/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/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DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date.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DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date.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: 4
   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'
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>

<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 1/10 ===== round 1/50 ======================================
100%|██████████| 2000/2000 [00:01<00:00, 1417.31it/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DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date.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(
episodes                                    2
episode_length                         1000.0
returns                           -235.645814
return_std                          17.334005
average_reward                      -0.235646
round_time             0 days 00:00:01.485821
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -9.209626
return_std_test                      2.976997
average_reward_test                  -0.00921
round_time_test        0 days 00:00:07.318884
round_time_total       0 days 00:00:09.003988 

=== epoch 1/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1422.48it/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(
episodes                                    4
episode_length                         1000.0
returns                           -235.877396
return_std                          46.667932
average_reward                      -0.235877
round_time             0 days 00:00:01.890748
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                          -8.3275
return_std_test                      4.426628
average_reward_test                 -0.008328
round_time_test        0 days 00:00:07.394993
round_time_total       0 days 00:00:09.013776 

=== epoch 1/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1271.73it/s]
/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
episodes                                    6
episode_length                         1000.0
returns                           -250.041599
return_std                          44.250185
average_reward                      -0.250042
round_time             0 days 00:00:02.024210
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         -7.78805
return_std_test                      4.611209
average_reward_test                 -0.007788
round_time_test        0 days 00:00:07.559006
round_time_total       0 days 00:00:09.265229 

=== epoch 1/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1384.03it/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(
episodes                                    8
episode_length                         1000.0
returns                           -270.331846
return_std                          75.485556
average_reward                      -0.270332
round_time             0 days 00:00:01.902529
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -7.527189
return_std_test                      5.225061
average_reward_test                 -0.007527
round_time_test        0 days 00:00:07.431891
round_time_total       0 days 00:00:09.056300 

=== epoch 1/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
100%|██████████| 2000/2000 [00:01<00:00, 1397.30it/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(
episodes                                   10
episode_length                         1000.0
returns                           -270.027541
return_std                          67.984626
average_reward                      -0.270028
round_time             0 days 00:00:01.913451
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -5.658627
return_std_test                      3.613095
average_reward_test                 -0.005659
round_time_test        0 days 00:00:07.473121
round_time_total       0 days 00:00:09.136546 

=== epoch 1/10 ===== round 6/50 ======================================
<GE432_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%|          | 3/2000 [00:01<16:18,  2.04it/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 [14:43<00:00,  2.26it/s]
starting training
episodes                                   10
episode_length                         1000.0
returns                           -260.802777
return_std                          89.086258
average_reward                      -0.260803
round_time             0 days 00:14:44.051295
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -9.559201
return_std_test                      3.645959
average_reward_test                 -0.009559
round_time_test        0 days 00:00:07.392913
round_time_total       0 days 00:14:44.052563
loss_total                          559.64535
loss_critic                        724.931346
loss_actor                         -101.49868
memory_size                         10610.061 

=== epoch 1/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:13,  1.93it/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 [15:38<00:00,  2.13it/s]
episodes                                   10
episode_length                         1000.0
returns                           -253.607782
return_std                          91.765615
average_reward                      -0.253608
round_time             0 days 00:15:39.328027
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -65.701789
return_std_test                      8.699051
average_reward_test                 -0.065702
round_time_test        0 days 00:00:08.296259
round_time_total       0 days 00:15:39.329148
loss_total                         273.913225
loss_critic                        391.368744
loss_actor                        -195.908878
memory_size                         12542.061 

=== epoch 1/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:07,  1.94it/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 [15:38<00:00,  2.13it/s]
episodes                                   10
episode_length                         1000.0
returns                           -248.232293
return_std                          90.724454
average_reward                      -0.248232
round_time             0 days 00:15:39.042636
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -179.726056
return_std_test                    108.292038
average_reward_test                 -0.179726
round_time_test        0 days 00:00:08.261419
round_time_total       0 days 00:15:39.043739
loss_total                         196.235672
loss_critic                         306.65987
loss_actor                        -245.461133
memory_size                         14474.061 

=== epoch 1/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:16,  1.93it/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 [15:41<00:00,  2.12it/s]
episodes                                   10
episode_length                         1000.0
returns                           -238.316628
return_std                          67.800957
average_reward                      -0.238317
round_time             0 days 00:15:42.389637
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -83.152115
return_std_test                     77.743811
average_reward_test                 -0.083152
round_time_test        0 days 00:00:08.347355
round_time_total       0 days 00:15:42.390752
loss_total                         164.837598
loss_critic                        274.623318
loss_actor                        -274.305288
memory_size                         16406.061 

=== epoch 1/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:22,  1.91it/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 [15:50<00:00,  2.10it/s]
episodes                                   10
episode_length                         1000.0
returns                           -225.113073
return_std                          69.116493
average_reward                      -0.225113
round_time             0 days 00:15:50.792434
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -30.732507
return_std_test                     242.36047
average_reward_test                 -0.030733
round_time_test        0 days 00:00:08.226994
round_time_total       0 days 00:15:50.793830
loss_total                         188.805108
loss_critic                         307.45229
loss_actor                        -285.783633
memory_size                         18338.061 

=== epoch 1/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:23,  2.16it/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 [15:53<00:00,  2.10it/s]
episodes                                   10
episode_length                         1000.0
returns                           -227.974622
return_std                           52.79561
average_reward                      -0.227975
round_time             0 days 00:15:53.738643
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -112.937181
return_std_test                     13.566525
average_reward_test                 -0.112937
round_time_test        0 days 00:00:08.478830
round_time_total       0 days 00:15:53.739783
loss_total                         170.611317
loss_critic                        283.878363
loss_actor                        -282.456875
memory_size                         20270.061 

=== epoch 1/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:48,  1.87it/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 [15:53<00:00,  2.10it/s]
episodes                                   10
episode_length                         1000.0
returns                           -235.847588
return_std                          48.227142
average_reward                      -0.235848
round_time             0 days 00:15:53.918515
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -292.632692
return_std_test                     25.463079
average_reward_test                 -0.292633
round_time_test        0 days 00:00:08.271130
round_time_total       0 days 00:15:53.919787
loss_total                         261.296821
loss_critic                         396.31187
loss_actor                        -278.763397
memory_size                         22202.061 

=== epoch 1/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:57,  2.09it/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 [15:59<00:00,  2.09it/s]
episodes                                   10
episode_length                         1000.0
returns                           -240.332582
return_std                          50.504893
average_reward                      -0.240333
round_time             0 days 00:15:59.612539
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -216.022999
return_std_test                     22.547358
average_reward_test                 -0.216023
round_time_test        0 days 00:00:08.289863
round_time_total       0 days 00:15:59.613868
loss_total                         189.312144
loss_critic                        304.508223
loss_actor                        -271.472185
memory_size                         24134.061 

=== epoch 1/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:09,  2.06it/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 [16:02<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                           -240.722478
return_std                          64.477055
average_reward                      -0.240722
round_time             0 days 00:16:02.862904
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -29.685484
return_std_test                     70.649965
average_reward_test                 -0.029685
round_time_test        0 days 00:00:08.231075
round_time_total       0 days 00:16:02.864096
loss_total                         235.277553
loss_critic                        359.806608
loss_actor                        -262.838691
memory_size                         26066.061 

=== epoch 1/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:55,  1.86it/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 [16:03<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                           -236.080361
return_std                          67.225532
average_reward                       -0.23608
round_time             0 days 00:16:03.624159
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -266.945054
return_std_test                     39.209933
average_reward_test                 -0.266945
round_time_test        0 days 00:00:08.284917
round_time_total       0 days 00:16:03.625601
loss_total                         240.183652
loss_critic                        364.297388
loss_actor                        -256.271314
memory_size                         27998.061 

=== epoch 1/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:41,  1.99it/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 [16:06<00:00,  2.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -230.628455
return_std                          69.356709
average_reward                      -0.230628
round_time             0 days 00:16:06.717308
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         6.830192
return_std_test                    162.920498
average_reward_test                   0.00683
round_time_test        0 days 00:00:08.242596
round_time_total       0 days 00:16:06.718431
loss_total                         237.018332
loss_critic                        359.480964
loss_actor                        -252.832221
memory_size                         29930.061 

=== epoch 1/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:19,  1.92it/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 [16:06<00:00,  2.07it/s]
episodes                                   10
episode_length                         1000.0
returns                           -235.825866
return_std                          67.476834
average_reward                      -0.235826
round_time             0 days 00:16:06.768617
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        -36.54565
return_std_test                    139.205061
average_reward_test                 -0.036546
round_time_test        0 days 00:00:08.251819
round_time_total       0 days 00:16:06.769728
loss_total                         264.549813
loss_critic                        393.526311
loss_actor                        -251.356201
memory_size                         31862.061 

=== epoch 1/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:49,  1.87it/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 [16:12<00:00,  2.06it/s]
episodes                                   10
episode_length                         1000.0
returns                           -214.487414
return_std                          77.005081
average_reward                      -0.214487
round_time             0 days 00:16:13.350926
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -91.314176
return_std_test                     38.601207
average_reward_test                 -0.091314
round_time_test        0 days 00:00:08.706132
round_time_total       0 days 00:16:13.352188
loss_total                          303.46807
loss_critic                        441.234328
loss_actor                        -247.596994
memory_size                         33794.061 

=== epoch 1/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:53,  1.97it/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 [16:13<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -211.111379
return_std                           66.59993
average_reward                      -0.211111
round_time             0 days 00:16:14.521866
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -151.964637
return_std_test                     15.340489
average_reward_test                 -0.151965
round_time_test        0 days 00:00:08.316117
round_time_total       0 days 00:16:14.523013
loss_total                         323.580177
loss_critic                        465.071081
loss_actor                        -242.383472
memory_size                         35726.061 

=== epoch 1/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:50,  1.87it/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 [16:20<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                           -213.253932
return_std                          65.675503
average_reward                      -0.213254
round_time             0 days 00:16:20.971864
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        52.749985
return_std_test                     86.415872
average_reward_test                   0.05275
round_time_test        0 days 00:00:08.417355
round_time_total       0 days 00:16:20.972969
loss_total                          335.06192
loss_critic                        478.251205
loss_actor                         -237.69525
memory_size                         37658.061 

=== epoch 1/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:16,  1.93it/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 [16:17<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                           -215.711742
return_std                          61.784243
average_reward                      -0.215712
round_time             0 days 00:16:18.393804
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -126.376289
return_std_test                     19.302209
average_reward_test                 -0.126376
round_time_test        0 days 00:00:08.382588
round_time_total       0 days 00:16:18.394915
loss_total                         330.941859
loss_critic                        472.347632
loss_actor                        -234.681265
memory_size                         39590.061 

=== epoch 1/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:38,  2.00it/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 [16:21<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                            -196.17404
return_std                           58.58761
average_reward                      -0.196174
round_time             0 days 00:16:22.218453
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -34.936629
return_std_test                     48.000093
average_reward_test                 -0.034937
round_time_test        0 days 00:00:08.355637
round_time_total       0 days 00:16:22.219823
loss_total                         313.024414
loss_critic                         449.95775
loss_actor                         -234.70896
memory_size                         41522.061 

=== epoch 1/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:46,  1.87it/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 [16:22<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                           -189.763775
return_std                          54.709988
average_reward                      -0.189764
round_time             0 days 00:16:23.240554
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -147.093976
return_std_test                     67.236144
average_reward_test                 -0.147094
round_time_test        0 days 00:00:08.315642
round_time_total       0 days 00:16:23.242029
loss_total                         311.539547
loss_critic                        448.491665
loss_actor                        -236.268958
memory_size                         43454.061 

=== epoch 1/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:38,  2.00it/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 [16:22<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.492506
return_std                          32.457712
average_reward                      -0.170493
round_time             0 days 00:16:22.708130
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         12.49334
return_std_test                     82.780315
average_reward_test                  0.012493
round_time_test        0 days 00:00:08.248783
round_time_total       0 days 00:16:22.709240
loss_total                         327.236912
loss_critic                         468.07921
loss_actor                        -236.132315
memory_size                         45386.061 

=== epoch 1/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:08,  1.83it/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 [16:27<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.118731
return_std                          37.537602
average_reward                      -0.162119
round_time             0 days 00:16:27.886298
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        71.264769
return_std_test                    173.219772
average_reward_test                  0.071265
round_time_test        0 days 00:00:08.160065
round_time_total       0 days 00:16:27.887424
loss_total                          327.64244
loss_critic                        468.539896
loss_actor                        -235.947415
memory_size                         47318.061 

=== epoch 1/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:50,  1.87it/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 [16:28<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -170.429152
return_std                          47.690286
average_reward                      -0.170429
round_time             0 days 00:16:28.615194
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         4.281999
return_std_test                    193.150535
average_reward_test                  0.004282
round_time_test        0 days 00:00:08.604912
round_time_total       0 days 00:16:28.616437
loss_total                          319.05741
loss_critic                         457.60076
loss_actor                        -235.116023
memory_size                         49250.061 

=== epoch 1/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:34,  1.79it/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 [16:29<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                            -166.70419
return_std                          50.873036
average_reward                      -0.166704
round_time             0 days 00:16:30.489534
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       -78.576907
return_std_test                     80.235738
average_reward_test                 -0.078577
round_time_test        0 days 00:00:08.220319
round_time_total       0 days 00:16:30.490835
loss_total                         324.864637
loss_critic                        464.632011
loss_actor                        -234.204888
memory_size                         51182.061 

=== epoch 1/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:04,  1.95it/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 [16:27<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                           -181.151906
return_std                          53.013811
average_reward                      -0.181152
round_time             0 days 00:16:28.184404
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        38.329581
return_std_test                    159.172946
average_reward_test                   0.03833
round_time_test        0 days 00:00:08.283449
round_time_total       0 days 00:16:28.185496
loss_total                         328.941935
loss_critic                        469.307573
loss_actor                        -232.520649
memory_size                         53114.061 

=== epoch 1/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:10,  1.94it/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 [16:31<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -179.977346
return_std                          53.538398
average_reward                      -0.179977
round_time             0 days 00:16:31.827524
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -113.509683
return_std_test                     53.965149
average_reward_test                  -0.11351
round_time_test        0 days 00:00:08.197064
round_time_total       0 days 00:16:31.828623
loss_total                         319.211242
loss_critic                         457.08637
loss_actor                        -232.289298
memory_size                         55046.061 

=== epoch 1/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:35,  1.89it/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 [16:29<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -177.430424
return_std                          61.537099
average_reward                       -0.17743
round_time             0 days 00:16:30.117494
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -104.390618
return_std_test                     60.900086
average_reward_test                 -0.104391
round_time_test        0 days 00:00:08.428501
round_time_total       0 days 00:16:30.118812
loss_total                         327.555438
loss_critic                          467.4479
loss_actor                        -232.014437
memory_size                         56978.061 

=== epoch 1/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<19:57,  1.67it/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 [16:32<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                           -162.395911
return_std                          53.792899
average_reward                      -0.162396
round_time             0 days 00:16:33.070931
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       433.865897
return_std_test                    111.497194
average_reward_test                  0.433866
round_time_test        0 days 00:00:08.450683
round_time_total       0 days 00:16:33.072037
loss_total                         333.694905
loss_critic                        475.265916
loss_actor                        -232.589171
memory_size                         58910.061 

=== epoch 1/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:04,  1.84it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -157.032074
return_std                          53.823606
average_reward                      -0.157032
round_time             0 days 00:16:36.730132
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      -138.825965
return_std_test                     12.559168
average_reward_test                 -0.138826
round_time_test        0 days 00:00:08.356393
round_time_total       0 days 00:16:36.731284
loss_total                         324.170627
loss_critic                        463.706766
loss_actor                        -233.973964
memory_size                         60842.061 

=== epoch 1/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:17,  1.93it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -143.837889
return_std                          42.862994
average_reward                      -0.143838
round_time             0 days 00:16:37.376151
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       338.275649
return_std_test                    316.844895
average_reward_test                  0.338276
round_time_test        0 days 00:00:08.301478
round_time_total       0 days 00:16:37.377498
loss_total                         325.465909
loss_critic                        465.914956
loss_actor                        -236.330311
memory_size                         62774.061 

=== epoch 1/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:33,  1.90it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -146.764309
return_std                          45.898485
average_reward                      -0.146764
round_time             0 days 00:16:36.947757
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       327.492685
return_std_test                    237.342192
average_reward_test                  0.327493
round_time_test        0 days 00:00:08.104375
round_time_total       0 days 00:16:36.948899
loss_total                         332.327642
loss_critic                        475.101618
loss_actor                        -238.768292
memory_size                         64706.061 

=== epoch 1/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:16,  1.82it/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 [16:34<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -146.635872
return_std                          27.152297
average_reward                      -0.146636
round_time             0 days 00:16:35.503852
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        344.63585
return_std_test                    176.561162
average_reward_test                  0.344636
round_time_test        0 days 00:00:08.134894
round_time_total       0 days 00:16:35.505273
loss_total                         334.027416
loss_critic                        477.483482
loss_actor                        -239.796881
memory_size                         66638.061 

=== epoch 1/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:25,  1.81it/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 [16:34<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -136.788393
return_std                          32.006842
average_reward                      -0.136788
round_time             0 days 00:16:35.504576
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       442.611557
return_std_test                     71.674344
average_reward_test                  0.442612
round_time_test        0 days 00:00:08.035667
round_time_total       0 days 00:16:35.505685
loss_total                          330.93114
loss_critic                        473.764898
loss_actor                        -240.403921
memory_size                         68570.061 

=== epoch 1/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:02,  1.85it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -138.918795
return_std                          31.379878
average_reward                      -0.138919
round_time             0 days 00:16:36.842399
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       384.358678
return_std_test                    161.562172
average_reward_test                  0.384359
round_time_test        0 days 00:00:08.020130
round_time_total       0 days 00:16:36.843854
loss_total                         317.756446
loss_critic                        457.674113
loss_actor                        -241.914252
memory_size                         70502.061 

=== epoch 1/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:49,  1.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [16:34<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -136.769401
return_std                          30.754635
average_reward                      -0.136769
round_time             0 days 00:16:35.313964
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       384.035466
return_std_test                    206.976195
average_reward_test                  0.384035
round_time_test        0 days 00:00:08.308243
round_time_total       0 days 00:16:35.315085
loss_total                         315.378482
loss_critic                        455.198881
loss_actor                        -243.903146
memory_size                         72434.061 

=== epoch 1/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:02,  1.84it/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 [16:35<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                           -128.865292
return_std                          20.108444
average_reward                      -0.128865
round_time             0 days 00:16:35.762732
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       426.882355
return_std_test                    143.403697
average_reward_test                  0.426882
round_time_test        0 days 00:00:08.090618
round_time_total       0 days 00:16:35.764182
loss_total                         309.886434
loss_critic                        448.810559
loss_actor                        -245.810101
memory_size                         74366.061 

=== epoch 1/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:32,  2.01it/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 [16:38<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -132.997535
return_std                          34.347461
average_reward                      -0.132998
round_time             0 days 00:16:39.111860
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       509.942271
return_std_test                     63.646111
average_reward_test                  0.509942
round_time_test        0 days 00:00:08.387185
round_time_total       0 days 00:16:39.113184
loss_total                         330.658056
loss_critic                         475.08813
loss_actor                        -247.062269
memory_size                         76298.061 

=== epoch 1/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:25,  1.91it/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 [16:39<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -139.384022
return_std                          31.536129
average_reward                      -0.139384
round_time             0 days 00:16:39.841284
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       538.759914
return_std_test                    102.995428
average_reward_test                   0.53876
round_time_test        0 days 00:00:08.139624
round_time_total       0 days 00:16:39.842468
loss_total                         326.053318
loss_critic                        469.538657
loss_actor                        -247.888067
memory_size                         78230.061 

=== epoch 1/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:33,  1.79it/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 [16:42<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                           -129.354899
return_std                          41.452026
average_reward                      -0.129355
round_time             0 days 00:16:42.553341
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       574.344205
return_std_test                    102.455557
average_reward_test                  0.574344
round_time_test        0 days 00:00:08.218837
round_time_total       0 days 00:16:42.554807
loss_total                         324.878494
loss_critic                         468.14732
loss_actor                        -248.196839
memory_size                         80162.061 

=== epoch 1/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:06,  1.84it/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 [16:44<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -136.550083
return_std                          43.749806
average_reward                       -0.13655
round_time             0 days 00:16:44.939027
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        468.35141
return_std_test                     63.758228
average_reward_test                  0.468351
round_time_test        0 days 00:00:08.174249
round_time_total       0 days 00:16:44.940396
loss_total                         317.399002
loss_critic                        458.859774
loss_actor                        -248.444119
memory_size                         82094.061 

=== epoch 1/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:32,  1.90it/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 [16:45<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -127.440162
return_std                          47.404415
average_reward                       -0.12744
round_time             0 days 00:16:46.478644
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       464.483419
return_std_test                    101.151817
average_reward_test                  0.464483
round_time_test        0 days 00:00:08.081864
round_time_total       0 days 00:16:46.479772
loss_total                         321.889855
loss_critic                        464.601105
loss_actor                        -248.955175
memory_size                         84026.061 

=== epoch 1/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:28,  1.80it/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 [16:50<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -121.298558
return_std                          46.615511
average_reward                      -0.121299
round_time             0 days 00:16:50.741215
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       495.628994
return_std_test                     105.02175
average_reward_test                  0.495629
round_time_test        0 days 00:00:08.083625
round_time_total       0 days 00:16:50.742432
loss_total                         327.023406
loss_critic                        471.300879
loss_actor                        -250.086512
memory_size                         85958.061 

=== epoch 1/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:26,  1.80it/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 [16:49<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -120.891456
return_std                          46.171416
average_reward                      -0.120891
round_time             0 days 00:16:49.787546
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       456.259139
return_std_test                      84.65195
average_reward_test                  0.456259
round_time_test        0 days 00:00:08.498379
round_time_total       0 days 00:16:49.788680
loss_total                         331.442698
loss_critic                        477.054017
loss_actor                        -251.002608
memory_size                         87890.061 

=== epoch 1/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:53,  1.76it/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 [16:49<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                           -137.705225
return_std                          42.828466
average_reward                      -0.137705
round_time             0 days 00:16:50.242945
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        477.53516
return_std_test                    135.641509
average_reward_test                  0.477535
round_time_test        0 days 00:00:08.214996
round_time_total       0 days 00:16:50.244054
loss_total                         328.904717
loss_critic                        474.071999
loss_actor                        -251.764441
memory_size                         89822.061 

=== epoch 1/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:22,  2.03it/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 [16:45<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -130.359711
return_std                          40.127323
average_reward                       -0.13036
round_time             0 days 00:16:46.106017
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       514.065674
return_std_test                      71.03048
average_reward_test                  0.514066
round_time_test        0 days 00:00:07.965446
round_time_total       0 days 00:16:46.107178
loss_total                         329.698851
loss_critic                        475.322105
loss_actor                        -252.794195
memory_size                         91754.061 

=== epoch 1/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:04,  1.84it/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 [16:47<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                           -121.402799
return_std                          49.829169
average_reward                      -0.121403
round_time             0 days 00:16:47.630387
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       566.509608
return_std_test                      40.80895
average_reward_test                   0.56651
round_time_test        0 days 00:00:08.143440
round_time_total       0 days 00:16:47.631497
loss_total                         325.721389
loss_critic                        470.819562
loss_actor                        -254.671335
memory_size                         93686.061 

=== epoch 1/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:17,  1.92it/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 [16:51<00:00,  1.98it/s]
<GE432_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                           -113.445818
return_std                          43.196725
average_reward                      -0.113446
round_time             0 days 00:16:51.686886
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       500.123497
return_std_test                    321.595795
average_reward_test                  0.500123
round_time_test        0 days 00:00:08.132542
round_time_total       0 days 00:16:51.688150
loss_total                         322.659262
loss_critic                        467.391245
loss_actor                        -256.268697
memory_size                         95618.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 2/10 ===== round 1/50 ======================================
  0%|          | 4/2000 [00:01<15:07,  2.20it/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 [15:25<00:00,  2.16it/s]
episodes                                    2
episode_length                         1000.0
returns                            -89.014683
return_std                           21.05417
average_reward                      -0.089015
round_time             0 days 00:15:25.182552
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       526.315036
return_std_test                     96.344137
average_reward_test                  0.526315
round_time_test        0 days 00:00:08.017584
round_time_total       0 days 00:15:25.183778
loss_total                          317.64823
loss_critic                        461.552395
loss_actor                        -257.968464
memory_size                         97551.061 

=== epoch 2/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:01,  1.96it/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 [15:31<00:00,  2.15it/s]
episodes                                    4
episode_length                         1000.0
returns                            -99.737883
return_std                          18.377889
average_reward                      -0.099738
round_time             0 days 00:15:31.861170
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       637.937591
return_std_test                    118.633645
average_reward_test                  0.637938
round_time_test        0 days 00:00:08.039842
round_time_total       0 days 00:15:31.862510
loss_total                         320.376032
loss_critic                        465.376777
loss_actor                        -259.626978
memory_size                         99483.061 

=== epoch 2/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:42,  1.99it/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 [15:35<00:00,  2.14it/s]
episodes                                    6
episode_length                         1000.0
returns                           -106.813286
return_std                          37.557229
average_reward                      -0.106813
round_time             0 days 00:15:35.816649
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       612.292437
return_std_test                     67.783453
average_reward_test                  0.612292
round_time_test        0 days 00:00:08.266684
round_time_total       0 days 00:15:35.817788
loss_total                         321.926742
loss_critic                        467.444498
loss_actor                        -260.144313
memory_size                        101415.061 

=== epoch 2/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:11,  2.06it/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 [15:37<00:00,  2.13it/s]
episodes                                    8
episode_length                         1000.0
returns                           -110.499052
return_std                          33.978365
average_reward                      -0.110499
round_time             0 days 00:15:38.264845
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       667.851974
return_std_test                     71.931064
average_reward_test                  0.667852
round_time_test        0 days 00:00:08.111389
round_time_total       0 days 00:15:38.266145
loss_total                         327.653899
loss_critic                         474.76857
loss_actor                        -260.804816
memory_size                        103347.061 

=== epoch 2/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:20,  1.92it/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 [15:42<00:00,  2.12it/s]
episodes                                   10
episode_length                         1000.0
returns                           -107.921764
return_std                          47.785537
average_reward                      -0.107922
round_time             0 days 00:15:43.187282
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       665.334601
return_std_test                     84.925002
average_reward_test                  0.665335
round_time_test        0 days 00:00:08.169202
round_time_total       0 days 00:15:43.188618
loss_total                         328.265626
loss_critic                        475.696805
loss_actor                        -261.459118
memory_size                        105279.061 

=== epoch 2/10 ===== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:23,  2.03it/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 [15:43<00:00,  2.12it/s]
episodes                                   10
episode_length                         1000.0
returns                           -122.499493
return_std                          50.197725
average_reward                      -0.122499
round_time             0 days 00:15:44.252499
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       609.119544
return_std_test                     102.66964
average_reward_test                   0.60912
round_time_test        0 days 00:00:08.216766
round_time_total       0 days 00:15:44.253608
loss_total                         326.949045
loss_critic                         474.14137
loss_actor                        -261.820285
memory_size                        107211.061 

=== epoch 2/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:12,  1.93it/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 [15:47<00:00,  2.11it/s]
episodes                                   10
episode_length                         1000.0
returns                           -113.111512
return_std                          55.987925
average_reward                      -0.113112
round_time             0 days 00:15:47.839021
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       700.420924
return_std_test                    117.310635
average_reward_test                  0.700421
round_time_test        0 days 00:00:08.221231
round_time_total       0 days 00:15:47.840359
loss_total                         323.536814
loss_critic                        470.034174
loss_actor                        -262.452656
memory_size                        109143.061 

=== epoch 2/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:29,  1.80it/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 [15:51<00:00,  2.10it/s]
episodes                                   10
episode_length                         1000.0
returns                            -86.038988
return_std                          70.817531
average_reward                      -0.086039
round_time             0 days 00:15:51.625929
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       661.120888
return_std_test                     80.227507
average_reward_test                  0.661121
round_time_test        0 days 00:00:08.146748
round_time_total       0 days 00:15:51.627405
loss_total                          327.48559
loss_critic                          475.1845
loss_actor                        -263.310081
memory_size                        111075.061 

=== epoch 2/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:39,  2.00it/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 [15:52<00:00,  2.10it/s]
episodes                                   10
episode_length                         1000.0
returns                            -70.291631
return_std                          69.714981
average_reward                      -0.070292
round_time             0 days 00:15:53.159000
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       705.114116
return_std_test                    103.085081
average_reward_test                  0.705114
round_time_test        0 days 00:00:08.230868
round_time_total       0 days 00:15:53.160165
loss_total                         325.522349
loss_critic                        473.149527
loss_actor                        -264.986393
memory_size                        113007.061 

=== epoch 2/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:46,  1.87it/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 [15:54<00:00,  2.10it/s]
episodes                                   10
episode_length                         1000.0
returns                            -74.111314
return_std                          69.258782
average_reward                      -0.074111
round_time             0 days 00:15:55.240330
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       659.622709
return_std_test                     92.608485
average_reward_test                  0.659623
round_time_test        0 days 00:00:08.247980
round_time_total       0 days 00:15:55.241703
loss_total                         342.515161
loss_critic                        494.507337
loss_actor                        -265.453577
memory_size                        114939.061 

=== epoch 2/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:52,  1.86it/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 [16:00<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                            -52.677943
return_std                          53.834477
average_reward                      -0.052678
round_time             0 days 00:16:00.777768
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       672.176937
return_std_test                     77.448461
average_reward_test                  0.672177
round_time_test        0 days 00:00:08.048664
round_time_total       0 days 00:16:00.779228
loss_total                         336.385764
loss_critic                        487.121792
loss_actor                        -266.558376
memory_size                        116871.061 

=== epoch 2/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:12,  1.93it/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 [16:03<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                            -51.357127
return_std                          53.698507
average_reward                      -0.051357
round_time             0 days 00:16:04.319771
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       599.443693
return_std_test                    108.234465
average_reward_test                  0.599444
round_time_test        0 days 00:00:07.999646
round_time_total       0 days 00:16:04.320888
loss_total                         342.771807
loss_critic                        495.308853
loss_actor                        -267.376411
memory_size                        118803.061 

=== epoch 2/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:58,  2.08it/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 [16:01<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                            -60.242194
return_std                          45.907194
average_reward                      -0.060242
round_time             0 days 00:16:02.294542
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       631.273558
return_std_test                     84.765763
average_reward_test                  0.631274
round_time_test        0 days 00:00:08.029530
round_time_total       0 days 00:16:02.295651
loss_total                         340.352954
loss_critic                        492.506732
loss_actor                        -268.262186
memory_size                        120735.061 

=== epoch 2/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:39,  1.88it/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 [16:08<00:00,  2.06it/s]
episodes                                   10
episode_length                         1000.0
returns                            -66.398282
return_std                          49.701285
average_reward                      -0.066398
round_time             0 days 00:16:09.425855
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       668.979507
return_std_test                    102.342248
average_reward_test                   0.66898
round_time_test        0 days 00:00:08.201403
round_time_total       0 days 00:16:09.427241
loss_total                         347.295417
loss_critic                        501.278164
loss_actor                        -268.635602
memory_size                        122667.061 

=== epoch 2/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:05,  2.07it/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 [16:14<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                             -41.49899
return_std                           38.48713
average_reward                      -0.041499
round_time             0 days 00:16:15.019549
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       664.130558
return_std_test                    109.944866
average_reward_test                  0.664131
round_time_test        0 days 00:00:08.126365
round_time_total       0 days 00:16:15.020692
loss_total                         345.896691
loss_critic                        499.761258
loss_actor                        -269.561609
memory_size                        124599.061 

=== epoch 2/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:41,  1.78it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [16:16<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                            -34.761675
return_std                           42.59099
average_reward                      -0.034762
round_time             0 days 00:16:16.760747
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       649.289166
return_std_test                     104.83543
average_reward_test                  0.649289
round_time_test        0 days 00:00:08.132618
round_time_total       0 days 00:16:16.762201
loss_total                         350.148857
loss_critic                        505.469349
loss_actor                        -271.133144
memory_size                        126531.061 

=== epoch 2/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:23,  2.03it/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 [16:17<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                            -25.438558
return_std                          43.954135
average_reward                      -0.025439
round_time             0 days 00:16:18.148882
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       657.740167
return_std_test                     49.230138
average_reward_test                   0.65774
round_time_test        0 days 00:00:08.144127
round_time_total       0 days 00:16:18.150394
loss_total                         360.382202
loss_critic                        518.527749
loss_actor                        -272.200019
memory_size                        128463.061 

=== epoch 2/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:23,  1.91it/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 [16:59<00:00,  1.96it/s]
episodes                                   10
episode_length                         1000.0
returns                            -21.649515
return_std                          44.041454
average_reward                       -0.02165
round_time             0 days 00:17:00.092784
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       690.333762
return_std_test                     63.496806
average_reward_test                  0.690334
round_time_test        0 days 00:00:08.279521
round_time_total       0 days 00:17:00.093917
loss_total                          360.84786
loss_critic                        519.411649
loss_actor                         -273.40733
memory_size                        130395.061 

=== epoch 2/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:28,  2.15it/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 [16:19<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                              4.886698
return_std                          43.605773
average_reward                       0.004887
round_time             0 days 00:16:20.355051
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       709.081355
return_std_test                    102.106751
average_reward_test                  0.709081
round_time_test        0 days 00:00:08.070614
round_time_total       0 days 00:16:20.356181
loss_total                          360.93375
loss_critic                        519.827526
loss_actor                        -274.641387
memory_size                        132327.061 

=== epoch 2/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:52,  1.86it/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 [16:22<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                             14.922305
return_std                          59.660651
average_reward                       0.014922
round_time             0 days 00:16:23.066787
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       664.647744
return_std_test                     73.290673
average_reward_test                  0.664648
round_time_test        0 days 00:00:08.128606
round_time_total       0 days 00:16:23.067911
loss_total                         359.547677
loss_critic                        518.536075
loss_actor                        -276.405948
memory_size                        134259.061 

=== epoch 2/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<17:48,  1.87it/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 [16:21<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                             19.288981
return_std                          66.299858
average_reward                       0.019289
round_time             0 days 00:16:21.839683
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       767.362454
return_std_test                     72.056227
average_reward_test                  0.767362
round_time_test        0 days 00:00:08.105462
round_time_total       0 days 00:16:21.840793
loss_total                         366.059441
loss_critic                         526.87215
loss_actor                        -277.191431
memory_size                        136191.061 

=== epoch 2/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:20,  1.92it/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 [16:21<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                             29.462737
return_std                          63.481666
average_reward                       0.029463
round_time             0 days 00:16:22.075853
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       720.256822
return_std_test                     78.471373
average_reward_test                  0.720257
round_time_test        0 days 00:00:08.328588
round_time_total       0 days 00:16:22.077153
loss_total                         373.540354
loss_critic                         536.45669
loss_actor                        -278.125026
memory_size                        138123.061 

=== epoch 2/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:59,  1.96it/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 [16:28<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                             39.344328
return_std                          64.685484
average_reward                       0.039344
round_time             0 days 00:16:28.729295
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       828.159699
return_std_test                     49.732252
average_reward_test                   0.82816
round_time_test        0 days 00:00:08.087776
round_time_total       0 days 00:16:28.730466
loss_total                         365.371495
loss_critic                        526.350932
loss_actor                        -278.546289
memory_size                        140055.061 

=== epoch 2/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:30,  1.80it/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 [16:27<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                             33.050475
return_std                          61.452759
average_reward                        0.03305
round_time             0 days 00:16:27.803606
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       747.308075
return_std_test                     79.628211
average_reward_test                  0.747308
round_time_test        0 days 00:00:08.204720
round_time_total       0 days 00:16:27.804708
loss_total                         365.219517
loss_critic                        526.348348
loss_actor                        -279.295841
memory_size                        141987.061 

=== epoch 2/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:11,  1.83it/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 [16:28<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                             24.276656
return_std                          51.444084
average_reward                       0.024277
round_time             0 days 00:16:29.482360
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       695.002933
return_std_test                     75.962022
average_reward_test                  0.695003
round_time_test        0 days 00:00:08.294559
round_time_total       0 days 00:16:29.483453
loss_total                         382.426989
loss_critic                        548.144779
loss_actor                        -280.444204
memory_size                        143919.061 

=== epoch 2/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:49,  1.77it/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 [16:34<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             25.653597
return_std                          35.670197
average_reward                       0.025654
round_time             0 days 00:16:34.963993
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         741.4464
return_std_test                    103.883473
average_reward_test                  0.741446
round_time_test        0 days 00:00:08.141254
round_time_total       0 days 00:16:34.965110
loss_total                          400.97381
loss_critic                        572.241422
loss_actor                        -284.096676
memory_size                        145851.061 

=== epoch 2/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:52,  1.86it/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 [16:34<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                              6.786014
return_std                          48.434364
average_reward                       0.006786
round_time             0 days 00:16:35.007473
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       771.399699
return_std_test                     93.161373
average_reward_test                    0.7714
round_time_test        0 days 00:00:08.126082
round_time_total       0 days 00:16:35.008924
loss_total                         403.379665
loss_critic                        575.433883
loss_actor                        -284.837244
memory_size                        147783.061 

=== epoch 2/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:37,  1.79it/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 [16:37<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                               5.68949
return_std                          48.367244
average_reward                       0.005689
round_time             0 days 00:16:37.827756
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       744.910828
return_std_test                     81.677167
average_reward_test                  0.744911
round_time_test        0 days 00:00:08.134676
round_time_total       0 days 00:16:37.828925
loss_total                         380.277836
loss_critic                        546.227017
loss_actor                        -283.518923
memory_size                        149715.061 

=== epoch 2/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:31,  1.80it/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 [16:34<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                              1.562985
return_std                          50.910763
average_reward                       0.001563
round_time             0 days 00:16:35.337034
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       859.200151
return_std_test                     89.105593
average_reward_test                    0.8592
round_time_test        0 days 00:00:08.037673
round_time_total       0 days 00:16:35.338317
loss_total                          393.41067
loss_critic                        562.837115
loss_actor                        -284.295144
memory_size                        151647.061 

=== epoch 2/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:17,  1.82it/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 [16:37<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             -5.396777
return_std                          49.067454
average_reward                      -0.005397
round_time             0 days 00:16:38.393096
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       733.365337
return_std_test                     80.004517
average_reward_test                  0.733365
round_time_test        0 days 00:00:08.452435
round_time_total       0 days 00:16:38.394366
loss_total                         400.024479
loss_critic                        571.264877
loss_actor                        -284.937152
memory_size                        153579.061 

=== epoch 2/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:48,  1.87it/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 [16:34<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                            -14.600734
return_std                          48.699085
average_reward                      -0.014601
round_time             0 days 00:16:35.213264
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       738.740267
return_std_test                     75.627877
average_reward_test                   0.73874
round_time_test        0 days 00:00:08.121622
round_time_total       0 days 00:16:35.214389
loss_total                         404.685198
loss_critic                        577.163551
loss_actor                        -285.228255
memory_size                        155511.061 

=== epoch 2/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:36,  1.89it/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 [16:35<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                              1.186791
return_std                          44.906723
average_reward                       0.001187
round_time             0 days 00:16:36.394625
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        724.65052
return_std_test                     59.243668
average_reward_test                  0.724651
round_time_test        0 days 00:00:08.092950
round_time_total       0 days 00:16:36.395744
loss_total                         421.479219
loss_critic                        598.355415
loss_actor                        -286.025604
memory_size                        157443.061 

=== epoch 2/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:35,  1.79it/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 [16:37<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             -7.253091
return_std                          39.728356
average_reward                      -0.007253
round_time             0 days 00:16:38.199427
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       702.712731
return_std_test                     82.683812
average_reward_test                  0.702713
round_time_test        0 days 00:00:08.178472
round_time_total       0 days 00:16:38.200781
loss_total                         423.265521
loss_critic                        600.805618
loss_actor                        -286.894906
memory_size                        159375.061 

=== epoch 2/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:54,  1.76it/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 [16:34<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                              4.318001
return_std                          51.051315
average_reward                       0.004318
round_time             0 days 00:16:35.465243
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       525.052569
return_std_test                     91.862416
average_reward_test                  0.525053
round_time_test        0 days 00:00:08.091680
round_time_total       0 days 00:16:35.466358
loss_total                          407.14049
loss_critic                        580.610425
loss_actor                        -286.739283
memory_size                        161307.061 

=== epoch 2/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:24,  1.81it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                              4.495793
return_std                          51.552271
average_reward                       0.004496
round_time             0 days 00:16:36.715208
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       530.896681
return_std_test                     79.064802
average_reward_test                  0.530897
round_time_test        0 days 00:00:08.149356
round_time_total       0 days 00:16:36.716441
loss_total                         404.340868
loss_critic                        577.385201
loss_actor                        -287.836499
memory_size                        163239.061 

=== epoch 2/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:01,  1.85it/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 [16:32<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                              30.01207
return_std                           56.45564
average_reward                       0.030012
round_time             0 days 00:16:33.192576
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       786.717146
return_std_test                      78.50729
average_reward_test                  0.786717
round_time_test        0 days 00:00:08.088799
round_time_total       0 days 00:16:33.193716
loss_total                          401.02219
loss_critic                        573.578571
loss_actor                        -289.203367
memory_size                        165171.061 

=== epoch 2/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:02<24:15,  1.37it/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 [16:35<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             20.818161
return_std                          59.096583
average_reward                       0.020818
round_time             0 days 00:16:35.787937
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        754.49125
return_std_test                     96.178473
average_reward_test                  0.754491
round_time_test        0 days 00:00:08.049833
round_time_total       0 days 00:16:35.789081
loss_total                         404.923555
loss_critic                        578.732848
loss_actor                        -290.313654
memory_size                        167103.061 

=== epoch 2/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:56,  2.09it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             11.239252
return_std                          65.257895
average_reward                       0.011239
round_time             0 days 00:16:37.229146
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       686.672221
return_std_test                     86.744261
average_reward_test                  0.686672
round_time_test        0 days 00:00:08.288148
round_time_total       0 days 00:16:37.230269
loss_total                         404.581391
loss_critic                        578.391749
loss_actor                        -290.660075
memory_size                        169035.061 

=== epoch 2/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:33,  2.01it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                              0.833194
return_std                          56.168087
average_reward                       0.000833
round_time             0 days 00:16:37.069972
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       698.257815
return_std_test                    101.693668
average_reward_test                  0.698258
round_time_test        0 days 00:00:08.186279
round_time_total       0 days 00:16:37.071515
loss_total                         403.520074
loss_critic                        577.453184
loss_actor                        -292.212402
memory_size                        170967.061 

=== epoch 2/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:33,  1.79it/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 [16:37<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             12.327921
return_std                          57.532991
average_reward                       0.012328
round_time             0 days 00:16:38.181298
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       713.702885
return_std_test                     71.082801
average_reward_test                  0.713703
round_time_test        0 days 00:00:08.056902
round_time_total       0 days 00:16:38.182441
loss_total                         409.841566
loss_critic                        585.723467
loss_actor                        -293.686079
memory_size                        172899.061 

=== epoch 2/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:17,  1.82it/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 [16:40<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             -1.840284
return_std                          43.004916
average_reward                       -0.00184
round_time             0 days 00:16:40.922554
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       642.152434
return_std_test                     39.608609
average_reward_test                  0.642152
round_time_test        0 days 00:00:08.196547
round_time_total       0 days 00:16:40.923641
loss_total                         412.093617
loss_critic                        588.773063
loss_actor                        -294.624205
memory_size                        174831.061 

=== epoch 2/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:05,  1.84it/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 [16:39<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                              2.073691
return_std                          41.777832
average_reward                       0.002074
round_time             0 days 00:16:40.152988
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       795.968976
return_std_test                     143.84157
average_reward_test                  0.795969
round_time_test        0 days 00:00:08.211379
round_time_total       0 days 00:16:40.154271
loss_total                         402.089261
loss_critic                         576.47471
loss_actor                         -295.45257
memory_size                        176763.061 

=== epoch 2/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:18,  1.82it/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 [16:43<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                             27.236428
return_std                          36.173883
average_reward                       0.027236
round_time             0 days 00:16:44.259139
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       736.391596
return_std_test                      91.48383
average_reward_test                  0.736392
round_time_test        0 days 00:00:08.097658
round_time_total       0 days 00:16:44.260236
loss_total                         398.564338
loss_critic                        572.380011
loss_actor                        -296.698392
memory_size                        178695.061 

=== epoch 2/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:27,  1.91it/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 [16:39<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             31.094675
return_std                          44.533247
average_reward                       0.031095
round_time             0 days 00:16:39.623301
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       797.631994
return_std_test                     65.510044
average_reward_test                  0.797632
round_time_test        0 days 00:00:08.273370
round_time_total       0 days 00:16:39.624790
loss_total                         405.959689
loss_critic                        581.981664
loss_actor                        -298.128247
memory_size                        180627.061 

=== epoch 2/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:44,  1.88it/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 [16:45<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                             33.854273
return_std                          45.558781
average_reward                       0.033854
round_time             0 days 00:16:46.231489
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       478.329989
return_std_test                     45.405243
average_reward_test                   0.47833
round_time_test        0 days 00:00:08.377026
round_time_total       0 days 00:16:46.232695
loss_total                         403.438108
loss_critic                        579.079494
loss_actor                        -299.127474
memory_size                        182559.061 

=== epoch 2/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:41,  1.88it/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 [16:44<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                             42.213515
return_std                          55.847259
average_reward                       0.042214
round_time             0 days 00:16:45.120839
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       676.989535
return_std_test                      81.57094
average_reward_test                   0.67699
round_time_test        0 days 00:00:08.336335
round_time_total       0 days 00:16:45.121948
loss_total                         405.384454
loss_critic                        581.962452
loss_actor                        -300.927574
memory_size                        184491.061 

=== epoch 2/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:30,  1.90it/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 [16:45<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                             51.645616
return_std                          58.482243
average_reward                       0.051646
round_time             0 days 00:16:46.510760
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       785.588077
return_std_test                     76.564559
average_reward_test                  0.785588
round_time_test        0 days 00:00:08.227003
round_time_total       0 days 00:16:46.512055
loss_total                         407.854801
loss_critic                        585.361173
loss_actor                        -302.170728
memory_size                        186423.061 

=== epoch 2/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:08,  1.94it/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 [16:45<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                              48.25408
return_std                          54.713793
average_reward                       0.048254
round_time             0 days 00:16:46.559080
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       823.825261
return_std_test                    112.561095
average_reward_test                  0.823825
round_time_test        0 days 00:00:08.208503
round_time_total       0 days 00:16:46.560194
loss_total                         411.814424
loss_critic                        590.574596
loss_actor                        -303.226302
memory_size                        188355.061 

=== epoch 2/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:09,  1.94it/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 [16:48<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                             47.675632
return_std                          54.097779
average_reward                       0.047676
round_time             0 days 00:16:48.866687
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       796.597196
return_std_test                     70.806138
average_reward_test                  0.796597
round_time_test        0 days 00:00:08.121231
round_time_total       0 days 00:16:48.868186
loss_total                         411.744869
loss_critic                        590.895565
loss_actor                        -304.857956
memory_size                        190287.061 

=== epoch 2/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:28,  1.80it/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 [16:47<00:00,  1.98it/s]
<GE432_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                             53.211754
return_std                          56.211194
average_reward                       0.053212
round_time             0 days 00:16:48.516114
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       790.799564
return_std_test                     85.436155
average_reward_test                    0.7908
round_time_test        0 days 00:00:08.089664
round_time_total       0 days 00:16:48.517214
loss_total                         410.370825
loss_critic                        589.344038
loss_actor                         -305.52206
memory_size                        192219.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 3/10 ===== round 1/50 ======================================
  0%|          | 4/2000 [00:01<15:17,  2.18it/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 [15:27<00:00,  2.16it/s]
episodes                                    2
episode_length                         1000.0
returns                            126.103498
return_std                           9.080362
average_reward                       0.126103
round_time             0 days 00:15:27.832311
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       847.231334
return_std_test                     57.654188
average_reward_test                  0.847231
round_time_test        0 days 00:00:08.173887
round_time_total       0 days 00:15:27.833842
loss_total                         406.686002
loss_critic                        584.674505
loss_actor                        -305.268049
memory_size                        194152.061 

=== epoch 3/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:18,  1.92it/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 [15:33<00:00,  2.14it/s]
episodes                                    4
episode_length                         1000.0
returns                            108.785533
return_std                          19.341995
average_reward                       0.108786
round_time             0 days 00:15:34.418281
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       837.571085
return_std_test                      89.65364
average_reward_test                  0.837571
round_time_test        0 days 00:00:08.060220
round_time_total       0 days 00:15:34.419377
loss_total                         402.526643
loss_critic                        579.624332
loss_actor                        -305.864153
memory_size                        196084.061 

=== epoch 3/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:08,  2.06it/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 [15:35<00:00,  2.14it/s]
episodes                                    6
episode_length                         1000.0
returns                            102.807431
return_std                          19.514069
average_reward                       0.102807
round_time             0 days 00:15:35.969933
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.790133
return_std_test                     94.201099
average_reward_test                   0.79879
round_time_test        0 days 00:00:08.026657
round_time_total       0 days 00:15:35.971046
loss_total                         401.780032
loss_critic                         578.67702
loss_actor                        -305.807958
memory_size                        198016.061 

=== epoch 3/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:11,  2.06it/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 [15:41<00:00,  2.13it/s]
episodes                                    8
episode_length                         1000.0
returns                            105.014359
return_std                          17.753889
average_reward                       0.105014
round_time             0 days 00:15:41.607380
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       868.394906
return_std_test                     58.216222
average_reward_test                  0.868395
round_time_test        0 days 00:00:08.022586
round_time_total       0 days 00:15:41.608501
loss_total                         402.243292
loss_critic                        579.629425
loss_actor                        -307.301279
memory_size                        199948.061 

=== epoch 3/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:42,  1.99it/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 [15:44<00:00,  2.12it/s]
episodes                                   10
episode_length                         1000.0
returns                             99.521169
return_std                          21.554919
average_reward                       0.099521
round_time             0 days 00:15:44.894757
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       868.347013
return_std_test                    100.341326
average_reward_test                  0.868347
round_time_test        0 days 00:00:08.056797
round_time_total       0 days 00:15:44.895862
loss_total                         397.455317
loss_critic                         574.08015
loss_actor                        -309.044054
memory_size                        201880.061 

=== epoch 3/10 ===== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:42,  2.12it/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 [15:45<00:00,  2.11it/s]
episodes                                   10
episode_length                         1000.0
returns                             92.448439
return_std                          24.668071
average_reward                       0.092448
round_time             0 days 00:15:46.280292
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       797.173476
return_std_test                     118.75389
average_reward_test                  0.797173
round_time_test        0 days 00:00:08.068329
round_time_total       0 days 00:15:46.281416
loss_total                         401.944821
loss_critic                        580.138723
loss_actor                        -310.830827
memory_size                        203812.061 

=== epoch 3/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:27,  2.02it/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 [15:49<00:00,  2.11it/s]
episodes                                   10
episode_length                         1000.0
returns                             88.213874
return_std                          31.616363
average_reward                       0.088214
round_time             0 days 00:15:50.240826
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       865.095228
return_std_test                     73.503369
average_reward_test                  0.865095
round_time_test        0 days 00:00:08.093567
round_time_total       0 days 00:15:50.242016
loss_total                         410.988177
loss_critic                        591.626617
loss_actor                        -311.565619
memory_size                        205744.061 

=== epoch 3/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:28,  1.91it/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 [15:56<00:00,  2.09it/s]
episodes                                   10
episode_length                         1000.0
returns                             86.751918
return_std                          31.058231
average_reward                       0.086752
round_time             0 days 00:15:57.256408
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       871.323345
return_std_test                     106.90328
average_reward_test                  0.871323
round_time_test        0 days 00:00:08.283893
round_time_total       0 days 00:15:57.257506
loss_total                         408.783334
loss_critic                        589.186727
loss_actor                        -312.830275
memory_size                        207676.061 

=== epoch 3/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:06,  1.95it/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 [16:01<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                             82.769422
return_std                          29.746885
average_reward                       0.082769
round_time             0 days 00:16:02.252799
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       784.482049
return_std_test                     70.589485
average_reward_test                  0.784482
round_time_test        0 days 00:00:08.115057
round_time_total       0 days 00:16:02.254005
loss_total                         402.036135
loss_critic                        580.906594
loss_actor                        -313.445736
memory_size                        209608.061 

=== epoch 3/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:24,  2.03it/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 [15:58<00:00,  2.09it/s]
episodes                                   10
episode_length                         1000.0
returns                             78.460214
return_std                           31.69531
average_reward                        0.07846
round_time             0 days 00:15:59.215512
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       824.429383
return_std_test                    103.016343
average_reward_test                  0.824429
round_time_test        0 days 00:00:08.134006
round_time_total       0 days 00:15:59.216635
loss_total                          403.27952
loss_critic                        582.540666
loss_actor                        -313.765103
memory_size                        211540.061 

=== epoch 3/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:02<17:16,  1.93it/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 [16:03<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                             60.905232
return_std                          61.014867
average_reward                       0.060905
round_time             0 days 00:16:04.050920
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       865.737081
return_std_test                     58.663954
average_reward_test                  0.865737
round_time_test        0 days 00:00:08.137547
round_time_total       0 days 00:16:04.052018
loss_total                         420.675031
loss_critic                        604.518327
loss_actor                        -314.698198
memory_size                        213472.061 

=== epoch 3/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:20,  1.92it/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 [16:03<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                             52.545526
return_std                          65.866078
average_reward                       0.052546
round_time             0 days 00:16:03.670385
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       740.157276
return_std_test                    178.318979
average_reward_test                  0.740157
round_time_test        0 days 00:00:08.165240
round_time_total       0 days 00:16:03.671560
loss_total                          412.34387
loss_critic                        594.263353
loss_actor                        -315.334097
memory_size                        215404.061 

=== epoch 3/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:20,  1.92it/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 [16:07<00:00,  2.07it/s]
episodes                                   10
episode_length                         1000.0
returns                             37.226386
return_std                          66.886759
average_reward                       0.037226
round_time             0 days 00:16:07.674307
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       860.545537
return_std_test                     97.249465
average_reward_test                  0.860546
round_time_test        0 days 00:00:08.269159
round_time_total       0 days 00:16:07.675620
loss_total                         414.104838
loss_critic                        596.849263
loss_actor                        -316.872898
memory_size                        217336.061 

=== epoch 3/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:39,  1.78it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [16:10<00:00,  2.06it/s]
episodes                                   10
episode_length                         1000.0
returns                              20.11761
return_std                           61.27369
average_reward                       0.020118
round_time             0 days 00:16:11.459345
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       408.089848
return_std_test                     25.296622
average_reward_test                   0.40809
round_time_test        0 days 00:00:08.119851
round_time_total       0 days 00:16:11.460437
loss_total                         415.474186
loss_critic                        598.940599
loss_actor                        -318.391497
memory_size                        219268.061 

=== epoch 3/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:03,  1.84it/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 [16:13<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                             13.927492
return_std                          58.896486
average_reward                       0.013927
round_time             0 days 00:16:14.562322
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       399.790525
return_std_test                     33.493784
average_reward_test                  0.399791
round_time_test        0 days 00:00:08.185327
round_time_total       0 days 00:16:14.563552
loss_total                         417.403813
loss_critic                        601.698262
loss_actor                        -319.774016
memory_size                        221200.061 

=== epoch 3/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:43,  1.88it/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 [16:12<00:00,  2.06it/s]
episodes                                   10
episode_length                         1000.0
returns                             21.808416
return_std                           37.37268
average_reward                       0.021808
round_time             0 days 00:16:12.976902
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       330.053385
return_std_test                     13.431361
average_reward_test                  0.330053
round_time_test        0 days 00:00:08.319286
round_time_total       0 days 00:16:12.978198
loss_total                         412.228271
loss_critic                        595.409491
loss_actor                        -320.496642
memory_size                        223132.061 

=== epoch 3/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:36,  1.89it/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 [16:18<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                             28.582424
return_std                          30.903649
average_reward                       0.028582
round_time             0 days 00:16:19.415757
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       369.355734
return_std_test                     34.726847
average_reward_test                  0.369356
round_time_test        0 days 00:00:08.499763
round_time_total       0 days 00:16:19.416870
loss_total                          418.41684
loss_critic                        603.364517
loss_actor                        -321.373899
memory_size                        225064.061 

=== epoch 3/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:13,  1.93it/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 [16:15<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                             34.628832
return_std                          26.407727
average_reward                       0.034629
round_time             0 days 00:16:16.373558
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       473.059401
return_std_test                     34.979273
average_reward_test                  0.473059
round_time_test        0 days 00:00:08.196300
round_time_total       0 days 00:16:16.374933
loss_total                         406.520363
loss_critic                        588.765321
loss_actor                        -322.459494
memory_size                        226996.061 

=== epoch 3/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:39,  1.89it/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 [16:20<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                             41.583302
return_std                          21.602455
average_reward                       0.041583
round_time             0 days 00:16:21.382404
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       339.663818
return_std_test                     26.221707
average_reward_test                  0.339664
round_time_test        0 days 00:00:08.388863
round_time_total       0 days 00:16:21.383559
loss_total                         411.998859
loss_critic                         595.91823
loss_actor                        -323.678653
memory_size                        228928.061 

=== epoch 3/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:38,  2.00it/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 [16:24<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                             43.435937
return_std                          22.096558
average_reward                       0.043436
round_time             0 days 00:16:24.841660
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       407.862793
return_std_test                      35.23738
average_reward_test                  0.407863
round_time_test        0 days 00:00:08.324545
round_time_total       0 days 00:16:24.842780
loss_total                         416.056676
loss_critic                        601.386835
loss_actor                        -325.263987
memory_size                        230860.061 

=== epoch 3/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<18:23,  1.81it/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 [16:28<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                                 49.31
return_std                          30.254437
average_reward                        0.04931
round_time             0 days 00:16:28.767855
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       409.730773
return_std_test                     26.041824
average_reward_test                  0.409731
round_time_test        0 days 00:00:08.105401
round_time_total       0 days 00:16:28.769023
loss_total                          409.41956
loss_critic                        593.232138
loss_actor                        -325.830777
memory_size                        232792.061 

=== epoch 3/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:10,  1.94it/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 [16:24<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                             54.594647
return_std                          35.197215
average_reward                       0.054595
round_time             0 days 00:16:25.442032
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       461.147255
return_std_test                     48.396094
average_reward_test                  0.461147
round_time_test        0 days 00:00:08.139440
round_time_total       0 days 00:16:25.443264
loss_total                         408.354229
loss_critic                        592.118388
loss_actor                         -326.70243
memory_size                        234724.061 

=== epoch 3/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:21,  2.03it/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 [16:28<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                             57.187186
return_std                          45.970396
average_reward                       0.057187
round_time             0 days 00:16:29.285562
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       428.190929
return_std_test                     35.212711
average_reward_test                  0.428191
round_time_test        0 days 00:00:08.255985
round_time_total       0 days 00:16:29.286660
loss_total                         407.127326
loss_critic                        590.872593
loss_actor                        -327.853767
memory_size                        236656.061 

=== epoch 3/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:46,  1.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [16:32<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                             42.787334
return_std                           59.84652
average_reward                       0.042787
round_time             0 days 00:16:32.671473
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       320.756665
return_std_test                     32.105541
average_reward_test                  0.320757
round_time_test        0 days 00:00:08.165757
round_time_total       0 days 00:16:32.672580
loss_total                         405.682983
loss_critic                        589.337803
loss_actor                        -328.936321
memory_size                        238588.061 

=== epoch 3/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:24,  1.91it/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 [16:29<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                             55.514139
return_std                          62.173233
average_reward                       0.055514
round_time             0 days 00:16:29.778393
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       454.333353
return_std_test                     51.233183
average_reward_test                  0.454333
round_time_test        0 days 00:00:08.291230
round_time_total       0 days 00:16:29.779493
loss_total                         407.720577
loss_critic                        592.226206
loss_actor                        -330.301966
memory_size                        240520.061 

=== epoch 3/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:58,  1.85it/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 [16:32<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             46.157757
return_std                          59.364885
average_reward                       0.046158
round_time             0 days 00:16:33.189025
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       376.670209
return_std_test                     29.492674
average_reward_test                   0.37667
round_time_test        0 days 00:00:08.328092
round_time_total       0 days 00:16:33.190229
loss_total                         409.434138
loss_critic                        594.774093
loss_actor                        -331.925711
memory_size                        242452.061 

=== epoch 3/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:21,  2.04it/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 [16:28<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                             38.628802
return_std                          54.461654
average_reward                       0.038629
round_time             0 days 00:16:28.596199
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       326.372628
return_std_test                     45.455499
average_reward_test                  0.326373
round_time_test        0 days 00:00:08.405040
round_time_total       0 days 00:16:28.597307
loss_total                         405.308982
loss_critic                        590.011421
loss_actor                        -333.500799
memory_size                        244384.061 

=== epoch 3/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:13,  1.83it/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 [16:32<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             35.220184
return_std                          44.656051
average_reward                        0.03522
round_time             0 days 00:16:33.204918
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       400.603429
return_std_test                     35.753137
average_reward_test                  0.400603
round_time_test        0 days 00:00:08.054991
round_time_total       0 days 00:16:33.206091
loss_total                         405.080084
loss_critic                        589.838122
loss_actor                        -333.952096
memory_size                        246316.061 

=== epoch 3/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:23,  1.91it/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 [16:37<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             53.794267
return_std                           27.56984
average_reward                       0.053794
round_time             0 days 00:16:37.759427
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       638.431659
return_std_test                     56.344127
average_reward_test                  0.638432
round_time_test        0 days 00:00:08.285014
round_time_total       0 days 00:16:37.760546
loss_total                         407.551878
loss_critic                         593.14182
loss_actor                        -334.807912
memory_size                        248248.061 

=== epoch 3/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:24,  1.91it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             36.524333
return_std                          24.565613
average_reward                       0.036524
round_time             0 days 00:16:36.688614
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       482.718657
return_std_test                     45.736353
average_reward_test                  0.482719
round_time_test        0 days 00:00:08.244765
round_time_total       0 days 00:16:36.689834
loss_total                         403.873124
loss_critic                        588.857868
loss_actor                        -336.065877
memory_size                        250180.061 

=== epoch 3/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:27,  1.80it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             35.379414
return_std                          25.196251
average_reward                       0.035379
round_time             0 days 00:16:36.791132
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       392.725835
return_std_test                     24.015496
average_reward_test                  0.392726
round_time_test        0 days 00:00:08.346625
round_time_total       0 days 00:16:36.792232
loss_total                         400.861367
loss_critic                        585.293683
loss_actor                        -336.867921
memory_size                        252112.061 

=== epoch 3/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:46,  1.77it/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 [16:36<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             32.308687
return_std                          23.408322
average_reward                       0.032309
round_time             0 days 00:16:37.477563
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       621.390409
return_std_test                     91.680159
average_reward_test                   0.62139
round_time_test        0 days 00:00:08.098639
round_time_total       0 days 00:16:37.478790
loss_total                           404.9046
loss_critic                        590.357109
loss_actor                        -336.905461
memory_size                        254044.061 

=== epoch 3/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:05,  1.84it/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 [16:41<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             28.475041
return_std                          27.640879
average_reward                       0.028475
round_time             0 days 00:16:41.925769
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       320.763379
return_std_test                      19.97905
average_reward_test                  0.320763
round_time_test        0 days 00:00:08.227123
round_time_total       0 days 00:16:41.926873
loss_total                         407.912866
loss_critic                        594.345734
loss_actor                        -337.818633
memory_size                        255976.061 

=== epoch 3/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:41,  1.78it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [16:41<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             27.495818
return_std                          29.935159
average_reward                       0.027496
round_time             0 days 00:16:41.709804
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       527.736767
return_std_test                      34.06949
average_reward_test                  0.527737
round_time_test        0 days 00:00:08.215718
round_time_total       0 days 00:16:41.710918
loss_total                         397.466923
loss_critic                        581.748075
loss_actor                        -339.657711
memory_size                        257908.061 

=== epoch 3/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:47,  1.77it/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 [16:37<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             34.915005
return_std                          27.194495
average_reward                       0.034915
round_time             0 days 00:16:38.219981
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       570.380833
return_std_test                     56.262501
average_reward_test                  0.570381
round_time_test        0 days 00:00:08.307407
round_time_total       0 days 00:16:38.221248
loss_total                         400.294692
loss_critic                        585.443788
loss_actor                        -340.301716
memory_size                        259840.061 

=== epoch 3/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<18:20,  1.82it/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 [16:38<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             44.874794
return_std                          29.191219
average_reward                       0.044875
round_time             0 days 00:16:38.822268
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       446.489502
return_std_test                     51.470327
average_reward_test                   0.44649
round_time_test        0 days 00:00:08.187449
round_time_total       0 days 00:16:38.823387
loss_total                         399.725238
loss_critic                        584.988301
loss_actor                        -341.327036
memory_size                        261772.061 

=== epoch 3/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:48,  1.87it/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 [16:41<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             46.423274
return_std                          32.975001
average_reward                       0.046423
round_time             0 days 00:16:41.812577
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       724.777075
return_std_test                     65.502235
average_reward_test                  0.724777
round_time_test        0 days 00:00:08.013668
round_time_total       0 days 00:16:41.813702
loss_total                         400.809786
loss_critic                         586.63586
loss_actor                        -342.494534
memory_size                        263704.061 

=== epoch 3/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:29,  1.80it/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 [16:44<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                             43.736772
return_std                          34.703111
average_reward                       0.043737
round_time             0 days 00:16:45.124588
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       297.964483
return_std_test                     43.840221
average_reward_test                  0.297964
round_time_test        0 days 00:00:08.455530
round_time_total       0 days 00:16:45.125721
loss_total                         402.212112
loss_critic                        588.541766
loss_actor                        -343.106532
memory_size                        265636.061 

=== epoch 3/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:14,  1.82it/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 [16:40<00:00,  2.00it/s]
episodes                                   10
episode_length                         1000.0
returns                             45.168056
return_std                          32.009571
average_reward                       0.045168
round_time             0 days 00:16:40.640314
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       387.268128
return_std_test                     32.324229
average_reward_test                  0.387268
round_time_test        0 days 00:00:08.173005
round_time_total       0 days 00:16:40.641428
loss_total                         405.517326
loss_critic                        592.726981
loss_actor                        -343.321318
memory_size                        267568.061 

=== epoch 3/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:25,  1.81it/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 [16:44<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                             47.449834
return_std                          35.635541
average_reward                        0.04745
round_time             0 days 00:16:44.641678
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       395.835849
return_std_test                     29.377259
average_reward_test                  0.395836
round_time_test        0 days 00:00:08.201487
round_time_total       0 days 00:16:44.642802
loss_total                         402.183599
loss_critic                        588.770933
loss_actor                        -344.165759
memory_size                        269500.061 

=== epoch 3/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:54,  1.86it/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 [16:44<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                              42.01086
return_std                          35.057384
average_reward                       0.042011
round_time             0 days 00:16:45.297780
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       554.342369
return_std_test                     55.429056
average_reward_test                  0.554342
round_time_test        0 days 00:00:08.261647
round_time_total       0 days 00:16:45.298881
loss_total                         402.108219
loss_critic                        588.761435
loss_actor                         -344.50467
memory_size                        271432.061 

=== epoch 3/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:36,  1.89it/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 [16:44<00:00,  1.99it/s]
episodes                                   10
episode_length                         1000.0
returns                             36.657127
return_std                           33.82151
average_reward                       0.036657
round_time             0 days 00:16:44.563580
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       446.310196
return_std_test                     87.128402
average_reward_test                   0.44631
round_time_test        0 days 00:00:08.243253
round_time_total       0 days 00:16:44.564687
loss_total                         404.989157
loss_critic                        592.695257
loss_actor                        -345.835269
memory_size                        273364.061 

=== epoch 3/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:45,  1.87it/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 [16:48<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                             42.409004
return_std                          31.077949
average_reward                       0.042409
round_time             0 days 00:16:49.356865
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       578.392601
return_std_test                     63.147031
average_reward_test                  0.578393
round_time_test        0 days 00:00:08.328066
round_time_total       0 days 00:16:49.358302
loss_total                         403.684879
loss_critic                        591.286151
loss_actor                        -346.720233
memory_size                        275296.061 

=== epoch 3/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:46,  1.87it/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 [16:48<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                             53.308004
return_std                          43.780771
average_reward                       0.053308
round_time             0 days 00:16:49.049616
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       667.321113
return_std_test                     76.289564
average_reward_test                  0.667321
round_time_test        0 days 00:00:08.206339
round_time_total       0 days 00:16:49.050890
loss_total                          407.97703
loss_critic                        596.851574
loss_actor                        -347.521168
memory_size                        277228.061 

=== epoch 3/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:02,  1.84it/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 [16:52<00:00,  1.97it/s]
episodes                                   10
episode_length                         1000.0
returns                             57.061968
return_std                          48.689041
average_reward                       0.057062
round_time             0 days 00:16:53.583904
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       589.358993
return_std_test                     40.589251
average_reward_test                  0.589359
round_time_test        0 days 00:00:08.151964
round_time_total       0 days 00:16:53.585185
loss_total                         401.314928
loss_critic                        588.700462
loss_actor                         -348.22723
memory_size                        279160.061 

=== epoch 3/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:42,  1.88it/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 [16:49<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                             77.463954
return_std                          58.010392
average_reward                       0.077464
round_time             0 days 00:16:49.686903
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       537.439686
return_std_test                     46.083744
average_reward_test                   0.53744
round_time_test        0 days 00:00:08.220026
round_time_total       0 days 00:16:49.688026
loss_total                         413.118651
loss_critic                        603.746067
loss_actor                        -349.391041
memory_size                        281092.061 

=== epoch 3/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<19:01,  1.75it/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 [16:50<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                             89.221353
return_std                          55.562663
average_reward                       0.089221
round_time             0 days 00:16:50.723657
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       681.221616
return_std_test                     76.464724
average_reward_test                  0.681222
round_time_test        0 days 00:00:08.089576
round_time_total       0 days 00:16:50.725015
loss_total                         402.854034
loss_critic                        590.865259
loss_actor                        -349.190891
memory_size                        283024.061 

=== epoch 3/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:48,  1.77it/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 [16:52<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                              94.76079
return_std                          51.445919
average_reward                       0.094761
round_time             0 days 00:16:52.812497
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       648.024433
return_std_test                     49.588883
average_reward_test                  0.648024
round_time_test        0 days 00:00:08.200800
round_time_total       0 days 00:16:52.813623
loss_total                         408.388426
loss_critic                        598.097357
loss_actor                        -350.447323
memory_size                        284956.061 

=== epoch 3/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<18:00,  1.85it/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 [16:49<00:00,  1.98it/s]
episodes                                   10
episode_length                         1000.0
returns                             88.634475
return_std                          52.111478
average_reward                       0.088634
round_time             0 days 00:16:50.107983
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       588.821402
return_std_test                     47.283305
average_reward_test                  0.588821
round_time_test        0 days 00:00:08.194774
round_time_total       0 days 00:16:50.109250
loss_total                         412.013082
loss_critic                        603.159602
loss_actor                        -352.573021
memory_size                        286888.061 

=== epoch 3/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<19:00,  1.75it/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 [16:53<00:00,  1.97it/s]
<GE432_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                            108.408896
return_std                          62.131143
average_reward                       0.108409
round_time             0 days 00:16:53.570099
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       673.969804
return_std_test                     39.154788
average_reward_test                   0.67397
round_time_test        0 days 00:00:08.268719
round_time_total       0 days 00:16:53.571211
loss_total                         410.299816
loss_critic                        600.916634
loss_actor                        -352.167482
memory_size                        288820.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 4/10 ===== round 1/50 ======================================
  0%|          | 4/2000 [00:01<15:32,  2.14it/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 [15:28<00:00,  2.15it/s]
episodes                                    2
episode_length                         1000.0
returns                            171.640243
return_std                          31.334835
average_reward                        0.17164
round_time             0 days 00:15:28.499743
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       764.912548
return_std_test                     66.003511
average_reward_test                  0.764913
round_time_test        0 days 00:00:08.172696
round_time_total       0 days 00:15:28.500868
loss_total                         407.198083
loss_critic                         597.14099
loss_actor                         -352.57357
memory_size                        290753.061 

=== epoch 4/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:52,  2.24it/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 [15:35<00:00,  2.14it/s]
episodes                                    4
episode_length                         1000.0
returns                            187.813039
return_std                          27.686308
average_reward                       0.187813
round_time             0 days 00:15:36.196378
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       652.353454
return_std_test                     77.801406
average_reward_test                  0.652353
round_time_test        0 days 00:00:08.207754
round_time_total       0 days 00:15:36.197472
loss_total                         410.393855
loss_critic                        601.193444
loss_actor                        -352.804527
memory_size                        292685.061 

=== epoch 4/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:14,  1.93it/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 [15:39<00:00,  2.13it/s]
episodes                                    6
episode_length                         1000.0
returns                             175.13028
return_std                          35.154159
average_reward                        0.17513
round_time             0 days 00:15:40.012025
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       724.742264
return_std_test                     56.138187
average_reward_test                  0.724742
round_time_test        0 days 00:00:08.150138
round_time_total       0 days 00:15:40.013471
loss_total                         403.389708
loss_critic                        592.440342
loss_actor                        -352.812854
memory_size                        294617.061 

=== epoch 4/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:37,  1.89it/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 [15:40<00:00,  2.13it/s]
episodes                                    8
episode_length                         1000.0
returns                            188.371096
return_std                          38.117216
average_reward                       0.188371
round_time             0 days 00:15:41.336427
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       789.986272
return_std_test                     75.193099
average_reward_test                  0.789986
round_time_test        0 days 00:00:08.232188
round_time_total       0 days 00:15:41.337543
loss_total                         401.505209
loss_critic                        590.131867
loss_actor                        -353.001448
memory_size                        296549.061 

=== epoch 4/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:38,  2.13it/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 [15:43<00:00,  2.12it/s]
episodes                                   10
episode_length                         1000.0
returns                             197.94229
return_std                          40.716986
average_reward                       0.197942
round_time             0 days 00:15:44.176035
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        754.35321
return_std_test                    111.228508
average_reward_test                  0.754353
round_time_test        0 days 00:00:07.938059
round_time_total       0 days 00:15:44.177154
loss_total                         413.775407
loss_critic                        605.838767
loss_actor                        -354.478063
memory_size                        298481.061 

=== epoch 4/10 ===== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:07,  1.94it/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 [15:45<00:00,  2.12it/s]
episodes                                   10
episode_length                         1000.0
returns                            202.799449
return_std                          61.552061
average_reward                       0.202799
round_time             0 days 00:15:45.989452
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       798.636516
return_std_test                    108.495453
average_reward_test                  0.798637
round_time_test        0 days 00:00:08.251352
round_time_total       0 days 00:15:45.990565
loss_total                         412.888494
loss_critic                        604.630686
loss_actor                        -354.080302
memory_size                        300413.061 

=== epoch 4/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:44,  2.11it/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 [15:49<00:00,  2.11it/s]
episodes                                   10
episode_length                         1000.0
returns                            208.336501
return_std                          64.598157
average_reward                       0.208337
round_time             0 days 00:15:50.323704
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       822.411394
return_std_test                     80.108246
average_reward_test                  0.822411
round_time_test        0 days 00:00:08.366137
round_time_total       0 days 00:15:50.324905
loss_total                         408.796836
loss_critic                        599.642057
loss_actor                        -354.584076
memory_size                        302345.061 

=== epoch 4/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:30,  1.90it/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 [15:55<00:00,  2.09it/s]
episodes                                   10
episode_length                         1000.0
returns                             225.99805
return_std                          55.798485
average_reward                       0.225998
round_time             0 days 00:15:55.768614
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       815.524507
return_std_test                     94.941855
average_reward_test                  0.815525
round_time_test        0 days 00:00:08.127918
round_time_total       0 days 00:15:55.769748
loss_total                         413.161697
loss_critic                        605.226727
loss_actor                        -355.098449
memory_size                        304277.061 

=== epoch 4/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:53,  2.09it/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 [15:56<00:00,  2.09it/s]
episodes                                   10
episode_length                         1000.0
returns                            232.969641
return_std                           69.80907
average_reward                        0.23297
round_time             0 days 00:15:56.660308
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        851.77886
return_std_test                     71.121107
average_reward_test                  0.851779
round_time_test        0 days 00:00:08.087273
round_time_total       0 days 00:15:56.661550
loss_total                         418.404816
loss_critic                        612.081765
loss_actor                        -356.303004
memory_size                        306209.061 

=== epoch 4/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:34,  1.89it/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 [15:58<00:00,  2.09it/s]
episodes                                   10
episode_length                         1000.0
returns                            242.066558
return_std                          71.979675
average_reward                       0.242067
round_time             0 days 00:15:59.219809
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       769.422872
return_std_test                     84.281603
average_reward_test                  0.769423
round_time_test        0 days 00:00:07.944593
round_time_total       0 days 00:15:59.220913
loss_total                         415.910022
loss_critic                        609.244394
loss_actor                        -357.427492
memory_size                        308141.061 

=== epoch 4/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:25,  1.91it/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 [15:59<00:00,  2.08it/s]
episodes                                   10
episode_length                         1000.0
returns                            254.662537
return_std                            51.3356
average_reward                       0.254663
round_time             0 days 00:16:00.080016
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       831.935809
return_std_test                    101.992856
average_reward_test                  0.831936
round_time_test        0 days 00:00:08.155149
round_time_total       0 days 00:16:00.081123
loss_total                         420.345864
loss_critic                        615.288605
loss_actor                        -359.425128
memory_size                        310073.061 

=== epoch 4/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:11,  1.83it/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 [16:06<00:00,  2.07it/s]
episodes                                   10
episode_length                         1000.0
returns                            267.996227
return_std                          50.580726
average_reward                       0.267996
round_time             0 days 00:16:07.470864
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       799.787353
return_std_test                     76.635308
average_reward_test                  0.799787
round_time_test        0 days 00:00:08.168070
round_time_total       0 days 00:16:07.471975
loss_total                          410.48136
loss_critic                        603.242944
loss_actor                        -360.565007
memory_size                        312005.061 

=== epoch 4/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:53,  1.86it/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 [16:04<00:00,  2.07it/s]
episodes                                   10
episode_length                         1000.0
returns                            280.416568
return_std                          60.969271
average_reward                       0.280417
round_time             0 days 00:16:04.910180
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       855.719335
return_std_test                    127.237907
average_reward_test                  0.855719
round_time_test        0 days 00:00:08.058924
round_time_total       0 days 00:16:04.911311
loss_total                         420.383874
loss_critic                        615.831121
loss_actor                        -361.405146
memory_size                        313937.061 

=== epoch 4/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:36,  1.79it/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 [16:08<00:00,  2.06it/s]
episodes                                   10
episode_length                         1000.0
returns                            280.086623
return_std                          52.371923
average_reward                       0.280087
round_time             0 days 00:16:09.479015
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       774.787913
return_std_test                     62.002336
average_reward_test                  0.774788
round_time_test        0 days 00:00:08.077350
round_time_total       0 days 00:16:09.480122
loss_total                          418.88728
loss_critic                        614.301924
loss_actor                        -362.771328
memory_size                        315869.061 

=== epoch 4/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:12,  1.93it/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 [16:13<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                            284.888781
return_std                          53.428423
average_reward                       0.284889
round_time             0 days 00:16:14.056108
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       815.251023
return_std_test                     73.997948
average_reward_test                  0.815251
round_time_test        0 days 00:00:08.329985
round_time_total       0 days 00:16:14.057223
loss_total                         425.084777
loss_critic                        622.158541
loss_actor                        -363.210311
memory_size                        317801.061 

=== epoch 4/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:27,  1.80it/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 [16:10<00:00,  2.06it/s]
episodes                                   10
episode_length                         1000.0
returns                            303.879863
return_std                          53.617873
average_reward                        0.30388
round_time             0 days 00:16:10.565348
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       749.512403
return_std_test                    113.497441
average_reward_test                  0.749512
round_time_test        0 days 00:00:08.214221
round_time_total       0 days 00:16:10.566496
loss_total                         421.083044
loss_critic                        617.309788
loss_actor                        -363.823959
memory_size                        319733.061 

=== epoch 4/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:54,  1.97it/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 [16:14<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                            295.643933
return_std                          58.391429
average_reward                       0.295644
round_time             0 days 00:16:15.417767
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       792.194729
return_std_test                     42.085536
average_reward_test                  0.792195
round_time_test        0 days 00:00:08.139418
round_time_total       0 days 00:16:15.418866
loss_total                         423.346635
loss_critic                        620.570723
loss_actor                        -365.549743
memory_size                        321665.061 

=== epoch 4/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:10,  1.83it/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 [16:16<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                            285.807611
return_std                          51.422057
average_reward                       0.285808
round_time             0 days 00:16:17.521723
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       786.902402
return_std_test                     60.475768
average_reward_test                  0.786902
round_time_test        0 days 00:00:08.182918
round_time_total       0 days 00:16:17.522851
loss_total                         426.567996
loss_critic                         624.98405
loss_actor                        -367.096251
memory_size                        323597.061 

=== epoch 4/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:22,  1.81it/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 [16:19<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                            272.992291
return_std                          58.221546
average_reward                       0.272992
round_time             0 days 00:16:19.610654
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       837.649466
return_std_test                     89.922984
average_reward_test                  0.837649
round_time_test        0 days 00:00:08.336431
round_time_total       0 days 00:16:19.611760
loss_total                          427.16624
loss_critic                        625.910703
loss_actor                        -367.811642
memory_size                        325529.061 

=== epoch 4/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:41,  2.12it/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 [16:23<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                            261.917838
return_std                          63.653991
average_reward                       0.261918
round_time             0 days 00:16:24.527629
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       837.931778
return_std_test                     75.717784
average_reward_test                  0.837932
round_time_test        0 days 00:00:08.263613
round_time_total       0 days 00:16:24.528840
loss_total                         424.407328
loss_critic                        622.580998
loss_actor                        -368.287385
memory_size                        327461.061 

=== epoch 4/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:50,  1.87it/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 [16:23<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                            224.245205
return_std                          57.619216
average_reward                       0.224245
round_time             0 days 00:16:24.305891
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       902.318077
return_std_test                     81.768133
average_reward_test                  0.902318
round_time_test        0 days 00:00:08.167825
round_time_total       0 days 00:16:24.307268
loss_total                         431.217746
loss_critic                        631.406201
loss_actor                        -369.536108
memory_size                        329393.061 

=== epoch 4/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:58,  1.85it/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 [16:27<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                             220.79115
return_std                          57.748047
average_reward                       0.220791
round_time             0 days 00:16:27.715924
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       809.632688
return_std_test                     94.203102
average_reward_test                  0.809633
round_time_test        0 days 00:00:08.153226
round_time_total       0 days 00:16:27.717023
loss_total                         435.012078
loss_critic                        636.188294
loss_actor                        -369.692814
memory_size                        331325.061 

=== epoch 4/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:35,  1.79it/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 [16:27<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                            233.741158
return_std                          77.494074
average_reward                       0.233741
round_time             0 days 00:16:28.246872
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       838.867814
return_std_test                     74.189004
average_reward_test                  0.838868
round_time_test        0 days 00:00:08.105583
round_time_total       0 days 00:16:28.248009
loss_total                         435.817692
loss_critic                        637.410226
loss_actor                        -370.552477
memory_size                        333257.061 

=== epoch 4/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:42,  1.88it/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 [16:28<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                            240.577995
return_std                          75.837712
average_reward                       0.240578
round_time             0 days 00:16:29.280673
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       811.001038
return_std_test                     50.681762
average_reward_test                  0.811001
round_time_test        0 days 00:00:08.116215
round_time_total       0 days 00:16:29.281778
loss_total                         432.276862
loss_critic                        633.038965
loss_actor                        -370.771581
memory_size                        335189.061 

=== epoch 4/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:39,  2.00it/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 [16:33<00:00,  2.01it/s]
episodes                                   10
episode_length                         1000.0
returns                             250.57848
return_std                          90.919533
average_reward                       0.250578
round_time             0 days 00:16:33.899373
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       827.692457
return_std_test                     91.494272
average_reward_test                  0.827692
round_time_test        0 days 00:00:08.245790
round_time_total       0 days 00:16:33.900688
loss_total                         437.592676
loss_critic                        639.971671
loss_actor                        -371.923339
memory_size                        337121.061 

=== epoch 4/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<19:36,  1.70it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [16:20<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                            283.394898
return_std                          80.982761
average_reward                       0.283395
round_time             0 days 00:16:20.940021
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       833.828969
return_std_test                    119.842164
average_reward_test                  0.833829
round_time_test        0 days 00:00:08.200912
round_time_total       0 days 00:16:20.941131
loss_total                         436.264785
loss_critic                         638.72304
loss_actor                        -373.568268
memory_size                        339053.061 

=== epoch 4/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:51,  2.10it/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 [16:20<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                            292.020141
return_std                          75.378897
average_reward                        0.29202
round_time             0 days 00:16:20.962828
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       852.061786
return_std_test                     44.234191
average_reward_test                  0.852062
round_time_test        0 days 00:00:08.462751
round_time_total       0 days 00:16:20.964168
loss_total                         429.653259
loss_critic                        630.356413
loss_actor                        -373.159384
memory_size                        340985.061 

=== epoch 4/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:05,  1.95it/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 [16:22<00:00,  2.04it/s]
episodes                                   10
episode_length                         1000.0
returns                            280.639825
return_std                          65.163141
average_reward                        0.28064
round_time             0 days 00:16:22.651645
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       836.927621
return_std_test                    137.447962
average_reward_test                  0.836928
round_time_test        0 days 00:00:07.895674
round_time_total       0 days 00:16:22.652789
loss_total                         443.007769
loss_critic                        647.378318
loss_actor                        -374.474459
memory_size                        342917.061 

=== epoch 4/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:54,  1.86it/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 [16:29<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                            286.269042
return_std                          62.415643
average_reward                       0.286269
round_time             0 days 00:16:30.187199
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       837.348217
return_std_test                     83.050881
average_reward_test                  0.837348
round_time_test        0 days 00:00:07.965540
round_time_total       0 days 00:16:30.188321
loss_total                         447.963579
loss_critic                        653.857256
loss_actor                        -375.611161
memory_size                        344849.061 

=== epoch 4/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:20,  1.92it/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 [16:24<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                            267.583762
return_std                          44.903631
average_reward                       0.267584
round_time             0 days 00:16:25.435567
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       832.943843
return_std_test                    111.872772
average_reward_test                  0.832944
round_time_test        0 days 00:00:08.101636
round_time_total       0 days 00:16:25.436912
loss_total                         438.029724
loss_critic                        641.513272
loss_actor                        -375.904499
memory_size                        346781.061 

=== epoch 4/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:36,  1.89it/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 [16:29<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                            251.833326
return_std                          32.202942
average_reward                       0.251833
round_time             0 days 00:16:29.938829
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       794.327724
return_std_test                     88.397513
average_reward_test                  0.794328
round_time_test        0 days 00:00:08.335566
round_time_total       0 days 00:16:29.939944
loss_total                         437.473707
loss_critic                        640.680804
loss_actor                        -375.354716
memory_size                        348713.061 

=== epoch 4/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:32,  1.90it/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 [16:28<00:00,  2.02it/s]
episodes                                   10
episode_length                         1000.0
returns                             242.62465
return_std                          34.793329
average_reward                       0.242625
round_time             0 days 00:16:29.270491
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       814.953438
return_std_test                     61.333431
average_reward_test                  0.814953
round_time_test        0 days 00:00:08.093820
round_time_total       0 days 00:16:29.271612
loss_total                          440.56933
loss_critic                        644.935629
loss_actor                        -376.895901
memory_size                        350645.061 

=== epoch 4/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:43,  1.88it/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 [16:27<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                             249.87875
return_std                          44.207694
average_reward                       0.249879
round_time             0 days 00:16:28.043752
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       831.985862
return_std_test                     69.535223
average_reward_test                  0.831986
round_time_test        0 days 00:00:08.051145
round_time_total       0 days 00:16:28.045083
loss_total                         445.365213
loss_critic                         651.35427
loss_actor                        -378.591049
memory_size                        352577.061 

=== epoch 4/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:25,  1.81it/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 [16:26<00:00,  2.03it/s]
episodes                                   10
episode_length                         1000.0
returns                            255.965235
return_std                          46.940989
average_reward                       0.255965
round_time             0 days 00:16:26.980080
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        786.74058
return_std_test                    103.419466
average_reward_test                  0.786741
round_time_test        0 days 00:00:08.024742
round_time_total       0 days 00:16:26.981394
loss_total                         438.687848
loss_critic                        643.095677
loss_actor                        -378.943499
memory_size                        354509.061 

=== epoch 4/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:07,  1.84it/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 [16:08<00:00,  2.07it/s]
episodes                                   10
episode_length                         1000.0
returns                            261.404435
return_std                          43.472472
average_reward                       0.261404
round_time             0 days 00:16:08.960135
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       753.143248
return_std_test                    132.482353
average_reward_test                  0.753143
round_time_test        0 days 00:00:08.031623
round_time_total       0 days 00:16:08.961228
loss_total                         438.559248
loss_critic                        642.929149
loss_actor                        -378.920391
memory_size                        356441.061 

=== epoch 4/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:21,  2.17it/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 [14:55<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                             278.86141
return_std                          52.567899
average_reward                       0.278861
round_time             0 days 00:14:55.697152
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       727.265606
return_std_test                    118.925985
average_reward_test                  0.727266
round_time_test        0 days 00:00:07.603959
round_time_total       0 days 00:14:55.698243
loss_total                         432.509662
loss_critic                        635.390647
loss_actor                        -379.014312
memory_size                        358373.061 

=== epoch 4/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:43,  2.12it/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 [14:56<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            267.409288
return_std                          69.212948
average_reward                       0.267409
round_time             0 days 00:14:57.148536
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       713.315611
return_std_test                     80.984662
average_reward_test                  0.713316
round_time_test        0 days 00:00:07.746931
round_time_total       0 days 00:14:57.149613
loss_total                         430.307061
loss_critic                        632.728628
loss_actor                        -379.379238
memory_size                        360305.061 

=== epoch 4/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:09,  2.20it/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 [14:56<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            260.026177
return_std                          75.742563
average_reward                       0.260026
round_time             0 days 00:14:56.766204
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       733.790273
return_std_test                     69.209515
average_reward_test                   0.73379
round_time_test        0 days 00:00:07.681605
round_time_total       0 days 00:14:56.767280
loss_total                         435.676824
loss_critic                         639.65461
loss_actor                        -380.234354
memory_size                        362237.061 

=== epoch 4/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:50,  2.10it/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 [14:58<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            253.148949
return_std                          77.071955
average_reward                       0.253149
round_time             0 days 00:14:59.100262
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       776.829249
return_std_test                      78.48014
average_reward_test                  0.776829
round_time_test        0 days 00:00:07.598243
round_time_total       0 days 00:14:59.101346
loss_total                         436.247848
loss_critic                        640.542091
loss_actor                        -380.929159
memory_size                        364169.061 

=== epoch 4/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:20,  2.17it/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 [15:00<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            257.800012
return_std                          75.289954
average_reward                         0.2578
round_time             0 days 00:15:00.793102
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       739.494458
return_std_test                      89.96097
average_reward_test                  0.739494
round_time_test        0 days 00:00:07.721587
round_time_total       0 days 00:15:00.794404
loss_total                         433.553342
loss_critic                        637.436645
loss_actor                        -381.979898
memory_size                        366101.061 

=== epoch 4/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:42,  2.12it/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 [15:02<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            237.689469
return_std                          63.038888
average_reward                       0.237689
round_time             0 days 00:15:02.643280
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       752.350092
return_std_test                     91.721215
average_reward_test                   0.75235
round_time_test        0 days 00:00:07.736781
round_time_total       0 days 00:15:02.644382
loss_total                         431.308138
loss_critic                        634.704575
loss_actor                        -382.277641
memory_size                        368033.061 

=== epoch 4/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:55,  1.86it/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 [15:02<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            254.628432
return_std                          46.732452
average_reward                       0.254628
round_time             0 days 00:15:02.789867
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       773.010371
return_std_test                     81.039453
average_reward_test                   0.77301
round_time_test        0 days 00:00:07.656756
round_time_total       0 days 00:15:02.790940
loss_total                         435.032757
loss_critic                        639.161019
loss_actor                        -381.480322
memory_size                        369965.061 

=== epoch 4/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:59,  1.96it/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 [15:08<00:00,  2.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            251.366868
return_std                           30.28387
average_reward                       0.251367
round_time             0 days 00:15:09.361030
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       712.886294
return_std_test                     50.600088
average_reward_test                  0.712886
round_time_test        0 days 00:00:07.757559
round_time_total       0 days 00:15:09.362128
loss_total                         441.482643
loss_critic                        647.522559
loss_actor                        -382.677053
memory_size                        371897.061 

=== epoch 4/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:55,  1.97it/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 [15:04<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            245.600012
return_std                          25.122292
average_reward                         0.2456
round_time             0 days 00:15:05.115588
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       782.382635
return_std_test                     68.220419
average_reward_test                  0.782383
round_time_test        0 days 00:00:07.630587
round_time_total       0 days 00:15:05.116673
loss_total                         436.627753
loss_critic                        641.684484
loss_actor                        -383.599204
memory_size                        373829.061 

=== epoch 4/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:29,  2.15it/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 [15:03<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            233.738266
return_std                          30.277358
average_reward                       0.233738
round_time             0 days 00:15:03.923104
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       770.156538
return_std_test                     57.647938
average_reward_test                  0.770157
round_time_test        0 days 00:00:07.620964
round_time_total       0 days 00:15:03.924193
loss_total                         437.355248
loss_critic                        642.544396
loss_actor                        -383.401376
memory_size                        375761.061 

=== epoch 4/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:26,  2.03it/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 [15:06<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            231.157337
return_std                          46.270531
average_reward                       0.231157
round_time             0 days 00:15:06.620631
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       760.290992
return_std_test                     88.893308
average_reward_test                  0.760291
round_time_test        0 days 00:00:07.666117
round_time_total       0 days 00:15:06.621719
loss_total                         429.987829
loss_critic                        633.371281
loss_actor                        -383.546012
memory_size                        377693.061 

=== epoch 4/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:31,  2.14it/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 [15:07<00:00,  2.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            233.250786
return_std                          48.031316
average_reward                       0.233251
round_time             0 days 00:15:07.838494
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       771.801908
return_std_test                     63.862964
average_reward_test                  0.771802
round_time_test        0 days 00:00:07.655401
round_time_total       0 days 00:15:07.839592
loss_total                         432.351324
loss_critic                        636.526292
loss_actor                         -384.34858
memory_size                        379625.061 

=== epoch 4/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:01,  2.22it/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 [15:07<00:00,  2.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            226.025491
return_std                           47.45178
average_reward                       0.226025
round_time             0 days 00:15:08.293975
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       745.255412
return_std_test                    106.199614
average_reward_test                  0.745255
round_time_test        0 days 00:00:07.744024
round_time_total       0 days 00:15:08.295073
loss_total                         443.225621
loss_critic                        650.364553
loss_actor                         -385.33014
memory_size                        381557.061 

=== epoch 4/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:49,  1.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [15:11<00:00,  2.19it/s]
episodes                                   10
episode_length                         1000.0
returns                            221.492221
return_std                          46.690238
average_reward                       0.221492
round_time             0 days 00:15:11.803714
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        757.41969
return_std_test                    113.490221
average_reward_test                   0.75742
round_time_test        0 days 00:00:07.879038
round_time_total       0 days 00:15:11.804795
loss_total                         442.781241
loss_critic                        650.089279
loss_actor                        -386.450948
memory_size                        383489.061 

=== epoch 4/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:28,  2.02it/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 [15:10<00:00,  2.20it/s]
<GE432_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                            245.727593
return_std                          63.771488
average_reward                       0.245728
round_time             0 days 00:15:10.987244
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       818.511916
return_std_test                     60.645037
average_reward_test                  0.818512
round_time_test        0 days 00:00:07.578954
round_time_total       0 days 00:15:10.988371
loss_total                         448.835938
loss_critic                        657.923431
loss_actor                        -387.514071
memory_size                        385421.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 5/10 ===== round 1/50 ======================================
  0%|          | 4/2000 [00:01<14:35,  2.28it/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 [14:10<00:00,  2.35it/s]
episodes                                    2
episode_length                         1000.0
returns                            264.643127
return_std                          21.406894
average_reward                       0.264643
round_time             0 days 00:14:10.098511
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       828.390517
return_std_test                      83.66183
average_reward_test                  0.828391
round_time_test        0 days 00:00:07.542063
round_time_total       0 days 00:14:10.099604
loss_total                         452.737812
loss_critic                        662.961352
loss_actor                        -388.156389
memory_size                        387354.061 

=== epoch 5/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:57,  2.22it/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 [14:14<00:00,  2.34it/s]
episodes                                    4
episode_length                         1000.0
returns                            264.192405
return_std                          35.536154
average_reward                       0.264192
round_time             0 days 00:14:14.639949
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       774.735827
return_std_test                     48.195148
average_reward_test                  0.774736
round_time_test        0 days 00:00:07.666891
round_time_total       0 days 00:14:14.641070
loss_total                         452.832021
loss_critic                        663.175087
loss_actor                        -388.540278
memory_size                        389286.061 

=== epoch 5/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:09,  2.20it/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 [14:16<00:00,  2.33it/s]
episodes                                    6
episode_length                         1000.0
returns                             246.03636
return_std                          40.764746
average_reward                       0.246036
round_time             0 days 00:14:17.267525
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       745.903001
return_std_test                     40.548606
average_reward_test                  0.745903
round_time_test        0 days 00:00:07.701048
round_time_total       0 days 00:14:17.268605
loss_total                         449.046912
loss_critic                        658.738701
loss_actor                        -389.720275
memory_size                        391218.061 

=== epoch 5/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:31,  2.29it/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 [14:19<00:00,  2.33it/s]
episodes                                    8
episode_length                         1000.0
returns                            251.639569
return_std                          39.606206
average_reward                        0.25164
round_time             0 days 00:14:20.181828
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        695.73526
return_std_test                    101.318769
average_reward_test                  0.695735
round_time_test        0 days 00:00:07.652711
round_time_total       0 days 00:14:20.182910
loss_total                         446.181272
loss_critic                        655.160515
loss_actor                        -389.735734
memory_size                        393150.061 

=== epoch 5/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:45,  2.25it/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 [14:19<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            257.429984
return_std                          50.763049
average_reward                        0.25743
round_time             0 days 00:14:20.290110
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       795.063445
return_std_test                    100.800899
average_reward_test                  0.795063
round_time_test        0 days 00:00:07.643876
round_time_total       0 days 00:14:20.291197
loss_total                         448.010633
loss_critic                        657.583765
loss_actor                        -390.281929
memory_size                        395082.061 

=== epoch 5/10 ===== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:47,  2.25it/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 [14:18<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            257.657613
return_std                          52.597531
average_reward                       0.257658
round_time             0 days 00:14:18.617516
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       844.308731
return_std_test                     86.991233
average_reward_test                  0.844309
round_time_test        0 days 00:00:07.697784
round_time_total       0 days 00:14:18.618589
loss_total                          448.30996
loss_critic                        658.002657
loss_actor                        -390.460861
memory_size                        397014.061 

=== epoch 5/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:39,  2.27it/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 [14:18<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            251.732779
return_std                          49.446159
average_reward                       0.251733
round_time             0 days 00:14:19.533132
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       725.637983
return_std_test                     80.492343
average_reward_test                  0.725638
round_time_test        0 days 00:00:07.593777
round_time_total       0 days 00:14:19.534213
loss_total                          446.34394
loss_critic                        655.383985
loss_actor                        -389.816279
memory_size                        398946.061 

=== epoch 5/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:09,  2.35it/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 [14:19<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            260.403258
return_std                          45.209569
average_reward                       0.260403
round_time             0 days 00:14:20.287545
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       745.696593
return_std_test                      58.53772
average_reward_test                  0.745697
round_time_test        0 days 00:00:07.508584
round_time_total       0 days 00:14:20.288666
loss_total                         454.141651
loss_critic                        665.403679
loss_actor                        -390.906498
memory_size                        400878.061 

=== epoch 5/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:12,  2.19it/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 [14:21<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                            259.391772
return_std                          66.984496
average_reward                       0.259392
round_time             0 days 00:14:22.267609
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        856.35628
return_std_test                     70.529024
average_reward_test                  0.856356
round_time_test        0 days 00:00:07.608110
round_time_total       0 days 00:14:22.268689
loss_total                         446.054509
loss_critic                        655.288607
loss_actor                        -390.881923
memory_size                        402810.061 

=== epoch 5/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:11,  2.19it/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 [14:23<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                             262.94507
return_std                           61.42742
average_reward                       0.262945
round_time             0 days 00:14:24.124319
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       796.523478
return_std_test                     70.993995
average_reward_test                  0.796523
round_time_test        0 days 00:00:07.671351
round_time_total       0 days 00:14:24.125392
loss_total                         447.584388
loss_critic                        657.188283
loss_actor                        -390.831228
memory_size                        404742.061 

=== epoch 5/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:13,  2.34it/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 [14:23<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                            258.190145
return_std                          88.176196
average_reward                        0.25819
round_time             0 days 00:14:24.037847
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       785.867015
return_std_test                     63.136263
average_reward_test                  0.785867
round_time_test        0 days 00:00:07.595839
round_time_total       0 days 00:14:24.038946
loss_total                         452.023262
loss_critic                        662.815179
loss_actor                        -391.144438
memory_size                        406674.061 

=== epoch 5/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:14,  2.18it/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 [14:24<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                             278.49664
return_std                          93.673044
average_reward                       0.278497
round_time             0 days 00:14:25.461257
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       784.455144
return_std_test                     58.607219
average_reward_test                  0.784455
round_time_test        0 days 00:00:07.627850
round_time_total       0 days 00:14:25.462417
loss_total                         453.794906
loss_critic                        665.308968
loss_actor                        -392.261378
memory_size                        408606.061 

=== epoch 5/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:19,  2.04it/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 [14:26<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            289.245905
return_std                          92.735817
average_reward                       0.289246
round_time             0 days 00:14:26.615407
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       863.714927
return_std_test                     65.413825
average_reward_test                  0.863715
round_time_test        0 days 00:00:07.625445
round_time_total       0 days 00:14:26.616485
loss_total                         448.757393
loss_critic                        659.004847
loss_actor                         -392.23246
memory_size                        410538.061 

=== epoch 5/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:38,  2.27it/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 [14:28<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            306.234197
return_std                          79.666681
average_reward                       0.306234
round_time             0 days 00:14:29.452907
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       782.985612
return_std_test                     47.257793
average_reward_test                  0.782986
round_time_test        0 days 00:00:07.758645
round_time_total       0 days 00:14:29.453992
loss_total                         458.127566
loss_critic                        670.866071
loss_actor                         -392.82649
memory_size                        412470.061 

=== epoch 5/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:10,  2.19it/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 [14:28<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            296.570048
return_std                          81.237647
average_reward                        0.29657
round_time             0 days 00:14:28.798337
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       795.859493
return_std_test                     86.612301
average_reward_test                  0.795859
round_time_test        0 days 00:00:07.681696
round_time_total       0 days 00:14:28.799423
loss_total                         447.968745
loss_critic                        658.176338
loss_actor                        -392.861663
memory_size                        414402.061 

=== epoch 5/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:58,  2.22it/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 [14:30<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            305.525505
return_std                          41.836375
average_reward                       0.305526
round_time             0 days 00:14:30.626804
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        758.78453
return_std_test                     80.385648
average_reward_test                  0.758785
round_time_test        0 days 00:00:07.681300
round_time_total       0 days 00:14:30.628012
loss_total                         452.732726
loss_critic                        664.275507
loss_actor                        -393.438429
memory_size                        416334.061 

=== epoch 5/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:40,  2.27it/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 [14:29<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            292.592453
return_std                          37.348715
average_reward                       0.292592
round_time             0 days 00:14:30.159213
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       788.915929
return_std_test                     85.909252
average_reward_test                  0.788916
round_time_test        0 days 00:00:07.653456
round_time_total       0 days 00:14:30.160303
loss_total                         462.831715
loss_critic                        677.289252
loss_actor                         -394.99847
memory_size                        418266.061 

=== epoch 5/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:35,  2.28it/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 [14:32<00:00,  2.29it/s]
episodes                                   10
episode_length                         1000.0
returns                            324.941188
return_std                          80.887473
average_reward                       0.324941
round_time             0 days 00:14:32.917456
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       866.449796
return_std_test                    100.294427
average_reward_test                   0.86645
round_time_test        0 days 00:00:07.625252
round_time_total       0 days 00:14:32.918532
loss_total                         475.048904
loss_critic                        693.077331
loss_actor                        -397.064844
memory_size                        420198.061 

=== epoch 5/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:18,  2.04it/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 [14:32<00:00,  2.29it/s]
episodes                                   10
episode_length                         1000.0
returns                            337.625809
return_std                          94.072499
average_reward                       0.337626
round_time             0 days 00:14:33.276492
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       936.235084
return_std_test                     72.685007
average_reward_test                  0.936235
round_time_test        0 days 00:00:07.649366
round_time_total       0 days 00:14:33.277576
loss_total                         478.553404
loss_critic                        698.081128
loss_actor                        -399.557534
memory_size                        422130.061 

=== epoch 5/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:12,  2.34it/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 [14:35<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                            363.883001
return_std                          84.010693
average_reward                       0.363883
round_time             0 days 00:14:36.409762
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       870.662381
return_std_test                     84.145878
average_reward_test                  0.870662
round_time_test        0 days 00:00:07.567172
round_time_total       0 days 00:14:36.410872
loss_total                         489.383172
loss_critic                        712.217581
loss_actor                        -401.954506
memory_size                        424062.061 

=== epoch 5/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:17,  2.04it/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 [14:38<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                            396.656631
return_std                           79.26306
average_reward                       0.396657
round_time             0 days 00:14:38.645583
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       814.701069
return_std_test                    123.266632
average_reward_test                  0.814701
round_time_test        0 days 00:00:07.669076
round_time_total       0 days 00:14:38.646673
loss_total                         491.718893
loss_critic                        715.380115
loss_actor                        -402.926035
memory_size                        425994.061 

=== epoch 5/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:45,  2.11it/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 [14:43<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            421.378073
return_std                          49.425333
average_reward                       0.421378
round_time             0 days 00:14:44.122277
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       855.470528
return_std_test                     84.199412
average_reward_test                  0.855471
round_time_test        0 days 00:00:07.740895
round_time_total       0 days 00:14:44.123374
loss_total                         492.614119
loss_critic                        716.671127
loss_actor                        -403.613956
memory_size                        427926.061 

=== epoch 5/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:06,  2.07it/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 [14:42<00:00,  2.27it/s]
episodes                                   10
episode_length                         1000.0
returns                            420.541429
return_std                          48.240571
average_reward                       0.420541
round_time             0 days 00:14:42.675440
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       873.322285
return_std_test                    115.715489
average_reward_test                  0.873322
round_time_test        0 days 00:00:07.607477
round_time_total       0 days 00:14:42.676525
loss_total                         494.535762
loss_critic                        719.214081
loss_actor                        -404.177555
memory_size                        429858.061 

=== epoch 5/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:14,  2.05it/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 [14:41<00:00,  2.27it/s]
episodes                                   10
episode_length                         1000.0
returns                            430.394467
return_std                          38.734799
average_reward                       0.430394
round_time             0 days 00:14:41.879837
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       913.894399
return_std_test                     68.663848
average_reward_test                  0.913894
round_time_test        0 days 00:00:07.601766
round_time_total       0 days 00:14:41.880916
loss_total                         490.169043
loss_critic                        713.821809
loss_actor                        -404.442064
memory_size                        431790.061 

=== epoch 5/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:28,  2.15it/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 [14:41<00:00,  2.27it/s]
episodes                                   10
episode_length                         1000.0
returns                            416.294807
return_std                          60.576762
average_reward                       0.416295
round_time             0 days 00:14:42.391092
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       875.237512
return_std_test                     116.47058
average_reward_test                  0.875238
round_time_test        0 days 00:00:07.689017
round_time_total       0 days 00:14:42.392178
loss_total                         495.590202
loss_critic                        720.615266
loss_actor                        -404.510097
memory_size                        433722.061 

=== epoch 5/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:55,  1.97it/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 [14:43<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            418.933095
return_std                          63.557294
average_reward                       0.418933
round_time             0 days 00:14:44.435841
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       917.617241
return_std_test                     79.977618
average_reward_test                  0.917617
round_time_test        0 days 00:00:07.658637
round_time_total       0 days 00:14:44.436927
loss_total                          485.57035
loss_critic                        708.001505
loss_actor                        -404.154311
memory_size                        435654.061 

=== epoch 5/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:50,  1.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [14:46<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            434.685146
return_std                          66.829445
average_reward                       0.434685
round_time             0 days 00:14:46.565416
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       867.368754
return_std_test                     72.333852
average_reward_test                  0.867369
round_time_test        0 days 00:00:07.489948
round_time_total       0 days 00:14:46.566509
loss_total                         487.875612
loss_critic                        710.931418
loss_actor                         -404.34765
memory_size                        437586.061 

=== epoch 5/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:29,  2.15it/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 [14:45<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            418.039454
return_std                          72.522519
average_reward                       0.418039
round_time             0 days 00:14:45.486733
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       967.576804
return_std_test                     95.589793
average_reward_test                  0.967577
round_time_test        0 days 00:00:07.649255
round_time_total       0 days 00:14:45.487817
loss_total                         484.246453
loss_critic                        706.542717
loss_actor                        -404.938646
memory_size                        439518.061 

=== epoch 5/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:27,  2.02it/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 [14:47<00:00,  2.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            392.603073
return_std                          74.331251
average_reward                       0.392603
round_time             0 days 00:14:48.199177
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        954.33885
return_std_test                    107.263058
average_reward_test                  0.954339
round_time_test        0 days 00:00:07.574786
round_time_total       0 days 00:14:48.200273
loss_total                         490.093938
loss_critic                         713.71147
loss_actor                        -404.376231
memory_size                        441450.061 

=== epoch 5/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:44,  1.99it/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 [14:46<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            403.283443
return_std                          65.285107
average_reward                       0.403283
round_time             0 days 00:14:47.225123
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       838.319001
return_std_test                     73.489882
average_reward_test                  0.838319
round_time_test        0 days 00:00:07.526252
round_time_total       0 days 00:14:47.226215
loss_total                         489.498039
loss_critic                        713.083501
loss_actor                        -404.843852
memory_size                        443382.061 

=== epoch 5/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:09,  2.06it/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 [14:49<00:00,  2.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            378.908807
return_std                          72.979399
average_reward                       0.378909
round_time             0 days 00:14:49.925190
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       913.006979
return_std_test                     67.831645
average_reward_test                  0.913007
round_time_test        0 days 00:00:07.541818
round_time_total       0 days 00:14:49.926267
loss_total                         493.272813
loss_critic                        717.687854
loss_actor                        -404.387397
memory_size                        445314.061 

=== epoch 5/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:04,  2.07it/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 [14:48<00:00,  2.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            359.948096
return_std                          60.237074
average_reward                       0.359948
round_time             0 days 00:14:49.362601
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       923.272308
return_std_test                    101.346467
average_reward_test                  0.923272
round_time_test        0 days 00:00:07.591014
round_time_total       0 days 00:14:49.363689
loss_total                         491.259642
loss_critic                        715.271156
loss_actor                        -404.786461
memory_size                        447246.061 

=== epoch 5/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:49,  2.10it/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 [14:50<00:00,  2.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            362.883703
return_std                          66.056105
average_reward                       0.362884
round_time             0 days 00:14:50.614136
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       911.046205
return_std_test                     74.993889
average_reward_test                  0.911046
round_time_test        0 days 00:00:07.747267
round_time_total       0 days 00:14:50.615216
loss_total                         490.593521
loss_critic                        714.499913
loss_actor                        -405.032085
memory_size                        449178.061 

=== epoch 5/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:38,  2.27it/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 [14:49<00:00,  2.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            365.687669
return_std                          77.456342
average_reward                       0.365688
round_time             0 days 00:14:50.450476
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       865.968706
return_std_test                    103.796568
average_reward_test                  0.865969
round_time_test        0 days 00:00:07.577810
round_time_total       0 days 00:14:50.451562
loss_total                         490.365965
loss_critic                        714.499013
loss_actor                        -406.166277
memory_size                        451110.061 

=== epoch 5/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:33,  2.14it/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 [14:52<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            369.003643
return_std                          77.483445
average_reward                       0.369004
round_time             0 days 00:14:53.105697
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       913.810098
return_std_test                    121.363358
average_reward_test                   0.91381
round_time_test        0 days 00:00:07.550305
round_time_total       0 days 00:14:53.106780
loss_total                          492.99292
loss_critic                        718.030523
loss_actor                        -407.157536
memory_size                        453042.061 

=== epoch 5/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:57,  2.09it/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 [14:52<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            384.898986
return_std                          67.339663
average_reward                       0.384899
round_time             0 days 00:14:52.983136
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       876.259346
return_std_test                     79.493687
average_reward_test                  0.876259
round_time_test        0 days 00:00:07.621471
round_time_total       0 days 00:14:52.984265
loss_total                         487.847064
loss_critic                        711.588837
loss_actor                        -407.120073
memory_size                        454974.061 

=== epoch 5/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:54,  2.23it/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 [14:51<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                             391.61224
return_std                          70.365029
average_reward                       0.391612
round_time             0 days 00:14:52.277331
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       945.545958
return_std_test                     74.067013
average_reward_test                  0.945546
round_time_test        0 days 00:00:07.631299
round_time_total       0 days 00:14:52.278414
loss_total                         490.207701
loss_critic                        714.618829
loss_actor                        -407.436853
memory_size                        456906.061 

=== epoch 5/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:13,  2.05it/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 [14:57<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            383.348014
return_std                          62.228908
average_reward                       0.383348
round_time             0 days 00:14:58.264041
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       886.657755
return_std_test                     83.614734
average_reward_test                  0.886658
round_time_test        0 days 00:00:07.473157
round_time_total       0 days 00:14:58.265129
loss_total                         489.074693
loss_critic                        713.181667
loss_actor                        -407.353246
memory_size                        458838.061 

=== epoch 5/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:47,  2.11it/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 [14:55<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            396.643584
return_std                          43.479875
average_reward                       0.396644
round_time             0 days 00:14:55.704622
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       887.129907
return_std_test                      69.06483
average_reward_test                   0.88713
round_time_test        0 days 00:00:07.671231
round_time_total       0 days 00:14:55.705708
loss_total                         503.185096
loss_critic                        731.140858
loss_actor                           -408.638
memory_size                        460770.061 

=== epoch 5/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:23,  2.03it/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 [14:57<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            406.554868
return_std                          62.197956
average_reward                       0.406555
round_time             0 days 00:14:57.867778
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       968.181229
return_std_test                     79.362931
average_reward_test                  0.968181
round_time_test        0 days 00:00:07.710304
round_time_total       0 days 00:14:57.868872
loss_total                         503.741364
loss_critic                        732.187924
loss_actor                        -410.044919
memory_size                        462702.061 

=== epoch 5/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:04,  2.07it/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 [14:56<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            404.629586
return_std                           60.47253
average_reward                        0.40463
round_time             0 days 00:14:57.337777
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       935.026358
return_std_test                     67.939493
average_reward_test                  0.935026
round_time_test        0 days 00:00:07.652091
round_time_total       0 days 00:14:57.338854
loss_total                         499.927997
loss_critic                        727.398149
loss_actor                        -409.952651
memory_size                        464634.061 

=== epoch 5/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:47,  2.11it/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 [15:00<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            406.739856
return_std                          52.130732
average_reward                        0.40674
round_time             0 days 00:15:01.061170
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       875.294399
return_std_test                    117.497114
average_reward_test                  0.875294
round_time_test        0 days 00:00:07.590321
round_time_total       0 days 00:15:01.062304
loss_total                         505.655675
loss_critic                        734.729644
loss_actor                        -410.640247
memory_size                        466566.061 

=== epoch 5/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:44,  2.26it/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 [15:04<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            414.206206
return_std                          47.661102
average_reward                       0.414206
round_time             0 days 00:15:04.565551
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       922.291202
return_std_test                     88.791605
average_reward_test                  0.922291
round_time_test        0 days 00:00:07.648094
round_time_total       0 days 00:15:04.566637
loss_total                         504.089687
loss_critic                        732.788702
loss_actor                        -410.706417
memory_size                        468498.061 

=== epoch 5/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:18,  1.92it/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 [15:05<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            391.239504
return_std                          70.623881
average_reward                        0.39124
round_time             0 days 00:15:06.140572
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       895.690036
return_std_test                     52.332877
average_reward_test                   0.89569
round_time_test        0 days 00:00:07.671223
round_time_total       0 days 00:15:06.141652
loss_total                         499.752953
loss_critic                        727.482102
loss_actor                        -411.163688
memory_size                        470430.061 

=== epoch 5/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:03,  2.21it/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 [14:59<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            395.414929
return_std                          58.714872
average_reward                       0.395415
round_time             0 days 00:15:00.196211
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       958.585812
return_std_test                     90.417448
average_reward_test                  0.958586
round_time_test        0 days 00:00:07.608181
round_time_total       0 days 00:15:00.197300
loss_total                         503.336156
loss_critic                        732.047354
loss_actor                        -411.508679
memory_size                        472362.061 

=== epoch 5/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:20,  2.17it/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 [14:59<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            373.808142
return_std                          71.767632
average_reward                       0.373808
round_time             0 days 00:15:00.377612
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        925.65875
return_std_test                      82.86763
average_reward_test                  0.925659
round_time_test        0 days 00:00:07.691187
round_time_total       0 days 00:15:00.378697
loss_total                         494.327486
loss_critic                        720.598631
loss_actor                        -410.757137
memory_size                        474294.061 

=== epoch 5/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:31,  2.01it/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 [14:58<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            387.545596
return_std                          85.214105
average_reward                       0.387546
round_time             0 days 00:14:59.142885
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       881.409073
return_std_test                     95.836015
average_reward_test                  0.881409
round_time_test        0 days 00:00:07.657134
round_time_total       0 days 00:14:59.144012
loss_total                         493.751265
loss_critic                         720.12287
loss_actor                        -411.735196
memory_size                        476226.061 

=== epoch 5/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:37,  2.00it/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 [15:03<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            371.279223
return_std                          92.615371
average_reward                       0.371279
round_time             0 days 00:15:04.271944
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       860.764849
return_std_test                     93.796467
average_reward_test                  0.860765
round_time_test        0 days 00:00:07.681364
round_time_total       0 days 00:15:04.273038
loss_total                         495.528307
loss_critic                        722.277427
loss_actor                        -411.468213
memory_size                        478158.061 

=== epoch 5/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:43,  2.12it/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 [15:05<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            414.371796
return_std                          95.836085
average_reward                       0.414372
round_time             0 days 00:15:05.526173
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       926.288586
return_std_test                     97.298399
average_reward_test                  0.926289
round_time_test        0 days 00:00:07.527984
round_time_total       0 days 00:15:05.527260
loss_total                         503.891798
loss_critic                        732.801595
loss_actor                        -411.747435
memory_size                        480090.061 

=== epoch 5/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:42,  2.12it/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 [15:04<00:00,  2.21it/s]
<GE432_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                            402.297771
return_std                         101.357759
average_reward                       0.402298
round_time             0 days 00:15:04.991732
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       900.739429
return_std_test                    124.843016
average_reward_test                  0.900739
round_time_test        0 days 00:00:07.755107
round_time_total       0 days 00:15:04.992810
loss_total                         498.999889
loss_critic                        726.838355
loss_actor                        -412.354017
memory_size                        482022.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 6/10 ===== round 1/50 ======================================
  0%|          | 4/2000 [00:01<13:50,  2.40it/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 [14:09<00:00,  2.36it/s]
episodes                                    2
episode_length                         1000.0
returns                            379.668847
return_std                          36.842157
average_reward                       0.379669
round_time             0 days 00:14:09.202978
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       904.580102
return_std_test                     89.453898
average_reward_test                   0.90458
round_time_test        0 days 00:00:07.669338
round_time_total       0 days 00:14:09.204110
loss_total                         508.983901
loss_critic                        739.557207
loss_actor                        -413.309372
memory_size                        483955.061 

=== epoch 6/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:01,  2.37it/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 [14:11<00:00,  2.35it/s]
episodes                                    4
episode_length                         1000.0
returns                            339.619743
return_std                          84.683848
average_reward                        0.33962
round_time             0 days 00:14:12.226903
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       896.225109
return_std_test                     99.807631
average_reward_test                  0.896225
round_time_test        0 days 00:00:07.536123
round_time_total       0 days 00:14:12.228016
loss_total                         509.150111
loss_critic                        739.695049
loss_actor                        -413.029689
memory_size                        485887.061 

=== epoch 6/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:19,  2.32it/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 [14:16<00:00,  2.34it/s]
episodes                                    6
episode_length                         1000.0
returns                            316.746272
return_std                          78.598876
average_reward                       0.316746
round_time             0 days 00:14:16.991216
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       934.352609
return_std_test                     72.213625
average_reward_test                  0.934353
round_time_test        0 days 00:00:07.599952
round_time_total       0 days 00:14:16.992304
loss_total                         511.242477
loss_critic                        742.393879
loss_actor                        -413.363178
memory_size                        487819.061 

=== epoch 6/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:31,  2.29it/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 [14:18<00:00,  2.33it/s]
episodes                                    8
episode_length                         1000.0
returns                             332.90822
return_std                          73.633139
average_reward                       0.332908
round_time             0 days 00:14:19.137868
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       937.582021
return_std_test                     70.819345
average_reward_test                  0.937582
round_time_test        0 days 00:00:07.633318
round_time_total       0 days 00:14:19.138960
loss_total                         506.043664
loss_critic                        736.053102
loss_actor                        -413.994132
memory_size                        489751.061 

=== epoch 6/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:51,  2.10it/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 [14:18<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            352.846015
return_std                          78.951103
average_reward                       0.352846
round_time             0 days 00:14:19.451799
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       933.355968
return_std_test                     125.00364
average_reward_test                  0.933356
round_time_test        0 days 00:00:07.619626
round_time_total       0 days 00:14:19.452878
loss_total                         510.300915
loss_critic                        741.512321
loss_actor                        -414.544752
memory_size                        491683.061 

=== epoch 6/10 ===== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:37,  2.13it/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 [14:19<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            363.636036
return_std                          83.705126
average_reward                       0.363636
round_time             0 days 00:14:19.728090
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       956.320957
return_std_test                     91.710931
average_reward_test                  0.956321
round_time_test        0 days 00:00:07.552063
round_time_total       0 days 00:14:19.729186
loss_total                          509.89651
loss_critic                        741.292932
loss_actor                        -415.689223
memory_size                        493615.061 

=== epoch 6/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:14,  2.18it/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 [14:20<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                            394.014922
return_std                          71.509102
average_reward                       0.394015
round_time             0 days 00:14:20.797140
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        934.36424
return_std_test                     86.428415
average_reward_test                  0.934364
round_time_test        0 days 00:00:07.634117
round_time_total       0 days 00:14:20.798234
loss_total                         514.764269
loss_critic                         747.64129
loss_actor                        -416.743857
memory_size                        495547.061 

=== epoch 6/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:41,  2.27it/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 [14:20<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                            427.674917
return_std                            34.1342
average_reward                       0.427675
round_time             0 days 00:14:20.909719
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       920.269751
return_std_test                     82.207402
average_reward_test                   0.92027
round_time_test        0 days 00:00:07.546735
round_time_total       0 days 00:14:20.910807
loss_total                         510.568414
loss_critic                        742.383774
loss_actor                        -416.693068
memory_size                        497479.061 

=== epoch 6/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:57,  2.09it/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 [14:20<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            410.500582
return_std                          65.549184
average_reward                       0.410501
round_time             0 days 00:14:20.523002
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       979.791754
return_std_test                     59.753543
average_reward_test                  0.979792
round_time_test        0 days 00:00:07.539097
round_time_total       0 days 00:14:20.524139
loss_total                         513.808492
loss_critic                        746.423122
loss_actor                        -416.650073
memory_size                        499411.061 

=== epoch 6/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:43,  2.26it/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 [14:24<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            399.878533
return_std                          67.482832
average_reward                       0.399879
round_time             0 days 00:14:24.788985
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       908.722374
return_std_test                     88.569455
average_reward_test                  0.908722
round_time_test        0 days 00:00:07.581602
round_time_total       0 days 00:14:24.790063
loss_total                         508.970345
loss_critic                        740.539384
loss_actor                        -417.305862
memory_size                        501343.061 

=== epoch 6/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:39,  2.27it/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 [14:24<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            400.122175
return_std                          67.952967
average_reward                       0.400122
round_time             0 days 00:14:25.456630
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       959.374631
return_std_test                     52.412304
average_reward_test                  0.959375
round_time_test        0 days 00:00:07.682863
round_time_total       0 days 00:14:25.457713
loss_total                         518.127603
loss_critic                        752.079167
loss_actor                        -417.678697
memory_size                        503275.061 

=== epoch 6/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:31,  2.29it/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 [14:22<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                            394.236559
return_std                          69.917819
average_reward                       0.394237
round_time             0 days 00:14:23.475903
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       851.842374
return_std_test                     95.249162
average_reward_test                  0.851842
round_time_test        0 days 00:00:07.621099
round_time_total       0 days 00:14:23.476991
loss_total                           516.0818
loss_critic                        749.715823
loss_actor                        -418.454343
memory_size                        505207.061 

=== epoch 6/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:10,  2.19it/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 [14:25<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                             379.78347
return_std                          70.896453
average_reward                       0.379783
round_time             0 days 00:14:25.633123
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                         901.4379
return_std_test                     90.971351
average_reward_test                  0.901438
round_time_test        0 days 00:00:07.660806
round_time_total       0 days 00:14:25.634200
loss_total                         514.219954
loss_critic                        747.371715
loss_actor                         -418.38714
memory_size                        507139.061 

=== epoch 6/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:10,  2.35it/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 [14:26<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            391.715859
return_std                           59.44142
average_reward                       0.391716
round_time             0 days 00:14:26.516220
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       891.727972
return_std_test                    137.937557
average_reward_test                  0.891728
round_time_test        0 days 00:00:07.530760
round_time_total       0 days 00:14:26.517302
loss_total                         508.032102
loss_critic                          739.7814
loss_actor                        -418.965137
memory_size                        509071.061 

=== epoch 6/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:12,  2.19it/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 [14:28<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            399.507899
return_std                          56.919647
average_reward                       0.399508
round_time             0 days 00:14:28.863737
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       871.875679
return_std_test                    102.254573
average_reward_test                  0.871876
round_time_test        0 days 00:00:07.727905
round_time_total       0 days 00:14:28.864820
loss_total                         511.988841
loss_critic                        744.712248
loss_actor                        -418.904833
memory_size                        511003.061 

=== epoch 6/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:40,  2.00it/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 [14:30<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            402.912742
return_std                          59.069326
average_reward                       0.402913
round_time             0 days 00:14:30.940289
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       868.908716
return_std_test                    119.236004
average_reward_test                  0.868909
round_time_test        0 days 00:00:07.624447
round_time_total       0 days 00:14:30.941369
loss_total                         513.576525
loss_critic                        746.809281
loss_actor                        -419.354544
memory_size                        512935.061 

=== epoch 6/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:23,  2.16it/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 [14:30<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            399.530019
return_std                          51.275425
average_reward                        0.39953
round_time             0 days 00:14:30.631048
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       928.920658
return_std_test                    110.538276
average_reward_test                  0.928921
round_time_test        0 days 00:00:07.732151
round_time_total       0 days 00:14:30.632142
loss_total                         508.217626
loss_critic                        740.061444
loss_actor                        -419.157692
memory_size                        514867.061 

=== epoch 6/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:37,  2.28it/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 [14:31<00:00,  2.29it/s]
episodes                                   10
episode_length                         1000.0
returns                            400.685206
return_std                          52.777216
average_reward                       0.400685
round_time             0 days 00:14:32.412120
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       993.730646
return_std_test                      98.20649
average_reward_test                  0.993731
round_time_test        0 days 00:00:07.662038
round_time_total       0 days 00:14:32.413376
loss_total                          510.81008
loss_critic                        743.352933
loss_actor                        -419.361376
memory_size                        516799.061 

=== epoch 6/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:33,  2.01it/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 [14:36<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                            414.627944
return_std                          54.928509
average_reward                       0.414628
round_time             0 days 00:14:36.736669
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       985.927328
return_std_test                     74.055075
average_reward_test                  0.985927
round_time_test        0 days 00:00:07.534703
round_time_total       0 days 00:14:36.737761
loss_total                         521.604925
loss_critic                        757.005844
loss_actor                        -419.998794
memory_size                        518731.061 

=== epoch 6/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:21,  2.17it/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 [14:34<00:00,  2.29it/s]
episodes                                   10
episode_length                         1000.0
returns                            411.860292
return_std                          58.969479
average_reward                        0.41186
round_time             0 days 00:14:34.862536
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       942.805321
return_std_test                     76.255401
average_reward_test                  0.942805
round_time_test        0 days 00:00:07.600721
round_time_total       0 days 00:14:34.863630
loss_total                         516.694736
loss_critic                        751.023362
loss_actor                        -420.619819
memory_size                        520663.061 

=== epoch 6/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:18,  2.17it/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 [14:37<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                            398.306277
return_std                          55.844105
average_reward                       0.398306
round_time             0 days 00:14:37.681930
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       902.729752
return_std_test                     75.522895
average_reward_test                   0.90273
round_time_test        0 days 00:00:07.555029
round_time_total       0 days 00:14:37.683015
loss_total                         516.667023
loss_critic                        751.048876
loss_actor                        -420.860432
memory_size                        522595.061 

=== epoch 6/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:45,  2.26it/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 [14:37<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                            394.354493
return_std                          63.842989
average_reward                       0.394354
round_time             0 days 00:14:37.792060
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       945.883247
return_std_test                     97.771428
average_reward_test                  0.945883
round_time_test        0 days 00:00:07.731057
round_time_total       0 days 00:14:37.793153
loss_total                         508.368324
loss_critic                        740.650777
loss_actor                        -420.761539
memory_size                        524527.061 

=== epoch 6/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:24,  2.03it/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 [14:38<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                            405.240739
return_std                          57.048521
average_reward                       0.405241
round_time             0 days 00:14:38.476457
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1021.190073
return_std_test                      89.84143
average_reward_test                   1.02119
round_time_test        0 days 00:00:07.608433
round_time_total       0 days 00:14:38.477549
loss_total                         503.083706
loss_critic                        734.223318
loss_actor                        -421.474791
memory_size                        526459.061 

=== epoch 6/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:17,  2.04it/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 [14:40<00:00,  2.27it/s]
episodes                                   10
episode_length                         1000.0
returns                            386.552547
return_std                          63.185417
average_reward                       0.386553
round_time             0 days 00:14:41.528198
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       877.686445
return_std_test                    121.806131
average_reward_test                  0.877686
round_time_test        0 days 00:00:07.621035
round_time_total       0 days 00:14:41.529287
loss_total                         515.384915
loss_critic                        749.740986
loss_actor                        -422.039414
memory_size                        528391.061 

=== epoch 6/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:51,  1.97it/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 [14:43<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            358.584697
return_std                          91.059695
average_reward                       0.358585
round_time             0 days 00:14:44.316303
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       886.204686
return_std_test                     78.430494
average_reward_test                  0.886205
round_time_test        0 days 00:00:07.496193
round_time_total       0 days 00:14:44.317405
loss_total                         519.760364
loss_critic                        755.262368
loss_actor                        -422.247701
memory_size                        530323.061 

=== epoch 6/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:24,  2.03it/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 [14:46<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            360.150302
return_std                          91.588836
average_reward                        0.36015
round_time             0 days 00:14:46.627717
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       946.047839
return_std_test                     95.610215
average_reward_test                  0.946048
round_time_test        0 days 00:00:07.657413
round_time_total       0 days 00:14:46.628797
loss_total                         523.529009
loss_critic                        760.020906
loss_actor                        -422.438628
memory_size                        532255.061 

=== epoch 6/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:08,  2.20it/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 [14:43<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                             365.91293
return_std                          92.338778
average_reward                       0.365913
round_time             0 days 00:14:44.337480
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       986.143006
return_std_test                     75.978403
average_reward_test                  0.986143
round_time_test        0 days 00:00:07.776365
round_time_total       0 days 00:14:44.338571
loss_total                         518.611425
loss_critic                        753.910217
loss_actor                         -422.58379
memory_size                        534187.061 

=== epoch 6/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:09,  1.94it/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 [14:45<00:00,  2.26it/s]
episodes                                   10
episode_length                         1000.0
returns                            366.998885
return_std                          95.390184
average_reward                       0.366999
round_time             0 days 00:14:45.999538
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       934.692627
return_std_test                    108.040992
average_reward_test                  0.934693
round_time_test        0 days 00:00:07.620291
round_time_total       0 days 00:14:46.000620
loss_total                         517.978286
loss_critic                        753.217535
loss_actor                        -422.978758
memory_size                        536119.061 

=== epoch 6/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:43,  2.12it/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 [14:49<00:00,  2.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            386.558055
return_std                          91.025631
average_reward                       0.386558
round_time             0 days 00:14:49.785967
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       947.734682
return_std_test                     67.450763
average_reward_test                  0.947735
round_time_test        0 days 00:00:07.704277
round_time_total       0 days 00:14:49.787069
loss_total                         527.931043
loss_critic                        765.647427
loss_actor                        -422.934547
memory_size                        538051.061 

=== epoch 6/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:14,  2.05it/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 [14:52<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            422.427107
return_std                          43.659969
average_reward                       0.422427
round_time             0 days 00:14:53.089300
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       928.121137
return_std_test                     92.648389
average_reward_test                  0.928121
round_time_test        0 days 00:00:07.611178
round_time_total       0 days 00:14:53.090390
loss_total                         526.622499
loss_critic                        764.352232
loss_actor                        -424.296479
memory_size                        539983.061 

=== epoch 6/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:39,  2.27it/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 [14:48<00:00,  2.25it/s]
episodes                                   10
episode_length                         1000.0
returns                            437.825643
return_std                           43.71119
average_reward                       0.437826
round_time             0 days 00:14:49.058723
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       971.436387
return_std_test                     50.995896
average_reward_test                  0.971436
round_time_test        0 days 00:00:07.769975
round_time_total       0 days 00:14:49.059830
loss_total                         527.886979
loss_critic                         766.41771
loss_actor                        -426.235993
memory_size                        541915.061 

=== epoch 6/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:59,  2.22it/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 [14:51<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            443.139189
return_std                          31.459416
average_reward                       0.443139
round_time             0 days 00:14:52.182173
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       969.962355
return_std_test                     73.285942
average_reward_test                  0.969962
round_time_test        0 days 00:00:07.495076
round_time_total       0 days 00:14:52.183264
loss_total                         536.751202
loss_critic                        777.525925
loss_actor                        -426.347737
memory_size                        543847.061 

=== epoch 6/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:50,  2.24it/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 [14:52<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            451.189899
return_std                          54.256118
average_reward                        0.45119
round_time             0 days 00:14:52.555269
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       937.475996
return_std_test                     76.023956
average_reward_test                  0.937476
round_time_test        0 days 00:00:07.671741
round_time_total       0 days 00:14:52.556367
loss_total                          541.28688
loss_critic                        783.356899
loss_actor                        -426.993246
memory_size                        545779.061 

=== epoch 6/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:53,  1.97it/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 [14:53<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            446.597862
return_std                          55.414623
average_reward                       0.446598
round_time             0 days 00:14:54.199718
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       991.772458
return_std_test                    102.445523
average_reward_test                  0.991772
round_time_test        0 days 00:00:07.576328
round_time_total       0 days 00:14:54.200814
loss_total                         545.377523
loss_critic                        788.511939
loss_actor                        -427.160193
memory_size                        547711.061 

=== epoch 6/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:10,  2.19it/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 [14:53<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            473.366104
return_std                          75.906559
average_reward                       0.473366
round_time             0 days 00:14:54.267894
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       979.530908
return_std_test                      94.44277
average_reward_test                  0.979531
round_time_test        0 days 00:00:07.618619
round_time_total       0 days 00:14:54.268988
loss_total                         547.412917
loss_critic                        791.616848
loss_actor                        -429.402859
memory_size                        549643.061 

=== epoch 6/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:07,  2.06it/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 [14:54<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            480.979864
return_std                          86.711478
average_reward                        0.48098
round_time             0 days 00:14:55.119185
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       952.166048
return_std_test                     73.793168
average_reward_test                  0.952166
round_time_test        0 days 00:00:07.551566
round_time_total       0 days 00:14:55.120275
loss_total                           552.9703
loss_critic                        798.821074
loss_actor                        -430.432844
memory_size                        551575.061 

=== epoch 6/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:39,  2.00it/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 [14:55<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            498.845497
return_std                          89.359884
average_reward                       0.498845
round_time             0 days 00:14:55.948325
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1001.787358
return_std_test                    106.911359
average_reward_test                  1.001787
round_time_test        0 days 00:00:07.639128
round_time_total       0 days 00:14:55.949412
loss_total                         544.751124
loss_critic                        788.331931
loss_actor                        -429.572153
memory_size                        553507.061 

=== epoch 6/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:31,  2.14it/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 [14:55<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            513.261291
return_std                          76.045187
average_reward                       0.513261
round_time             0 days 00:14:56.043942
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1017.730431
return_std_test                     91.583081
average_reward_test                   1.01773
round_time_test        0 days 00:00:07.737035
round_time_total       0 days 00:14:56.045024
loss_total                         543.216534
loss_critic                        786.243006
loss_actor                        -428.889404
memory_size                        555439.061 

=== epoch 6/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:07,  2.06it/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 [14:54<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            534.668256
return_std                          55.097179
average_reward                       0.534668
round_time             0 days 00:14:54.578917
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1031.417461
return_std_test                      74.10699
average_reward_test                  1.031417
round_time_test        0 days 00:00:07.557542
round_time_total       0 days 00:14:54.580002
loss_total                          546.12417
loss_critic                        789.913255
loss_actor                        -429.032226
memory_size                        557371.061 

=== epoch 6/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:35,  2.13it/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 [14:56<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            510.883414
return_std                          71.769037
average_reward                       0.510883
round_time             0 days 00:14:56.870351
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       992.207344
return_std_test                     93.700676
average_reward_test                  0.992207
round_time_test        0 days 00:00:07.685772
round_time_total       0 days 00:14:56.871435
loss_total                         544.199023
loss_critic                        787.521427
loss_actor                        -429.090646
memory_size                        559303.061 

=== epoch 6/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:03,  1.95it/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 [14:59<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            528.946653
return_std                          80.408016
average_reward                       0.528947
round_time             0 days 00:14:59.786543
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1036.853716
return_std_test                     65.530588
average_reward_test                  1.036854
round_time_test        0 days 00:00:07.721374
round_time_total       0 days 00:14:59.787695
loss_total                         541.453354
loss_critic                        783.994129
loss_actor                        -428.709797
memory_size                        561235.061 

=== epoch 6/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:34,  2.28it/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 [14:59<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            527.803705
return_std                          92.431075
average_reward                       0.527804
round_time             0 days 00:15:00.275580
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       993.581768
return_std_test                     73.330117
average_reward_test                  0.993582
round_time_test        0 days 00:00:07.520817
round_time_total       0 days 00:15:00.276659
loss_total                         540.436514
loss_critic                        782.684026
loss_actor                         -428.55358
memory_size                        563167.061 

=== epoch 6/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:06,  2.07it/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 [14:59<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            513.788049
return_std                           97.42829
average_reward                       0.513788
round_time             0 days 00:14:59.663252
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1000.842753
return_std_test                     85.497853
average_reward_test                  1.000843
round_time_test        0 days 00:00:07.509828
round_time_total       0 days 00:14:59.664344
loss_total                         538.868973
loss_critic                        780.814896
loss_actor                         -428.91477
memory_size                        565099.061 

=== epoch 6/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:18,  2.17it/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 [14:59<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            516.772632
return_std                         102.344124
average_reward                       0.516773
round_time             0 days 00:15:00.146598
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       994.918944
return_std_test                    108.120727
average_reward_test                  0.994919
round_time_test        0 days 00:00:07.759942
round_time_total       0 days 00:15:00.147685
loss_total                         541.516809
loss_critic                        784.445941
loss_actor                        -430.199766
memory_size                        567031.061 

=== epoch 6/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:21,  1.92it/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 [15:00<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            525.685642
return_std                          89.847165
average_reward                       0.525686
round_time             0 days 00:15:00.940246
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       988.575604
return_std_test                     139.55222
average_reward_test                  0.988576
round_time_test        0 days 00:00:07.475414
round_time_total       0 days 00:15:00.941328
loss_total                         543.702449
loss_critic                        787.497971
loss_actor                        -431.479689
memory_size                        568963.061 

=== epoch 6/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:13,  2.19it/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 [15:00<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            496.128148
return_std                          74.795454
average_reward                       0.496128
round_time             0 days 00:15:00.614790
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       959.893936
return_std_test                     75.119681
average_reward_test                  0.959894
round_time_test        0 days 00:00:07.555524
round_time_total       0 days 00:15:00.615883
loss_total                         543.733502
loss_critic                        787.477249
loss_actor                         -431.24153
memory_size                        570895.061 

=== epoch 6/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:10,  2.06it/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 [15:00<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            474.848517
return_std                          68.019509
average_reward                       0.474849
round_time             0 days 00:15:01.257549
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1026.052333
return_std_test                    113.314377
average_reward_test                  1.026052
round_time_test        0 days 00:00:07.554491
round_time_total       0 days 00:15:01.258639
loss_total                         536.396208
loss_critic                        778.485369
loss_actor                        -431.960485
memory_size                        572827.061 

=== epoch 6/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:26,  2.02it/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 [15:03<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                             461.22295
return_std                          75.551848
average_reward                       0.461223
round_time             0 days 00:15:03.529082
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1022.306213
return_std_test                    125.819559
average_reward_test                  1.022306
round_time_test        0 days 00:00:07.810532
round_time_total       0 days 00:15:03.530177
loss_total                         538.000063
loss_critic                        780.309468
loss_actor                        -431.237605
memory_size                        574759.061 

=== epoch 6/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:32,  2.14it/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 [15:04<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            448.386986
return_std                          62.227395
average_reward                       0.448387
round_time             0 days 00:15:05.277969
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       913.661864
return_std_test                     90.430342
average_reward_test                  0.913662
round_time_test        0 days 00:00:07.622105
round_time_total       0 days 00:15:05.279055
loss_total                         529.931187
loss_critic                        770.098521
loss_actor                        -430.738194
memory_size                        576691.061 

=== epoch 6/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:00<16:40,  2.00it/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 [15:05<00:00,  2.21it/s]
<GE432_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                            444.348677
return_std                          61.084179
average_reward                       0.444349
round_time             0 days 00:15:06.494810
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       966.251893
return_std_test                    103.334999
average_reward_test                  0.966252
round_time_test        0 days 00:00:07.493262
round_time_total       0 days 00:15:06.495907
loss_total                         524.509421
loss_critic                        763.251498
loss_actor                         -430.45894
memory_size                        578623.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 7/10 ===== round 1/50 ======================================
  0%|          | 4/2000 [00:01<14:30,  2.29it/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 [14:10<00:00,  2.35it/s]
episodes                                    2
episode_length                         1000.0
returns                            434.848889
return_std                          25.271441
average_reward                       0.434849
round_time             0 days 00:14:10.802811
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       992.038331
return_std_test                     99.546513
average_reward_test                  0.992038
round_time_test        0 days 00:00:07.713943
round_time_total       0 days 00:14:10.803903
loss_total                         529.541464
loss_critic                         769.94808
loss_actor                        -432.085047
memory_size                        580556.061 

=== epoch 7/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:17,  2.18it/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 [14:14<00:00,  2.34it/s]
episodes                                    4
episode_length                         1000.0
returns                            468.454684
return_std                           57.46726
average_reward                       0.468455
round_time             0 days 00:14:14.869603
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1005.298412
return_std_test                     61.441757
average_reward_test                  1.005298
round_time_test        0 days 00:00:07.641109
round_time_total       0 days 00:14:14.870694
loss_total                         537.085845
loss_critic                        779.560794
loss_actor                        -432.814001
memory_size                        582488.061 

=== epoch 7/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:37,  2.28it/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 [14:16<00:00,  2.34it/s]
episodes                                    6
episode_length                         1000.0
returns                            470.699064
return_std                          53.139234
average_reward                       0.470699
round_time             0 days 00:14:16.956726
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       991.720301
return_std_test                     93.002891
average_reward_test                   0.99172
round_time_test        0 days 00:00:07.561038
round_time_total       0 days 00:14:16.957806
loss_total                         534.886084
loss_critic                        776.763323
loss_actor                        -432.622917
memory_size                        584420.061 

=== epoch 7/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:59,  2.22it/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 [14:18<00:00,  2.33it/s]
episodes                                    8
episode_length                         1000.0
returns                            457.296897
return_std                          53.464973
average_reward                       0.457297
round_time             0 days 00:14:19.264880
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        953.92251
return_std_test                    106.233801
average_reward_test                  0.953923
round_time_test        0 days 00:00:07.479031
round_time_total       0 days 00:14:19.265956
loss_total                         531.011306
loss_critic                        772.112418
loss_actor                        -433.393188
memory_size                        586352.061 

=== epoch 7/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:22,  2.17it/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 [14:20<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                            459.938645
return_std                          54.024773
average_reward                       0.459939
round_time             0 days 00:14:21.202114
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       959.575816
return_std_test                      89.33708
average_reward_test                  0.959576
round_time_test        0 days 00:00:07.841890
round_time_total       0 days 00:14:21.203194
loss_total                         542.163637
loss_critic                        786.260638
loss_actor                        -434.224417
memory_size                        588284.061 

=== epoch 7/10 ===== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:45,  2.11it/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 [14:18<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            459.583678
return_std                          56.168241
average_reward                       0.459584
round_time             0 days 00:14:19.361741
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1024.308339
return_std_test                     75.975173
average_reward_test                  1.024308
round_time_test        0 days 00:00:07.597005
round_time_total       0 days 00:14:19.362829
loss_total                         534.441925
loss_critic                        776.870505
loss_actor                        -435.272447
memory_size                        590216.061 

=== epoch 7/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:25,  2.16it/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 [14:19<00:00,  2.33it/s]
episodes                                   10
episode_length                         1000.0
returns                            460.119352
return_std                          49.666598
average_reward                       0.460119
round_time             0 days 00:14:20.404131
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1048.428351
return_std_test                     60.738021
average_reward_test                  1.048428
round_time_test        0 days 00:00:07.724862
round_time_total       0 days 00:14:20.405202
loss_total                         542.963915
loss_critic                        787.462463
loss_actor                        -435.030324
memory_size                        592148.061 

=== epoch 7/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:59,  2.08it/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 [14:21<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                            458.687029
return_std                          59.213807
average_reward                       0.458687
round_time             0 days 00:14:21.720416
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1012.169932
return_std_test                     78.821834
average_reward_test                   1.01217
round_time_test        0 days 00:00:07.629933
round_time_total       0 days 00:14:21.721501
loss_total                         549.923932
loss_critic                        796.159656
loss_actor                        -435.019009
memory_size                        594080.061 

=== epoch 7/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:10,  2.06it/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 [14:22<00:00,  2.32it/s]
episodes                                   10
episode_length                         1000.0
returns                            465.088627
return_std                          63.181542
average_reward                       0.465089
round_time             0 days 00:14:23.321218
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       964.099929
return_std_test                     76.884972
average_reward_test                    0.9641
round_time_test        0 days 00:00:07.698714
round_time_total       0 days 00:14:23.322309
loss_total                         553.041739
loss_critic                        800.321891
loss_actor                        -436.078918
memory_size                        596012.061 

=== epoch 7/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:17,  2.33it/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 [14:25<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            474.911613
return_std                          83.560921
average_reward                       0.474912
round_time             0 days 00:14:25.715753
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       995.655772
return_std_test                     73.857796
average_reward_test                  0.995656
round_time_test        0 days 00:00:07.616325
round_time_total       0 days 00:14:25.716843
loss_total                         552.924351
loss_critic                        800.465249
loss_actor                        -437.239288
memory_size                        597944.061 

=== epoch 7/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:43,  2.12it/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 [14:27<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            496.435325
return_std                          82.062733
average_reward                       0.496435
round_time             0 days 00:14:28.256785
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1000.043522
return_std_test                    114.232582
average_reward_test                  1.000044
round_time_test        0 days 00:00:07.597168
round_time_total       0 days 00:14:28.257871
loss_total                         552.178995
loss_critic                        799.644258
loss_actor                        -437.682109
memory_size                        599876.061 

=== epoch 7/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:54,  2.23it/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 [14:27<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            492.797008
return_std                          95.558769
average_reward                       0.492797
round_time             0 days 00:14:28.429159
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1045.776701
return_std_test                     84.673771
average_reward_test                  1.045777
round_time_test        0 days 00:00:07.533439
round_time_total       0 days 00:14:28.430244
loss_total                         563.376697
loss_critic                        813.514244
loss_actor                        -437.173538
memory_size                        601808.061 

=== epoch 7/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:40,  2.27it/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 [14:26<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            511.861915
return_std                          94.685156
average_reward                       0.511862
round_time             0 days 00:14:27.332757
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1001.466149
return_std_test                    100.628129
average_reward_test                  1.001466
round_time_test        0 days 00:00:07.669540
round_time_total       0 days 00:14:27.333932
loss_total                         553.173118
loss_critic                        800.689819
loss_actor                        -436.893732
memory_size                        603740.061 

=== epoch 7/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:41,  2.27it/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 [14:26<00:00,  2.31it/s]
episodes                                   10
episode_length                         1000.0
returns                            510.275522
return_std                           90.32998
average_reward                       0.510276
round_time             0 days 00:14:27.237691
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1037.076184
return_std_test                    109.555448
average_reward_test                  1.037076
round_time_test        0 days 00:00:07.689604
round_time_total       0 days 00:14:27.238786
loss_total                         548.975777
loss_critic                        795.477799
loss_actor                        -437.032363
memory_size                        605672.061 

=== epoch 7/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:28,  2.30it/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 [14:28<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            500.519017
return_std                          74.885972
average_reward                       0.500519
round_time             0 days 00:14:28.703599
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       971.573776
return_std_test                     88.335842
average_reward_test                  0.971574
round_time_test        0 days 00:00:07.579071
round_time_total       0 days 00:14:28.704685
loss_total                         543.577175
loss_critic                         788.85942
loss_actor                        -437.551855
memory_size                        607604.061 

=== epoch 7/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:36,  2.28it/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 [14:31<00:00,  2.29it/s]
episodes                                   10
episode_length                         1000.0
returns                            481.846396
return_std                          76.438325
average_reward                       0.481846
round_time             0 days 00:14:32.024053
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       985.991898
return_std_test                    123.375989
average_reward_test                  0.985992
round_time_test        0 days 00:00:07.637139
round_time_total       0 days 00:14:32.025134
loss_total                          550.41715
loss_critic                        797.412853
loss_actor                        -437.565714
memory_size                        609536.061 

=== epoch 7/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:07,  2.06it/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 [14:30<00:00,  2.30it/s]
episodes                                   10
episode_length                         1000.0
returns                            481.658077
return_std                          68.604228
average_reward                       0.481658
round_time             0 days 00:14:31.062721
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       976.445736
return_std_test                     55.741356
average_reward_test                  0.976446
round_time_test        0 days 00:00:07.524995
round_time_total       0 days 00:14:31.063814
loss_total                         551.848951
loss_critic                        799.148973
loss_actor                        -437.351194
memory_size                        611468.061 

=== epoch 7/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:36,  2.28it/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 [14:31<00:00,  2.29it/s]
episodes                                   10
episode_length                         1000.0
returns                            463.546847
return_std                          49.412157
average_reward                       0.463547
round_time             0 days 00:14:32.374620
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1023.966577
return_std_test                      52.93583
average_reward_test                  1.023967
round_time_test        0 days 00:00:07.539029
round_time_total       0 days 00:14:32.375716
loss_total                         547.712651
loss_critic                        794.143057
loss_actor                        -438.009023
memory_size                        613400.061 

=== epoch 7/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:18,  2.17it/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 [14:36<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                            454.203413
return_std                           65.60046
average_reward                       0.454203
round_time             0 days 00:14:37.338305
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       950.490992
return_std_test                     50.450987
average_reward_test                  0.950491
round_time_test        0 days 00:00:07.581777
round_time_total       0 days 00:14:37.339393
loss_total                         562.856971
loss_critic                        813.471666
loss_actor                         -439.60186
memory_size                        615332.061 

=== epoch 7/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:00,  2.08it/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 [14:35<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                              475.2489
return_std                          80.159747
average_reward                       0.475249
round_time             0 days 00:14:36.063995
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1005.704739
return_std_test                      67.17221
average_reward_test                  1.005705
round_time_test        0 days 00:00:07.583151
round_time_total       0 days 00:14:36.065090
loss_total                         551.352359
loss_critic                        799.218393
loss_actor                         -440.11183
memory_size                        617264.061 

=== epoch 7/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:52,  1.97it/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 [14:36<00:00,  2.28it/s]
episodes                                   10
episode_length                         1000.0
returns                            474.559301
return_std                          86.588523
average_reward                       0.474559
round_time             0 days 00:14:37.345482
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        909.67365
return_std_test                    127.855599
average_reward_test                  0.909674
round_time_test        0 days 00:00:07.505814
round_time_total       0 days 00:14:37.346565
loss_total                         549.334156
loss_critic                        796.780421
loss_actor                        -440.450953
memory_size                        619196.061 

=== epoch 7/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:09,  2.06it/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 [13:23<00:00,  2.49it/s]
episodes                                   10
episode_length                         1000.0
returns                            468.498168
return_std                          83.145836
average_reward                       0.468498
round_time             0 days 00:13:24.306554
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       944.348944
return_std_test                     46.140719
average_reward_test                  0.944349
round_time_test        0 days 00:00:07.614532
round_time_total       0 days 00:13:24.307636
loss_total                         551.631919
loss_critic                        799.576275
loss_actor                        -440.145555
memory_size                        621128.061 

=== epoch 7/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:10,  2.35it/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 [13:03<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            472.888286
return_std                          83.151557
average_reward                       0.472888
round_time             0 days 00:13:04.021441
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       980.252907
return_std_test                    105.548622
average_reward_test                  0.980253
round_time_test        0 days 00:00:07.799408
round_time_total       0 days 00:13:04.022518
loss_total                         556.375042
loss_critic                        805.829521
loss_actor                        -441.442926
memory_size                        623060.061 

=== epoch 7/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:27,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:01<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            491.922207
return_std                          66.368156
average_reward                       0.491922
round_time             0 days 00:13:02.474912
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       954.557789
return_std_test                     71.773667
average_reward_test                  0.954558
round_time_test        0 days 00:00:07.575557
round_time_total       0 days 00:13:02.476000
loss_total                         575.014819
loss_critic                        829.486659
loss_actor                        -442.872601
memory_size                        624992.061 

=== epoch 7/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:35,  2.45it/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 [13:02<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            465.638594
return_std                          59.032497
average_reward                       0.465639
round_time             0 days 00:13:02.511877
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1033.315525
return_std_test                    108.158789
average_reward_test                  1.033316
round_time_test        0 days 00:00:07.559949
round_time_total       0 days 00:13:02.512974
loss_total                          571.02732
loss_critic                        824.707053
loss_actor                        -443.691662
memory_size                        626924.061 

=== epoch 7/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:43,  2.43it/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 [13:03<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            472.431835
return_std                          63.623793
average_reward                       0.472432
round_time             0 days 00:13:03.914971
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       953.137105
return_std_test                     85.003711
average_reward_test                  0.953137
round_time_test        0 days 00:00:07.692422
round_time_total       0 days 00:13:03.916043
loss_total                         567.688136
loss_critic                        820.675521
loss_actor                        -444.261453
memory_size                        628856.061 

=== epoch 7/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:59,  2.38it/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 [12:56<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            489.289522
return_std                          62.715615
average_reward                        0.48929
round_time             0 days 00:12:57.431067
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       988.205027
return_std_test                     115.21458
average_reward_test                  0.988205
round_time_test        0 days 00:00:07.554145
round_time_total       0 days 00:12:57.432148
loss_total                         557.411859
loss_critic                        807.914672
loss_actor                        -444.599447
memory_size                        630788.061 

=== epoch 7/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:24,  2.48it/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 [12:58<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            470.180124
return_std                          85.539473
average_reward                        0.47018
round_time             0 days 00:12:59.432281
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       931.483414
return_std_test                     72.768494
average_reward_test                  0.931483
round_time_test        0 days 00:00:07.486121
round_time_total       0 days 00:12:59.433353
loss_total                           556.9675
loss_critic                        807.135775
loss_actor                        -443.705651
memory_size                        632720.061 

=== epoch 7/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:28,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:08<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            459.771661
return_std                          85.265532
average_reward                       0.459772
round_time             0 days 00:13:09.466353
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1052.127829
return_std_test                     49.186213
average_reward_test                  1.052128
round_time_test        0 days 00:00:07.448818
round_time_total       0 days 00:13:09.467438
loss_total                          561.15573
loss_critic                        812.328232
loss_actor                        -443.534332
memory_size                        634652.061 

=== epoch 7/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:25,  2.48it/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 [13:07<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            477.310622
return_std                           85.68259
average_reward                       0.477311
round_time             0 days 00:13:07.638584
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1005.898017
return_std_test                    114.950111
average_reward_test                  1.005898
round_time_test        0 days 00:00:07.596752
round_time_total       0 days 00:13:07.639663
loss_total                         555.621076
loss_critic                        805.469165
loss_actor                        -443.771335
memory_size                        636584.061 

=== epoch 7/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:33,  2.46it/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 [13:05<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            488.231886
return_std                          86.096314
average_reward                       0.488232
round_time             0 days 00:13:06.006716
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       936.084315
return_std_test                     99.641485
average_reward_test                  0.936084
round_time_test        0 days 00:00:07.569246
round_time_total       0 days 00:13:06.007783
loss_total                          556.86365
loss_critic                        807.145261
loss_actor                        -444.262843
memory_size                        638516.061 

=== epoch 7/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:28,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:07<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            497.946615
return_std                          96.197948
average_reward                       0.497947
round_time             0 days 00:13:08.021175
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        955.37529
return_std_test                    107.241328
average_reward_test                  0.955375
round_time_test        0 days 00:00:07.607920
round_time_total       0 days 00:13:08.022250
loss_total                         559.624453
loss_critic                        810.725535
loss_actor                        -444.779926
memory_size                        640448.061 

=== epoch 7/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:49,  2.41it/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 [13:08<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                             515.03424
return_std                           70.92429
average_reward                       0.515034
round_time             0 days 00:13:09.342254
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       973.345441
return_std_test                     82.142829
average_reward_test                  0.973345
round_time_test        0 days 00:00:07.612141
round_time_total       0 days 00:13:09.343334
loss_total                         554.912646
loss_critic                        804.967629
loss_actor                        -445.307344
memory_size                        642380.061 

=== epoch 7/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:07,  2.36it/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 [13:08<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            498.391959
return_std                          95.767206
average_reward                       0.498392
round_time             0 days 00:13:09.373545
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1024.193988
return_std_test                     95.986813
average_reward_test                  1.024194
round_time_test        0 days 00:00:07.400249
round_time_total       0 days 00:13:09.374618
loss_total                         563.945667
loss_critic                        816.355981
loss_actor                        -445.695645
memory_size                        644312.061 

=== epoch 7/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:38,  2.44it/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 [15:01<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            480.424771
return_std                         109.746331
average_reward                       0.480425
round_time             0 days 00:15:02.168004
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1040.092101
return_std_test                     65.182617
average_reward_test                  1.040092
round_time_test        0 days 00:00:07.674558
round_time_total       0 days 00:15:02.169087
loss_total                         569.404235
loss_critic                        823.231104
loss_actor                        -445.903295
memory_size                        646244.061 

=== epoch 7/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:37,  2.44it/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 [13:14<00:00,  2.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            472.198727
return_std                          99.150373
average_reward                       0.472199
round_time             0 days 00:13:15.249675
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       980.778426
return_std_test                     81.061693
average_reward_test                  0.980778
round_time_test        0 days 00:00:07.456268
round_time_total       0 days 00:13:15.250755
loss_total                         568.832747
loss_critic                         822.73507
loss_actor                        -446.776595
memory_size                        648176.061 

=== epoch 7/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:38,  2.44it/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 [14:55<00:00,  2.23it/s]
episodes                                   10
episode_length                         1000.0
returns                            431.645135
return_std                         101.589073
average_reward                       0.431645
round_time             0 days 00:14:56.222045
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        923.20817
return_std_test                    125.231181
average_reward_test                  0.923208
round_time_test        0 days 00:00:07.536038
round_time_total       0 days 00:14:56.223138
loss_total                         557.874044
loss_critic                        809.171818
loss_actor                        -447.317103
memory_size                        650108.061 

=== epoch 7/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:14,  2.34it/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 [17:55<00:00,  1.86it/s]
episodes                                   10
episode_length                         1000.0
returns                            435.940493
return_std                         103.513565
average_reward                        0.43594
round_time             0 days 00:17:55.824976
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        938.57778
return_std_test                     77.718155
average_reward_test                  0.938578
round_time_test        0 days 00:00:07.481527
round_time_total       0 days 00:17:55.826182
loss_total                          561.96515
loss_critic                         814.19997
loss_actor                         -446.97418
memory_size                        652040.061 

=== epoch 7/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:06,  1.84it/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 [13:16<00:00,  2.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            458.107354
return_std                          95.367847
average_reward                       0.458107
round_time             0 days 00:13:16.643115
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       978.119722
return_std_test                    117.820618
average_reward_test                   0.97812
round_time_test        0 days 00:00:07.620706
round_time_total       0 days 00:13:16.644214
loss_total                         562.609932
loss_critic                        814.897504
loss_actor                        -446.540412
memory_size                        653972.061 

=== epoch 7/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:12,  2.34it/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 [13:08<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            468.298478
return_std                          81.318481
average_reward                       0.468298
round_time             0 days 00:13:09.189876
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       999.917002
return_std_test                    100.564686
average_reward_test                  0.999917
round_time_test        0 days 00:00:07.672426
round_time_total       0 days 00:13:09.190955
loss_total                         564.723382
loss_critic                        817.701153
loss_actor                        -447.187755
memory_size                        655904.061 

=== epoch 7/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:36,  2.44it/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 [13:13<00:00,  2.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            472.428589
return_std                          84.553333
average_reward                       0.472429
round_time             0 days 00:13:13.520433
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       986.827584
return_std_test                     78.312465
average_reward_test                  0.986828
round_time_test        0 days 00:00:07.688827
round_time_total       0 days 00:13:13.521518
loss_total                         568.702317
loss_critic                          823.0951
loss_actor                         -448.86887
memory_size                        657836.061 

=== epoch 7/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:40,  2.43it/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 [13:11<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            500.588608
return_std                          46.577583
average_reward                       0.500589
round_time             0 days 00:13:11.632105
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       994.412613
return_std_test                     90.569264
average_reward_test                  0.994413
round_time_test        0 days 00:00:07.352238
round_time_total       0 days 00:13:11.633179
loss_total                         566.809862
loss_critic                         820.69872
loss_actor                        -448.745627
memory_size                        659768.061 

=== epoch 7/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:41,  2.43it/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 [13:09<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            494.477049
return_std                          47.444083
average_reward                       0.494477
round_time             0 days 00:13:10.298121
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       973.330147
return_std_test                    113.124422
average_reward_test                   0.97333
round_time_test        0 days 00:00:07.516531
round_time_total       0 days 00:13:10.299256
loss_total                         578.603325
loss_critic                        835.609538
loss_actor                        -449.421586
memory_size                        661700.061 

=== epoch 7/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:37,  2.44it/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 [13:48<00:00,  2.42it/s]
episodes                                   10
episode_length                         1000.0
returns                            501.174484
return_std                          55.450456
average_reward                       0.501174
round_time             0 days 00:13:48.543538
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       999.157274
return_std_test                     83.782679
average_reward_test                  0.999157
round_time_test        0 days 00:00:07.519852
round_time_total       0 days 00:13:48.544626
loss_total                         563.460872
loss_critic                        816.796119
loss_actor                        -449.880165
memory_size                        663632.061 

=== epoch 7/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:41,  2.43it/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 [20:47<00:00,  1.60it/s]
episodes                                   10
episode_length                         1000.0
returns                            476.377994
return_std                          83.996875
average_reward                       0.476378
round_time             0 days 00:20:48.165507
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       986.662805
return_std_test                    103.799034
average_reward_test                  0.986663
round_time_test        0 days 00:00:07.648675
round_time_total       0 days 00:20:48.166808
loss_total                         562.592141
loss_critic                        815.876929
loss_actor                        -450.547064
memory_size                        665564.061 

=== epoch 7/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<21:23,  1.56it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [21:26<00:00,  1.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            477.560527
return_std                          82.811281
average_reward                       0.477561
round_time             0 days 00:21:27.038620
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       948.298952
return_std_test                     94.193527
average_reward_test                  0.948299
round_time_test        0 days 00:00:08.359106
round_time_total       0 days 00:21:27.040297
loss_total                         573.484897
loss_critic                         829.37547
loss_actor                        -450.077447
memory_size                        667496.061 

=== epoch 7/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<21:47,  1.53it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [21:31<00:00,  1.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            471.915407
return_std                          79.988063
average_reward                       0.471915
round_time             0 days 00:21:32.118649
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1016.533024
return_std_test                     91.039953
average_reward_test                  1.016533
round_time_test        0 days 00:00:08.434617
round_time_total       0 days 00:21:32.119832
loss_total                         577.233955
loss_critic                        834.070438
loss_actor                        -450.112032
memory_size                        669428.061 

=== epoch 7/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<21:21,  1.56it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [21:31<00:00,  1.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            468.982844
return_std                          88.367303
average_reward                       0.468983
round_time             0 days 00:21:32.364861
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1020.282265
return_std_test                    103.639254
average_reward_test                  1.020282
round_time_test        0 days 00:00:08.345636
round_time_total       0 days 00:21:32.366067
loss_total                         576.326014
loss_critic                         832.76402
loss_actor                        -449.426062
memory_size                        671360.061 

=== epoch 7/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<21:12,  1.57it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [21:14<00:00,  1.57it/s]
episodes                                   10
episode_length                         1000.0
returns                              459.4616
return_std                          83.442181
average_reward                       0.459462
round_time             0 days 00:21:15.441965
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       971.813315
return_std_test                     123.64644
average_reward_test                  0.971813
round_time_test        0 days 00:00:08.308303
round_time_total       0 days 00:21:15.443278
loss_total                         580.416495
loss_critic                        838.095389
loss_actor                        -450.299129
memory_size                        673292.061 

=== epoch 7/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<21:29,  1.55it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [21:11<00:00,  1.57it/s]
<GE432_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                            476.514463
return_std                          64.089694
average_reward                       0.476514
round_time             0 days 00:21:11.872858
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1034.369514
return_std_test                      94.54318
average_reward_test                   1.03437
round_time_test        0 days 00:00:08.402780
round_time_total       0 days 00:21:11.874028
loss_total                         574.735916
loss_critic                        831.184495
loss_actor                        -451.058455
memory_size                        675224.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 8/10 ===== round 1/50 ======================================
  0%|          | 3/2000 [00:01<20:08,  1.65it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [19:24<00:00,  1.72it/s]
episodes                                    2
episode_length                         1000.0
returns                            391.147539
return_std                          89.728421
average_reward                       0.391148
round_time             0 days 00:19:24.701474
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       986.203849
return_std_test                    104.497675
average_reward_test                  0.986204
round_time_test        0 days 00:00:08.426239
round_time_total       0 days 00:19:24.702809
loss_total                         575.605303
loss_critic                        832.328395
loss_actor                        -451.287116
memory_size                        677157.061 

=== epoch 8/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<19:23,  1.72it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [19:31<00:00,  1.71it/s]
episodes                                    4
episode_length                         1000.0
returns                            422.722014
return_std                          72.456034
average_reward                       0.422722
round_time             0 days 00:19:31.726737
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1007.082082
return_std_test                    134.724594
average_reward_test                  1.007082
round_time_test        0 days 00:00:08.373224
round_time_total       0 days 00:19:31.727931
loss_total                         576.447268
loss_critic                        833.369389
loss_actor                        -451.241268
memory_size                        679089.061 

=== epoch 8/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<19:51,  1.68it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [14:14<00:00,  2.34it/s]
episodes                                    6
episode_length                         1000.0
returns                            467.964561
return_std                           87.18469
average_reward                       0.467965
round_time             0 days 00:14:15.422288
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1009.221905
return_std_test                    103.189799
average_reward_test                  1.009222
round_time_test        0 days 00:00:08.192232
round_time_total       0 days 00:14:15.423368
loss_total                         575.604142
loss_critic                        832.468135
loss_actor                        -451.851882
memory_size                        681021.061 

=== epoch 8/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:02,  2.55it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:42<00:00,  2.62it/s]
episodes                                    8
episode_length                         1000.0
returns                            473.927621
return_std                          80.025737
average_reward                       0.473928
round_time             0 days 00:12:42.513293
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1025.527623
return_std_test                     58.511859
average_reward_test                  1.025528
round_time_test        0 days 00:00:07.395980
round_time_total       0 days 00:12:42.514358
loss_total                         576.654597
loss_critic                        833.712541
loss_actor                        -451.577234
memory_size                        682953.061 

=== epoch 8/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:00,  2.56it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:45<00:00,  2.61it/s]
episodes                                   10
episode_length                         1000.0
returns                            471.637586
return_std                          75.280642
average_reward                       0.471638
round_time             0 days 00:12:45.912128
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1076.530041
return_std_test                     56.644108
average_reward_test                   1.07653
round_time_test        0 days 00:00:07.574185
round_time_total       0 days 00:12:45.913201
loss_total                         578.938738
loss_critic                        836.765425
loss_actor                        -452.368068
memory_size                        684885.061 

=== epoch 8/10 ===== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:29,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:45<00:00,  2.61it/s]
episodes                                   10
episode_length                         1000.0
returns                             495.53478
return_std                          54.362683
average_reward                       0.495535
round_time             0 days 00:12:46.313338
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        936.96101
return_std_test                     85.335656
average_reward_test                  0.936961
round_time_test        0 days 00:00:07.642193
round_time_total       0 days 00:12:46.314399
loss_total                         578.460075
loss_critic                        836.284646
loss_actor                        -452.838259
memory_size                        686817.061 

=== epoch 8/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:06,  2.54it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:46<00:00,  2.61it/s]
episodes                                   10
episode_length                         1000.0
returns                            504.958483
return_std                          61.570817
average_reward                       0.504958
round_time             0 days 00:12:47.112132
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       970.781473
return_std_test                    103.416468
average_reward_test                  0.970781
round_time_test        0 days 00:00:07.512210
round_time_total       0 days 00:12:47.113203
loss_total                         581.131475
loss_critic                        839.660997
loss_actor                        -452.986667
memory_size                        688749.061 

=== epoch 8/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:32,  2.46it/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 [12:47<00:00,  2.61it/s]
episodes                                   10
episode_length                         1000.0
returns                            486.650847
return_std                         100.308533
average_reward                       0.486651
round_time             0 days 00:12:48.056019
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       994.610156
return_std_test                      97.64084
average_reward_test                   0.99461
round_time_test        0 days 00:00:07.423028
round_time_total       0 days 00:12:48.057089
loss_total                         568.776664
loss_critic                        824.160379
loss_actor                        -452.758245
memory_size                        690681.061 

=== epoch 8/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:19,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:50<00:00,  2.60it/s]
episodes                                   10
episode_length                         1000.0
returns                             485.47246
return_std                          99.545943
average_reward                       0.485472
round_time             0 days 00:12:50.481116
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       978.830815
return_std_test                    218.191221
average_reward_test                  0.978831
round_time_test        0 days 00:00:07.504876
round_time_total       0 days 00:12:50.482184
loss_total                         576.061682
loss_critic                        833.389078
loss_actor                        -453.247951
memory_size                        692613.061 

=== epoch 8/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:47,  2.41it/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 [12:51<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            474.317456
return_std                         102.101107
average_reward                       0.474317
round_time             0 days 00:12:52.149445
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       988.859637
return_std_test                     76.262066
average_reward_test                   0.98886
round_time_test        0 days 00:00:07.442084
round_time_total       0 days 00:12:52.150516
loss_total                         571.272258
loss_critic                        827.389176
loss_actor                        -453.195473
memory_size                        694545.061 

=== epoch 8/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<13:28,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:02<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            465.759027
return_std                          98.661229
average_reward                       0.465759
round_time             0 days 00:13:02.834894
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1049.000245
return_std_test                    108.259922
average_reward_test                     1.049
round_time_test        0 days 00:00:07.513430
round_time_total       0 days 00:13:02.835972
loss_total                         568.668202
loss_critic                        824.242865
loss_actor                        -453.630502
memory_size                        696477.061 

=== epoch 8/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:28,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:59<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                             458.28617
return_std                          89.915637
average_reward                       0.458286
round_time             0 days 00:12:59.834135
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1032.318136
return_std_test                     72.811891
average_reward_test                  1.032318
round_time_test        0 days 00:00:07.379657
round_time_total       0 days 00:12:59.835223
loss_total                         576.499893
loss_critic                        834.014808
loss_actor                        -453.559828
memory_size                        698409.061 

=== epoch 8/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<13:12,  2.52it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:58<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            449.909534
return_std                          43.984104
average_reward                        0.44991
round_time             0 days 00:12:59.444384
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       923.819646
return_std_test                    122.905265
average_reward_test                   0.92382
round_time_test        0 days 00:00:07.522790
round_time_total       0 days 00:12:59.445466
loss_total                         577.137875
loss_critic                        834.933958
loss_actor                        -454.046513
memory_size                        700341.061 

=== epoch 8/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:21,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:58<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            441.640301
return_std                          39.265892
average_reward                        0.44164
round_time             0 days 00:12:58.813129
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1009.362991
return_std_test                    139.885198
average_reward_test                  1.009363
round_time_test        0 days 00:00:07.736158
round_time_total       0 days 00:12:58.814198
loss_total                         576.252999
loss_critic                        833.770649
loss_actor                        -453.817652
memory_size                        702273.061 

=== epoch 8/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:24,  2.48it/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 [12:52<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                              440.7021
return_std                           61.70197
average_reward                       0.440702
round_time             0 days 00:12:52.737550
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       954.045506
return_std_test                    145.725197
average_reward_test                  0.954046
round_time_test        0 days 00:00:07.558492
round_time_total       0 days 00:12:52.738623
loss_total                         568.786751
loss_critic                        824.685438
loss_actor                        -454.808055
memory_size                        704205.061 

=== epoch 8/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:46,  2.42it/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 [12:56<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                            438.574181
return_std                          60.380395
average_reward                       0.438574
round_time             0 days 00:12:56.817428
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1028.306236
return_std_test                     68.112389
average_reward_test                  1.028306
round_time_test        0 days 00:00:07.498966
round_time_total       0 days 00:12:56.818498
loss_total                         579.709045
loss_critic                        838.601466
loss_actor                        -455.860694
memory_size                        706137.061 

=== epoch 8/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:18,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:55<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                            449.856887
return_std                          72.764155
average_reward                       0.449857
round_time             0 days 00:12:56.349600
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       974.775125
return_std_test                     109.89214
average_reward_test                  0.974775
round_time_test        0 days 00:00:07.383990
round_time_total       0 days 00:12:56.350674
loss_total                         582.621026
loss_critic                        842.379306
loss_actor                        -456.412151
memory_size                        708069.061 

=== epoch 8/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:58,  2.38it/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 [12:56<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                            474.440216
return_std                         100.246896
average_reward                        0.47444
round_time             0 days 00:12:56.772646
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       918.906689
return_std_test                    104.094098
average_reward_test                  0.918907
round_time_test        0 days 00:00:07.523240
round_time_total       0 days 00:12:56.773719
loss_total                          590.23589
loss_critic                        852.005418
loss_actor                        -456.842276
memory_size                        710001.061 

=== epoch 8/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:50,  2.40it/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 [12:49<00:00,  2.60it/s]
episodes                                   10
episode_length                         1000.0
returns                            479.979029
return_std                          98.326119
average_reward                       0.479979
round_time             0 days 00:12:50.030414
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       902.954111
return_std_test                      71.03408
average_reward_test                  0.902954
round_time_test        0 days 00:00:07.472747
round_time_total       0 days 00:12:50.031484
loss_total                         585.379238
loss_critic                        845.923909
loss_actor                        -456.799496
memory_size                        711933.061 

=== epoch 8/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:54,  2.39it/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 [12:51<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            488.606206
return_std                          87.183594
average_reward                       0.488606
round_time             0 days 00:12:52.190633
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1015.777815
return_std_test                     78.154211
average_reward_test                  1.015778
round_time_test        0 days 00:00:07.571794
round_time_total       0 days 00:12:52.191706
loss_total                         586.557328
loss_critic                        847.605434
loss_actor                        -457.635153
memory_size                        713865.061 

=== epoch 8/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:57,  2.39it/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 [12:50<00:00,  2.60it/s]
episodes                                   10
episode_length                         1000.0
returns                            518.224767
return_std                          96.629404
average_reward                       0.518225
round_time             0 days 00:12:51.034930
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       973.341222
return_std_test                    110.763351
average_reward_test                  0.973341
round_time_test        0 days 00:00:07.573726
round_time_total       0 days 00:12:51.036018
loss_total                         582.103235
loss_critic                        842.026934
loss_actor                        -457.591612
memory_size                        715797.061 

=== epoch 8/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:14,  2.51it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:53<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            509.591262
return_std                         117.004005
average_reward                       0.509591
round_time             0 days 00:12:53.628291
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1079.086325
return_std_test                     82.003159
average_reward_test                  1.079086
round_time_test        0 days 00:00:07.565797
round_time_total       0 days 00:12:53.629374
loss_total                         588.460874
loss_critic                        849.997798
loss_actor                        -457.686878
memory_size                        717729.061 

=== epoch 8/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:57,  2.39it/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 [12:53<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            505.875947
return_std                         101.403214
average_reward                       0.505876
round_time             0 days 00:12:53.836657
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        970.37188
return_std_test                    106.647352
average_reward_test                  0.970372
round_time_test        0 days 00:00:07.479286
round_time_total       0 days 00:12:53.837730
loss_total                         584.619056
loss_critic                        845.254587
loss_actor                        -457.923122
memory_size                        719661.061 

=== epoch 8/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:13,  2.34it/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 [12:53<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                             521.55003
return_std                          102.13943
average_reward                        0.52155
round_time             0 days 00:12:54.516695
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       997.903209
return_std_test                    100.145736
average_reward_test                  0.997903
round_time_test        0 days 00:00:07.649842
round_time_total       0 days 00:12:54.517767
loss_total                         581.292447
loss_critic                        841.121244
loss_actor                        -458.022796
memory_size                        721593.061 

=== epoch 8/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:27,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:58<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                             531.22501
return_std                          90.698971
average_reward                       0.531225
round_time             0 days 00:12:58.757134
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       952.643261
return_std_test                    133.406928
average_reward_test                  0.952643
round_time_test        0 days 00:00:07.563913
round_time_total       0 days 00:12:58.758217
loss_total                         583.075368
loss_critic                        843.395697
loss_actor                        -458.205999
memory_size                        723525.061 

=== epoch 8/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:43,  2.43it/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 [12:59<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                             483.58962
return_std                         103.758833
average_reward                        0.48359
round_time             0 days 00:13:00.467879
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1029.949103
return_std_test                     86.047658
average_reward_test                  1.029949
round_time_test        0 days 00:00:07.607588
round_time_total       0 days 00:13:00.468987
loss_total                         582.145656
loss_critic                        842.272845
loss_actor                        -458.363159
memory_size                        725457.061 

=== epoch 8/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:12,  2.34it/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 [12:56<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                            500.224795
return_std                          89.629496
average_reward                       0.500225
round_time             0 days 00:12:56.640178
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       983.421508
return_std_test                     76.578456
average_reward_test                  0.983422
round_time_test        0 days 00:00:07.564037
round_time_total       0 days 00:12:56.641247
loss_total                         593.301579
loss_critic                        856.248148
loss_actor                         -458.48476
memory_size                        727389.061 

=== epoch 8/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:31,  2.46it/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 [13:00<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            505.270962
return_std                          87.786791
average_reward                       0.505271
round_time             0 days 00:13:00.506302
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1028.873858
return_std_test                     78.798253
average_reward_test                  1.028874
round_time_test        0 days 00:00:07.425637
round_time_total       0 days 00:13:00.507381
loss_total                         587.559385
loss_critic                        848.975965
loss_actor                        -458.106986
memory_size                        729321.061 

=== epoch 8/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:15,  2.33it/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 [13:01<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                             497.11625
return_std                          83.614198
average_reward                       0.497116
round_time             0 days 00:13:01.530757
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       972.538185
return_std_test                     94.946538
average_reward_test                  0.972538
round_time_test        0 days 00:00:07.379917
round_time_total       0 days 00:13:01.531842
loss_total                         591.995071
loss_critic                        854.578385
loss_actor                        -458.338241
memory_size                        731253.061 

=== epoch 8/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:28,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:00<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            503.723498
return_std                          83.767953
average_reward                       0.503723
round_time             0 days 00:13:01.109224
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1003.00769
return_std_test                      86.40096
average_reward_test                  1.003008
round_time_test        0 days 00:00:07.441016
round_time_total       0 days 00:13:01.110298
loss_total                         604.226667
loss_critic                        870.260125
loss_actor                        -459.907219
memory_size                        733185.061 

=== epoch 8/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:23,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:06<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            538.830189
return_std                          42.717891
average_reward                        0.53883
round_time             0 days 00:13:06.885272
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1011.790673
return_std_test                     73.404994
average_reward_test                  1.011791
round_time_test        0 days 00:00:07.451395
round_time_total       0 days 00:13:06.886367
loss_total                         602.074565
loss_critic                        867.684098
loss_actor                        -460.363628
memory_size                        735117.061 

=== epoch 8/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:30,  2.46it/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 [13:05<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            530.735521
return_std                           50.79464
average_reward                       0.530736
round_time             0 days 00:13:06.151524
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1002.380577
return_std_test                    118.399212
average_reward_test                  1.002381
round_time_test        0 days 00:00:07.430421
round_time_total       0 days 00:13:06.152592
loss_total                         598.509622
loss_critic                        862.813232
loss_actor                        -458.704872
memory_size                        737049.061 

=== epoch 8/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:18,  2.33it/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 [13:05<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            510.559975
return_std                          56.009578
average_reward                        0.51056
round_time             0 days 00:13:06.147104
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1034.057111
return_std_test                    114.014467
average_reward_test                  1.034057
round_time_test        0 days 00:00:07.463110
round_time_total       0 days 00:13:06.148183
loss_total                         590.232433
loss_critic                        852.348427
loss_actor                        -458.231598
memory_size                        738981.061 

=== epoch 8/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:26,  2.48it/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 [13:08<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            499.021346
return_std                          62.432391
average_reward                       0.499021
round_time             0 days 00:13:09.296203
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1039.058737
return_std_test                     70.808572
average_reward_test                  1.039059
round_time_test        0 days 00:00:07.463308
round_time_total       0 days 00:13:09.297288
loss_total                         590.704951
loss_critic                        852.974066
loss_actor                        -458.371567
memory_size                        740913.061 

=== epoch 8/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:44,  2.42it/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 [13:07<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            488.674191
return_std                          62.861614
average_reward                       0.488674
round_time             0 days 00:13:08.033638
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       967.854788
return_std_test                     108.78908
average_reward_test                  0.967855
round_time_test        0 days 00:00:07.486094
round_time_total       0 days 00:13:08.034716
loss_total                         592.625253
loss_critic                        855.323345
loss_actor                        -458.167171
memory_size                        742845.061 

=== epoch 8/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:39,  2.44it/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 [13:06<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            492.890872
return_std                          72.575227
average_reward                       0.492891
round_time             0 days 00:13:06.856142
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       992.194489
return_std_test                     82.888461
average_reward_test                  0.992194
round_time_test        0 days 00:00:07.527798
round_time_total       0 days 00:13:06.857208
loss_total                         596.976068
loss_critic                        861.026034
loss_actor                        -459.223859
memory_size                        744777.061 

=== epoch 8/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:34,  2.45it/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 [13:10<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            491.406054
return_std                          58.105197
average_reward                       0.491406
round_time             0 days 00:13:11.251074
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1009.414075
return_std_test                     76.699155
average_reward_test                  1.009414
round_time_test        0 days 00:00:07.501181
round_time_total       0 days 00:13:11.252157
loss_total                         592.374272
loss_critic                        855.211574
loss_actor                        -458.974992
memory_size                        746709.061 

=== epoch 8/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:35,  2.45it/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 [13:05<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            498.044569
return_std                          68.595623
average_reward                       0.498045
round_time             0 days 00:13:06.127918
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1009.586169
return_std_test                    106.453118
average_reward_test                  1.009586
round_time_test        0 days 00:00:07.494179
round_time_total       0 days 00:13:06.128984
loss_total                         593.023731
loss_critic                        856.133062
loss_actor                        -459.413647
memory_size                        748641.061 

=== epoch 8/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:11,  2.35it/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 [13:06<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            511.967028
return_std                          64.278196
average_reward                       0.511967
round_time             0 days 00:13:06.840092
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       956.960936
return_std_test                    123.126176
average_reward_test                  0.956961
round_time_test        0 days 00:00:07.535161
round_time_total       0 days 00:13:06.841168
loss_total                         586.406273
loss_critic                        848.010281
loss_actor                        -460.009812
memory_size                        750573.061 

=== epoch 8/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:33,  2.45it/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 [13:19<00:00,  2.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            528.948584
return_std                           66.53532
average_reward                       0.528949
round_time             0 days 00:13:19.546993
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       966.300142
return_std_test                      65.70341
average_reward_test                    0.9663
round_time_test        0 days 00:00:07.468967
round_time_total       0 days 00:13:19.548092
loss_total                         591.530328
loss_critic                        854.622011
loss_actor                         -460.83646
memory_size                        752505.061 

=== epoch 8/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:44,  2.42it/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 [13:08<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            549.980419
return_std                          82.211431
average_reward                        0.54998
round_time             0 days 00:13:09.204017
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       944.672151
return_std_test                    101.664965
average_reward_test                  0.944672
round_time_test        0 days 00:00:07.496885
round_time_total       0 days 00:13:09.205083
loss_total                         600.164539
loss_critic                        865.786052
loss_actor                        -462.321571
memory_size                        754437.061 

=== epoch 8/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:58,  2.38it/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 [13:11<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            566.362883
return_std                          84.654179
average_reward                       0.566363
round_time             0 days 00:13:11.803597
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1023.480908
return_std_test                    118.770267
average_reward_test                  1.023481
round_time_test        0 days 00:00:07.519771
round_time_total       0 days 00:13:11.804670
loss_total                         603.152649
loss_critic                        869.398936
loss_actor                         -461.83255
memory_size                        756369.061 

=== epoch 8/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:11,  2.19it/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 [13:13<00:00,  2.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            563.101688
return_std                          88.270562
average_reward                       0.563102
round_time             0 days 00:13:13.500049
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       994.408969
return_std_test                     81.806827
average_reward_test                  0.994409
round_time_test        0 days 00:00:07.528969
round_time_total       0 days 00:13:13.501130
loss_total                         608.726575
loss_critic                        876.394183
loss_actor                        -461.943906
memory_size                        758301.061 

=== epoch 8/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:44,  2.42it/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 [13:09<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            561.705409
return_std                          91.363516
average_reward                       0.561705
round_time             0 days 00:13:10.142768
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1052.290532
return_std_test                     62.327081
average_reward_test                  1.052291
round_time_test        0 days 00:00:07.465403
round_time_total       0 days 00:13:10.143832
loss_total                         609.234459
loss_critic                        877.031998
loss_actor                        -461.955756
memory_size                        760233.061 

=== epoch 8/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:40,  2.43it/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 [13:12<00:00,  2.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            567.015169
return_std                          88.603596
average_reward                       0.567015
round_time             0 days 00:13:12.706927
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1072.21414
return_std_test                    115.082174
average_reward_test                  1.072214
round_time_test        0 days 00:00:07.414586
round_time_total       0 days 00:13:12.708003
loss_total                         592.115549
loss_critic                        855.599644
loss_actor                        -461.820888
memory_size                        762165.061 

=== epoch 8/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:37,  2.44it/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 [13:11<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            535.438941
return_std                          74.978782
average_reward                       0.535439
round_time             0 days 00:13:11.493302
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       942.798397
return_std_test                       76.8068
average_reward_test                  0.942798
round_time_test        0 days 00:00:07.418722
round_time_total       0 days 00:13:11.494373
loss_total                          604.34084
loss_critic                        871.048041
loss_actor                        -462.488023
memory_size                        764097.061 

=== epoch 8/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:35,  2.45it/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 [13:12<00:00,  2.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            533.303324
return_std                          75.995966
average_reward                       0.533303
round_time             0 days 00:13:13.413843
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1010.814942
return_std_test                     72.373529
average_reward_test                  1.010815
round_time_test        0 days 00:00:07.421912
round_time_total       0 days 00:13:13.414924
loss_total                         599.523445
loss_critic                        865.199141
loss_actor                        -463.179398
memory_size                        766029.061 

=== epoch 8/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:48,  2.41it/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 [15:07<00:00,  2.20it/s]
episodes                                   10
episode_length                         1000.0
returns                            529.639866
return_std                          67.654153
average_reward                        0.52964
round_time             0 days 00:15:08.055837
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       958.351612
return_std_test                    109.618055
average_reward_test                  0.958352
round_time_test        0 days 00:00:07.411587
round_time_total       0 days 00:15:08.057126
loss_total                         606.926405
loss_critic                        874.410298
loss_actor                        -463.009223
memory_size                        767961.061 

=== epoch 8/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:45,  1.77it/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 [16:14<00:00,  2.05it/s]
episodes                                   10
episode_length                         1000.0
returns                            513.525905
return_std                          74.825733
average_reward                       0.513526
round_time             0 days 00:16:14.822395
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       978.641182
return_std_test                    124.465889
average_reward_test                  0.978641
round_time_test        0 days 00:00:07.993744
round_time_total       0 days 00:16:14.823574
loss_total                          608.99783
loss_critic                        877.149333
loss_actor                        -463.608243
memory_size                        769893.061 

=== epoch 8/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<18:05,  1.84it/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 [16:06<00:00,  2.07it/s]
<GE432_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                            517.663395
return_std                          79.132397
average_reward                       0.517663
round_time             0 days 00:16:06.799827
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1074.551441
return_std_test                      97.95658
average_reward_test                  1.074551
round_time_test        0 days 00:00:07.826787
round_time_total       0 days 00:16:06.801030
loss_total                         606.230518
loss_critic                        873.919135
loss_actor                        -464.524008
memory_size                        771825.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 9/10 ===== round 1/50 ======================================
  0%|          | 4/2000 [00:01<14:42,  2.26it/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 [14:54<00:00,  2.24it/s]
episodes                                    2
episode_length                         1000.0
returns                            574.490173
return_std                           3.744967
average_reward                        0.57449
round_time             0 days 00:14:54.379126
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1038.864588
return_std_test                     82.209571
average_reward_test                  1.038865
round_time_test        0 days 00:00:07.788223
round_time_total       0 days 00:14:54.380219
loss_total                         602.505145
loss_critic                        869.472798
loss_actor                         -465.36552
memory_size                        773758.061 

=== epoch 9/10 ===== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:01,  2.56it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:30<00:00,  2.66it/s]
episodes                                    4
episode_length                         1000.0
returns                            550.253161
return_std                          39.459167
average_reward                       0.550253
round_time             0 days 00:12:31.103066
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1040.865868
return_std_test                      94.88983
average_reward_test                  1.040866
round_time_test        0 days 00:00:07.528848
round_time_total       0 days 00:12:31.104138
loss_total                          604.23982
loss_critic                        871.486505
loss_actor                        -464.746979
memory_size                        775690.061 

=== epoch 9/10 ===== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<12:59,  2.56it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:32<00:00,  2.66it/s]
episodes                                    6
episode_length                         1000.0
returns                            512.054115
return_std                          89.309127
average_reward                       0.512054
round_time             0 days 00:12:32.845597
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1009.077778
return_std_test                       79.3445
average_reward_test                  1.009078
round_time_test        0 days 00:00:07.448330
round_time_total       0 days 00:12:32.846670
loss_total                         601.610833
loss_critic                        868.002243
loss_actor                        -463.954859
memory_size                        777622.061 

=== epoch 9/10 ===== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<12:58,  2.57it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:35<00:00,  2.65it/s]
episodes                                    8
episode_length                         1000.0
returns                             498.45145
return_std                          84.022407
average_reward                       0.498451
round_time             0 days 00:12:35.792986
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       997.126967
return_std_test                     85.753912
average_reward_test                  0.997127
round_time_test        0 days 00:00:07.483419
round_time_total       0 days 00:12:35.794062
loss_total                         607.203522
loss_critic                        875.275462
loss_actor                        -465.084298
memory_size                        779554.061 

=== epoch 9/10 ===== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:08,  2.53it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:35<00:00,  2.65it/s]
episodes                                   10
episode_length                         1000.0
returns                            503.877126
return_std                          76.290612
average_reward                       0.503877
round_time             0 days 00:12:35.489716
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       974.178976
return_std_test                     46.859159
average_reward_test                  0.974179
round_time_test        0 days 00:00:07.454469
round_time_total       0 days 00:12:35.490802
loss_total                         605.088253
loss_critic                        872.549365
loss_actor                        -464.756255
memory_size                        781486.061 

=== epoch 9/10 ===== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:22,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:37<00:00,  2.64it/s]
episodes                                   10
episode_length                         1000.0
returns                             497.12464
return_std                          75.305879
average_reward                       0.497125
round_time             0 days 00:12:37.849516
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1006.866074
return_std_test                    121.908388
average_reward_test                  1.006866
round_time_test        0 days 00:00:07.317553
round_time_total       0 days 00:12:37.850575
loss_total                         604.999715
loss_critic                        872.529815
loss_actor                        -465.120743
memory_size                        783418.061 

=== epoch 9/10 ===== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:14,  2.51it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:37<00:00,  2.64it/s]
episodes                                   10
episode_length                         1000.0
returns                            496.480312
return_std                          73.237093
average_reward                        0.49648
round_time             0 days 00:12:38.179041
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1000.284024
return_std_test                     62.171425
average_reward_test                  1.000284
round_time_test        0 days 00:00:07.479881
round_time_total       0 days 00:12:38.180105
loss_total                         617.141371
loss_critic                        887.967774
loss_actor                        -466.164296
memory_size                        785350.061 

=== epoch 9/10 ===== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:05,  2.54it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:39<00:00,  2.63it/s]
episodes                                   10
episode_length                         1000.0
returns                            494.733648
return_std                          59.268078
average_reward                       0.494734
round_time             0 days 00:12:40.121867
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       987.025234
return_std_test                     84.914124
average_reward_test                  0.987025
round_time_test        0 days 00:00:07.520464
round_time_total       0 days 00:12:40.122929
loss_total                         612.625878
loss_critic                        882.195897
loss_actor                        -465.654256
memory_size                        787282.061 

=== epoch 9/10 ===== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:21,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:37<00:00,  2.64it/s]
episodes                                   10
episode_length                         1000.0
returns                            504.845953
return_std                           53.89764
average_reward                       0.504846
round_time             0 days 00:12:38.022791
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       988.419162
return_std_test                     64.209413
average_reward_test                  0.988419
round_time_test        0 days 00:00:07.615625
round_time_total       0 days 00:12:38.023863
loss_total                          619.68394
loss_critic                        891.175601
loss_actor                         -466.28276
memory_size                        789214.061 

=== epoch 9/10 ===== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:28,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:38<00:00,  2.64it/s]
episodes                                   10
episode_length                         1000.0
returns                            508.625269
return_std                          59.960453
average_reward                       0.508625
round_time             0 days 00:12:38.863547
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1068.505697
return_std_test                    163.981388
average_reward_test                  1.068506
round_time_test        0 days 00:00:07.386722
round_time_total       0 days 00:12:38.864632
loss_total                         618.621309
loss_critic                        889.742051
loss_actor                        -465.861718
memory_size                        791146.061 

=== epoch 9/10 ===== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:35,  2.45it/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 [12:40<00:00,  2.63it/s]
episodes                                   10
episode_length                         1000.0
returns                            516.316279
return_std                          64.747535
average_reward                       0.516316
round_time             0 days 00:12:41.384057
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1028.944046
return_std_test                      91.53198
average_reward_test                  1.028944
round_time_test        0 days 00:00:07.482689
round_time_total       0 days 00:12:41.385180
loss_total                          609.91209
loss_critic                        878.559971
loss_actor                        -464.679494
memory_size                        793078.061 

=== epoch 9/10 ===== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:39,  2.44it/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 [12:41<00:00,  2.63it/s]
episodes                                   10
episode_length                         1000.0
returns                            520.415601
return_std                            72.8301
average_reward                       0.520416
round_time             0 days 00:12:41.756657
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       964.378989
return_std_test                     47.598132
average_reward_test                  0.964379
round_time_test        0 days 00:00:07.478661
round_time_total       0 days 00:12:41.757736
loss_total                         601.414415
loss_critic                        867.902544
loss_actor                        -464.538154
memory_size                        795010.061 

=== epoch 9/10 ===== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:08,  2.53it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:42<00:00,  2.62it/s]
episodes                                   10
episode_length                         1000.0
returns                            551.268776
return_std                          65.522459
average_reward                       0.551269
round_time             0 days 00:12:42.530660
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1003.587752
return_std_test                     104.43284
average_reward_test                  1.003588
round_time_test        0 days 00:00:07.491072
round_time_total       0 days 00:12:42.531733
loss_total                         605.907021
loss_critic                        873.437201
loss_actor                        -464.213756
memory_size                        796942.061 

=== epoch 9/10 ===== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:13,  2.52it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:42<00:00,  2.62it/s]
episodes                                   10
episode_length                         1000.0
returns                             568.65481
return_std                          64.241987
average_reward                       0.568655
round_time             0 days 00:12:43.358621
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1005.073103
return_std_test                    130.257175
average_reward_test                  1.005073
round_time_test        0 days 00:00:07.506055
round_time_total       0 days 00:12:43.359709
loss_total                         613.628961
loss_critic                        883.433626
loss_actor                        -465.589757
memory_size                        798874.061 

=== epoch 9/10 ===== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:44,  2.42it/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 [12:45<00:00,  2.61it/s]
episodes                                   10
episode_length                         1000.0
returns                            560.183844
return_std                          77.610517
average_reward                       0.560184
round_time             0 days 00:12:46.274777
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1002.10397
return_std_test                    131.804379
average_reward_test                  1.002104
round_time_test        0 days 00:00:07.428122
round_time_total       0 days 00:12:46.275876
loss_total                          600.84423
loss_critic                        867.547718
loss_actor                        -465.969779
memory_size                        800806.061 

=== epoch 9/10 ===== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:39,  2.44it/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 [12:44<00:00,  2.61it/s]
episodes                                   10
episode_length                         1000.0
returns                            548.879269
return_std                          77.239371
average_reward                       0.548879
round_time             0 days 00:12:45.339308
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1055.544305
return_std_test                    104.653129
average_reward_test                  1.055544
round_time_test        0 days 00:00:07.390533
round_time_total       0 days 00:12:45.340394
loss_total                         609.744496
loss_critic                         878.86204
loss_actor                        -466.725737
memory_size                        802738.061 

=== epoch 9/10 ===== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:20,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:48<00:00,  2.60it/s]
episodes                                   10
episode_length                         1000.0
returns                            565.099696
return_std                          75.783558
average_reward                         0.5651
round_time             0 days 00:12:49.315697
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1053.438334
return_std_test                    100.028739
average_reward_test                  1.053438
round_time_test        0 days 00:00:07.549937
round_time_total       0 days 00:12:49.316765
loss_total                         612.506181
loss_critic                         882.34958
loss_actor                         -466.86747
memory_size                        804670.061 

=== epoch 9/10 ===== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:16,  2.51it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:47<00:00,  2.60it/s]
episodes                                   10
episode_length                         1000.0
returns                            572.734469
return_std                          75.812543
average_reward                       0.572734
round_time             0 days 00:12:48.347891
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1017.002784
return_std_test                    135.138019
average_reward_test                  1.017003
round_time_test        0 days 00:00:07.547350
round_time_total       0 days 00:12:48.348960
loss_total                         603.829391
loss_critic                        871.590836
loss_actor                        -467.216442
memory_size                        806602.061 

=== epoch 9/10 ===== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:16,  2.51it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:49<00:00,  2.60it/s]
episodes                                   10
episode_length                         1000.0
returns                            565.285592
return_std                          75.907701
average_reward                       0.565286
round_time             0 days 00:12:50.206890
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1041.164704
return_std_test                     89.355804
average_reward_test                  1.041165
round_time_test        0 days 00:00:07.429459
round_time_total       0 days 00:12:50.207984
loss_total                         602.132095
loss_critic                        869.464185
loss_actor                        -467.196321
memory_size                        808534.061 

=== epoch 9/10 ===== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<13:25,  2.48it/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 [12:48<00:00,  2.60it/s]
episodes                                   10
episode_length                         1000.0
returns                            576.394178
return_std                          61.721311
average_reward                       0.576394
round_time             0 days 00:12:49.102422
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       972.835333
return_std_test                     87.425295
average_reward_test                  0.972835
round_time_test        0 days 00:00:07.460748
round_time_total       0 days 00:12:49.103502
loss_total                         609.077136
loss_critic                        878.284359
loss_actor                        -467.751807
memory_size                        810466.061 

=== epoch 9/10 ===== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:18,  2.33it/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 [12:53<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            566.998187
return_std                          71.711854
average_reward                       0.566998
round_time             0 days 00:12:54.011069
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1058.825475
return_std_test                     64.849995
average_reward_test                  1.058825
round_time_test        0 days 00:00:07.636122
round_time_total       0 days 00:12:54.012137
loss_total                         614.256757
loss_critic                        884.675875
loss_actor                        -467.419772
memory_size                        812398.061 

=== epoch 9/10 ===== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:19,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:52<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            559.428619
return_std                          72.117356
average_reward                       0.559429
round_time             0 days 00:12:52.475916
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1002.228702
return_std_test                    123.299104
average_reward_test                  1.002229
round_time_test        0 days 00:00:07.420493
round_time_total       0 days 00:12:52.476977
loss_total                         617.503279
loss_critic                        888.957864
loss_actor                        -468.315124
memory_size                        814330.061 

=== epoch 9/10 ===== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:21,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:55<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                            542.126783
return_std                          60.937952
average_reward                       0.542127
round_time             0 days 00:12:55.907977
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1046.833911
return_std_test                    100.823144
average_reward_test                  1.046834
round_time_test        0 days 00:00:07.533481
round_time_total       0 days 00:12:55.909043
loss_total                         615.878511
loss_critic                        887.066271
loss_actor                         -468.87259
memory_size                        816262.061 

=== epoch 9/10 ===== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:19,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:54<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                            540.066839
return_std                          65.455701
average_reward                       0.540067
round_time             0 days 00:12:55.396251
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       968.890167
return_std_test                    146.511988
average_reward_test                   0.96889
round_time_test        0 days 00:00:07.567308
round_time_total       0 days 00:12:55.397326
loss_total                         619.463226
loss_critic                        891.638871
loss_actor                        -469.239408
memory_size                        818194.061 

=== epoch 9/10 ===== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:19,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:57<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            542.566067
return_std                           61.67028
average_reward                       0.542566
round_time             0 days 00:12:57.871436
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1052.233633
return_std_test                     85.772452
average_reward_test                  1.052234
round_time_test        0 days 00:00:07.595043
round_time_total       0 days 00:12:57.872516
loss_total                         613.675201
loss_critic                        884.482398
loss_actor                        -469.553645
memory_size                        820126.061 

=== epoch 9/10 ===== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:28,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:59<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            539.608591
return_std                          62.543583
average_reward                       0.539609
round_time             0 days 00:12:59.575202
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1053.007967
return_std_test                    119.817958
average_reward_test                  1.053008
round_time_test        0 days 00:00:07.460883
round_time_total       0 days 00:12:59.576273
loss_total                         608.076716
loss_critic                        877.449175
loss_actor                        -469.413177
memory_size                        822058.061 

=== epoch 9/10 ===== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:25,  2.48it/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 [12:59<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            538.957089
return_std                          60.118202
average_reward                       0.538957
round_time             0 days 00:13:00.137181
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1003.55034
return_std_test                    103.007218
average_reward_test                   1.00355
round_time_test        0 days 00:00:07.565145
round_time_total       0 days 00:13:00.138262
loss_total                         607.189091
loss_critic                        876.212817
loss_actor                        -468.905869
memory_size                        823990.061 

=== epoch 9/10 ===== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:22,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:01<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            547.618954
return_std                          62.353834
average_reward                       0.547619
round_time             0 days 00:13:01.462174
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1028.483032
return_std_test                    133.411125
average_reward_test                  1.028483
round_time_test        0 days 00:00:07.504065
round_time_total       0 days 00:13:01.463244
loss_total                         615.466437
loss_critic                        886.631505
loss_actor                        -469.193892
memory_size                        825922.061 

=== epoch 9/10 ===== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:14,  2.34it/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 [13:03<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            532.375047
return_std                          61.876986
average_reward                       0.532375
round_time             0 days 00:13:04.250876
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1034.184767
return_std_test                      98.07625
average_reward_test                  1.034185
round_time_test        0 days 00:00:07.391321
round_time_total       0 days 00:13:04.251958
loss_total                         616.415492
loss_critic                        887.942219
loss_actor                        -469.691475
memory_size                        827854.061 

=== epoch 9/10 ===== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:25,  2.48it/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 [13:01<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            521.439411
return_std                          58.237542
average_reward                       0.521439
round_time             0 days 00:13:02.038605
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1035.290196
return_std_test                     97.827758
average_reward_test                   1.03529
round_time_test        0 days 00:00:07.384897
round_time_total       0 days 00:13:02.039685
loss_total                         614.628104
loss_critic                        885.946145
loss_actor                        -470.644123
memory_size                        829786.061 

=== epoch 9/10 ===== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:32,  2.46it/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 [13:04<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                             547.03844
return_std                          56.138116
average_reward                       0.547038
round_time             0 days 00:13:05.299994
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       986.494374
return_std_test                    114.382687
average_reward_test                  0.986494
round_time_test        0 days 00:00:07.524009
round_time_total       0 days 00:13:05.301110
loss_total                         619.587779
loss_critic                        892.458956
loss_actor                        -471.896983
memory_size                        831718.061 

=== epoch 9/10 ===== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:38,  2.44it/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 [13:10<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                             562.81094
return_std                          70.867099
average_reward                       0.562811
round_time             0 days 00:13:10.870638
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1022.836431
return_std_test                    126.342833
average_reward_test                  1.022836
round_time_test        0 days 00:00:07.442300
round_time_total       0 days 00:13:10.871755
loss_total                         608.875118
loss_critic                        878.892061
loss_actor                        -471.192708
memory_size                        833650.061 

=== epoch 9/10 ===== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:07,  2.36it/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 [13:11<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            570.978556
return_std                          74.647287
average_reward                       0.570979
round_time             0 days 00:13:11.789872
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       902.302658
return_std_test                    383.438923
average_reward_test                  0.902303
round_time_test        0 days 00:00:07.626054
round_time_total       0 days 00:13:11.790970
loss_total                         609.707487
loss_critic                        879.838334
loss_actor                        -470.815955
memory_size                        835582.061 

=== epoch 9/10 ===== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:35,  2.45it/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 [13:10<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            596.051491
return_std                          55.342548
average_reward                       0.596051
round_time             0 days 00:13:11.261936
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1032.277147
return_std_test                     84.124247
average_reward_test                  1.032277
round_time_test        0 days 00:00:07.436779
round_time_total       0 days 00:13:11.263017
loss_total                         612.320341
loss_critic                        883.330932
loss_actor                        -471.722073
memory_size                        837514.061 

=== epoch 9/10 ===== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:48,  2.41it/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 [13:04<00:00,  2.55it/s]
episodes                                   10
episode_length                         1000.0
returns                            601.936616
return_std                          48.211135
average_reward                       0.601937
round_time             0 days 00:13:05.253784
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       993.428842
return_std_test                     100.62302
average_reward_test                  0.993429
round_time_test        0 days 00:00:07.518913
round_time_total       0 days 00:13:05.254858
loss_total                         610.412487
loss_critic                        881.157064
loss_actor                        -472.565879
memory_size                        839446.061 

=== epoch 9/10 ===== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:35,  2.45it/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 [13:09<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            607.303258
return_std                          63.533538
average_reward                       0.607303
round_time             0 days 00:13:10.440073
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1074.309123
return_std_test                     98.545664
average_reward_test                  1.074309
round_time_test        0 days 00:00:07.550343
round_time_total       0 days 00:13:10.441157
loss_total                         619.662608
loss_critic                        892.842264
loss_actor                         -473.05608
memory_size                        841378.061 

=== epoch 9/10 ===== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:29,  2.47it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:06<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            591.436299
return_std                          58.834549
average_reward                       0.591436
round_time             0 days 00:13:06.727488
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1094.669967
return_std_test                     66.193147
average_reward_test                   1.09467
round_time_test        0 days 00:00:07.554142
round_time_total       0 days 00:13:06.728599
loss_total                         619.944034
loss_critic                        893.302455
loss_actor                        -473.489704
memory_size                        843310.061 

=== epoch 9/10 ===== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:36,  2.44it/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 [13:09<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            599.346344
return_std                          69.264809
average_reward                       0.599346
round_time             0 days 00:13:10.042626
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       973.250154
return_std_test                     63.145478
average_reward_test                   0.97325
round_time_test        0 days 00:00:07.505149
round_time_total       0 days 00:13:10.043708
loss_total                         623.581969
loss_critic                        898.058652
loss_actor                        -474.324819
memory_size                        845242.061 

=== epoch 9/10 ===== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:39,  2.44it/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 [13:13<00:00,  2.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            595.887844
return_std                          87.619647
average_reward                       0.595888
round_time             0 days 00:13:13.953155
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1068.535051
return_std_test                     91.945911
average_reward_test                  1.068535
round_time_test        0 days 00:00:07.492347
round_time_total       0 days 00:13:13.954264
loss_total                         622.690655
loss_critic                        897.240761
loss_actor                         -475.50983
memory_size                        847174.061 

=== epoch 9/10 ===== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:33,  2.45it/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 [13:08<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            604.939642
return_std                          97.401213
average_reward                        0.60494
round_time             0 days 00:13:09.346861
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1008.683594
return_std_test                    101.296678
average_reward_test                  1.008684
round_time_test        0 days 00:00:07.677340
round_time_total       0 days 00:13:09.347938
loss_total                         627.341169
loss_critic                        903.006495
loss_actor                        -475.320185
memory_size                        849106.061 

=== epoch 9/10 ===== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:46,  2.42it/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 [13:10<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            575.075105
return_std                         102.354296
average_reward                       0.575075
round_time             0 days 00:13:10.545471
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1033.580109
return_std_test                    101.619964
average_reward_test                   1.03358
round_time_test        0 days 00:00:07.437711
round_time_total       0 days 00:13:10.546546
loss_total                         626.105225
loss_critic                        901.507011
loss_actor                        -475.501974
memory_size                        851038.061 

=== epoch 9/10 ===== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:37,  2.44it/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 [13:13<00:00,  2.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            559.803308
return_std                         110.475646
average_reward                       0.559803
round_time             0 days 00:13:13.879550
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1003.285205
return_std_test                     74.625986
average_reward_test                  1.003285
round_time_test        0 days 00:00:07.462154
round_time_total       0 days 00:13:13.880632
loss_total                         626.180138
loss_critic                        901.538127
loss_actor                        -475.251879
memory_size                        852970.061 

=== epoch 9/10 ===== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:54,  2.39it/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 [13:17<00:00,  2.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            520.703552
return_std                          99.389169
average_reward                       0.520704
round_time             0 days 00:13:18.257125
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       963.329181
return_std_test                    115.705907
average_reward_test                  0.963329
round_time_test        0 days 00:00:07.576953
round_time_total       0 days 00:13:18.258221
loss_total                         630.925359
loss_critic                        907.464125
loss_actor                        -475.229766
memory_size                        854902.061 

=== epoch 9/10 ===== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:40,  2.43it/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 [13:15<00:00,  2.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            522.711164
return_std                          90.398493
average_reward                       0.522711
round_time             0 days 00:13:16.123888
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1033.634527
return_std_test                    112.590044
average_reward_test                  1.033635
round_time_test        0 days 00:00:07.376418
round_time_total       0 days 00:13:16.124972
loss_total                         619.541221
loss_critic                        893.029456
loss_actor                         -474.41178
memory_size                        856834.061 

=== epoch 9/10 ===== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:08,  2.35it/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 [13:14<00:00,  2.52it/s]
episodes                                   10
episode_length                         1000.0
returns                            517.717244
return_std                           74.44383
average_reward                       0.517717
round_time             0 days 00:13:15.120858
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1010.818012
return_std_test                    136.818657
average_reward_test                  1.010818
round_time_test        0 days 00:00:07.725905
round_time_total       0 days 00:13:15.121931
loss_total                         622.246574
loss_critic                        896.502806
loss_actor                        -474.778414
memory_size                        858766.061 

=== epoch 9/10 ===== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:11,  2.35it/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 [13:16<00:00,  2.51it/s]
episodes                                   10
episode_length                         1000.0
returns                            543.777533
return_std                          82.493362
average_reward                       0.543778
round_time             0 days 00:13:17.208508
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1050.789189
return_std_test                     97.873079
average_reward_test                  1.050789
round_time_test        0 days 00:00:07.566009
round_time_total       0 days 00:13:17.209578
loss_total                         622.471303
loss_critic                        896.931308
loss_actor                        -475.368777
memory_size                        860698.061 

=== epoch 9/10 ===== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:54,  2.39it/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 [13:21<00:00,  2.49it/s]
episodes                                   10
episode_length                         1000.0
returns                            527.308304
return_std                          87.932817
average_reward                       0.527308
round_time             0 days 00:13:22.115792
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1031.195052
return_std_test                    143.400282
average_reward_test                  1.031195
round_time_test        0 days 00:00:07.603499
round_time_total       0 days 00:13:22.116867
loss_total                         634.425275
loss_critic                        912.101668
loss_actor                        -476.280362
memory_size                        862630.061 

=== epoch 9/10 ===== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:38,  2.44it/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 [13:20<00:00,  2.50it/s]
episodes                                   10
episode_length                         1000.0
returns                            542.482154
return_std                          81.331477
average_reward                       0.542482
round_time             0 days 00:13:21.300495
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       980.689645
return_std_test                    310.837871
average_reward_test                   0.98069
round_time_test        0 days 00:00:07.529200
round_time_total       0 days 00:13:21.301569
loss_total                         629.034466
loss_critic                        905.351956
loss_actor                         -476.23555
memory_size                        864562.061 

=== epoch 9/10 ===== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:42,  2.43it/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 [15:24<00:00,  2.16it/s]
episodes                                   10
episode_length                         1000.0
returns                             538.85376
return_std                          81.803542
average_reward                       0.538854
round_time             0 days 00:15:25.029527
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1033.277602
return_std_test                    116.315715
average_reward_test                  1.033278
round_time_test        0 days 00:00:07.436297
round_time_total       0 days 00:15:25.030835
loss_total                          629.58905
loss_critic                        906.043779
loss_actor                        -476.229917
memory_size                        866494.061 

=== epoch 9/10 ===== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:46,  1.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [16:18<00:00,  2.04it/s]
<GE432_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                            537.975696
return_std                          88.267622
average_reward                       0.537976
round_time             0 days 00:16:18.998990
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1035.059378
return_std_test                    100.715291
average_reward_test                  1.035059
round_time_test        0 days 00:00:07.795991
round_time_total       0 days 00:16:19.000238
loss_total                         634.230538
loss_critic                        911.829128
loss_actor                        -476.163878
memory_size                        868426.061 


<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
=== epoch 10/10 ==== round 1/50 ======================================
  0%|          | 4/2000 [00:01<15:05,  2.20it/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 [14:47<00:00,  2.25it/s]
episodes                                    2
episode_length                         1000.0
returns                            555.320078
return_std                         119.258278
average_reward                        0.55532
round_time             0 days 00:14:47.182128
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1083.52719
return_std_test                     86.413391
average_reward_test                  1.083527
round_time_test        0 days 00:00:07.861423
round_time_total       0 days 00:14:47.183346
loss_total                         643.453359
loss_critic                        923.626624
loss_actor                        -477.239762
memory_size                        870359.061 

=== epoch 10/10 ==== round 2/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:43,  2.12it/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 [13:26<00:00,  2.48it/s]
episodes                                    4
episode_length                         1000.0
returns                            511.671092
return_std                          125.68249
average_reward                       0.511671
round_time             0 days 00:13:27.451720
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1040.839275
return_std_test                    119.881486
average_reward_test                  1.040839
round_time_test        0 days 00:00:07.768783
round_time_total       0 days 00:13:27.452791
loss_total                         641.069002
loss_critic                        920.414045
loss_actor                        -476.311232
memory_size                        872291.061 

=== epoch 10/10 ==== round 3/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:10,  2.53it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:32<00:00,  2.66it/s]
episodes                                    6
episode_length                         1000.0
returns                            566.592241
return_std                         128.859545
average_reward                       0.566592
round_time             0 days 00:12:33.117486
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1026.916012
return_std_test                    108.865171
average_reward_test                  1.026916
round_time_test        0 days 00:00:07.554956
round_time_total       0 days 00:12:33.118559
loss_total                         634.069796
loss_critic                        911.541317
loss_actor                        -475.816343
memory_size                        874223.061 

=== epoch 10/10 ==== round 4/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<13:15,  2.51it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:34<00:00,  2.65it/s]
episodes                                    8
episode_length                         1000.0
returns                            592.396568
return_std                         121.840997
average_reward                       0.592397
round_time             0 days 00:12:35.002261
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1062.86643
return_std_test                    119.734908
average_reward_test                  1.062866
round_time_test        0 days 00:00:07.558470
round_time_total       0 days 00:12:35.003332
loss_total                         624.751749
loss_critic                        899.791324
loss_actor                         -475.40661
memory_size                        876155.061 

=== epoch 10/10 ==== round 5/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:00,  2.56it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:43<00:00,  2.62it/s]
episodes                                   10
episode_length                         1000.0
returns                            594.589944
return_std                         111.667214
average_reward                        0.59459
round_time             0 days 00:12:43.956764
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1039.767718
return_std_test                    111.400553
average_reward_test                  1.039768
round_time_test        0 days 00:00:07.551455
round_time_total       0 days 00:12:43.958009
loss_total                         631.286028
loss_critic                        908.087032
loss_actor                        -475.918049
memory_size                        878087.061 

=== epoch 10/10 ==== round 6/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:08,  2.20it/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 [15:13<00:00,  2.19it/s]
episodes                                   10
episode_length                         1000.0
returns                            607.904112
return_std                          99.354583
average_reward                       0.607904
round_time             0 days 00:15:14.418045
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1114.039836
return_std_test                    125.534034
average_reward_test                   1.11404
round_time_test        0 days 00:00:07.843788
round_time_total       0 days 00:15:14.419236
loss_total                         635.997432
loss_critic                        913.816323
loss_actor                        -475.278187
memory_size                        880019.061 

=== epoch 10/10 ==== round 7/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:31,  2.01it/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 [15:24<00:00,  2.16it/s]
episodes                                   10
episode_length                         1000.0
returns                             627.72255
return_std                          56.491631
average_reward                       0.627723
round_time             0 days 00:15:24.788191
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1112.128873
return_std_test                     69.364859
average_reward_test                  1.112129
round_time_test        0 days 00:00:07.795293
round_time_total       0 days 00:15:24.789566
loss_total                         619.745235
loss_critic                        893.482157
loss_actor                        -475.202508
memory_size                        881951.061 

=== epoch 10/10 ==== round 8/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:48,  1.87it/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 [15:20<00:00,  2.17it/s]
episodes                                   10
episode_length                         1000.0
returns                             612.09849
return_std                          55.167851
average_reward                       0.612098
round_time             0 days 00:15:20.919747
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1032.741838
return_std_test                    134.501354
average_reward_test                  1.032742
round_time_test        0 days 00:00:07.819338
round_time_total       0 days 00:15:20.920826
loss_total                         615.421497
loss_critic                        888.201025
loss_actor                        -475.696666
memory_size                        883883.061 

=== epoch 10/10 ==== round 9/50 ======================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:52,  2.40it/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 [15:24<00:00,  2.16it/s]
episodes                                   10
episode_length                         1000.0
returns                            583.120243
return_std                          66.017442
average_reward                        0.58312
round_time             0 days 00:15:24.734746
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1020.707188
return_std_test                    136.591371
average_reward_test                  1.020707
round_time_test        0 days 00:00:07.427922
round_time_total       0 days 00:15:24.736116
loss_total                         631.921414
loss_critic                        909.293696
loss_actor                        -477.567772
memory_size                        885815.061 

=== epoch 10/10 ==== round 10/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<20:29,  1.62it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [21:11<00:00,  1.57it/s]
episodes                                   10
episode_length                         1000.0
returns                             576.15699
return_std                          65.723754
average_reward                       0.576157
round_time             0 days 00:21:11.622944
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1122.765471
return_std_test                     63.324035
average_reward_test                  1.122765
round_time_test        0 days 00:00:08.387636
round_time_total       0 days 00:21:11.624195
loss_total                         630.589313
loss_critic                        907.969936
loss_actor                        -478.933237
memory_size                        887747.061 

=== epoch 10/10 ==== round 11/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<25:22,  1.31it/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 [25:38<00:00,  1.30it/s]
episodes                                   10
episode_length                         1000.0
returns                             566.44792
return_std                          59.318254
average_reward                       0.566448
round_time             0 days 00:25:39.505914
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1100.214957
return_std_test                    113.838375
average_reward_test                  1.100215
round_time_test        0 days 00:00:09.043331
round_time_total       0 days 00:25:39.507310
loss_total                          632.89832
loss_critic                        911.002305
loss_actor                        -479.517682
memory_size                        889679.061 

=== epoch 10/10 ==== round 12/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<25:28,  1.31it/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 [25:37<00:00,  1.30it/s]
episodes                                   10
episode_length                         1000.0
returns                             563.90432
return_std                          60.981997
average_reward                       0.563904
round_time             0 days 00:25:38.068512
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1056.046091
return_std_test                    114.457014
average_reward_test                  1.056046
round_time_test        0 days 00:00:09.519898
round_time_total       0 days 00:25:38.069956
loss_total                         643.879056
loss_critic                         924.52151
loss_actor                        -478.690821
memory_size                        891611.061 

=== epoch 10/10 ==== round 13/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<24:49,  1.34it/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 [23:45<00:00,  1.40it/s]
episodes                                   10
episode_length                         1000.0
returns                            566.119679
return_std                          58.891177
average_reward                        0.56612
round_time             0 days 00:23:46.193244
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1053.466162
return_std_test                     65.478413
average_reward_test                  1.053466
round_time_test        0 days 00:00:09.321417
round_time_total       0 days 00:23:46.194625
loss_total                         637.455003
loss_critic                        916.357186
loss_actor                        -478.153785
memory_size                        893543.061 

=== epoch 10/10 ==== round 14/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<20:35,  1.62it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [20:57<00:00,  1.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            563.311289
return_std                          82.009949
average_reward                       0.563311
round_time             0 days 00:20:57.742229
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1085.660024
return_std_test                     76.396902
average_reward_test                   1.08566
round_time_test        0 days 00:00:08.347611
round_time_total       0 days 00:20:57.743398
loss_total                         645.226994
loss_critic                        926.233218
loss_actor                        -478.797962
memory_size                        895475.061 

=== epoch 10/10 ==== round 15/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<20:37,  1.61it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [24:01<00:00,  1.39it/s]
episodes                                   10
episode_length                         1000.0
returns                            555.875477
return_std                          87.819156
average_reward                       0.555875
round_time             0 days 00:24:02.335128
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1057.614749
return_std_test                     106.55323
average_reward_test                  1.057615
round_time_test        0 days 00:00:08.675093
round_time_total       0 days 00:24:02.336446
loss_total                         644.094699
loss_critic                        924.893955
loss_actor                        -479.102387
memory_size                        897407.061 

=== epoch 10/10 ==== round 16/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 2/2000 [00:01<26:38,  1.25it/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 [22:45<00:00,  1.46it/s]
episodes                                   10
episode_length                         1000.0
returns                            558.522464
return_std                          88.841293
average_reward                       0.558522
round_time             0 days 00:22:46.357404
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1032.16385
return_std_test                    127.916454
average_reward_test                  1.032164
round_time_test        0 days 00:00:09.340283
round_time_total       0 days 00:22:46.358587
loss_total                         646.851147
loss_critic                         928.31695
loss_actor                        -479.012122
memory_size                        899339.061 

=== epoch 10/10 ==== round 17/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:25,  1.91it/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 [15:04<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            568.889133
return_std                          96.980166
average_reward                       0.568889
round_time             0 days 00:15:04.716303
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1038.436054
return_std_test                    109.420954
average_reward_test                  1.038436
round_time_test        0 days 00:00:07.869944
round_time_total       0 days 00:15:04.717415
loss_total                         657.117399
loss_critic                        941.460143
loss_actor                        -480.253636
memory_size                        901271.061 

=== epoch 10/10 ==== round 18/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:47,  2.41it/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 [12:57<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            568.137188
return_std                          97.357629
average_reward                       0.568137
round_time             0 days 00:12:57.622985
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1040.169316
return_std_test                     95.284988
average_reward_test                  1.040169
round_time_test        0 days 00:00:07.473809
round_time_total       0 days 00:12:57.624086
loss_total                         645.199015
loss_critic                        926.354037
loss_actor                        -479.421138
memory_size                        903203.061 

=== epoch 10/10 ==== round 19/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:18,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:57<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            595.468405
return_std                          69.123959
average_reward                       0.595468
round_time             0 days 00:12:57.831819
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       979.644575
return_std_test                    213.293298
average_reward_test                  0.979645
round_time_test        0 days 00:00:07.508252
round_time_total       0 days 00:12:57.832899
loss_total                         628.178653
loss_critic                        904.836178
loss_actor                        -478.451511
memory_size                        905135.061 

=== epoch 10/10 ==== round 20/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:10,  2.53it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:02<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            616.338913
return_std                           48.78183
average_reward                       0.616339
round_time             0 days 00:13:02.859176
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                        1014.5806
return_std_test                    120.173985
average_reward_test                  1.014581
round_time_test        0 days 00:00:07.357057
round_time_total       0 days 00:13:02.860251
loss_total                         636.891766
loss_critic                        916.005123
loss_actor                        -479.561721
memory_size                        907067.061 

=== epoch 10/10 ==== round 21/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:23,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [13:00<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            604.446249
return_std                          66.772463
average_reward                       0.604446
round_time             0 days 00:13:01.332626
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1045.613006
return_std_test                     95.835504
average_reward_test                  1.045613
round_time_test        0 days 00:00:07.618539
round_time_total       0 days 00:13:01.333719
loss_total                         643.676499
loss_critic                        924.792279
loss_actor                         -480.78668
memory_size                        908999.061 

=== epoch 10/10 ==== round 22/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:18,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:53<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            606.592736
return_std                          55.987094
average_reward                       0.606593
round_time             0 days 00:12:54.070156
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1040.28002
return_std_test                    109.883941
average_reward_test                   1.04028
round_time_test        0 days 00:00:07.544258
round_time_total       0 days 00:12:54.071235
loss_total                         644.791562
loss_critic                        926.208128
loss_actor                         -480.87476
memory_size                        910931.061 

=== epoch 10/10 ==== round 23/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 4/2000 [00:01<13:22,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:54<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                            603.386772
return_std                          57.694785
average_reward                       0.603387
round_time             0 days 00:12:55.426063
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1074.466138
return_std_test                     52.707294
average_reward_test                  1.074466
round_time_test        0 days 00:00:07.528899
round_time_total       0 days 00:12:55.427142
loss_total                         644.347131
loss_critic                        925.921512
loss_actor                        -481.950447
memory_size                        912863.061 

=== epoch 10/10 ==== round 24/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:03,  2.21it/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 [12:52<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            583.420465
return_std                          55.903548
average_reward                        0.58342
round_time             0 days 00:12:53.076450
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1070.527177
return_std_test                     95.869157
average_reward_test                  1.070527
round_time_test        0 days 00:00:07.486020
round_time_total       0 days 00:12:53.077525
loss_total                         644.452543
loss_critic                        925.856753
loss_actor                        -481.164365
memory_size                        914795.061 

=== epoch 10/10 ==== round 25/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:19,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:57<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            552.415752
return_std                          66.421313
average_reward                       0.552416
round_time             0 days 00:12:57.694703
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1073.084013
return_std_test                    100.546056
average_reward_test                  1.073084
round_time_test        0 days 00:00:07.541408
round_time_total       0 days 00:12:57.695792
loss_total                         639.857248
loss_critic                        919.944665
loss_actor                        -480.492481
memory_size                        916727.061 

=== epoch 10/10 ==== round 26/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:21,  2.49it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:58<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            560.830495
return_std                          55.861907
average_reward                        0.56083
round_time             0 days 00:12:59.116961
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1076.928607
return_std_test                     90.817716
average_reward_test                  1.076929
round_time_test        0 days 00:00:07.377863
round_time_total       0 days 00:12:59.118034
loss_total                         637.272856
loss_critic                        916.720447
loss_actor                        -480.517566
memory_size                        918659.061 

=== epoch 10/10 ==== round 27/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:52,  2.40it/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 [12:58<00:00,  2.57it/s]
episodes                                   10
episode_length                         1000.0
returns                            552.027006
return_std                          68.912414
average_reward                       0.552027
round_time             0 days 00:12:58.891777
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1002.109031
return_std_test                    108.922799
average_reward_test                  1.002109
round_time_test        0 days 00:00:07.449797
round_time_total       0 days 00:12:58.892857
loss_total                         633.022944
loss_critic                        911.777123
loss_actor                        -481.993834
memory_size                        920591.061 

=== epoch 10/10 ==== round 28/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:03,  2.37it/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 [13:00<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            562.402138
return_std                          75.420872
average_reward                       0.562402
round_time             0 days 00:13:00.525993
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1096.644708
return_std_test                    103.066241
average_reward_test                  1.096645
round_time_test        0 days 00:00:07.452934
round_time_total       0 days 00:13:00.527065
loss_total                         654.367701
loss_critic                        938.555798
loss_actor                        -482.384755
memory_size                        922523.061 

=== epoch 10/10 ==== round 29/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:20,  2.50it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [12:56<00:00,  2.58it/s]
episodes                                   10
episode_length                         1000.0
returns                            584.773768
return_std                          85.535598
average_reward                       0.584774
round_time             0 days 00:12:56.499211
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1011.723652
return_std_test                    127.201272
average_reward_test                  1.011724
round_time_test        0 days 00:00:07.446276
round_time_total       0 days 00:12:56.500321
loss_total                         648.191963
loss_critic                        930.749002
loss_actor                        -482.036252
memory_size                        924455.061 

=== epoch 10/10 ==== round 30/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:24,  2.48it/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 [12:52<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            611.386308
return_std                          71.974311
average_reward                       0.611386
round_time             0 days 00:12:52.617067
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1075.07339
return_std_test                     77.453616
average_reward_test                  1.075073
round_time_test        0 days 00:00:07.506671
round_time_total       0 days 00:12:52.618141
loss_total                         641.592079
loss_critic                        922.554515
loss_actor                        -482.257729
memory_size                        926387.061 

=== epoch 10/10 ==== round 31/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:44,  2.42it/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 [12:52<00:00,  2.59it/s]
episodes                                   10
episode_length                         1000.0
returns                            628.657696
return_std                          73.844527
average_reward                       0.628658
round_time             0 days 00:12:53.184778
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1058.303335
return_std_test                    124.298532
average_reward_test                  1.058303
round_time_test        0 days 00:00:07.543431
round_time_total       0 days 00:12:53.185895
loss_total                         639.110302
loss_critic                        919.369496
loss_actor                        -481.926535
memory_size                        928319.061 

=== epoch 10/10 ==== round 32/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:53,  2.39it/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 [13:01<00:00,  2.56it/s]
episodes                                   10
episode_length                         1000.0
returns                            627.009413
return_std                          78.467499
average_reward                       0.627009
round_time             0 days 00:13:01.893524
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1033.516278
return_std_test                    112.055467
average_reward_test                  1.033516
round_time_test        0 days 00:00:07.387422
round_time_total       0 days 00:13:01.894753
loss_total                         635.822057
loss_critic                        915.178753
loss_actor                         -481.60478
memory_size                        930251.061 

=== epoch 10/10 ==== round 33/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<17:34,  1.89it/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 [14:51<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            595.515792
return_std                         111.430984
average_reward                       0.595516
round_time             0 days 00:14:52.195196
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1034.094325
return_std_test                    121.236535
average_reward_test                  1.034094
round_time_test        0 days 00:00:07.884105
round_time_total       0 days 00:14:52.196527
loss_total                         638.503891
loss_critic                        918.429877
loss_actor                        -481.200113
memory_size                        932183.061 

=== epoch 10/10 ==== round 34/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:26,  2.16it/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 [14:50<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                             576.87122
return_std                         110.991026
average_reward                       0.576871
round_time             0 days 00:14:51.511304
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       990.096785
return_std_test                    115.676127
average_reward_test                  0.990097
round_time_test        0 days 00:00:07.716167
round_time_total       0 days 00:14:51.512879
loss_total                         638.818902
loss_critic                        918.945616
loss_actor                         -481.68801
memory_size                        934115.061 

=== epoch 10/10 ==== round 35/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:27,  2.15it/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 [14:51<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                            586.180698
return_std                         117.100428
average_reward                       0.586181
round_time             0 days 00:14:51.943518
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1055.485682
return_std_test                    138.025365
average_reward_test                  1.055486
round_time_test        0 days 00:00:07.700922
round_time_total       0 days 00:14:51.944597
loss_total                         638.327944
loss_critic                        918.439479
loss_actor                        -482.118251
memory_size                        936047.061 

=== epoch 10/10 ==== round 36/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:42,  2.26it/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 [13:26<00:00,  2.48it/s]
episodes                                   10
episode_length                         1000.0
returns                            593.158289
return_std                         119.705284
average_reward                       0.593158
round_time             0 days 00:13:27.380138
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1020.867897
return_std_test                    121.655153
average_reward_test                  1.020868
round_time_test        0 days 00:00:07.695866
round_time_total       0 days 00:13:27.381246
loss_total                         638.020845
loss_critic                        918.272787
loss_actor                        -482.986989
memory_size                        937979.061 

=== epoch 10/10 ==== round 37/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:34,  2.45it/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 [13:30<00:00,  2.47it/s]
episodes                                   10
episode_length                         1000.0
returns                            591.477884
return_std                         111.927944
average_reward                       0.591478
round_time             0 days 00:13:30.821878
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1033.76565
return_std_test                     81.340471
average_reward_test                  1.033766
round_time_test        0 days 00:00:07.822786
round_time_total       0 days 00:13:30.822991
loss_total                          640.06854
loss_critic                        921.036509
loss_actor                        -483.803391
memory_size                        939911.061 

=== epoch 10/10 ==== round 38/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<14:00,  2.38it/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 [13:28<00:00,  2.47it/s]
episodes                                   10
episode_length                         1000.0
returns                            627.173857
return_std                          85.086762
average_reward                       0.627174
round_time             0 days 00:13:28.621915
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1112.184728
return_std_test                    113.224209
average_reward_test                  1.112185
round_time_test        0 days 00:00:07.743592
round_time_total       0 days 00:13:28.622992
loss_total                         644.705176
loss_critic                        927.167753
loss_actor                         -485.14519
memory_size                        941843.061 

=== epoch 10/10 ==== round 39/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:34,  2.45it/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 [13:32<00:00,  2.46it/s]
episodes                                   10
episode_length                         1000.0
returns                            640.353145
return_std                          72.621316
average_reward                       0.640353
round_time             0 days 00:13:33.426145
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1054.986127
return_std_test                     85.001083
average_reward_test                  1.054986
round_time_test        0 days 00:00:07.662185
round_time_total       0 days 00:13:33.427214
loss_total                         644.570723
loss_critic                        927.170755
loss_actor                        -485.829466
memory_size                        943775.061 

=== epoch 10/10 ==== round 40/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:47,  2.41it/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 [13:32<00:00,  2.46it/s]
episodes                                   10
episode_length                         1000.0
returns                            643.872713
return_std                          64.833861
average_reward                       0.643873
round_time             0 days 00:13:32.504047
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1092.421296
return_std_test                    109.111893
average_reward_test                  1.092421
round_time_test        0 days 00:00:07.647198
round_time_total       0 days 00:13:32.505119
loss_total                         646.477435
loss_critic                        929.463224
loss_actor                        -485.465779
memory_size                        945707.061 

=== epoch 10/10 ==== round 41/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:33,  2.46it/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 [13:29<00:00,  2.47it/s]
episodes                                   10
episode_length                         1000.0
returns                            636.611134
return_std                          66.258196
average_reward                       0.636611
round_time             0 days 00:13:29.898150
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1032.309583
return_std_test                    163.077274
average_reward_test                   1.03231
round_time_test        0 days 00:00:07.576663
round_time_total       0 days 00:13:29.899231
loss_total                         643.911541
loss_critic                        926.161144
loss_actor                        -485.086925
memory_size                        947639.061 

=== epoch 10/10 ==== round 42/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:47,  2.41it/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 [13:33<00:00,  2.46it/s]
episodes                                   10
episode_length                         1000.0
returns                            649.662796
return_std                          54.450443
average_reward                       0.649663
round_time             0 days 00:13:34.260264
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1077.641691
return_std_test                     75.377895
average_reward_test                  1.077642
round_time_test        0 days 00:00:07.463720
round_time_total       0 days 00:13:34.261414
loss_total                         656.797722
loss_critic                        942.170435
loss_actor                        -484.693192
memory_size                        949571.061 

=== epoch 10/10 ==== round 43/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:48,  2.41it/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 [13:11<00:00,  2.53it/s]
episodes                                   10
episode_length                         1000.0
returns                            640.424982
return_std                          51.083399
average_reward                       0.640425
round_time             0 days 00:13:12.317508
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1123.468625
return_std_test                    100.340523
average_reward_test                  1.123469
round_time_test        0 days 00:00:07.718159
round_time_total       0 days 00:13:12.318583
loss_total                         653.043148
loss_critic                        937.664711
loss_actor                        -485.443159
memory_size                        951503.061 

=== epoch 10/10 ==== round 44/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:36,  2.45it/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 [14:51<00:00,  2.24it/s]
episodes                                   10
episode_length                         1000.0
returns                             641.23719
return_std                          50.737769
average_reward                       0.641237
round_time             0 days 00:14:51.661448
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1060.596149
return_std_test                    121.739681
average_reward_test                  1.060596
round_time_test        0 days 00:00:07.451959
round_time_total       0 days 00:14:51.662598
loss_total                         656.097191
loss_critic                        941.906409
loss_actor                        -487.139746
memory_size                        953435.061 

=== epoch 10/10 ==== round 45/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:35,  2.13it/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 [15:06<00:00,  2.21it/s]
episodes                                   10
episode_length                         1000.0
returns                            636.611377
return_std                           44.32578
average_reward                       0.636611
round_time             0 days 00:15:07.389842
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1051.644108
return_std_test                      58.60074
average_reward_test                  1.051644
round_time_test        0 days 00:00:07.860295
round_time_total       0 days 00:15:07.391053
loss_total                         663.464062
loss_critic                        951.215741
loss_actor                        -487.542714
memory_size                        955367.061 

=== epoch 10/10 ==== round 46/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:31,  2.14it/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 [15:02<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            635.752969
return_std                          35.848785
average_reward                       0.635753
round_time             0 days 00:15:03.025800
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1107.333962
return_std_test                     84.719811
average_reward_test                  1.107334
round_time_test        0 days 00:00:07.632967
round_time_total       0 days 00:15:03.026860
loss_total                         646.457655
loss_critic                        929.831834
loss_actor                        -487.039118
memory_size                        957299.061 

=== epoch 10/10 ==== round 47/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:51,  2.40it/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 [13:06<00:00,  2.54it/s]
episodes                                   10
episode_length                         1000.0
returns                            606.111036
return_std                          85.027926
average_reward                       0.606111
round_time             0 days 00:13:07.092929
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1052.869326
return_std_test                    168.558714
average_reward_test                  1.052869
round_time_test        0 days 00:00:07.393148
round_time_total       0 days 00:13:07.093998
loss_total                         650.414724
loss_critic                        934.453193
loss_actor                        -485.739207
memory_size                        959231.061 

=== epoch 10/10 ==== round 48/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<13:26,  2.48it/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 [14:32<00:00,  2.29it/s]
episodes                                   10
episode_length                         1000.0
returns                            608.504287
return_std                          95.861032
average_reward                       0.608504
round_time             0 days 00:14:33.423245
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                       1092.73434
return_std_test                     60.200633
average_reward_test                  1.092734
round_time_test        0 days 00:00:07.517021
round_time_total       0 days 00:14:33.424379
loss_total                         650.144179
loss_critic                        934.455329
loss_actor                        -487.100479
memory_size                        961163.061 

=== epoch 10/10 ==== round 49/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<15:31,  2.14it/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 [14:59<00:00,  2.22it/s]
episodes                                   10
episode_length                         1000.0
returns                            605.065932
return_std                          95.200987
average_reward                       0.605066
round_time             0 days 00:15:00.489066
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1074.675044
return_std_test                    112.417936
average_reward_test                  1.074675
round_time_test        0 days 00:00:07.642954
round_time_total       0 days 00:15:00.490324
loss_total                         662.442794
loss_critic                        950.087722
loss_actor                         -488.13698
memory_size                        963095.061 

=== epoch 10/10 ==== round 50/50 =====================================
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
  0%|          | 3/2000 [00:01<16:46,  1.98it/s]/<ANONYMIZED PATH>/python3.12/site-packages/gymnasium/envs/registration.py:519: DeprecationWarning: [33mWARN: The environment HalfCheetah-v4 is out of date. You should consider upgrading to version `v5`.[0m
  logger.deprecation(
100%|██████████| 2000/2000 [14:59<00:00,  2.22it/s]
<GE432_Delay<NormalizeActionWrapper<Float64ToFloat32<CompatWrapper<NoisyActionWrapper<TimeLimit<OrderEnforcing<PassiveEnvChecker<HalfCheetahEnv<HalfCheetah-v4>>>>>>>>>>
episodes                                   10
episode_length                         1000.0
returns                            588.167322
return_std                          92.569002
average_reward                       0.588167
round_time             0 days 00:15:00.588886
episodes_test                            10.0
episode_length_test                    1000.0
returns_test                      1089.867505
return_std_test                    115.410262
average_reward_test                  1.089868
round_time_test        0 days 00:00:07.844241
round_time_total       0 days 00:15:00.590241
loss_total                         649.333773
loss_critic                        933.400446
loss_actor                         -486.93298
memory_size                        965027.061 


