -426.206429
memory_size                        429525.825 

=== epoch 5/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<11:50,  2.81it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            227.402679
return_std                          55.274655
average_reward                       0.227403
round_time             0 days 00:10:22.972479
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       661.154131
return_std_test                     47.634543
average_reward_test                  0.661154
round_time_test        0 days 00:00:07.744942
round_time_total       0 days 00:10:22.973583
loss_total                         242.196866
loss_critic                        409.450824
loss_actor                        -426.818982
memory_size                        431473.825 

=== epoch 5/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:29,  3.17it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            212.406095
return_std                           54.91564
average_reward                       0.212406
round_time             0 days 00:10:21.802045
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       698.980171
return_std_test                     46.029043
average_reward_test                   0.69898
round_time_test        0 days 00:00:07.548194
round_time_total       0 days 00:10:21.803630
loss_total                         243.546895
loss_critic                        411.222463
loss_actor                        -427.155393
memory_size                        433421.825 

=== epoch 5/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:42,  3.10it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            206.503065
return_std                          53.153649
average_reward                       0.206503
round_time             0 days 00:10:21.401881
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       715.311093
return_std_test                       42.7899
average_reward_test                  0.715311
round_time_test        0 days 00:00:07.529389
round_time_total       0 days 00:10:21.402980
loss_total                         242.734976
loss_critic                        410.216646
loss_actor                        -427.191719
memory_size                        435369.825 

=== epoch 5/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:49,  3.07it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            197.407385
return_std                          46.776055
average_reward                       0.197407
round_time             0 days 00:10:21.126358
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        692.24986
return_std_test                     68.238435
average_reward_test                   0.69225
round_time_test        0 days 00:00:07.370832
round_time_total       0 days 00:10:21.127457
loss_total                         242.135475
loss_critic                         409.74744
loss_actor                        -428.312402
memory_size                        437317.825 

=== epoch 5/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:15,  2.95it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            217.290889
return_std                          54.928442
average_reward                       0.217291
round_time             0 days 00:10:22.313857
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       676.886204
return_std_test                     78.878359
average_reward_test                  0.676886
round_time_test        0 days 00:00:07.715885
round_time_total       0 days 00:10:22.315087
loss_total                         246.241713
loss_critic                        415.176784
loss_actor                        -429.498585
memory_size                        439265.825 

=== epoch 5/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:29,  3.17it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            218.919522
return_std                          43.566221
average_reward                        0.21892
round_time             0 days 00:10:22.787016
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        688.82972
return_std_test                      30.74184
average_reward_test                   0.68883
round_time_test        0 days 00:00:07.676126
round_time_total       0 days 00:10:22.788141
loss_total                         244.869414
loss_critic                         413.61029
loss_actor                        -430.094104
memory_size                        441213.825 

=== epoch 5/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:41,  2.84it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            244.827705
return_std                           49.61892
average_reward                       0.244828
round_time             0 days 00:10:24.767984
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       701.773607
return_std_test                     48.724454
average_reward_test                  0.701774
round_time_test        0 days 00:00:07.443059
round_time_total       0 days 00:10:24.769093
loss_total                          249.64575
loss_critic                        419.770721
loss_actor                        -430.854147
memory_size                        443161.825 

=== epoch 5/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:59,  3.02it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            245.350733
return_std                          48.291445
average_reward                       0.245351
round_time             0 days 00:10:21.921502
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        670.04701
return_std_test                     74.785419
average_reward_test                  0.670047
round_time_test        0 days 00:00:07.519106
round_time_total       0 days 00:10:21.922640
loss_total                         248.768185
loss_critic                        418.779491
loss_actor                        -431.277051
memory_size                        445109.825 

=== epoch 5/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:17,  2.94it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            252.526944
return_std                          39.780138
average_reward                       0.252527
round_time             0 days 00:10:20.760704
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       687.222681
return_std_test                     65.531631
average_reward_test                  0.687223
round_time_test        0 days 00:00:07.557201
round_time_total       0 days 00:10:20.761825
loss_total                         248.791302
loss_critic                        418.882738
loss_actor                        -431.574456
memory_size                        447057.825 

=== epoch 5/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            226.339106
return_std                          55.463398
average_reward                       0.226339
round_time             0 days 00:10:21.735899
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       734.342556
return_std_test                     50.439146
average_reward_test                  0.734343
round_time_test        0 days 00:00:07.485768
round_time_total       0 days 00:10:21.737006
loss_total                         247.274129
loss_critic                        417.244767
loss_actor                        -432.608442
memory_size                        449005.825 

=== epoch 5/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:54,  3.05it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            212.275917
return_std                          61.104437
average_reward                       0.212276
round_time             0 days 00:10:20.047618
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       703.759348
return_std_test                     74.918725
average_reward_test                  0.703759
round_time_test        0 days 00:00:07.592948
round_time_total       0 days 00:10:20.048707
loss_total                         257.145518
loss_critic                        429.657645
loss_actor                        -432.903007
memory_size                        450953.825 

=== epoch 5/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<11:14,  2.96it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            194.379838
return_std                          44.245845
average_reward                        0.19438
round_time             0 days 00:10:23.156196
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       723.559825
return_std_test                     89.637121
average_reward_test                   0.72356
round_time_test        0 days 00:00:07.568883
round_time_total       0 days 00:10:23.157288
loss_total                         250.876903
loss_critic                         421.91667
loss_actor                        -433.282183
memory_size                        452901.825 

=== epoch 5/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:37,  3.13it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            183.468418
return_std                          42.719989
average_reward                       0.183468
round_time             0 days 00:10:23.686262
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       682.107914
return_std_test                     85.962464
average_reward_test                  0.682108
round_time_test        0 days 00:00:07.634555
round_time_total       0 days 00:10:23.687355
loss_total                         259.662007
loss_critic                        432.832642
loss_actor                        -433.020548
memory_size                        454849.825 

=== epoch 5/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<11:23,  2.92it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            186.833955
return_std                          51.115394
average_reward                       0.186834
round_time             0 days 00:10:22.455798
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       710.055777
return_std_test                     47.525525
average_reward_test                  0.710056
round_time_test        0 days 00:00:07.476379
round_time_total       0 days 00:10:22.457008
loss_total                         250.585954
loss_critic                        421.629346
loss_actor                        -433.587631
memory_size                        456797.825 

=== epoch 5/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:50,  3.07it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            204.608365
return_std                          52.002489
average_reward                       0.204608
round_time             0 days 00:10:25.353415
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       745.438252
return_std_test                     37.658869
average_reward_test                  0.745438
round_time_test        0 days 00:00:07.439276
round_time_total       0 days 00:10:25.354504
loss_total                         252.213205
loss_critic                        423.778686
loss_actor                         -434.04873
memory_size                        458745.825 

=== epoch 5/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:56,  3.04it/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 [10:24<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            221.140865
return_std                          48.150207
average_reward                       0.221141
round_time             0 days 00:10:24.574385
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       744.168224
return_std_test                     76.924389
average_reward_test                  0.744168
round_time_test        0 days 00:00:07.689217
round_time_total       0 days 00:10:24.575494
loss_total                         259.052625
loss_critic                        432.416252
loss_actor                        -434.401896
memory_size                        460693.825 

=== epoch 5/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:54,  2.79it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                             231.71097
return_std                          48.438929
average_reward                       0.231711
round_time             0 days 00:10:25.747895
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       684.078449
return_std_test                     39.166654
average_reward_test                  0.684078
round_time_test        0 days 00:00:07.603689
round_time_total       0 days 00:10:25.749067
loss_total                         254.760241
loss_critic                        427.246403
loss_actor                        -435.184418
memory_size                        462641.825 

=== epoch 5/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:12,  2.97it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            256.495258
return_std                          40.749534
average_reward                       0.256495
round_time             0 days 00:10:24.777752
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       632.452119
return_std_test                     83.089923
average_reward_test                  0.632452
round_time_test        0 days 00:00:07.426725
round_time_total       0 days 00:10:24.778881
loss_total                         255.668005
loss_critic                        428.451173
loss_actor                         -435.46468
memory_size                        464589.825 

=== epoch 5/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:04,  3.00it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            261.136341
return_std                          41.316779
average_reward                       0.261136
round_time             0 days 00:10:23.361573
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       708.161951
return_std_test                     50.035126
average_reward_test                  0.708162
round_time_test        0 days 00:00:07.615088
round_time_total       0 days 00:10:23.362703
loss_total                           250.2329
loss_critic                        421.829066
loss_actor                        -436.151782
memory_size                        466537.825 

=== epoch 5/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:29,  2.90it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            248.212028
return_std                          51.991261
average_reward                       0.248212
round_time             0 days 00:10:24.940628
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       657.155053
return_std_test                     57.879912
average_reward_test                  0.657155
round_time_test        0 days 00:00:07.528603
round_time_total       0 days 00:10:24.941709
loss_total                         257.822829
loss_critic                        431.271279
loss_actor                        -435.970991
memory_size                        468485.825 

=== epoch 5/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:56,  3.04it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            253.207313
return_std                           58.56245
average_reward                       0.253207
round_time             0 days 00:10:23.584005
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       717.854582
return_std_test                     76.744608
average_reward_test                  0.717855
round_time_test        0 days 00:00:07.495080
round_time_total       0 days 00:10:23.585133
loss_total                         252.981127
loss_critic                         425.30488
loss_actor                        -436.313899
memory_size                        470433.825 

=== epoch 5/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:57,  3.04it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            234.674566
return_std                          65.248067
average_reward                       0.234675
round_time             0 days 00:10:22.061077
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       702.573098
return_std_test                     55.428844
average_reward_test                  0.702573
round_time_test        0 days 00:00:07.637759
round_time_total       0 days 00:10:22.062196
loss_total                         253.622317
loss_critic                        426.198392
loss_actor                        -436.681994
memory_size                        472381.825 

=== epoch 5/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:11,  2.97it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            225.674372
return_std                          63.325333
average_reward                       0.225674
round_time             0 days 00:10:23.756539
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       703.641555
return_std_test                     91.967921
average_reward_test                  0.703642
round_time_test        0 days 00:00:07.627978
round_time_total       0 days 00:10:23.757715
loss_total                          259.07852
loss_critic                        433.129527
loss_actor                        -437.125526
memory_size                        474329.825 

=== epoch 5/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:35,  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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            224.095166
return_std                          57.215164
average_reward                       0.224095
round_time             0 days 00:10:25.739681
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       716.449755
return_std_test                     61.550805
average_reward_test                   0.71645
round_time_test        0 days 00:00:07.615014
round_time_total       0 days 00:10:25.740779
loss_total                         259.607447
loss_critic                        433.969173
loss_actor                        -437.839474
memory_size                        476277.825 

=== epoch 5/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:13,  2.96it/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 [10:25<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            235.949009
return_std                          52.401681
average_reward                       0.235949
round_time             0 days 00:10:25.902618
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        726.72428
return_std_test                     43.725057
average_reward_test                  0.726724
round_time_test        0 days 00:00:07.517867
round_time_total       0 days 00:10:25.903785
loss_total                         264.612081
loss_critic                        440.503903
loss_actor                         -438.95522
memory_size                        478225.825 

=== epoch 5/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:18,  2.94it/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 [10:24<00:00,  3.20it/s]
episodes                                   10
episode_length                         1000.0
returns                             218.15898
return_std                          43.838451
average_reward                       0.218159
round_time             0 days 00:10:25.335746
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        721.85723
return_std_test                     58.753148
average_reward_test                  0.721857
round_time_test        0 days 00:00:07.530517
round_time_total       0 days 00:10:25.336845
loss_total                         262.218805
loss_critic                        437.742622
loss_actor                        -439.876479
memory_size                        480173.825 

=== epoch 5/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:30,  3.17it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            246.015398
return_std                          52.171589
average_reward                       0.246015
round_time             0 days 00:10:24.073505
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       685.699788
return_std_test                     58.833282
average_reward_test                    0.6857
round_time_test        0 days 00:00:07.583511
round_time_total       0 days 00:10:24.074613
loss_total                         263.421068
loss_critic                        439.357491
loss_actor                        -440.324637
memory_size                        482121.825 

=== epoch 5/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:53,  3.05it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            247.435778
return_std                          47.810355
average_reward                       0.247436
round_time             0 days 00:10:24.465340
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       709.008515
return_std_test                      56.57815
average_reward_test                  0.709009
round_time_test        0 days 00:00:07.526932
round_time_total       0 days 00:10:24.466875
loss_total                         263.306489
loss_critic                        439.341828
loss_actor                        -440.834884
memory_size                        484069.825 

=== epoch 5/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<11:36,  2.86it/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 [10:21<00:00,  3.22it/s]
<GE123_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                            256.682785
return_std                          51.405783
average_reward                       0.256683
round_time             0 days 00:10:22.360391
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       666.749024
return_std_test                     65.176955
average_reward_test                  0.666749
round_time_test        0 days 00:00:07.480950
round_time_total       0 days 00:10:22.361498
loss_total                         264.300207
loss_critic                        440.758886
loss_actor                        -441.534523
memory_size                        486017.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 6/10 ===== round 1/50 ======================================
  0%|          | 6/2000 [00:01<10:43,  3.10it/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 [10:11<00:00,  3.27it/s]
episodes                                    2
episode_length                         1000.0
returns                             283.88721
return_std                           8.115857
average_reward                       0.283887
round_time             0 days 00:10:11.390897
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       705.284027
return_std_test                     60.889736
average_reward_test                  0.705284
round_time_test        0 days 00:00:07.558779
round_time_total       0 days 00:10:11.391994
loss_total                         262.055322
loss_critic                        438.163739
loss_actor                        -442.378364
memory_size                        487966.825 

=== epoch 6/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:21,  3.21it/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 [10:15<00:00,  3.25it/s]
episodes                                    4
episode_length                         1000.0
returns                            300.190176
return_std                          53.285381
average_reward                        0.30019
round_time             0 days 00:10:15.855720
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       732.229125
return_std_test                     74.394592
average_reward_test                  0.732229
round_time_test        0 days 00:00:07.480912
round_time_total       0 days 00:10:15.857175
loss_total                         265.593261
loss_critic                        442.661483
loss_actor                        -442.679644
memory_size                        489914.825 

=== epoch 6/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:15,  2.95it/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 [10:15<00:00,  3.25it/s]
episodes                                    6
episode_length                         1000.0
returns                            296.280936
return_std                          61.823426
average_reward                       0.296281
round_time             0 days 00:10:15.621242
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       701.018364
return_std_test                     59.584548
average_reward_test                  0.701018
round_time_test        0 days 00:00:07.763648
round_time_total       0 days 00:10:15.622320
loss_total                         263.689105
loss_critic                        440.347756
loss_actor                        -442.945516
memory_size                        491862.825 

=== epoch 6/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:06,  2.99it/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 [10:18<00:00,  3.23it/s]
episodes                                    8
episode_length                         1000.0
returns                            271.664189
return_std                           74.84668
average_reward                       0.271664
round_time             0 days 00:10:19.301287
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        688.29946
return_std_test                     46.904022
average_reward_test                  0.688299
round_time_test        0 days 00:00:07.426809
round_time_total       0 days 00:10:19.302394
loss_total                         265.138493
loss_critic                        442.228614
loss_actor                        -443.222005
memory_size                        493810.825 

=== epoch 6/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:47,  3.08it/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 [10:17<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            265.931057
return_std                          70.540565
average_reward                       0.265931
round_time             0 days 00:10:17.662043
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       689.345662
return_std_test                     63.379594
average_reward_test                  0.689346
round_time_test        0 days 00:00:07.595862
round_time_total       0 days 00:10:17.663180
loss_total                         269.929611
loss_critic                        448.270069
loss_actor                        -443.432236
memory_size                        495758.825 

=== epoch 6/10 ===== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:26,  2.91it/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 [10:16<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            254.812758
return_std                          80.006623
average_reward                       0.254813
round_time             0 days 00:10:17.214237
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       703.960133
return_std_test                     49.201263
average_reward_test                   0.70396
round_time_test        0 days 00:00:07.552120
round_time_total       0 days 00:10:17.215387
loss_total                         276.062181
loss_critic                        456.071414
loss_actor                        -443.974766
memory_size                        497706.825 

=== epoch 6/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:26,  2.91it/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 [10:16<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            235.613866
return_std                          72.466933
average_reward                       0.235614
round_time             0 days 00:10:16.999774
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       664.514715
return_std_test                     85.433459
average_reward_test                  0.664515
round_time_test        0 days 00:00:07.520910
round_time_total       0 days 00:10:17.000969
loss_total                         270.526504
loss_critic                        449.364994
loss_actor                        -444.827473
memory_size                        499654.825 

=== epoch 6/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:20,  2.93it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            219.452687
return_std                          63.677671
average_reward                       0.219453
round_time             0 days 00:10:22.202770
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       735.773222
return_std_test                     40.702993
average_reward_test                  0.735773
round_time_test        0 days 00:00:07.569624
round_time_total       0 days 00:10:22.203889
loss_total                         277.136214
loss_critic                        457.859515
loss_actor                        -445.757005
memory_size                        501602.825 

=== epoch 6/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:15,  2.96it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            244.944462
return_std                          69.902793
average_reward                       0.244944
round_time             0 days 00:10:19.798193
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       712.733967
return_std_test                     52.181558
average_reward_test                  0.712734
round_time_test        0 days 00:00:07.473858
round_time_total       0 days 00:10:19.799299
loss_total                         272.584446
loss_critic                        452.382587
loss_actor                        -446.608134
memory_size                        503550.825 

=== epoch 6/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:39,  3.12it/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 [10:19<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            252.385081
return_std                          69.240047
average_reward                       0.252385
round_time             0 days 00:10:20.292278
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       721.826041
return_std_test                     63.288945
average_reward_test                  0.721826
round_time_test        0 days 00:00:07.615516
round_time_total       0 days 00:10:20.293650
loss_total                         270.766942
loss_critic                        450.227862
loss_actor                        -447.076758
memory_size                        505498.825 

=== epoch 6/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:27,  2.90it/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 [10:20<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            263.112222
return_std                           63.62336
average_reward                       0.263112
round_time             0 days 00:10:20.608863
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       776.232751
return_std_test                     46.514941
average_reward_test                  0.776233
round_time_test        0 days 00:00:07.510576
round_time_total       0 days 00:10:20.609960
loss_total                         270.640625
loss_critic                        450.057804
loss_actor                        -447.028103
memory_size                        507446.825 

=== epoch 6/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:20,  2.93it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                             280.48041
return_std                          58.732611
average_reward                        0.28048
round_time             0 days 00:10:21.962616
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       732.863066
return_std_test                     37.074391
average_reward_test                  0.732863
round_time_test        0 days 00:00:07.428125
round_time_total       0 days 00:10:21.963702
loss_total                         276.740861
loss_critic                        457.877864
loss_actor                        -447.807166
memory_size                        509394.825 

=== epoch 6/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:27,  2.90it/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 [10:20<00:00,  3.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            292.436598
return_std                          45.185271
average_reward                       0.292437
round_time             0 days 00:10:20.604018
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       712.752213
return_std_test                     67.963008
average_reward_test                  0.712752
round_time_test        0 days 00:00:07.746517
round_time_total       0 days 00:10:20.605517
loss_total                         275.606254
loss_critic                        456.545539
loss_actor                        -448.150902
memory_size                        511342.825 

=== epoch 6/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:54,  2.79it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            276.752977
return_std                          44.850804
average_reward                       0.276753
round_time             0 days 00:10:20.856971
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       740.475161
return_std_test                     51.796674
average_reward_test                  0.740475
round_time_test        0 days 00:00:07.548292
round_time_total       0 days 00:10:20.858363
loss_total                         273.292968
loss_critic                        453.748877
loss_actor                        -448.530688
memory_size                        513290.825 

=== epoch 6/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:15,  3.24it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            271.967571
return_std                          44.838387
average_reward                       0.271968
round_time             0 days 00:10:20.757925
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       725.169145
return_std_test                     70.579303
average_reward_test                  0.725169
round_time_test        0 days 00:00:07.451515
round_time_total       0 days 00:10:20.759151
loss_total                         274.519387
loss_critic                        455.425622
loss_actor                        -449.105568
memory_size                        515238.825 

=== epoch 6/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:55,  3.04it/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 [10:21<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            272.382974
return_std                          37.173729
average_reward                       0.272383
round_time             0 days 00:10:21.858545
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       708.855893
return_std_test                     64.856157
average_reward_test                  0.708856
round_time_test        0 days 00:00:07.552505
round_time_total       0 days 00:10:21.859873
loss_total                         274.826548
loss_critic                        456.040541
loss_actor                        -450.029439
memory_size                        517186.825 

=== epoch 6/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:23,  2.92it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            260.500961
return_std                          32.767991
average_reward                       0.260501
round_time             0 days 00:10:22.816330
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       708.401366
return_std_test                     62.979734
average_reward_test                  0.708401
round_time_test        0 days 00:00:07.563075
round_time_total       0 days 00:10:22.817436
loss_total                          278.93167
loss_critic                        461.335184
loss_actor                        -450.682399
memory_size                        519134.825 

=== epoch 6/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:42,  2.84it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            271.657737
return_std                          36.859674
average_reward                       0.271658
round_time             0 days 00:10:21.022745
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       705.409615
return_std_test                     97.728333
average_reward_test                   0.70541
round_time_test        0 days 00:00:07.671252
round_time_total       0 days 00:10:21.023837
loss_total                         281.908017
loss_critic                        465.037229
loss_actor                         -450.60885
memory_size                        521082.825 

=== epoch 6/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:03,  3.01it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            275.134271
return_std                          34.832063
average_reward                       0.275134
round_time             0 days 00:10:23.584129
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       692.799226
return_std_test                     68.337078
average_reward_test                  0.692799
round_time_test        0 days 00:00:07.609992
round_time_total       0 days 00:10:23.585216
loss_total                         285.028036
loss_critic                        469.044504
loss_actor                        -451.037852
memory_size                        523030.825 

=== epoch 6/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            265.906008
return_std                          43.513976
average_reward                       0.265906
round_time             0 days 00:10:20.836933
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       783.170721
return_std_test                     47.584133
average_reward_test                  0.783171
round_time_test        0 days 00:00:07.433749
round_time_total       0 days 00:10:20.838050
loss_total                         284.290559
loss_critic                        468.175037
loss_actor                        -451.247366
memory_size                        524978.825 

=== epoch 6/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:52,  3.06it/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 [10:20<00:00,  3.22it/s]
episodes                                   10
episode_length                         1000.0
returns                             267.00383
return_std                          44.670415
average_reward                       0.267004
round_time             0 days 00:10:21.486072
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       693.101608
return_std_test                     79.520669
average_reward_test                  0.693102
round_time_test        0 days 00:00:07.427548
round_time_total       0 days 00:10:21.487202
loss_total                         279.000046
loss_critic                        461.657547
loss_actor                        -451.629975
memory_size                        526926.825 

=== epoch 6/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:18,  2.94it/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 [10:23<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            273.534703
return_std                          39.169492
average_reward                       0.273535
round_time             0 days 00:10:23.665441
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       719.465788
return_std_test                     74.546217
average_reward_test                  0.719466
round_time_test        0 days 00:00:07.633077
round_time_total       0 days 00:10:23.666721
loss_total                          288.34033
loss_critic                        473.463666
loss_actor                        -452.153032
memory_size                        528874.825 

=== epoch 6/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:49,  3.07it/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 [10:22<00:00,  3.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            261.825129
return_std                          31.013965
average_reward                       0.261825
round_time             0 days 00:10:22.634029
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       703.768028
return_std_test                     52.047429
average_reward_test                  0.703768
round_time_test        0 days 00:00:07.485895
round_time_total       0 days 00:10:22.635129
loss_total                         283.138913
loss_critic                        467.113082
loss_actor                        -452.757783
memory_size                        530822.825 

=== epoch 6/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:08,  2.98it/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 [10:14<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                             264.72883
return_std                          33.995973
average_reward                       0.264729
round_time             0 days 00:10:15.611991
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       730.304721
return_std_test                     80.936462
average_reward_test                  0.730305
round_time_test        0 days 00:00:07.695073
round_time_total       0 days 00:10:15.613269
loss_total                         288.419033
loss_critic                        473.789971
loss_actor                        -453.064734
memory_size                        532770.825 

=== epoch 6/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:07,  2.99it/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 [10:16<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            265.728972
return_std                          32.258357
average_reward                       0.265729
round_time             0 days 00:10:17.100867
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       753.657312
return_std_test                     70.668201
average_reward_test                  0.753657
round_time_test        0 days 00:00:07.516984
round_time_total       0 days 00:10:17.102168
loss_total                         285.425275
loss_critic                        470.154638
loss_actor                        -453.492192
memory_size                        534718.825 

=== epoch 6/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:57,  3.03it/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 [10:16<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            259.792917
return_std                          30.220598
average_reward                       0.259793
round_time             0 days 00:10:16.974189
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       735.487406
return_std_test                     62.968055
average_reward_test                  0.735487
round_time_test        0 days 00:00:07.306949
round_time_total       0 days 00:10:16.975295
loss_total                         291.759089
loss_critic                        478.139433
loss_actor                        -453.762304
memory_size                        536666.825 

=== epoch 6/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:56,  3.04it/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 [10:14<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            250.663432
return_std                          30.708863
average_reward                       0.250663
round_time             0 days 00:10:15.183463
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        763.46351
return_std_test                     73.802429
average_reward_test                  0.763464
round_time_test        0 days 00:00:07.459534
round_time_total       0 days 00:10:15.184560
loss_total                         287.494136
loss_critic                        472.849258
loss_actor                        -453.926369
memory_size                        538614.825 

=== epoch 6/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 6/2000 [00:01<10:02,  3.31it/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 [10:15<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            242.102889
return_std                          30.908745
average_reward                       0.242103
round_time             0 days 00:10:15.857569
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       741.862701
return_std_test                     66.489306
average_reward_test                  0.741863
round_time_test        0 days 00:00:07.396484
round_time_total       0 days 00:10:15.858678
loss_total                         294.044087
loss_critic                        480.995418
loss_actor                        -453.761254
memory_size                        540562.825 

=== epoch 6/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:02,  3.01it/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 [10:13<00:00,  3.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            241.626154
return_std                           32.20691
average_reward                       0.241626
round_time             0 days 00:10:13.590588
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       678.443529
return_std_test                     70.027162
average_reward_test                  0.678444
round_time_test        0 days 00:00:07.498395
round_time_total       0 days 00:10:13.591885
loss_total                         290.205972
loss_critic                        476.197309
loss_actor                        -453.759391
memory_size                        542510.825 

=== epoch 6/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:04,  3.00it/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 [10:13<00:00,  3.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            253.213372
return_std                          47.574769
average_reward                       0.253213
round_time             0 days 00:10:14.211372
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       767.161001
return_std_test                     53.330585
average_reward_test                  0.767161
round_time_test        0 days 00:00:07.461609
round_time_total       0 days 00:10:14.212499
loss_total                         291.659036
loss_critic                        478.102598
loss_actor                        -454.115229
memory_size                        544458.825 

=== epoch 6/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:55,  3.05it/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 [10:16<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            250.569506
return_std                           46.57758
average_reward                        0.25057
round_time             0 days 00:10:16.953810
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       757.020095
return_std_test                     74.906261
average_reward_test                   0.75702
round_time_test        0 days 00:00:07.565333
round_time_total       0 days 00:10:16.954903
loss_total                         293.104725
loss_critic                        480.089568
loss_actor                        -454.834665
memory_size                        546406.825 

=== epoch 6/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:46,  3.08it/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 [10:16<00:00,  3.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            267.521687
return_std                          53.219452
average_reward                       0.267522
round_time             0 days 00:10:17.164652
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        759.00873
return_std_test                      48.32318
average_reward_test                  0.759009
round_time_test        0 days 00:00:07.552639
round_time_total       0 days 00:10:17.165750
loss_total                         290.839726
loss_critic                        477.437158
loss_actor                        -455.550018
memory_size                        548354.825 

=== epoch 6/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:52,  3.06it/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 [10:15<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            262.808043
return_std                          59.849081
average_reward                       0.262808
round_time             0 days 00:10:15.731618
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       778.225128
return_std_test                     36.271496
average_reward_test                  0.778225
round_time_test        0 days 00:00:07.381682
round_time_total       0 days 00:10:15.733150
loss_total                         292.502161
loss_critic                        479.629899
loss_actor                         -456.00881
memory_size                        550302.825 

=== epoch 6/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:36,  3.13it/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 [10:16<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                             257.77331
return_std                             59.513
average_reward                       0.257773
round_time             0 days 00:10:16.614174
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       742.727992
return_std_test                    100.073154
average_reward_test                  0.742728
round_time_test        0 days 00:00:07.448352
round_time_total       0 days 00:10:16.615336
loss_total                         297.969639
loss_critic                        486.403465
loss_actor                         -455.76568
memory_size                        552250.825 

=== epoch 6/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:07,  2.99it/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 [10:14<00:00,  3.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            255.013542
return_std                          56.631168
average_reward                       0.255014
round_time             0 days 00:10:14.633617
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       805.554275
return_std_test                     83.108345
average_reward_test                  0.805554
round_time_test        0 days 00:00:07.560683
round_time_total       0 days 00:10:14.634798
loss_total                           298.1517
loss_critic                        486.630256
loss_actor                        -455.762541
memory_size                        554198.825 

=== epoch 6/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:39,  3.12it/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 [10:15<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            258.725415
return_std                           57.95884
average_reward                       0.258725
round_time             0 days 00:10:16.343823
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         753.1008
return_std_test                     43.157989
average_reward_test                  0.753101
round_time_test        0 days 00:00:07.486312
round_time_total       0 days 00:10:16.344917
loss_total                         291.819611
loss_critic                        478.908029
loss_actor                        -456.534077
memory_size                        556146.825 

=== epoch 6/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:34,  3.15it/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 [10:15<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            240.600634
return_std                          52.910564
average_reward                       0.240601
round_time             0 days 00:10:15.811493
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       851.220014
return_std_test                     55.391381
average_reward_test                   0.85122
round_time_test        0 days 00:00:07.462311
round_time_total       0 days 00:10:15.812624
loss_total                         297.600546
loss_critic                        486.316648
loss_actor                         -457.26388
memory_size                        558094.825 

=== epoch 6/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:40,  3.11it/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 [10:16<00:00,  3.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            257.780305
return_std                          47.969626
average_reward                        0.25778
round_time             0 days 00:10:16.883134
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       746.517836
return_std_test                     83.305241
average_reward_test                  0.746518
round_time_test        0 days 00:00:07.436072
round_time_total       0 days 00:10:16.884225
loss_total                          301.37478
loss_critic                        491.141525
loss_actor                        -457.692217
memory_size                        560042.825 

=== epoch 6/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:58,  3.03it/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 [10:04<00:00,  3.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            256.767263
return_std                           45.03699
average_reward                       0.256767
round_time             0 days 00:10:05.111684
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       712.691439
return_std_test                     68.039137
average_reward_test                  0.712691
round_time_test        0 days 00:00:07.565694
round_time_total       0 days 00:10:05.112783
loss_total                         301.330365
loss_critic                        491.163253
loss_actor                        -458.001205
memory_size                        561990.825 

=== epoch 6/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:12,  3.26it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            270.771619
return_std                          49.575132
average_reward                       0.270772
round_time             0 days 00:09:30.282358
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       772.086433
return_std_test                     57.023758
average_reward_test                  0.772086
round_time_test        0 days 00:00:07.069544
round_time_total       0 days 00:09:30.283440
loss_total                         305.055229
loss_critic                        495.931491
loss_actor                         -458.44984
memory_size                        563938.825 

=== epoch 6/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:58,  3.34it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            276.996069
return_std                          54.231318
average_reward                       0.276996
round_time             0 days 00:09:30.842233
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       750.807588
return_std_test                     68.194613
average_reward_test                  0.750808
round_time_test        0 days 00:00:06.966937
round_time_total       0 days 00:09:30.843356
loss_total                         303.968228
loss_critic                        494.743764
loss_actor                        -459.133931
memory_size                        565886.825 

=== epoch 6/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:09,  3.28it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            288.381299
return_std                          49.605918
average_reward                       0.288381
round_time             0 days 00:09:30.574335
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        768.53363
return_std_test                    100.363092
average_reward_test                  0.768534
round_time_test        0 days 00:00:07.190997
round_time_total       0 days 00:09:30.575412
loss_total                          305.75099
loss_critic                         497.16749
loss_actor                        -459.915027
memory_size                        567834.825 

=== epoch 6/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:09,  3.27it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                             281.00651
return_std                          52.517754
average_reward                       0.281007
round_time             0 days 00:09:30.942010
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       782.837707
return_std_test                     46.610892
average_reward_test                  0.782838
round_time_test        0 days 00:00:07.076551
round_time_total       0 days 00:09:30.943114
loss_total                         308.376057
loss_critic                        500.568166
loss_actor                        -460.392399
memory_size                        569782.825 

=== epoch 6/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:54,  3.36it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            284.473214
return_std                          56.468439
average_reward                       0.284473
round_time             0 days 00:09:30.351399
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       741.565663
return_std_test                     90.957601
average_reward_test                  0.741566
round_time_test        0 days 00:00:07.100881
round_time_total       0 days 00:09:30.352497
loss_total                         305.738507
loss_critic                        497.349723
loss_actor                        -460.706376
memory_size                        571730.825 

=== epoch 6/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:41,  3.11it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            278.265124
return_std                          58.048788
average_reward                       0.278265
round_time             0 days 00:09:31.260326
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       737.417753
return_std_test                      72.25131
average_reward_test                  0.737418
round_time_test        0 days 00:00:06.913434
round_time_total       0 days 00:09:31.261404
loss_total                         309.796573
loss_critic                         502.42607
loss_actor                        -460.721435
memory_size                        573678.825 

=== epoch 6/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:18,  3.23it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            291.293899
return_std                          63.222968
average_reward                       0.291294
round_time             0 days 00:09:30.379179
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       776.827179
return_std_test                     50.909402
average_reward_test                  0.776827
round_time_test        0 days 00:00:07.109279
round_time_total       0 days 00:09:30.380261
loss_total                         312.199416
loss_critic                        505.427544
loss_actor                        -460.713114
memory_size                        575626.825 

=== epoch 6/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            291.981163
return_std                          58.909319
average_reward                       0.291981
round_time             0 days 00:09:30.309946
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       750.829177
return_std_test                     75.587851
average_reward_test                  0.750829
round_time_test        0 days 00:00:07.082901
round_time_total       0 days 00:09:30.311030
loss_total                         313.073465
loss_critic                        506.614474
loss_actor                        -461.090588
memory_size                        577574.825 

=== epoch 6/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:09,  3.27it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            289.472887
return_std                          60.824576
average_reward                       0.289473
round_time             0 days 00:09:31.562922
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       780.302218
return_std_test                     73.569631
average_reward_test                  0.780302
round_time_test        0 days 00:00:07.054376
round_time_total       0 days 00:09:31.564024
loss_total                         309.972611
loss_critic                        502.982289
loss_actor                         -462.06612
memory_size                        579522.825 

=== epoch 6/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            297.780834
return_std                          53.744134
average_reward                       0.297781
round_time             0 days 00:09:30.541842
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       745.539837
return_std_test                     73.301646
average_reward_test                   0.74554
round_time_test        0 days 00:00:06.996187
round_time_total       0 days 00:09:30.542932
loss_total                         310.349748
loss_critic                        503.553382
loss_actor                        -462.464811
memory_size                        581470.825 

=== epoch 6/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:06,  3.29it/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 [09:31<00:00,  3.50it/s]
<GE123_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                            292.554126
return_std                          42.587822
average_reward                       0.292554
round_time             0 days 00:09:31.850663
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       788.237861
return_std_test                     73.441619
average_reward_test                  0.788238
round_time_test        0 days 00:00:07.077985
round_time_total       0 days 00:09:31.851745
loss_total                         315.872814
loss_critic                        510.516699
loss_actor                         -462.70275
memory_size                        583418.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 7/10 ===== round 1/50 ======================================
  0%|          | 7/2000 [00:02<09:49,  3.38it/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 [09:21<00:00,  3.56it/s]
episodes                                    2
episode_length                         1000.0
returns                            242.022296
return_std                          34.698178
average_reward                       0.242022
round_time             0 days 00:09:21.480619
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       711.658675
return_std_test                    101.441875
average_reward_test                  0.711659
round_time_test        0 days 00:00:07.089852
round_time_total       0 days 00:09:21.481699
loss_total                         305.964112
loss_critic                        498.232793
loss_actor                         -463.11063
memory_size                        585367.825 

=== epoch 7/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:54,  3.35it/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 [09:23<00:00,  3.55it/s]
episodes                                    4
episode_length                         1000.0
returns                            290.724939
return_std                          54.534169
average_reward                       0.290725
round_time             0 days 00:09:23.641765
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        736.31876
return_std_test                       77.8274
average_reward_test                  0.736319
round_time_test        0 days 00:00:06.969170
round_time_total       0 days 00:09:23.642850
loss_total                         323.170717
loss_critic                         519.78417
loss_actor                        -463.283117
memory_size                        587315.825 

=== epoch 7/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:49,  3.38it/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 [09:25<00:00,  3.54it/s]
episodes                                    6
episode_length                         1000.0
returns                            292.680137
return_std                           44.65857
average_reward                        0.29268
round_time             0 days 00:09:25.566492
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       750.741192
return_std_test                     76.928767
average_reward_test                  0.750741
round_time_test        0 days 00:00:07.032800
round_time_total       0 days 00:09:25.567563
loss_total                         312.102605
loss_critic                        506.042388
loss_actor                        -463.656543
memory_size                        589263.825 

=== epoch 7/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:43,  3.42it/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 [09:25<00:00,  3.54it/s]
episodes                                    8
episode_length                         1000.0
returns                            293.218407
return_std                          42.398841
average_reward                       0.293218
round_time             0 days 00:09:26.222328
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       773.247432
return_std_test                    107.904469
average_reward_test                  0.773247
round_time_test        0 days 00:00:07.010945
round_time_total       0 days 00:09:26.223464
loss_total                         320.250965
loss_critic                        516.283588
loss_actor                        -463.879549
memory_size                        591211.825 

=== epoch 7/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:25,  3.19it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                             298.03962
return_std                          43.397535
average_reward                        0.29804
round_time             0 days 00:09:27.299895
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       776.219249
return_std_test                      68.46789
average_reward_test                  0.776219
round_time_test        0 days 00:00:07.075357
round_time_total       0 days 00:09:27.300984
loss_total                          309.06855
loss_critic                        502.255455
loss_actor                        -463.679089
memory_size                        593159.825 

=== epoch 7/10 ===== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:56,  3.34it/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 [09:24<00:00,  3.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            305.814698
return_std                          38.233206
average_reward                       0.305815
round_time             0 days 00:09:25.245827
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       762.689424
return_std_test                     83.415967
average_reward_test                  0.762689
round_time_test        0 days 00:00:07.133270
round_time_total       0 days 00:09:25.246939
loss_total                         317.915363
loss_critic                        513.392415
loss_actor                        -463.992865
memory_size                        595107.825 

=== epoch 7/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:12,  3.26it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                             289.03455
return_std                          56.321603
average_reward                       0.289035
round_time             0 days 00:09:27.264737
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.699732
return_std_test                     62.951465
average_reward_test                    0.7987
round_time_test        0 days 00:00:06.930614
round_time_total       0 days 00:09:27.265844
loss_total                         317.534264
loss_critic                        513.051875
loss_actor                          -464.5362
memory_size                        597055.825 

=== epoch 7/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:27,  3.18it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            297.949058
return_std                          67.836543
average_reward                       0.297949
round_time             0 days 00:09:26.809142
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       747.205167
return_std_test                     98.293922
average_reward_test                  0.747205
round_time_test        0 days 00:00:07.030324
round_time_total       0 days 00:09:26.810216
loss_total                         320.046368
loss_critic                        516.348191
loss_actor                        -465.160946
memory_size                        599003.825 

=== epoch 7/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:56,  3.34it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            291.982207
return_std                          70.230393
average_reward                       0.291982
round_time             0 days 00:09:27.714784
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       808.157117
return_std_test                    109.436745
average_reward_test                  0.808157
round_time_test        0 days 00:00:06.884931
round_time_total       0 days 00:09:27.715874
loss_total                         317.189504
loss_critic                        512.904759
loss_actor                        -465.671539
memory_size                        600951.825 

=== epoch 7/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            264.682679
return_std                          81.800196
average_reward                       0.264683
round_time             0 days 00:09:28.332387
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       767.017635
return_std_test                      85.55161
average_reward_test                  0.767018
round_time_test        0 days 00:00:06.947526
round_time_total       0 days 00:09:28.333508
loss_total                         309.586092
loss_critic                        503.540629
loss_actor                        -466.232079
memory_size                        602899.825 

=== epoch 7/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:11,  3.26it/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 [09:25<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            261.558519
return_std                          79.042377
average_reward                       0.261559
round_time             0 days 00:09:26.464011
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       727.887906
return_std_test                     59.353137
average_reward_test                  0.727888
round_time_test        0 days 00:00:06.975937
round_time_total       0 days 00:09:26.465200
loss_total                         317.925244
loss_critic                        514.038285
loss_actor                        -466.526943
memory_size                        604847.825 

=== epoch 7/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            252.965316
return_std                          76.361008
average_reward                       0.252965
round_time             0 days 00:09:29.002511
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       763.086158
return_std_test                     41.455964
average_reward_test                  0.763086
round_time_test        0 days 00:00:07.042177
round_time_total       0 days 00:09:29.003590
loss_total                           321.4726
loss_critic                        518.594032
loss_actor                        -467.013149
memory_size                        606795.825 

=== epoch 7/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:50,  3.38it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            245.529255
return_std                          64.432614
average_reward                       0.245529
round_time             0 days 00:09:27.814357
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       776.462442
return_std_test                     58.621702
average_reward_test                  0.776462
round_time_test        0 days 00:00:07.021931
round_time_total       0 days 00:09:27.815421
loss_total                         321.822659
loss_critic                        519.163218
loss_actor                        -467.539597
memory_size                        608743.825 

=== epoch 7/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:56,  3.04it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                             264.27848
return_std                          77.063726
average_reward                       0.264278
round_time             0 days 00:09:27.734991
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        747.95363
return_std_test                     82.651632
average_reward_test                  0.747954
round_time_test        0 days 00:00:06.983761
round_time_total       0 days 00:09:27.736114
loss_total                         322.465087
loss_critic                        520.110128
loss_actor                        -468.115099
memory_size                        610691.825 

=== epoch 7/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 6/2000 [00:01<10:43,  3.10it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            294.966168
return_std                          63.801292
average_reward                       0.294966
round_time             0 days 00:09:28.628594
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       746.928877
return_std_test                     85.524834
average_reward_test                  0.746929
round_time_test        0 days 00:00:07.026386
round_time_total       0 days 00:09:28.629686
loss_total                         327.675929
loss_critic                        526.704954
loss_actor                        -468.440188
memory_size                        612639.825 

=== epoch 7/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:58,  3.33it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            279.959226
return_std                          76.231857
average_reward                       0.279959
round_time             0 days 00:09:29.133711
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       738.034039
return_std_test                      84.52202
average_reward_test                  0.738034
round_time_test        0 days 00:00:07.115831
round_time_total       0 days 00:09:29.134784
loss_total                         324.147524
loss_critic                        522.354723
loss_actor                        -468.681288
memory_size                        614587.825 

=== epoch 7/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            297.861011
return_std                          67.859455
average_reward                       0.297861
round_time             0 days 00:09:29.320313
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       809.053143
return_std_test                     61.139378
average_reward_test                  0.809053
round_time_test        0 days 00:00:07.202173
round_time_total       0 days 00:09:29.321381
loss_total                         323.341514
loss_critic                        521.473992
loss_actor                        -469.188418
memory_size                        616535.825 

=== epoch 7/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:22,  3.21it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            296.791044
return_std                          64.933123
average_reward                       0.296791
round_time             0 days 00:09:30.194184
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.789583
return_std_test                     88.441157
average_reward_test                   0.79879
round_time_test        0 days 00:00:07.095446
round_time_total       0 days 00:09:30.195256
loss_total                         325.985399
loss_critic                        524.817708
loss_actor                        -469.343859
memory_size                        618483.825 

=== epoch 7/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:16,  3.23it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                             291.79525
return_std                           62.54268
average_reward                       0.291795
round_time             0 days 00:09:29.880156
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       802.614758
return_std_test                     79.426888
average_reward_test                  0.802615
round_time_test        0 days 00:00:07.014165
round_time_total       0 days 00:09:29.881235
loss_total                         323.317962
loss_critic                        521.448008
loss_actor                        -469.202242
memory_size                        620431.825 

=== epoch 7/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:04,  3.30it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            288.396242
return_std                          65.855162
average_reward                       0.288396
round_time             0 days 00:09:30.881167
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       794.391806
return_std_test                     37.896816
average_reward_test                  0.794392
round_time_test        0 days 00:00:07.047490
round_time_total       0 days 00:09:30.882258
loss_total                         326.042124
loss_critic                        524.887184
loss_actor                        -469.338137
memory_size                        622379.825 

=== epoch 7/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:16,  3.24it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            298.237706
return_std                          53.176811
average_reward                       0.298238
round_time             0 days 00:09:29.645938
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       731.822017
return_std_test                     56.361091
average_reward_test                  0.731822
round_time_test        0 days 00:00:07.080582
round_time_total       0 days 00:09:29.647022
loss_total                         328.719052
loss_critic                        528.294712
loss_actor                        -469.583607
memory_size                        624327.825 

=== epoch 7/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            293.364071
return_std                          53.332822
average_reward                       0.293364
round_time             0 days 00:09:29.707859
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        799.42597
return_std_test                     42.066424
average_reward_test                  0.799426
round_time_test        0 days 00:00:07.091305
round_time_total       0 days 00:09:29.708924
loss_total                         328.910095
loss_critic                        528.644992
loss_actor                        -470.029513
memory_size                        626275.825 

=== epoch 7/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:36,  3.46it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            284.369777
return_std                          59.056018
average_reward                        0.28437
round_time             0 days 00:09:30.440146
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       790.691948
return_std_test                    102.289187
average_reward_test                  0.790692
round_time_test        0 days 00:00:06.983584
round_time_total       0 days 00:09:30.441240
loss_total                         329.131155
loss_critic                        528.985324
loss_actor                        -470.285545
memory_size                        628223.825 

=== epoch 7/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:31,  3.16it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            273.128745
return_std                          51.241505
average_reward                       0.273129
round_time             0 days 00:09:29.197593
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       763.546793
return_std_test                     59.786102
average_reward_test                  0.763547
round_time_test        0 days 00:00:06.997501
round_time_total       0 days 00:09:29.198672
loss_total                         333.148229
loss_critic                        534.116216
loss_actor                         -470.72374
memory_size                        630171.825 

=== epoch 7/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:35,  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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            258.529399
return_std                          41.310831
average_reward                       0.258529
round_time             0 days 00:09:29.958810
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       813.032415
return_std_test                     40.767312
average_reward_test                  0.813032
round_time_test        0 days 00:00:07.059424
round_time_total       0 days 00:09:29.959902
loss_total                          328.18991
loss_critic                        528.054534
loss_actor                        -471.268606
memory_size                        632119.825 

=== epoch 7/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:42,  3.11it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            266.813257
return_std                          41.391663
average_reward                       0.266813
round_time             0 days 00:09:30.314420
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       761.189276
return_std_test                     67.986444
average_reward_test                  0.761189
round_time_test        0 days 00:00:07.092961
round_time_total       0 days 00:09:30.315494
loss_total                         332.668083
loss_critic                        533.709276
loss_actor                        -471.496714
memory_size                        634067.825 

=== epoch 7/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:43,  3.10it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            254.549952
return_std                          36.421841
average_reward                        0.25455
round_time             0 days 00:09:29.685842
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       822.900906
return_std_test                     65.146592
average_reward_test                  0.822901
round_time_test        0 days 00:00:06.962898
round_time_total       0 days 00:09:29.686907
loss_total                         331.919478
loss_critic                        532.907573
loss_actor                        -472.032929
memory_size                        636015.825 

=== epoch 7/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:12,  3.26it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            254.591353
return_std                          31.171043
average_reward                       0.254591
round_time             0 days 00:09:30.086027
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       749.306187
return_std_test                     65.169708
average_reward_test                  0.749306
round_time_test        0 days 00:00:06.954727
round_time_total       0 days 00:09:30.087103
loss_total                         331.889973
loss_critic                        532.917934
loss_actor                        -472.221895
memory_size                        637963.825 

=== epoch 7/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.30it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            268.001049
return_std                          54.067273
average_reward                       0.268001
round_time             0 days 00:09:31.159362
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       775.866241
return_std_test                     59.997812
average_reward_test                  0.775866
round_time_test        0 days 00:00:07.095686
round_time_total       0 days 00:09:31.160447
loss_total                         328.752513
loss_critic                        529.009331
loss_actor                        -472.274781
memory_size                        639911.825 

=== epoch 7/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:54,  3.36it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                             277.73929
return_std                          53.271124
average_reward                       0.277739
round_time             0 days 00:09:30.394376
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       796.585037
return_std_test                     61.014049
average_reward_test                  0.796585
round_time_test        0 days 00:00:07.121018
round_time_total       0 days 00:09:30.395468
loss_total                          329.76629
loss_critic                        530.308524
loss_actor                        -472.402668
memory_size                        641859.825 

=== epoch 7/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            278.358752
return_std                          56.113169
average_reward                       0.278359
round_time             0 days 00:09:29.201953
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       806.409259
return_std_test                     72.071528
average_reward_test                  0.806409
round_time_test        0 days 00:00:06.939822
round_time_total       0 days 00:09:29.203032
loss_total                         325.053325
loss_critic                        524.480034
loss_actor                         -472.65353
memory_size                        643807.825 

=== epoch 7/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:24,  3.20it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            306.497819
return_std                          58.715771
average_reward                       0.306498
round_time             0 days 00:09:30.541467
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       816.369271
return_std_test                     54.514074
average_reward_test                  0.816369
round_time_test        0 days 00:00:07.003435
round_time_total       0 days 00:09:30.542569
loss_total                         328.419499
loss_critic                         528.71704
loss_actor                        -472.770684
memory_size                        645755.825 

=== epoch 7/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:07,  3.29it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            322.946243
return_std                          52.739734
average_reward                       0.322946
round_time             0 days 00:09:31.567720
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        801.60034
return_std_test                     83.700297
average_reward_test                    0.8016
round_time_test        0 days 00:00:07.066668
round_time_total       0 days 00:09:31.568791
loss_total                         326.752783
loss_critic                        526.738355
loss_actor                        -473.189527
memory_size                        647703.825 

=== epoch 7/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:32,  3.15it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            322.320492
return_std                          46.503302
average_reward                        0.32232
round_time             0 days 00:09:30.818117
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       776.854921
return_std_test                     75.487197
average_reward_test                  0.776855
round_time_test        0 days 00:00:07.038399
round_time_total       0 days 00:09:30.819198
loss_total                         326.895331
loss_critic                        527.015214
loss_actor                         -473.58422
memory_size                        649651.825 

=== epoch 7/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:08,  3.28it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            323.735055
return_std                          54.593044
average_reward                       0.323735
round_time             0 days 00:09:29.411479
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       792.943676
return_std_test                     78.325493
average_reward_test                  0.792944
round_time_test        0 days 00:00:07.052741
round_time_total       0 days 00:09:29.412544
loss_total                         325.612496
loss_critic                        525.595674
loss_actor                        -474.320235
memory_size                        651599.825 

=== epoch 7/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:58,  3.33it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            331.546275
return_std                          49.300132
average_reward                       0.331546
round_time             0 days 00:09:31.586856
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       760.261652
return_std_test                    100.063365
average_reward_test                  0.760262
round_time_test        0 days 00:00:07.074439
round_time_total       0 days 00:09:31.587925
loss_total                         329.306828
loss_critic                        530.271949
loss_actor                        -474.553677
memory_size                        653547.825 

=== epoch 7/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:41,  3.11it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            325.726868
return_std                          39.975706
average_reward                       0.325727
round_time             0 days 00:09:30.580416
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       780.022598
return_std_test                    112.931013
average_reward_test                  0.780023
round_time_test        0 days 00:00:06.947942
round_time_total       0 days 00:09:30.581476
loss_total                         330.582224
loss_critic                        532.049909
loss_actor                        -475.288539
memory_size                        655495.825 

=== epoch 7/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:42,  3.11it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            330.065535
return_std                          41.856991
average_reward                       0.330066
round_time             0 days 00:09:29.944015
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       738.237632
return_std_test                     94.368661
average_reward_test                  0.738238
round_time_test        0 days 00:00:06.998322
round_time_total       0 days 00:09:29.945090
loss_total                         331.453148
loss_critic                        533.258262
loss_actor                        -475.767334
memory_size                        657443.825 

=== epoch 7/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            335.983767
return_std                          52.691291
average_reward                       0.335984
round_time             0 days 00:09:30.717470
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       799.434257
return_std_test                     53.692366
average_reward_test                  0.799434
round_time_test        0 days 00:00:07.052417
round_time_total       0 days 00:09:30.718545
loss_total                          336.29125
loss_critic                        539.359973
loss_actor                        -475.983666
memory_size                        659391.825 

=== epoch 7/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:18,  3.23it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            351.768858
return_std                           39.66308
average_reward                       0.351769
round_time             0 days 00:09:30.027049
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       768.299512
return_std_test                     79.417806
average_reward_test                    0.7683
round_time_test        0 days 00:00:07.048786
round_time_total       0 days 00:09:30.028125
loss_total                         340.978511
loss_critic                        545.288709
loss_actor                        -476.262303
memory_size                        661339.825 

=== epoch 7/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:31,  3.16it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            356.364851
return_std                          41.027601
average_reward                       0.356365
round_time             0 days 00:09:29.825304
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       799.614931
return_std_test                     61.894861
average_reward_test                  0.799615
round_time_test        0 days 00:00:06.966249
round_time_total       0 days 00:09:29.826380
loss_total                         333.170845
loss_critic                        535.647208
loss_actor                         -476.73463
memory_size                        663287.825 

=== epoch 7/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:08,  3.28it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            342.910377
return_std                          57.182689
average_reward                        0.34291
round_time             0 days 00:09:29.119674
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       808.669264
return_std_test                      78.98093
average_reward_test                  0.808669
round_time_test        0 days 00:00:07.127175
round_time_total       0 days 00:09:29.120762
loss_total                         350.155211
loss_critic                        556.880988
loss_actor                        -476.747922
memory_size                        665235.825 

=== epoch 7/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:58,  3.33it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            332.356791
return_std                          58.245668
average_reward                       0.332357
round_time             0 days 00:09:29.451461
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        800.51933
return_std_test                     68.546719
average_reward_test                  0.800519
round_time_test        0 days 00:00:06.984551
round_time_total       0 days 00:09:29.452536
loss_total                         339.264161
loss_critic                         543.46594
loss_actor                        -477.542974
memory_size                        667183.825 

=== epoch 7/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:31,  3.16it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            318.668882
return_std                          48.893999
average_reward                       0.318669
round_time             0 days 00:09:30.096145
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       795.107659
return_std_test                     60.636216
average_reward_test                  0.795108
round_time_test        0 days 00:00:07.013506
round_time_total       0 days 00:09:30.097215
loss_total                         347.202845
loss_critic                        553.517568
loss_actor                        -478.056071
memory_size                        669131.825 

=== epoch 7/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:50,  3.38it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            286.392189
return_std                           52.09602
average_reward                       0.286392
round_time             0 days 00:09:30.379182
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       738.347837
return_std_test                     63.029572
average_reward_test                  0.738348
round_time_test        0 days 00:00:06.925699
round_time_total       0 days 00:09:30.380251
loss_total                         345.053683
loss_critic                        550.954427
loss_actor                        -478.549318
memory_size                        671079.825 

=== epoch 7/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:14,  3.25it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            296.952758
return_std                          64.145973
average_reward                       0.296953
round_time             0 days 00:09:30.900612
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       751.758215
return_std_test                     67.273741
average_reward_test                  0.751758
round_time_test        0 days 00:00:07.157229
round_time_total       0 days 00:09:30.901683
loss_total                         347.315186
loss_critic                        553.912211
loss_actor                        -479.072941
memory_size                        673027.825 

=== epoch 7/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.29it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            313.003602
return_std                          63.388866
average_reward                       0.313004
round_time             0 days 00:09:30.958606
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       854.193165
return_std_test                      83.22064
average_reward_test                  0.854193
round_time_test        0 days 00:00:07.057072
round_time_total       0 days 00:09:30.959677
loss_total                         341.755573
loss_critic                        547.080876
loss_actor                        -479.545659
memory_size                        674975.825 

=== epoch 7/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.30it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            329.304598
return_std                          69.953851
average_reward                       0.329305
round_time             0 days 00:09:31.262608
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         769.2883
return_std_test                     72.362652
average_reward_test                  0.769288
round_time_test        0 days 00:00:07.100588
round_time_total       0 days 00:09:31.263697
loss_total                         344.304753
loss_critic                        550.241731
loss_actor                        -479.443181
memory_size                        676923.825 

=== epoch 7/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            345.487847
return_std                          74.297558
average_reward                       0.345488
round_time             0 days 00:09:32.011071
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.126525
return_std_test                     72.069881
average_reward_test                  0.798127
round_time_test        0 days 00:00:07.102924
round_time_total       0 days 00:09:32.012142
loss_total                         347.427709
loss_critic                        554.245009
loss_actor                        -479.841513
memory_size                        678871.825 

=== epoch 7/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:10,  3.27it/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 [09:29<00:00,  3.51it/s]
<GE123_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                            369.293986
return_std                          45.793389
average_reward                       0.369294
round_time             0 days 00:09:30.443215
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       800.150613
return_std_test                     103.10837
average_reward_test                  0.800151
round_time_test        0 days 00:00:06.971024
round_time_total       0 days 00:09:30.444293
loss_total                         349.102507
loss_critic                        556.347649
loss_actor                        -479.878082
memory_size                        680819.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 8/10 ===== round 1/50 ======================================
  0%|          | 7/2000 [00:02<09:41,  3.43it/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 [09:21<00:00,  3.56it/s]
episodes                                    2
episode_length                         1000.0
returns                            279.367638
return_std                          15.722612
average_reward                       0.279368
round_time             0 days 00:09:21.467900
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       779.116217
return_std_test                     104.66976
average_reward_test                  0.779116
round_time_test        0 days 00:00:06.946344
round_time_total       0 days 00:09:21.468980
loss_total                         345.105429
loss_critic                           551.442
loss_actor                        -480.240876
memory_size                        682768.825 

=== epoch 8/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:23,  3.20it/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 [09:22<00:00,  3.55it/s]
episodes                                    4
episode_length                         1000.0
returns                            326.546599
return_std                          49.984063
average_reward                       0.326547
round_time             0 days 00:09:23.402496
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       834.779778
return_std_test                     77.056823
average_reward_test                   0.83478
round_time_test        0 days 00:00:07.209062
round_time_total       0 days 00:09:23.403570
loss_total                         345.613125
loss_critic                        552.075605
loss_actor                        -480.236816
memory_size                        684716.825 

=== epoch 8/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:37,  3.45it/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 [09:25<00:00,  3.54it/s]
episodes                                    6
episode_length                         1000.0
returns                            345.345328
return_std                          48.733261
average_reward                       0.345345
round_time             0 days 00:09:25.571399
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       811.693404
return_std_test                     68.064335
average_reward_test                  0.811693
round_time_test        0 days 00:00:07.018800
round_time_total       0 days 00:09:25.572476
loss_total                         350.418223
loss_critic                        558.224836
loss_actor                        -480.808255
memory_size                        686664.825 

=== epoch 8/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:10,  3.27it/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 [09:25<00:00,  3.54it/s]
episodes                                    8
episode_length                         1000.0
returns                            346.347609
return_std                          42.542813
average_reward                       0.346348
round_time             0 days 00:09:25.894262
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        790.59601
return_std_test                      43.56565
average_reward_test                  0.790596
round_time_test        0 days 00:00:07.093230
round_time_total       0 days 00:09:25.895327
loss_total                         347.546235
loss_critic                        554.740221
loss_actor                        -481.229735
memory_size                        688612.825 

=== epoch 8/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:08,  3.28it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            332.215166
return_std                          52.700137
average_reward                       0.332215
round_time             0 days 00:09:27.304063
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        755.31939
return_std_test                     98.748218
average_reward_test                  0.755319
round_time_test        0 days 00:00:07.009184
round_time_total       0 days 00:09:27.305152
loss_total                         347.005965
loss_critic                        554.172582
loss_actor                        -481.660526
memory_size                        690560.825 

=== epoch 8/10 ===== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:38,  3.45it/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 [09:25<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            338.950056
return_std                           48.37747
average_reward                        0.33895
round_time             0 days 00:09:26.233729
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        802.93432
return_std_test                     52.191967
average_reward_test                  0.802934
round_time_test        0 days 00:00:06.969183
round_time_total       0 days 00:09:26.234793
loss_total                         348.544116
loss_critic                        556.160295
loss_actor                        -481.920622
memory_size                        692508.825 

=== epoch 8/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:04,  3.30it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            340.914243
return_std                          49.499877
average_reward                       0.340914
round_time             0 days 00:09:26.877002
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       791.432606
return_std_test                     53.574727
average_reward_test                  0.791433
round_time_test        0 days 00:00:07.036922
round_time_total       0 days 00:09:26.878082
loss_total                         347.425838
loss_critic                        554.942192
loss_actor                        -482.639601
memory_size                        694456.825 

=== epoch 8/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            325.659443
return_std                          49.500145
average_reward                       0.325659
round_time             0 days 00:09:27.637436
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.903953
return_std_test                     35.838526
average_reward_test                  0.798904
round_time_test        0 days 00:00:07.032648
round_time_total       0 days 00:09:27.638512
loss_total                         353.910518
loss_critic                        563.048098
loss_actor                        -482.639823
memory_size                        696404.825 

=== epoch 8/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:05,  3.00it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            325.643538
return_std                          52.347488
average_reward                       0.325644
round_time             0 days 00:09:28.030867
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.346723
return_std_test                    100.265189
average_reward_test                  0.798347
round_time_test        0 days 00:00:07.014809
round_time_total       0 days 00:09:28.031930
loss_total                         351.387895
loss_critic                         560.01673
loss_actor                        -483.127472
memory_size                        698352.825 

=== epoch 8/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:04,  3.30it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            324.747459
return_std                          49.510384
average_reward                       0.324747
round_time             0 days 00:09:26.608816
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        780.81209
return_std_test                    142.498872
average_reward_test                  0.780812
round_time_test        0 days 00:00:06.994082
round_time_total       0 days 00:09:26.609884
loss_total                         357.716803
loss_critic                        568.016262
loss_actor                        -483.481061
memory_size                        700300.825 

=== epoch 8/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            329.332187
return_std                          55.149931
average_reward                       0.329332
round_time             0 days 00:09:27.491955
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.002838
return_std_test                     53.761434
average_reward_test                  0.798003
round_time_test        0 days 00:00:07.060527
round_time_total       0 days 00:09:27.493025
loss_total                         359.013742
loss_critic                        569.649585
loss_actor                        -483.529653
memory_size                        702248.825 

=== epoch 8/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            316.671872
return_std                          51.320392
average_reward                       0.316672
round_time             0 days 00:09:29.571032
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       795.012621
return_std_test                     71.633974
average_reward_test                  0.795013
round_time_test        0 days 00:00:07.066109
round_time_total       0 days 00:09:29.572111
loss_total                         362.471059
loss_critic                        573.977873
loss_actor                        -483.556225
memory_size                        704196.825 

=== epoch 8/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:44,  3.41it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            332.794001
return_std                          55.181933
average_reward                       0.332794
round_time             0 days 00:09:29.164966
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       801.144144
return_std_test                     62.614532
average_reward_test                  0.801144
round_time_test        0 days 00:00:07.012170
round_time_total       0 days 00:09:29.166039
loss_total                         353.494605
loss_critic                        562.881047
loss_actor                        -484.051185
memory_size                        706144.825 

=== epoch 8/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:52,  3.37it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            315.799071
return_std                           63.01182
average_reward                       0.315799
round_time             0 days 00:09:27.940018
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       781.984899
return_std_test                     94.135895
average_reward_test                  0.781985
round_time_test        0 days 00:00:06.966388
round_time_total       0 days 00:09:27.941099
loss_total                         360.816836
loss_critic                        572.091543
loss_actor                        -484.282019
memory_size                        708092.825 

=== epoch 8/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:46,  3.40it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            332.817728
return_std                          59.505178
average_reward                       0.332818
round_time             0 days 00:09:29.071307
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       825.947592
return_std_test                      69.38788
average_reward_test                  0.825948
round_time_test        0 days 00:00:06.863942
round_time_total       0 days 00:09:29.072387
loss_total                          356.97694
loss_critic                        567.466198
loss_actor                        -484.980115
memory_size                        710040.825 

=== epoch 8/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:10,  3.27it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            333.962903
return_std                          52.965696
average_reward                       0.333963
round_time             0 days 00:09:27.791428
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       784.066086
return_std_test                     68.243542
average_reward_test                  0.784066
round_time_test        0 days 00:00:07.072606
round_time_total       0 days 00:09:27.792505
loss_total                         360.024985
loss_critic                        571.294652
loss_actor                        -485.053708
memory_size                        711988.825 

=== epoch 8/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:54,  3.36it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            345.410246
return_std                          51.718105
average_reward                        0.34541
round_time             0 days 00:09:28.689426
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       812.686765
return_std_test                     67.219398
average_reward_test                  0.812687
round_time_test        0 days 00:00:06.922755
round_time_total       0 days 00:09:28.690511
loss_total                         361.915154
loss_critic                        573.679043
loss_actor                        -485.140427
memory_size                        713936.825 

=== epoch 8/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:30,  3.16it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            344.095813
return_std                          50.892287
average_reward                       0.344096
round_time             0 days 00:09:26.603388
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       832.215185
return_std_test                     76.583355
average_reward_test                  0.832215
round_time_test        0 days 00:00:07.103900
round_time_total       0 days 00:09:26.604513
loss_total                          355.53572
loss_critic                        565.852927
loss_actor                        -485.733138
memory_size                        715884.825 

=== epoch 8/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:39,  3.44it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            354.224671
return_std                          30.171198
average_reward                       0.354225
round_time             0 days 00:09:28.112650
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       790.555448
return_std_test                      78.37257
average_reward_test                  0.790555
round_time_test        0 days 00:00:06.997528
round_time_total       0 days 00:09:28.113733
loss_total                         364.828396
loss_critic                        577.482305
loss_actor                        -485.787269
memory_size                        717832.825 

=== epoch 8/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:03,  3.31it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            346.687112
return_std                          36.963897
average_reward                       0.346687
round_time             0 days 00:09:27.340261
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       711.064044
return_std_test                     35.459016
average_reward_test                  0.711064
round_time_test        0 days 00:00:07.064144
round_time_total       0 days 00:09:27.341350
loss_total                         355.163156
loss_critic                        565.628743
loss_actor                        -486.699219
memory_size                        719780.825 

=== epoch 8/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:48,  3.39it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            350.643909
return_std                          39.810125
average_reward                       0.350644
round_time             0 days 00:09:27.099231
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       758.984829
return_std_test                     98.058319
average_reward_test                  0.758985
round_time_test        0 days 00:00:07.055661
round_time_total       0 days 00:09:27.100324
loss_total                         363.265622
loss_critic                        575.769224
loss_actor                        -486.748813
memory_size                        721728.825 

=== epoch 8/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:54,  3.36it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            338.569941
return_std                            48.5087
average_reward                        0.33857
round_time             0 days 00:09:27.993792
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       795.924755
return_std_test                     55.780348
average_reward_test                  0.795925
round_time_test        0 days 00:00:07.111560
round_time_total       0 days 00:09:27.994865
loss_total                          360.31553
loss_critic                        572.201894
loss_actor                        -487.229953
memory_size                        723676.825 

=== epoch 8/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:18,  3.22it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            338.518915
return_std                          55.200621
average_reward                       0.338519
round_time             0 days 00:09:27.382499
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       804.231428
return_std_test                     72.791938
average_reward_test                  0.804231
round_time_test        0 days 00:00:07.029284
round_time_total       0 days 00:09:27.383577
loss_total                         361.044184
loss_critic                         573.16866
loss_actor                        -487.453744
memory_size                        725624.825 

=== epoch 8/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:56,  3.35it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                             318.72406
return_std                          73.849819
average_reward                       0.318724
round_time             0 days 00:09:28.707320
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        862.39207
return_std_test                     49.182415
average_reward_test                  0.862392
round_time_test        0 days 00:00:06.987438
round_time_total       0 days 00:09:28.708382
loss_total                         360.012033
loss_critic                        572.018616
loss_actor                        -488.014326
memory_size                        727572.825 

=== epoch 8/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:23,  3.20it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            325.474705
return_std                           73.26385
average_reward                       0.325475
round_time             0 days 00:09:29.221040
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       771.892108
return_std_test                      89.32778
average_reward_test                  0.771892
round_time_test        0 days 00:00:06.961798
round_time_total       0 days 00:09:29.222121
loss_total                         365.310867
loss_critic                        578.596044
loss_actor                        -487.829863
memory_size                        729520.825 

=== epoch 8/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [09:25<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            304.253086
return_std                          73.953342
average_reward                       0.304253
round_time             0 days 00:09:26.406492
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.211467
return_std_test                     84.884218
average_reward_test                  0.798211
round_time_test        0 days 00:00:07.012497
round_time_total       0 days 00:09:26.407555
loss_total                         361.299364
loss_critic                        573.687228
loss_actor                        -488.252122
memory_size                        731468.825 

=== epoch 8/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:38,  3.13it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            296.921687
return_std                          70.526703
average_reward                       0.296922
round_time             0 days 00:09:27.803888
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       787.206951
return_std_test                     45.200519
average_reward_test                  0.787207
round_time_test        0 days 00:00:07.091772
round_time_total       0 days 00:09:27.804966
loss_total                         361.105876
loss_critic                        573.578809
loss_actor                        -488.785882
memory_size                        733416.825 

=== epoch 8/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:07,  3.28it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            281.518019
return_std                          50.853518
average_reward                       0.281518
round_time             0 days 00:09:28.104606
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       758.815116
return_std_test                     69.867986
average_reward_test                  0.758815
round_time_test        0 days 00:00:07.095286
round_time_total       0 days 00:09:28.105687
loss_total                         358.977888
loss_critic                        571.000287
loss_actor                        -489.111735
memory_size                        735364.825 

=== epoch 8/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            303.457374
return_std                          39.855474
average_reward                       0.303457
round_time             0 days 00:09:27.734159
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       852.212265
return_std_test                      54.21733
average_reward_test                  0.852212
round_time_test        0 days 00:00:07.150061
round_time_total       0 days 00:09:27.735251
loss_total                         361.610527
loss_critic                        574.354737
loss_actor                        -489.366338
memory_size                        737312.825 

=== epoch 8/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:58,  3.34it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            290.533152
return_std                           41.74711
average_reward                       0.290533
round_time             0 days 00:09:26.989884
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       823.388657
return_std_test                     81.863673
average_reward_test                  0.823389
round_time_test        0 days 00:00:07.030521
round_time_total       0 days 00:09:26.990965
loss_total                         361.422197
loss_critic                        574.131601
loss_actor                         -489.41544
memory_size                        739260.825 

=== epoch 8/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:27,  3.18it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            306.149427
return_std                          40.340644
average_reward                       0.306149
round_time             0 days 00:09:28.356904
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       816.525635
return_std_test                     77.843254
average_reward_test                  0.816526
round_time_test        0 days 00:00:06.978329
round_time_total       0 days 00:09:28.357980
loss_total                         363.021351
loss_critic                        576.285076
loss_actor                        -490.033575
memory_size                        741208.825 

=== epoch 8/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:58,  3.33it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            316.544204
return_std                          48.953411
average_reward                       0.316544
round_time             0 days 00:09:28.218837
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       772.380315
return_std_test                     91.650577
average_reward_test                   0.77238
round_time_test        0 days 00:00:06.926983
round_time_total       0 days 00:09:28.219916
loss_total                         361.903937
loss_critic                        574.974526
loss_actor                        -490.378443
memory_size                        743156.825 

=== epoch 8/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:01,  3.32it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            324.112078
return_std                          51.974437
average_reward                       0.324112
round_time             0 days 00:09:28.573827
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       816.441634
return_std_test                     46.587414
average_reward_test                  0.816442
round_time_test        0 days 00:00:07.064812
round_time_total       0 days 00:09:28.574899
loss_total                         367.443766
loss_critic                        581.760978
loss_actor                        -489.825107
memory_size                        745104.825 

=== epoch 8/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:24,  3.19it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            322.382472
return_std                          56.281994
average_reward                       0.322382
round_time             0 days 00:09:29.310305
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       778.941549
return_std_test                     81.767211
average_reward_test                  0.778942
round_time_test        0 days 00:00:06.987477
round_time_total       0 days 00:09:29.311386
loss_total                         365.226712
loss_critic                        579.082652
loss_actor                        -490.197071
memory_size                        747052.825 

=== epoch 8/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:22,  3.21it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            337.266452
return_std                          47.898469
average_reward                       0.337266
round_time             0 days 00:09:28.468116
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        827.98623
return_std_test                    116.641368
average_reward_test                  0.827986
round_time_test        0 days 00:00:07.088821
round_time_total       0 days 00:09:28.469178
loss_total                         365.334893
loss_critic                        579.353843
loss_actor                        -490.740938
memory_size                        749000.825 

=== epoch 8/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:50,  3.38it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            335.857739
return_std                           50.29857
average_reward                       0.335858
round_time             0 days 00:09:29.666716
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       822.279865
return_std_test                     79.893727
average_reward_test                   0.82228
round_time_test        0 days 00:00:07.071835
round_time_total       0 days 00:09:29.667789
loss_total                         363.999013
loss_critic                        577.819533
loss_actor                        -491.283095
memory_size                        750948.825 

=== epoch 8/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            344.608355
return_std                          41.013394
average_reward                       0.344608
round_time             0 days 00:09:27.372327
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       806.897613
return_std_test                     58.452568
average_reward_test                  0.806898
round_time_test        0 days 00:00:07.021443
round_time_total       0 days 00:09:27.373397
loss_total                         365.504364
loss_critic                        579.736369
loss_actor                        -491.423682
memory_size                        752896.825 

=== epoch 8/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:49,  3.38it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            351.117889
return_std                          39.324592
average_reward                       0.351118
round_time             0 days 00:09:28.589172
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       847.447418
return_std_test                     62.212961
average_reward_test                  0.847447
round_time_test        0 days 00:00:07.156500
round_time_total       0 days 00:09:28.590254
loss_total                         360.658907
loss_critic                        573.871753
loss_actor                        -492.192503
memory_size                        754844.825 

=== epoch 8/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:15,  3.24it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            354.077142
return_std                          36.096549
average_reward                       0.354077
round_time             0 days 00:09:29.309028
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       822.366062
return_std_test                     90.326398
average_reward_test                  0.822366
round_time_test        0 days 00:00:07.030805
round_time_total       0 days 00:09:29.310134
loss_total                         371.608196
loss_critic                        587.544272
loss_actor                        -492.136139
memory_size                        756792.825 

=== epoch 8/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            351.756675
return_std                          38.429828
average_reward                       0.351757
round_time             0 days 00:09:27.745012
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       825.817814
return_std_test                     73.753129
average_reward_test                  0.825818
round_time_test        0 days 00:00:07.043498
round_time_total       0 days 00:09:27.746102
loss_total                         366.103155
loss_critic                        580.716253
loss_actor                        -492.349268
memory_size                        758740.825 

=== epoch 8/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:51,  3.37it/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 [09:25<00:00,  3.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            360.923688
return_std                          34.046266
average_reward                       0.360924
round_time             0 days 00:09:25.980260
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        779.88286
return_std_test                     90.634115
average_reward_test                  0.779883
round_time_test        0 days 00:00:07.016995
round_time_total       0 days 00:09:25.981364
loss_total                         373.318199
loss_critic                        589.895202
loss_actor                         -492.98984
memory_size                        760688.825 

=== epoch 8/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:23,  3.20it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            349.908955
return_std                          41.859979
average_reward                       0.349909
round_time             0 days 00:09:28.661245
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       824.085639
return_std_test                     68.858924
average_reward_test                  0.824086
round_time_test        0 days 00:00:06.947803
round_time_total       0 days 00:09:28.662349
loss_total                         370.518584
loss_critic                        586.517031
loss_actor                        -493.475236
memory_size                        762636.825 

=== epoch 8/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:29,  3.17it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            343.002158
return_std                          40.764323
average_reward                       0.343002
round_time             0 days 00:09:28.393909
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       790.132367
return_std_test                     83.785624
average_reward_test                  0.790132
round_time_test        0 days 00:00:07.145024
round_time_total       0 days 00:09:28.394972
loss_total                         370.478074
loss_critic                        586.496021
loss_actor                        -493.593739
memory_size                        764584.825 

=== epoch 8/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:00,  3.32it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            350.065159
return_std                          38.760427
average_reward                       0.350065
round_time             0 days 00:09:28.522715
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       818.434667
return_std_test                     54.448388
average_reward_test                  0.818435
round_time_test        0 days 00:00:07.060676
round_time_total       0 days 00:09:28.523788
loss_total                          370.51789
loss_critic                          586.6674
loss_actor                        -494.080177
memory_size                        766532.825 

=== epoch 8/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:25,  3.19it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            358.404466
return_std                          41.254937
average_reward                       0.358404
round_time             0 days 00:09:28.814248
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       890.200184
return_std_test                     52.484853
average_reward_test                    0.8902
round_time_test        0 days 00:00:07.012562
round_time_total       0 days 00:09:28.815317
loss_total                         373.135165
loss_critic                        590.084546
loss_actor                        -494.662384
memory_size                        768480.825 

=== epoch 8/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:06,  3.29it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            354.543644
return_std                          41.280504
average_reward                       0.354544
round_time             0 days 00:09:30.502730
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       829.087586
return_std_test                     73.092758
average_reward_test                  0.829088
round_time_test        0 days 00:00:07.039951
round_time_total       0 days 00:09:30.503818
loss_total                         378.796687
loss_critic                        597.212644
loss_actor                        -494.867167
memory_size                        770428.825 

=== epoch 8/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:00,  3.32it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                             350.25772
return_std                           44.44552
average_reward                       0.350258
round_time             0 days 00:09:30.279466
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       809.388241
return_std_test                     60.417213
average_reward_test                  0.809388
round_time_test        0 days 00:00:06.976396
round_time_total       0 days 00:09:30.280543
loss_total                         379.226783
loss_critic                        597.755602
loss_actor                        -494.888521
memory_size                        772376.825 

=== epoch 8/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:08,  3.28it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            335.265361
return_std                          61.087329
average_reward                       0.335265
round_time             0 days 00:09:28.094382
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       824.990206
return_std_test                     55.201928
average_reward_test                   0.82499
round_time_test        0 days 00:00:07.086146
round_time_total       0 days 00:09:28.095444
loss_total                         380.037224
loss_critic                        598.728912
loss_actor                        -494.729557
memory_size                        774324.825 

=== epoch 8/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:23,  3.20it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            333.805385
return_std                          61.615031
average_reward                       0.333805
round_time             0 days 00:09:30.646474
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        863.17413
return_std_test                     66.175904
average_reward_test                  0.863174
round_time_test        0 days 00:00:07.022552
round_time_total       0 days 00:09:30.647563
loss_total                          382.75924
loss_critic                         602.21326
loss_actor                        -495.056865
memory_size                        776272.825 

=== epoch 8/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:57,  3.34it/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 [09:29<00:00,  3.51it/s]
<GE123_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                            322.447606
return_std                          58.671572
average_reward                       0.322448
round_time             0 days 00:09:30.390060
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       768.293285
return_std_test                     88.753372
average_reward_test                  0.768293
round_time_test        0 days 00:00:07.027674
round_time_total       0 days 00:09:30.391147
loss_total                         385.220598
loss_critic                        605.341512
loss_actor                        -495.263089
memory_size                        778220.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 9/10 ===== round 1/50 ======================================
  0%|          | 7/2000 [00:02<09:36,  3.46it/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 [09:22<00:00,  3.55it/s]
episodes                                    2
episode_length                         1000.0
returns                            327.603329
return_std                          37.355944
average_reward                       0.327603
round_time             0 days 00:09:22.963275
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       788.130193
return_std_test                     59.409161
average_reward_test                   0.78813
round_time_test        0 days 00:00:07.036378
round_time_total       0 days 00:09:22.964358
loss_total                         384.624155
loss_critic                        604.656933
loss_actor                        -495.506981
memory_size                        780169.825 

=== epoch 9/10 ===== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:19,  3.22it/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 [09:24<00:00,  3.54it/s]
episodes                                    4
episode_length                         1000.0
returns                            331.292299
return_std                          44.523363
average_reward                       0.331292
round_time             0 days 00:09:24.828375
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        829.64543
return_std_test                      66.98092
average_reward_test                  0.829645
round_time_test        0 days 00:00:06.992098
round_time_total       0 days 00:09:24.829438
loss_total                         375.651768
loss_critic                        593.524688
loss_actor                        -495.839939
memory_size                        782117.825 

=== epoch 9/10 ===== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:48,  3.39it/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 [09:26<00:00,  3.53it/s]
episodes                                    6
episode_length                         1000.0
returns                            319.118165
return_std                          41.237526
average_reward                       0.319118
round_time             0 days 00:09:27.045785
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       821.913953
return_std_test                    108.181115
average_reward_test                  0.821914
round_time_test        0 days 00:00:07.055431
round_time_total       0 days 00:09:27.046874
loss_total                         388.010584
loss_critic                        608.929877
loss_actor                        -495.666618
memory_size                        784065.825 

=== epoch 9/10 ===== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:08,  3.28it/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 [09:25<00:00,  3.54it/s]
episodes                                    8
episode_length                         1000.0
returns                            323.361737
return_std                          39.522364
average_reward                       0.323362
round_time             0 days 00:09:25.834126
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       843.510622
return_std_test                     23.439937
average_reward_test                  0.843511
round_time_test        0 days 00:00:07.015266
round_time_total       0 days 00:09:25.835202
loss_total                         383.128287
loss_critic                        602.928786
loss_actor                        -496.073737
memory_size                        786013.825 

=== epoch 9/10 ===== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            324.428953
return_std                          36.766159
average_reward                       0.324429
round_time             0 days 00:09:27.312957
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       826.904808
return_std_test                     61.769797
average_reward_test                  0.826905
round_time_test        0 days 00:00:07.079861
round_time_total       0 days 00:09:27.314030
loss_total                         386.870016
loss_critic                        607.625474
loss_actor                        -496.151846
memory_size                        787961.825 

=== epoch 9/10 ===== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:42,  3.42it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            323.397438
return_std                          42.773577
average_reward                       0.323397
round_time             0 days 00:09:27.374055
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       825.549321
return_std_test                     78.837083
average_reward_test                  0.825549
round_time_test        0 days 00:00:06.986366
round_time_total       0 days 00:09:27.375124
loss_total                         383.955469
loss_critic                        604.202731
loss_actor                        -497.033611
memory_size                        789909.825 

=== epoch 9/10 ===== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:23,  3.20it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            341.427962
return_std                          55.132403
average_reward                       0.341428
round_time             0 days 00:09:28.180536
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       826.015189
return_std_test                     86.143346
average_reward_test                  0.826015
round_time_test        0 days 00:00:07.135165
round_time_total       0 days 00:09:28.181632
loss_total                         385.289481
loss_critic                        606.021777
loss_actor                        -497.639729
memory_size                        791857.825 

=== epoch 9/10 ===== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:30,  3.16it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            342.340333
return_std                          54.861758
average_reward                        0.34234
round_time             0 days 00:09:28.561487
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       888.131949
return_std_test                     54.052648
average_reward_test                  0.888132
round_time_test        0 days 00:00:07.015613
round_time_total       0 days 00:09:28.562567
loss_total                         384.837908
loss_critic                        605.574724
loss_actor                        -498.109388
memory_size                        793805.825 

=== epoch 9/10 ===== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:00,  3.32it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            345.344925
return_std                          54.812297
average_reward                       0.345345
round_time             0 days 00:09:26.733978
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        831.69938
return_std_test                     59.773865
average_reward_test                  0.831699
round_time_test        0 days 00:00:07.004731
round_time_total       0 days 00:09:26.735079
loss_total                         384.795282
loss_critic                        605.618822
loss_actor                        -498.498906
memory_size                        795753.825 

=== epoch 9/10 ===== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:46,  3.40it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            343.813721
return_std                          65.766187
average_reward                       0.343814
round_time             0 days 00:09:28.797824
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       822.284971
return_std_test                     81.357098
average_reward_test                  0.822285
round_time_test        0 days 00:00:07.145232
round_time_total       0 days 00:09:28.798914
loss_total                         382.675563
loss_critic                        603.092749
loss_actor                        -498.993207
memory_size                        797701.825 

=== epoch 9/10 ===== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            348.546212
return_std                          63.322833
average_reward                       0.348546
round_time             0 days 00:09:29.410915
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       844.928295
return_std_test                     43.207551
average_reward_test                  0.844928
round_time_test        0 days 00:00:07.007455
round_time_total       0 days 00:09:29.411991
loss_total                          385.60648
loss_critic                        606.640946
loss_actor                        -498.531409
memory_size                        799649.825 

=== epoch 9/10 ===== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:08,  3.28it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            337.057659
return_std                          59.514601
average_reward                       0.337058
round_time             0 days 00:09:30.731308
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       837.309341
return_std_test                     59.983162
average_reward_test                  0.837309
round_time_test        0 days 00:00:06.951410
round_time_total       0 days 00:09:30.732417
loss_total                         382.438409
loss_critic                        602.579443
loss_actor                        -498.125757
memory_size                        801597.825 

=== epoch 9/10 ===== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:56,  3.04it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            340.118937
return_std                          58.885413
average_reward                       0.340119
round_time             0 days 00:09:28.830371
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       811.361327
return_std_test                     60.241789
average_reward_test                  0.811361
round_time_test        0 days 00:00:06.917409
round_time_total       0 days 00:09:28.831467
loss_total                         385.772772
loss_critic                        606.710821
loss_actor                        -497.979451
memory_size                        803545.825 

=== epoch 9/10 ===== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:18,  3.23it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            350.510271
return_std                          65.905959
average_reward                        0.35051
round_time             0 days 00:09:30.395196
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       845.236529
return_std_test                     59.453605
average_reward_test                  0.845237
round_time_test        0 days 00:00:07.116242
round_time_total       0 days 00:09:30.396322
loss_total                         383.971233
loss_critic                        604.625138
loss_actor                        -498.644416
memory_size                        805493.825 

=== epoch 9/10 ===== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:51,  3.37it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            362.395983
return_std                          53.795196
average_reward                       0.362396
round_time             0 days 00:09:30.046221
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       856.703472
return_std_test                     61.971477
average_reward_test                  0.856703
round_time_test        0 days 00:00:07.275330
round_time_total       0 days 00:09:30.047343
loss_total                           390.7159
loss_critic                        613.212731
loss_actor                        -499.271451
memory_size                        807441.825 

=== epoch 9/10 ===== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:47,  3.08it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            340.991971
return_std                          72.119302
average_reward                       0.340992
round_time             0 days 00:09:31.063889
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       816.684812
return_std_test                     69.440455
average_reward_test                  0.816685
round_time_test        0 days 00:00:06.860239
round_time_total       0 days 00:09:31.064978
loss_total                         394.487698
loss_critic                        617.946874
loss_actor                        -499.349038
memory_size                        809389.825 

=== epoch 9/10 ===== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:29,  3.17it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            340.139407
return_std                          66.587838
average_reward                       0.340139
round_time             0 days 00:09:31.745214
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       844.625555
return_std_test                     62.740472
average_reward_test                  0.844626
round_time_test        0 days 00:00:07.153373
round_time_total       0 days 00:09:31.746298
loss_total                         381.012383
loss_critic                        601.243503
loss_actor                        -499.912128
memory_size                        811337.825 

=== epoch 9/10 ===== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            352.278755
return_std                          68.348005
average_reward                       0.352279
round_time             0 days 00:09:30.862541
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       856.412495
return_std_test                     60.779211
average_reward_test                  0.856412
round_time_test        0 days 00:00:06.998254
round_time_total       0 days 00:09:30.863612
loss_total                         392.482192
loss_critic                        615.524853
loss_actor                         -499.68848
memory_size                        813285.825 

=== epoch 9/10 ===== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:15,  3.24it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            358.854414
return_std                          71.870867
average_reward                       0.358854
round_time             0 days 00:09:30.393306
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       857.302611
return_std_test                      82.99173
average_reward_test                  0.857303
round_time_test        0 days 00:00:07.071627
round_time_total       0 days 00:09:30.394385
loss_total                         393.338936
loss_critic                        616.632406
loss_actor                        -499.834979
memory_size                        815233.825 

=== epoch 9/10 ===== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:23,  3.20it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            366.308956
return_std                          76.757193
average_reward                       0.366309
round_time             0 days 00:09:30.029087
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       843.785387
return_std_test                     68.805945
average_reward_test                  0.843785
round_time_test        0 days 00:00:07.035178
round_time_total       0 days 00:09:30.030176
loss_total                         390.463184
loss_critic                        613.127675
loss_actor                        -500.194812
memory_size                        817181.825 

=== epoch 9/10 ===== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:27,  3.18it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            395.870397
return_std                           57.62265
average_reward                        0.39587
round_time             0 days 00:09:30.089623
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       772.593357
return_std_test                     63.738337
average_reward_test                  0.772593
round_time_test        0 days 00:00:07.075935
round_time_total       0 days 00:09:30.090715
loss_total                         385.273232
loss_critic                        606.736344
loss_actor                        -500.579244
memory_size                        819129.825 

=== epoch 9/10 ===== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:12,  3.26it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            412.160442
return_std                          59.045087
average_reward                        0.41216
round_time             0 days 00:09:29.466106
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       779.864306
return_std_test                    104.409778
average_reward_test                  0.779864
round_time_test        0 days 00:00:06.948500
round_time_total       0 days 00:09:29.467203
loss_total                         390.309054
loss_critic                        613.115973
loss_actor                        -500.918654
memory_size                        821077.825 

=== epoch 9/10 ===== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:18,  3.22it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            403.648824
return_std                          63.752536
average_reward                       0.403649
round_time             0 days 00:09:31.499135
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       750.205866
return_std_test                     91.250552
average_reward_test                  0.750206
round_time_test        0 days 00:00:07.078541
round_time_total       0 days 00:09:31.500222
loss_total                           395.4996
loss_critic                        619.639762
loss_actor                         -501.06108
memory_size                        823025.825 

=== epoch 9/10 ===== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:47,  3.39it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            399.929575
return_std                          64.957289
average_reward                        0.39993
round_time             0 days 00:09:28.642746
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       870.721961
return_std_test                     91.853214
average_reward_test                  0.870722
round_time_test        0 days 00:00:07.026477
round_time_total       0 days 00:09:28.643824
loss_total                         385.612584
loss_critic                        607.306969
loss_actor                        -501.164983
memory_size                        824973.825 

=== epoch 9/10 ===== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:08,  3.28it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            372.177762
return_std                          79.404536
average_reward                       0.372178
round_time             0 days 00:09:30.190692
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       852.089712
return_std_test                     75.609573
average_reward_test                   0.85209
round_time_test        0 days 00:00:07.062079
round_time_total       0 days 00:09:30.191773
loss_total                         392.436554
loss_critic                        615.930538
loss_actor                        -501.539412
memory_size                        826921.825 

=== epoch 9/10 ===== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:26,  3.19it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            365.858014
return_std                          67.364067
average_reward                       0.365858
round_time             0 days 00:09:30.453554
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       801.347621
return_std_test                     87.985858
average_reward_test                  0.801348
round_time_test        0 days 00:00:06.975732
round_time_total       0 days 00:09:30.454630
loss_total                         393.372006
loss_critic                        617.120818
loss_actor                         -501.62327
memory_size                        828869.825 

=== epoch 9/10 ===== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:30,  3.17it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            372.212334
return_std                          75.136144
average_reward                       0.372212
round_time             0 days 00:09:29.544510
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       873.405198
return_std_test                     91.675856
average_reward_test                  0.873405
round_time_test        0 days 00:00:07.143658
round_time_total       0 days 00:09:29.545581
loss_total                          394.13387
loss_critic                        618.117571
loss_actor                         -501.80096
memory_size                        830817.825 

=== epoch 9/10 ===== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:48,  3.39it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            374.035457
return_std                          75.905225
average_reward                       0.374035
round_time             0 days 00:09:30.806795
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       858.850315
return_std_test                     89.547306
average_reward_test                   0.85885
round_time_test        0 days 00:00:07.315907
round_time_total       0 days 00:09:30.807888
loss_total                         395.874601
loss_critic                          620.4924
loss_actor                        -502.596621
memory_size                        832765.825 

=== epoch 9/10 ===== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:07,  3.28it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            373.412447
return_std                          74.873952
average_reward                       0.373412
round_time             0 days 00:09:31.079091
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       799.067817
return_std_test                     82.557403
average_reward_test                  0.799068
round_time_test        0 days 00:00:06.972807
round_time_total       0 days 00:09:31.080171
loss_total                           400.2494
loss_critic                        626.135332
loss_actor                        -503.294359
memory_size                        834713.825 

=== epoch 9/10 ===== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:01,  3.32it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            399.322964
return_std                            77.9437
average_reward                       0.399323
round_time             0 days 00:09:29.835600
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       824.708961
return_std_test                     62.964614
average_reward_test                  0.824709
round_time_test        0 days 00:00:07.103636
round_time_total       0 days 00:09:29.836674
loss_total                         405.205958
loss_critic                        632.441253
loss_actor                        -503.735255
memory_size                        836661.825 

=== epoch 9/10 ===== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            404.284858
return_std                          75.660268
average_reward                       0.404285
round_time             0 days 00:09:30.738084
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       841.996982
return_std_test                     39.993168
average_reward_test                  0.841997
round_time_test        0 days 00:00:06.895717
round_time_total       0 days 00:09:30.739158
loss_total                         401.434575
loss_critic                        627.906266
loss_actor                        -504.452218
memory_size                        838609.825 

=== epoch 9/10 ===== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:01,  3.32it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            371.529728
return_std                          72.115174
average_reward                        0.37153
round_time             0 days 00:09:29.894439
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       901.803324
return_std_test                      76.80053
average_reward_test                  0.901803
round_time_test        0 days 00:00:07.018907
round_time_total       0 days 00:09:29.895510
loss_total                         399.649304
loss_critic                        625.595919
loss_actor                        -504.137185
memory_size                        840557.825 

=== epoch 9/10 ===== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                             376.21377
return_std                          69.648677
average_reward                       0.376214
round_time             0 days 00:09:30.079998
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       861.109856
return_std_test                     55.030225
average_reward_test                   0.86111
round_time_test        0 days 00:00:07.209663
round_time_total       0 days 00:09:30.081069
loss_total                         407.437234
loss_critic                        635.384793
loss_actor                        -504.353037
memory_size                        842505.825 

=== epoch 9/10 ===== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<10:31,  3.16it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            381.485487
return_std                          74.975438
average_reward                       0.381485
round_time             0 days 00:09:31.329777
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       878.043826
return_std_test                     66.244475
average_reward_test                  0.878044
round_time_test        0 days 00:00:07.072032
round_time_total       0 days 00:09:31.330856
loss_total                         399.427199
loss_critic                        625.416139
loss_actor                        -504.528594
memory_size                        844453.825 

=== epoch 9/10 ===== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:03,  3.31it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            364.678526
return_std                          59.291258
average_reward                       0.364679
round_time             0 days 00:09:30.361706
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        847.45753
return_std_test                     45.718728
average_reward_test                  0.847458
round_time_test        0 days 00:00:07.045009
round_time_total       0 days 00:09:30.362778
loss_total                         396.409901
loss_critic                        621.661753
loss_actor                        -504.597538
memory_size                        846401.825 

=== epoch 9/10 ===== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:43,  3.10it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            343.452188
return_std                          79.234994
average_reward                       0.343452
round_time             0 days 00:09:31.738557
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       872.176545
return_std_test                     52.324986
average_reward_test                  0.872177
round_time_test        0 days 00:00:06.938444
round_time_total       0 days 00:09:31.739637
loss_total                         405.453615
loss_critic                        632.966976
loss_actor                        -504.599864
memory_size                        848349.825 

=== epoch 9/10 ===== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:20,  3.21it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            361.605016
return_std                          80.245369
average_reward                       0.361605
round_time             0 days 00:09:29.972449
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        821.92561
return_std_test                    104.660943
average_reward_test                  0.821926
round_time_test        0 days 00:00:07.006656
round_time_total       0 days 00:09:29.973537
loss_total                         404.814396
loss_critic                        632.166181
loss_actor                        -504.592774
memory_size                        850297.825 

=== epoch 9/10 ===== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:07,  3.28it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            376.139974
return_std                          85.200182
average_reward                        0.37614
round_time             0 days 00:09:29.286198
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       858.767031
return_std_test                     66.367675
average_reward_test                  0.858767
round_time_test        0 days 00:00:06.907750
round_time_total       0 days 00:09:29.287265
loss_total                         396.118136
loss_critic                        621.428412
loss_actor                        -505.123002
memory_size                        852245.825 

=== epoch 9/10 ===== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:53,  3.36it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            347.951419
return_std                          80.764202
average_reward                       0.347951
round_time             0 days 00:09:31.497328
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       826.463895
return_std_test                     81.297317
average_reward_test                  0.826464
round_time_test        0 days 00:00:07.045742
round_time_total       0 days 00:09:31.498406
loss_total                         403.219017
loss_critic                        630.359286
loss_actor                        -505.342095
memory_size                        854193.825 

=== epoch 9/10 ===== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.29it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            361.068771
return_std                          77.629564
average_reward                       0.361069
round_time             0 days 00:09:31.095541
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       793.204485
return_std_test                      93.11756
average_reward_test                  0.793204
round_time_test        0 days 00:00:06.960876
round_time_total       0 days 00:09:31.096613
loss_total                         400.486389
loss_critic                        626.941081
loss_actor                        -505.332411
memory_size                        856141.825 

=== epoch 9/10 ===== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:43,  3.42it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            372.540813
return_std                          55.474063
average_reward                       0.372541
round_time             0 days 00:09:29.281689
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       800.553684
return_std_test                     105.79607
average_reward_test                  0.800554
round_time_test        0 days 00:00:07.019751
round_time_total       0 days 00:09:29.282769
loss_total                         406.423053
loss_critic                        634.357421
loss_actor                        -505.314452
memory_size                        858089.825 

=== epoch 9/10 ===== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.30it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            367.726262
return_std                          53.984718
average_reward                       0.367726
round_time             0 days 00:09:30.526741
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       792.633936
return_std_test                     66.983709
average_reward_test                  0.792634
round_time_test        0 days 00:00:07.018492
round_time_total       0 days 00:09:30.527827
loss_total                         407.478918
loss_critic                        635.839531
loss_actor                        -505.963564
memory_size                        860037.825 

=== epoch 9/10 ===== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:03,  3.31it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                             369.84618
return_std                          56.091383
average_reward                       0.369846
round_time             0 days 00:09:30.532769
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       858.779585
return_std_test                     53.056096
average_reward_test                   0.85878
round_time_test        0 days 00:00:07.095690
round_time_total       0 days 00:09:30.533835
loss_total                         400.807733
loss_critic                        627.729316
loss_actor                        -506.878629
memory_size                        861985.825 

=== epoch 9/10 ===== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:16,  3.24it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            364.495011
return_std                          62.402926
average_reward                       0.364495
round_time             0 days 00:09:30.557048
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       835.624066
return_std_test                    100.464648
average_reward_test                  0.835624
round_time_test        0 days 00:00:07.027661
round_time_total       0 days 00:09:30.558123
loss_total                         407.029238
loss_critic                        635.642404
loss_actor                         -507.42346
memory_size                        863933.825 

=== epoch 9/10 ===== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:56,  3.04it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            375.563841
return_std                          71.362454
average_reward                       0.375564
round_time             0 days 00:09:30.008422
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       784.115351
return_std_test                     73.765476
average_reward_test                  0.784115
round_time_test        0 days 00:00:06.995301
round_time_total       0 days 00:09:30.009483
loss_total                         403.460062
loss_critic                        631.250085
loss_actor                         -507.70006
memory_size                        865881.825 

=== epoch 9/10 ===== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:06,  3.29it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            386.203754
return_std                          68.940833
average_reward                       0.386204
round_time             0 days 00:09:30.286181
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       899.680563
return_std_test                     83.554829
average_reward_test                  0.899681
round_time_test        0 days 00:00:06.969037
round_time_total       0 days 00:09:30.287264
loss_total                         404.404718
loss_critic                        632.413595
loss_actor                        -507.630823
memory_size                        867829.825 

=== epoch 9/10 ===== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:15,  3.24it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            360.975301
return_std                          88.667525
average_reward                       0.360975
round_time             0 days 00:09:28.438555
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       856.993445
return_std_test                      73.92324
average_reward_test                  0.856993
round_time_test        0 days 00:00:07.095263
round_time_total       0 days 00:09:28.439641
loss_total                         401.143703
loss_critic                        628.428933
loss_actor                        -507.997243
memory_size                        869777.825 

=== epoch 9/10 ===== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:10,  3.27it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            365.081906
return_std                          93.025255
average_reward                       0.365082
round_time             0 days 00:09:31.198981
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        815.04186
return_std_test                     72.595877
average_reward_test                  0.815042
round_time_test        0 days 00:00:06.973455
round_time_total       0 days 00:09:31.200080
loss_total                         405.350158
loss_critic                        633.673874
loss_actor                        -507.944741
memory_size                        871725.825 

=== epoch 9/10 ===== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.30it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            378.921493
return_std                          83.515704
average_reward                       0.378921
round_time             0 days 00:09:29.215486
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       796.435402
return_std_test                     71.885019
average_reward_test                  0.796435
round_time_test        0 days 00:00:07.004586
round_time_total       0 days 00:09:29.216560
loss_total                         410.608659
loss_critic                        640.129797
loss_actor                         -507.47592
memory_size                        873673.825 

=== epoch 9/10 ===== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:36,  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 [09:29<00:00,  3.51it/s]
<GE123_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                            352.533605
return_std                          93.265695
average_reward                       0.352534
round_time             0 days 00:09:30.505748
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       912.130475
return_std_test                     75.806274
average_reward_test                   0.91213
round_time_test        0 days 00:00:06.973153
round_time_total       0 days 00:09:30.506832
loss_total                          403.23779
loss_critic                        630.866252
loss_actor                        -507.276092
memory_size                        875621.825 


<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 10/10 ==== round 1/50 ======================================
  0%|          | 7/2000 [00:02<09:44,  3.41it/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 [09:22<00:00,  3.55it/s]
episodes                                    2
episode_length                         1000.0
returns                            385.432157
return_std                           0.722767
average_reward                       0.385432
round_time             0 days 00:09:22.893669
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       884.853051
return_std_test                     78.782749
average_reward_test                  0.884853
round_time_test        0 days 00:00:06.972554
round_time_total       0 days 00:09:22.894767
loss_total                          409.16488
loss_critic                        638.259243
loss_actor                        -507.212604
memory_size                        877570.825 

=== epoch 10/10 ==== round 2/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:56,  3.34it/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 [09:22<00:00,  3.55it/s]
episodes                                    4
episode_length                         1000.0
returns                            408.826501
return_std                          53.620282
average_reward                       0.408827
round_time             0 days 00:09:23.195382
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       859.029548
return_std_test                     82.529104
average_reward_test                   0.85903
round_time_test        0 days 00:00:07.034836
round_time_total       0 days 00:09:23.196466
loss_total                         410.543961
loss_critic                        640.147004
loss_actor                        -507.868245
memory_size                        879518.825 

=== epoch 10/10 ==== round 3/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:54,  3.05it/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 [09:24<00:00,  3.54it/s]
episodes                                    6
episode_length                         1000.0
returns                            395.710167
return_std                          70.903825
average_reward                        0.39571
round_time             0 days 00:09:24.775328
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       783.358693
return_std_test                    121.386484
average_reward_test                  0.783359
round_time_test        0 days 00:00:07.023015
round_time_total       0 days 00:09:24.776395
loss_total                         406.460768
loss_critic                        635.160202
loss_actor                        -508.337003
memory_size                        881466.825 

=== epoch 10/10 ==== round 4/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:24<00:00,  3.55it/s]
episodes                                    8
episode_length                         1000.0
returns                            381.100929
return_std                          78.626146
average_reward                       0.381101
round_time             0 days 00:09:24.535933
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       812.921086
return_std_test                     35.799243
average_reward_test                  0.812921
round_time_test        0 days 00:00:07.189786
round_time_total       0 days 00:09:24.537003
loss_total                         404.751422
loss_critic                        633.117217
loss_actor                        -508.711792
memory_size                        883414.825 

=== epoch 10/10 ==== round 5/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:01,  3.32it/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 [09:24<00:00,  3.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            381.769418
return_std                          70.338799
average_reward                       0.381769
round_time             0 days 00:09:25.458681
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       877.862997
return_std_test                     97.180936
average_reward_test                  0.877863
round_time_test        0 days 00:00:07.053555
round_time_total       0 days 00:09:25.459761
loss_total                         401.700994
loss_critic                         629.38899
loss_actor                        -509.051022
memory_size                        885362.825 

=== epoch 10/10 ==== round 6/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:24<00:00,  3.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            375.915184
return_std                          71.275766
average_reward                       0.375915
round_time             0 days 00:09:25.209475
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       845.458484
return_std_test                     70.322385
average_reward_test                  0.845458
round_time_test        0 days 00:00:06.994315
round_time_total       0 days 00:09:25.210548
loss_total                         411.062207
loss_critic                        641.061642
loss_actor                        -508.935562
memory_size                        887310.825 

=== epoch 10/10 ==== round 7/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:08,  3.28it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            354.370407
return_std                          66.481823
average_reward                        0.35437
round_time             0 days 00:09:27.872210
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       856.807781
return_std_test                    105.915915
average_reward_test                  0.856808
round_time_test        0 days 00:00:07.057440
round_time_total       0 days 00:09:27.873288
loss_total                         418.437059
loss_critic                        650.323933
loss_actor                        -509.110473
memory_size                        889258.825 

=== epoch 10/10 ==== round 8/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:40,  3.12it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            350.570079
return_std                          53.545725
average_reward                        0.35057
round_time             0 days 00:09:27.553562
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       876.693234
return_std_test                     63.112893
average_reward_test                  0.876693
round_time_test        0 days 00:00:07.038219
round_time_total       0 days 00:09:27.554635
loss_total                         416.097534
loss_critic                        647.365345
loss_actor                        -508.973742
memory_size                        891206.825 

=== epoch 10/10 ==== round 9/50 ======================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:21,  3.21it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            355.351914
return_std                           38.08893
average_reward                       0.355352
round_time             0 days 00:09:27.484039
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       851.143804
return_std_test                     66.149348
average_reward_test                  0.851144
round_time_test        0 days 00:00:07.061708
round_time_total       0 days 00:09:27.485101
loss_total                         423.405767
loss_critic                        656.542408
loss_actor                        -509.140831
memory_size                        893154.825 

=== epoch 10/10 ==== round 10/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            317.961318
return_std                         135.628082
average_reward                       0.317961
round_time             0 days 00:09:28.227383
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        861.34289
return_std_test                      85.13112
average_reward_test                  0.861343
round_time_test        0 days 00:00:07.057672
round_time_total       0 days 00:09:28.228483
loss_total                         413.932608
loss_critic                        644.834827
loss_actor                        -509.676299
memory_size                        895102.825 

=== epoch 10/10 ==== round 11/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:03,  3.31it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            328.040146
return_std                         140.440604
average_reward                        0.32804
round_time             0 days 00:09:27.753559
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       835.625543
return_std_test                     88.672866
average_reward_test                  0.835626
round_time_test        0 days 00:00:06.956883
round_time_total       0 days 00:09:27.754626
loss_total                          415.07781
loss_critic                        646.409235
loss_actor                        -510.247927
memory_size                        897050.825 

=== epoch 10/10 ==== round 12/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:17,  3.23it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            354.720411
return_std                           148.1071
average_reward                        0.35472
round_time             0 days 00:09:29.013412
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       853.833479
return_std_test                     64.944929
average_reward_test                  0.853833
round_time_test        0 days 00:00:07.082278
round_time_total       0 days 00:09:29.014482
loss_total                          417.10191
loss_critic                        648.926525
loss_actor                        -510.196584
memory_size                        898998.825 

=== epoch 10/10 ==== round 13/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:56,  3.34it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            358.366318
return_std                         152.717916
average_reward                       0.358366
round_time             0 days 00:09:29.100614
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        832.92332
return_std_test                     47.209951
average_reward_test                  0.832923
round_time_test        0 days 00:00:06.967316
round_time_total       0 days 00:09:29.101713
loss_total                         409.864291
loss_critic                        639.916013
loss_actor                        -510.342628
memory_size                        900946.825 

=== epoch 10/10 ==== round 14/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:29,  3.17it/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 [09:27<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            365.003155
return_std                         160.622818
average_reward                       0.365003
round_time             0 days 00:09:28.051033
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       864.628264
return_std_test                     70.824827
average_reward_test                  0.864628
round_time_test        0 days 00:00:06.961275
round_time_total       0 days 00:09:28.052119
loss_total                         418.785202
loss_critic                        650.999675
loss_actor                        -510.072723
memory_size                        902894.825 

=== epoch 10/10 ==== round 15/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.30it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                             413.93445
return_std                          73.937552
average_reward                       0.413934
round_time             0 days 00:09:29.275089
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       812.153796
return_std_test                     67.068475
average_reward_test                  0.812154
round_time_test        0 days 00:00:07.006401
round_time_total       0 days 00:09:29.276176
loss_total                         416.484701
loss_critic                        648.205436
loss_actor                        -510.398276
memory_size                        904842.825 

=== epoch 10/10 ==== round 16/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:43,  3.42it/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 [09:27<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                             409.32114
return_std                          73.682944
average_reward                       0.409321
round_time             0 days 00:09:27.712060
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        836.43317
return_std_test                     61.892035
average_reward_test                  0.836433
round_time_test        0 days 00:00:07.096789
round_time_total       0 days 00:09:27.713130
loss_total                         431.723836
loss_critic                        667.321366
loss_actor                        -510.666321
memory_size                        906790.825 

=== epoch 10/10 ==== round 17/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:19,  3.22it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            390.034187
return_std                          68.964155
average_reward                       0.390034
round_time             0 days 00:09:29.255359
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       895.489332
return_std_test                     39.144594
average_reward_test                  0.895489
round_time_test        0 days 00:00:07.064626
round_time_total       0 days 00:09:29.256440
loss_total                           422.7541
loss_critic                        656.242629
loss_actor                        -511.200054
memory_size                        908738.825 

=== epoch 10/10 ==== round 18/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:50,  3.07it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            396.767824
return_std                          67.821102
average_reward                       0.396768
round_time             0 days 00:09:28.509630
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       839.923207
return_std_test                     81.778079
average_reward_test                  0.839923
round_time_test        0 days 00:00:06.898530
round_time_total       0 days 00:09:28.510712
loss_total                         421.376589
loss_critic                        654.620676
loss_actor                        -511.599792
memory_size                        910686.825 

=== epoch 10/10 ==== round 19/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.30it/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 [09:26<00:00,  3.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            383.687475
return_std                          55.391264
average_reward                       0.383687
round_time             0 days 00:09:27.355446
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       841.110773
return_std_test                     71.834167
average_reward_test                  0.841111
round_time_test        0 days 00:00:07.068851
round_time_total       0 days 00:09:27.356521
loss_total                         424.261032
loss_critic                        658.260652
loss_actor                        -511.737485
memory_size                        912634.825 

=== epoch 10/10 ==== round 20/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:18,  3.23it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            371.127209
return_std                           59.41894
average_reward                       0.371127
round_time             0 days 00:09:30.242009
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       874.260453
return_std_test                    107.295816
average_reward_test                   0.87426
round_time_test        0 days 00:00:07.005355
round_time_total       0 days 00:09:30.243081
loss_total                          416.03873
loss_critic                        648.118408
loss_actor                        -512.280018
memory_size                        914582.825 

=== epoch 10/10 ==== round 21/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:16,  3.24it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            365.561062
return_std                          60.712308
average_reward                       0.365561
round_time             0 days 00:09:29.638270
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       836.399157
return_std_test                    111.277972
average_reward_test                  0.836399
round_time_test        0 days 00:00:06.961869
round_time_total       0 days 00:09:29.639359
loss_total                         423.392852
loss_critic                        657.342214
loss_actor                        -512.404633
memory_size                        916530.825 

=== epoch 10/10 ==== round 22/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:09,  3.27it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                              371.0629
return_std                           79.18264
average_reward                       0.371063
round_time             0 days 00:09:30.452592
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       887.507812
return_std_test                     46.806775
average_reward_test                  0.887508
round_time_test        0 days 00:00:06.941814
round_time_total       0 days 00:09:30.453660
loss_total                         423.556642
loss_critic                         657.56843
loss_actor                        -512.490545
memory_size                        918478.825 

=== epoch 10/10 ==== round 23/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:08,  2.99it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            353.679045
return_std                          70.208781
average_reward                       0.353679
round_time             0 days 00:09:30.920828
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       855.342036
return_std_test                     58.398671
average_reward_test                  0.855342
round_time_test        0 days 00:00:07.020312
round_time_total       0 days 00:09:30.921919
loss_total                         419.770912
loss_critic                         652.93853
loss_actor                        -512.899592
memory_size                        920426.825 

=== epoch 10/10 ==== round 24/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:05,  3.29it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            367.494318
return_std                          71.457457
average_reward                       0.367494
round_time             0 days 00:09:30.317739
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        816.24378
return_std_test                     68.991743
average_reward_test                  0.816244
round_time_test        0 days 00:00:07.185080
round_time_total       0 days 00:09:30.318813
loss_total                         431.434508
loss_critic                        667.771509
loss_actor                        -513.913532
memory_size                        922374.825 

=== epoch 10/10 ==== round 25/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:59,  3.33it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            375.746544
return_std                          67.909284
average_reward                       0.375747
round_time             0 days 00:09:31.110794
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       872.774273
return_std_test                     90.581329
average_reward_test                  0.872774
round_time_test        0 days 00:00:07.080061
round_time_total       0 days 00:09:31.111921
loss_total                         414.478514
loss_critic                        646.670115
loss_actor                        -514.287928
memory_size                        924322.825 

=== epoch 10/10 ==== round 26/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            373.383848
return_std                          70.999955
average_reward                       0.373384
round_time             0 days 00:09:28.635798
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       895.010341
return_std_test                     70.589199
average_reward_test                   0.89501
round_time_test        0 days 00:00:06.914042
round_time_total       0 days 00:09:28.636862
loss_total                         424.247545
loss_critic                        658.951525
loss_actor                        -514.568406
memory_size                        926270.825 

=== epoch 10/10 ==== round 27/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:11,  2.97it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            372.479283
return_std                          53.362335
average_reward                       0.372479
round_time             0 days 00:09:30.794530
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       869.562862
return_std_test                     87.949149
average_reward_test                  0.869563
round_time_test        0 days 00:00:06.987790
round_time_total       0 days 00:09:30.795613
loss_total                           423.9216
loss_critic                        658.483528
loss_actor                        -514.326149
memory_size                        928218.825 

=== epoch 10/10 ==== round 28/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:50,  3.06it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            400.731337
return_std                          58.854768
average_reward                       0.400731
round_time             0 days 00:09:29.290104
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       863.277889
return_std_test                    103.129811
average_reward_test                  0.863278
round_time_test        0 days 00:00:07.056322
round_time_total       0 days 00:09:29.291174
loss_total                         426.583392
loss_critic                        661.701258
loss_actor                        -513.888113
memory_size                        930166.825 

=== epoch 10/10 ==== round 29/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<11:02,  3.01it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            394.804767
return_std                          59.704871
average_reward                       0.394805
round_time             0 days 00:09:30.246808
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       886.423759
return_std_test                     88.561244
average_reward_test                  0.886424
round_time_test        0 days 00:00:07.048964
round_time_total       0 days 00:09:30.247888
loss_total                         421.871274
loss_critic                        655.908802
loss_actor                        -514.278876
memory_size                        932114.825 

=== epoch 10/10 ==== round 30/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:57,  3.34it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            384.310647
return_std                          61.056429
average_reward                       0.384311
round_time             0 days 00:09:31.880000
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       851.823318
return_std_test                     77.574794
average_reward_test                  0.851823
round_time_test        0 days 00:00:07.146692
round_time_total       0 days 00:09:31.881082
loss_total                         429.484332
loss_critic                        665.404646
loss_actor                        -514.196957
memory_size                        934062.825 

=== epoch 10/10 ==== round 31/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:03,  3.31it/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 [09:28<00:00,  3.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            384.494082
return_std                          57.031305
average_reward                       0.384494
round_time             0 days 00:09:28.949331
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       843.248359
return_std_test                     60.550825
average_reward_test                  0.843248
round_time_test        0 days 00:00:07.116364
round_time_total       0 days 00:09:28.950449
loss_total                         430.732252
loss_critic                        666.972681
loss_actor                        -514.229498
memory_size                        936010.825 

=== epoch 10/10 ==== round 32/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:22,  3.21it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            385.200601
return_std                          53.402072
average_reward                       0.385201
round_time             0 days 00:09:31.274528
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       804.647544
return_std_test                    101.535056
average_reward_test                  0.804648
round_time_test        0 days 00:00:07.059435
round_time_total       0 days 00:09:31.275601
loss_total                         424.083088
loss_critic                        658.689992
loss_actor                        -514.344561
memory_size                        937958.825 

=== epoch 10/10 ==== round 33/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:11,  3.26it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            374.581009
return_std                          49.381782
average_reward                       0.374581
round_time             0 days 00:09:31.233819
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       855.779789
return_std_test                     64.465169
average_reward_test                   0.85578
round_time_test        0 days 00:00:06.963225
round_time_total       0 days 00:09:31.234893
loss_total                         434.548032
loss_critic                        671.798924
loss_actor                        -514.455574
memory_size                        939906.825 

=== epoch 10/10 ==== round 34/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:15,  3.24it/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 [09:30<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            377.869483
return_std                          57.605921
average_reward                       0.377869
round_time             0 days 00:09:30.854293
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       881.786615
return_std_test                     28.593894
average_reward_test                  0.881787
round_time_test        0 days 00:00:07.049372
round_time_total       0 days 00:09:30.855378
loss_total                         426.761254
loss_critic                        662.093266
loss_actor                        -514.566826
memory_size                        941854.825 

=== epoch 10/10 ==== round 35/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:32,  3.16it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            376.004683
return_std                          59.747977
average_reward                       0.376005
round_time             0 days 00:09:31.592152
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       857.590021
return_std_test                     69.491997
average_reward_test                   0.85759
round_time_test        0 days 00:00:07.044864
round_time_total       0 days 00:09:31.593214
loss_total                         433.601286
loss_critic                        670.620707
loss_actor                        -514.476437
memory_size                        943802.825 

=== epoch 10/10 ==== round 36/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:50,  3.38it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            364.841018
return_std                          72.030564
average_reward                       0.364841
round_time             0 days 00:09:31.421107
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       920.088359
return_std_test                      33.04931
average_reward_test                  0.920088
round_time_test        0 days 00:00:06.994064
round_time_total       0 days 00:09:31.422212
loss_total                         426.574535
loss_critic                        661.900492
loss_actor                        -514.729327
memory_size                        945750.825 

=== epoch 10/10 ==== round 37/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:39,  3.12it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                             355.90612
return_std                          71.255043
average_reward                       0.355906
round_time             0 days 00:09:31.956289
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       839.264396
return_std_test                     77.972562
average_reward_test                  0.839264
round_time_test        0 days 00:00:07.047054
round_time_total       0 days 00:09:31.957372
loss_total                         432.398443
loss_critic                        669.265127
loss_actor                        -515.068332
memory_size                        947698.825 

=== epoch 10/10 ==== round 38/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:33,  3.48it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            356.140156
return_std                          67.141366
average_reward                        0.35614
round_time             0 days 00:09:30.028650
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       883.381157
return_std_test                     80.113745
average_reward_test                  0.883381
round_time_test        0 days 00:00:07.018268
round_time_total       0 days 00:09:30.029739
loss_total                         438.785461
loss_critic                        677.347027
loss_actor                        -515.460841
memory_size                        949646.825 

=== epoch 10/10 ==== round 39/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                             354.80977
return_std                          66.359441
average_reward                        0.35481
round_time             0 days 00:09:31.184510
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       828.848387
return_std_test                     67.065183
average_reward_test                  0.828848
round_time_test        0 days 00:00:07.059479
round_time_total       0 days 00:09:31.185594
loss_total                         426.812506
loss_critic                        662.504906
loss_actor                        -515.957128
memory_size                        951594.825 

=== epoch 10/10 ==== round 40/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:11,  3.26it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            355.090936
return_std                          60.112159
average_reward                       0.355091
round_time             0 days 00:09:30.457267
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       825.028299
return_std_test                     66.731635
average_reward_test                  0.825028
round_time_test        0 days 00:00:06.984106
round_time_total       0 days 00:09:30.458364
loss_total                         440.222629
loss_critic                         679.17085
loss_actor                        -515.570292
memory_size                        953542.825 

=== epoch 10/10 ==== round 41/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:30,  3.16it/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 [09:32<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            387.286643
return_std                          57.463945
average_reward                       0.387287
round_time             0 days 00:09:32.672701
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       862.218335
return_std_test                    127.660529
average_reward_test                  0.862218
round_time_test        0 days 00:00:06.975856
round_time_total       0 days 00:09:32.673774
loss_total                         428.980248
loss_critic                        665.118707
loss_actor                        -515.573627
memory_size                        955490.825 

=== epoch 10/10 ==== round 42/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:47,  3.40it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            384.349537
return_std                          59.744926
average_reward                        0.38435
round_time             0 days 00:09:31.750830
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       877.200849
return_std_test                     60.033537
average_reward_test                  0.877201
round_time_test        0 days 00:00:06.984759
round_time_total       0 days 00:09:31.752006
loss_total                         443.067051
loss_critic                        682.762215
loss_actor                        -515.713646
memory_size                        957438.825 

=== epoch 10/10 ==== round 43/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:09,  3.27it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            378.425685
return_std                          53.575725
average_reward                       0.378426
round_time             0 days 00:09:32.242250
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       777.471126
return_std_test                    270.974745
average_reward_test                  0.777471
round_time_test        0 days 00:00:06.892457
round_time_total       0 days 00:09:32.243329
loss_total                         429.496642
loss_critic                        665.770009
loss_actor                        -515.596864
memory_size                        959386.825 

=== epoch 10/10 ==== round 44/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:30,  3.16it/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 [09:30<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            357.516957
return_std                          68.964313
average_reward                       0.357517
round_time             0 days 00:09:31.339169
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       857.717782
return_std_test                     87.336264
average_reward_test                  0.857718
round_time_test        0 days 00:00:06.878715
round_time_total       0 days 00:09:31.340239
loss_total                         431.728065
loss_critic                        668.775824
loss_actor                        -516.463005
memory_size                        961334.825 

=== epoch 10/10 ==== round 45/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:20,  3.21it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            363.595963
return_std                          71.596476
average_reward                       0.363596
round_time             0 days 00:09:29.802689
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       912.730761
return_std_test                     83.001013
average_reward_test                  0.912731
round_time_test        0 days 00:00:07.064796
round_time_total       0 days 00:09:29.803766
loss_total                          437.04415
loss_critic                        675.399958
loss_actor                         -516.37912
memory_size                        963282.825 

=== epoch 10/10 ==== round 46/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<09:52,  3.36it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            372.603389
return_std                          85.276287
average_reward                       0.372603
round_time             0 days 00:09:31.543337
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       851.778998
return_std_test                      87.70507
average_reward_test                  0.851779
round_time_test        0 days 00:00:06.925585
round_time_total       0 days 00:09:31.544411
loss_total                         441.560742
loss_critic                        681.095032
loss_actor                        -516.576458
memory_size                        965230.825 

=== epoch 10/10 ==== round 47/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:02,  3.31it/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 [09:29<00:00,  3.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            394.456338
return_std                          86.882062
average_reward                       0.394456
round_time             0 days 00:09:30.350885
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       821.802943
return_std_test                     74.210267
average_reward_test                  0.821803
round_time_test        0 days 00:00:07.023912
round_time_total       0 days 00:09:30.351964
loss_total                         427.669205
loss_critic                        663.879617
loss_actor                         -517.17248
memory_size                        967178.825 

=== epoch 10/10 ==== round 48/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:16,  3.24it/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 [09:32<00:00,  3.49it/s]
episodes                                   10
episode_length                         1000.0
returns                             393.05987
return_std                            86.5189
average_reward                        0.39306
round_time             0 days 00:09:33.419895
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       884.460301
return_std_test                     63.725922
average_reward_test                   0.88446
round_time_test        0 days 00:00:07.068639
round_time_total       0 days 00:09:33.420963
loss_total                         439.201104
loss_critic                        678.331597
loss_actor                        -517.320905
memory_size                        969126.825 

=== epoch 10/10 ==== round 49/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:16,  3.23it/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 [09:31<00:00,  3.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            415.774917
return_std                          64.375417
average_reward                       0.415775
round_time             0 days 00:09:31.732158
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       861.330172
return_std_test                      34.19742
average_reward_test                   0.86133
round_time_test        0 days 00:00:07.096936
round_time_total       0 days 00:09:31.733225
loss_total                         442.009468
loss_critic                        681.763413
loss_actor                        -517.006354
memory_size                        971074.825 

=== epoch 10/10 ==== round 50/50 =====================================
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 5/2000 [00:01<10:00,  3.32it/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 [09:31<00:00,  3.50it/s]
<GE123_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
episodes                                   10
episode_length                         1000.0
returns                            406.263559
return_std                          69.186688
average_reward                       0.406264
round_time             0 days 00:09:31.833489
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       794.733987
return_std_test                     73.751544
average_reward_test                  0.794734
round_time_test        0 days 00:00:07.051486
round_time_total       0 days 00:09:31.834555
loss_total                         439.251406
loss_critic                        678.297209
loss_actor                        -516.931848
memory_size                        973022.825 


