Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1694523001.rhmmedcatt-ProLiant-ML350-Gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0589a7feb1ff4864ac04e6fce4ae40a1c1e97722545c1ca797b6a83caafbc44e
+size 688745

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_two_colors_easy
     metrics:
     - type: mean_reward
-      value: 3.90 +/- 0.59
+      value: 4.53 +/- 2.21
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000002153_8818688_reward_12.789.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81f8cafe5e29bd10ef4e1081666b4378854794480edb0996614b07f515ce99c
+size 34934758

checkpoint_p0/checkpoint_000002138_8757248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61265768ac1956d30a9dfc437ead535f904df748fe45a4c75981c2dc700b910a
+size 34935172

checkpoint_p0/checkpoint_000002443_10006528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f466c83c71e32dccabc08a2158afe85b9480b0633826b1e6305826ac831512ba
+size 34935172

config.json

@@ -7,7 +7,7 @@
   "restart_behavior": "restart",
   "device": "gpu",
   "seed": null,
-  "num_policies": 1,
+  "num_policies": 2,
   "async_rl": true,
   "serial_mode": false,
   "batched_sampling": false,
@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 1000000,
+  "train_for_env_steps": 10000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,
@@ -102,8 +102,8 @@
   "env_framestack": 1,
   "pixel_format": "CHW",
   "use_record_episode_statistics": false,
-  "with_wandb": false,
-  "wandb_user": null,
+  "with_wandb": true,
+  "wandb_user": "matt-stammers",
   "wandb_project": "sample_factory",
   "wandb_group": null,
   "wandb_job_type": "SF",

git.diff

@@ -5,10 +5,10 @@ diff --git a/environments/ai_vs_ai/ml-agents b/environments/ai_vs_ai/ml-agents
 -Subproject commit 8bcedabd808ffb7097f88b800fc92dea82dfd610
 +Subproject commit 8bcedabd808ffb7097f88b800fc92dea82dfd610-dirty
 diff --git a/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/0.monitor.csv b/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/0.monitor.csv
-index fb7bd62..bf520b8 100644
+index fb7bd62..eeaff59 100644
 --- a/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/0.monitor.csv
 +++ b/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/0.monitor.csv
-@@ -18493,3 +18493,11778 @@ r,l,t
+@@ -18493,3 +18493,11851 @@ r,l,t
  19475.0,10454,121627.848456
  8600.0,4558,121633.704827
  14975.0,5637,121641.623816
@@ -11787,11 +11787,84 @@ index fb7bd62..bf520b8 100644
 +25825.0,11357,282129.504158
 +22250.0,9052,282140.854319
 +14850.0,5159,282147.229682
++22925.0,10032,282161.825632
++19275.0,9417,282178.304765
++15375.0,6662,282189.445194
++22500.0,10017,282206.106361
++18800.0,7775,282219.074695
++26025.0,11680,282238.537118
++26000.0,11857,282256.765218
++15675.0,6925,282287.412728
++22575.0,9537,282298.980867
++14925.0,4758,282304.782811
++23575.0,9892,282316.728288
++14975.0,5317,282323.144005
++15200.0,5877,282330.240721
++26000.0,11672,282344.357126
++26100.0,12070,282358.890885
++26325.0,11682,282373.199278
++15050.0,6107,282380.550238
++15250.0,6247,282388.108755
++23650.0,9882,282400.04745
++8400.0,4022,282404.913379
++18950.0,10270,282443.014621
++15375.0,7267,282451.84289
++25975.0,11042,282465.139765
++15300.0,6077,282472.495647
++26750.0,12054,282487.148096
++22600.0,9182,282498.342239
++26125.0,11254,282512.067826
++19625.0,8967,282522.877659
++15350.0,6132,282530.319936
++23125.0,10497,282543.0374
++19525.0,8772,282581.038901
++15225.0,5519,282587.681141
++19200.0,7820,282597.140002
++26100.0,11234,282610.7178
++25875.0,10619,282623.573375
++22425.0,9592,282635.290018
++22875.0,10902,282648.470669
++26075.0,11194,282661.993578
++14850.0,4997,282668.004048
++4250.0,2307,282670.727012
++25775.0,10832,282683.879624
++26175.0,12150,282698.608609
++18975.0,8127,282735.451614
++18700.0,7657,282744.775324
++14825.0,5538,282751.531505
++11675.0,5382,282758.016039
++19475.0,8752,282768.64435
++26150.0,11722,282782.827546
++22750.0,9862,282794.7549
++15125.0,5782,282801.716895
++12100.0,4972,282807.863577
++15325.0,6102,282815.245395
++15250.0,6807,282823.512894
++22525.0,10122,282835.896441
++27050.0,11782,282850.154135
++8025.0,3788,282876.890591
++26725.0,11322,282890.562404
++15275.0,6292,282898.223938
++825.0,1792,282900.366076
++22575.0,9507,282911.797788
++15075.0,5862,282918.822713
++15350.0,6792,282927.074413
++25825.0,10994,282940.462049
++11325.0,4113,282945.459857
++15125.0,5862,282952.656345
++26350.0,11472,282967.046163
++26150.0,11457,282981.857427
++22700.0,10902,282996.245395
++27050.0,11064,283039.899779
++22575.0,10957,283053.184556
++15400.0,5937,283060.406768
++14950.0,5432,283067.075765
++22550.0,10252,283079.807549
 diff --git a/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/best_model.zip b/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/best_model.zip
 index ade47c0..3e11ac4 100644
 Binary files a/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/best_model.zip and b/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/best_model.zip differ
 diff --git a/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/evaluations.npz b/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/evaluations.npz
-index c09117b..39cec60 100644
+index c09117b..7e8cf03 100644
 Binary files a/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/evaluations.npz and b/environments/atari/model/qrdqn/QbertNoFrameskip-v4_6/evaluations.npz differ
 diff --git a/environments/sample_factory/doom_healthgathering.ipynb b/environments/sample_factory/doom_healthgathering.ipynb
 index a7be1b5..84985a6 100644
@@ -11818,62 +11891,4 @@ index a7be1b5..84985a6 100644
 diff --git a/environments/sample_factory/train_dir/default_experiment/.summary/0/events.out.tfevents.1694360455.rhmmedcatt-ProLiant-ML350-Gen10 b/environments/sample_factory/train_dir/default_experiment/.summary/0/events.out.tfevents.1694360455.rhmmedcatt-ProLiant-ML350-Gen10
 deleted file mode 100644
 index 3cbb8a2..0000000
-Binary files a/environments/sample_factory/train_dir/default_experiment/.summary/0/events.out.tfevents.1694360455.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
-diff --git a/environments/sample_factory/train_dir/default_experiment/README.md b/environments/sample_factory/train_dir/default_experiment/README.md
-deleted file mode 100644
-index 67b28b9..0000000
---- a/environments/sample_factory/train_dir/default_experiment/README.md
-+++ /dev/null
-@@ -1,56 +0,0 @@
-----
--library_name: sample-factory
--tags:
--- deep-reinforcement-learning
--- reinforcement-learning
--- sample-factory
--model-index:
--- name: APPO
--  results:
--  - task:
--      type: reinforcement-learning
--      name: reinforcement-learning
--    dataset:
--      name: doom_health_gathering_supreme
--      type: doom_health_gathering_supreme
--    metrics:
--    - type: mean_reward
--      value: 9.02 +/- 3.07
--      name: mean_reward
--      verified: false
-----
--
--A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
--
--This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
--Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
--
--
--## Downloading the model
--
--After installing Sample-Factory, download the model with:
--```
--python -m sample_factory.huggingface.load_from_hub -r MattStammers/rl_course_vizdoom_health_gathering_supreme
--```
--
--    
--## Using the model
--
--To run the model after download, use the `enjoy` script corresponding to this environment:
--```
--python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
--```
--
--
--You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
--See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
--    
--## Training with this model
--
--To continue training with this model, use the `train` script corresponding to this environment:
--```
--python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_
+Binary files a/environments/sample_factory/train_dir/default_experiment/.summary

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1a058d390ea968a6df89a22a015e13f107c5b56e2f562f4f7f2cc02b0a5fcc
-size 4888196
+oid sha256:4d79f9811bb3e9c05a0128a8f761ac4bdbda3cb7310fa0bbbc9e659ce7fd145d
+size 7586102

sf_log.txt

@@ -1,16 +1,16 @@
-[2023-09-12 13:34:35,213][63361] Using GPUs [0] for process 0 (actually maps to GPUs [0])
-[2023-09-12 13:34:35,214][63361] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
-[2023-09-12 13:34:35,232][63361] Num visible devices: 1
-[2023-09-12 13:34:35,270][63361] Starting seed is not provided
-[2023-09-12 13:34:35,270][63361] Using GPUs [0] for process 0 (actually maps to GPUs [0])
-[2023-09-12 13:34:35,270][63361] Initializing actor-critic model on device cuda:0
-[2023-09-12 13:34:35,271][63361] RunningMeanStd input shape: (3, 72, 128)
-[2023-09-12 13:34:35,271][63361] RunningMeanStd input shape: (1,)
-[2023-09-12 13:34:35,284][63361] ConvEncoder: input_channels=3
-[2023-09-12 13:34:35,443][63361] Conv encoder output size: 512
-[2023-09-12 13:34:35,443][63361] Policy head output size: 512
-[2023-09-12 13:34:35,467][63361] Created Actor Critic model with architecture:
-[2023-09-12 13:34:35,467][63361] ActorCriticSharedWeights(
+[2023-09-12 13:50:06,113][122669] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-09-12 13:50:06,113][122669] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-09-12 13:50:06,155][122669] Num visible devices: 1
+[2023-09-12 13:50:06,197][122669] Starting seed is not provided
+[2023-09-12 13:50:06,197][122669] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-09-12 13:50:06,198][122669] Initializing actor-critic model on device cuda:0
+[2023-09-12 13:50:06,198][122669] RunningMeanStd input shape: (3, 72, 128)
+[2023-09-12 13:50:06,198][122669] RunningMeanStd input shape: (1,)
+[2023-09-12 13:50:06,216][122669] ConvEncoder: input_channels=3
+[2023-09-12 13:50:06,386][122669] Conv encoder output size: 512
+[2023-09-12 13:50:06,386][122669] Policy head output size: 512
+[2023-09-12 13:50:06,401][122669] Created Actor Critic model with architecture:
+[2023-09-12 13:50:06,401][122669] ActorCriticSharedWeights(
   (obs_normalizer): ObservationNormalizer(
     (running_mean_std): RunningMeanStdDictInPlace(
       (running_mean_std): ModuleDict(
@@ -51,119 +51,363 @@
     (distribution_linear): Linear(in_features=512, out_features=6, bias=True)
   )
 )
-[2023-09-12 13:34:36,777][63361] Using optimizer <class 'torch.optim.adam.Adam'>
-[2023-09-12 13:34:36,778][63361] No checkpoints found
-[2023-09-12 13:34:36,778][63361] Did not load from checkpoint, starting from scratch!
-[2023-09-12 13:34:36,778][63361] Initialized policy 0 weights for model version 0
-[2023-09-12 13:34:36,779][63361] LearnerWorker_p0 finished initialization!
-[2023-09-12 13:34:36,780][63361] Using GPUs [0] for process 0 (actually maps to GPUs [0])
-[2023-09-12 13:34:37,202][63596] Worker 7 uses CPU cores [28, 29, 30, 31]
-[2023-09-12 13:34:37,203][63553] Worker 1 uses CPU cores [4, 5, 6, 7]
-[2023-09-12 13:34:37,244][63587] Worker 0 uses CPU cores [0, 1, 2, 3]
-[2023-09-12 13:34:37,255][63595] Worker 6 uses CPU cores [24, 25, 26, 27]
-[2023-09-12 13:34:37,259][63594] Worker 5 uses CPU cores [20, 21, 22, 23]
-[2023-09-12 13:34:37,359][63586] Worker 3 uses CPU cores [12, 13, 14, 15]
-[2023-09-12 13:34:37,367][63590] Worker 2 uses CPU cores [8, 9, 10, 11]
-[2023-09-12 13:34:37,367][63593] Worker 4 uses CPU cores [16, 17, 18, 19]
-[2023-09-12 13:34:37,406][63552] Using GPUs [0] for process 0 (actually maps to GPUs [0])
-[2023-09-12 13:34:37,406][63552] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
-[2023-09-12 13:34:37,425][63552] Num visible devices: 1
-[2023-09-12 13:34:38,097][63552] RunningMeanStd input shape: (3, 72, 128)
-[2023-09-12 13:34:38,098][63552] RunningMeanStd input shape: (1,)
-[2023-09-12 13:34:38,109][63552] ConvEncoder: input_channels=3
-[2023-09-12 13:34:38,210][63552] Conv encoder output size: 512
-[2023-09-12 13:34:38,210][63552] Policy head output size: 512
-[2023-09-12 13:34:38,579][63596] Doom resolution: 160x120, resize resolution: (128, 72)
-[2023-09-12 13:34:38,585][63595] Doom resolution: 160x120, resize resolution: (128, 72)
-[2023-09-12 13:34:38,585][63593] Doom resolution: 160x120, resize resolution: (128, 72)
-[2023-09-12 13:34:38,585][63587] Doom resolution: 160x120, resize resolution: (128, 72)
-[2023-09-12 13:34:38,595][63586] Doom resolution: 160x120, resize resolution: (128, 72)
-[2023-09-12 13:34:38,597][63590] Doom resolution: 160x120, resize resolution: (128, 72)
-[2023-09-12 13:34:38,604][63553] Doom resolution: 160x120, resize resolution: (128, 72)
-[2023-09-12 13:34:38,604][63594] Doom resolution: 160x120, resize resolution: (128, 72)
-[2023-09-12 13:34:38,878][63596] Decorrelating experience for 0 frames...
-[2023-09-12 13:34:38,895][63593] Decorrelating experience for 0 frames...
-[2023-09-12 13:34:38,900][63595] Decorrelating experience for 0 frames...
-[2023-09-12 13:34:38,922][63586] Decorrelating experience for 0 frames...
-[2023-09-12 13:34:39,153][63587] Decorrelating experience for 0 frames...
-[2023-09-12 13:34:39,181][63593] Decorrelating experience for 32 frames...
-[2023-09-12 13:34:39,182][63595] Decorrelating experience for 32 frames...
-[2023-09-12 13:34:39,228][63596] Decorrelating experience for 32 frames...
-[2023-09-12 13:34:39,229][63594] Decorrelating experience for 0 frames...
-[2023-09-12 13:34:39,231][63586] Decorrelating experience for 32 frames...
-[2023-09-12 13:34:39,254][63590] Decorrelating experience for 0 frames...
-[2023-09-12 13:34:39,500][63594] Decorrelating experience for 32 frames...
-[2023-09-12 13:34:39,513][63587] Decorrelating experience for 32 frames...
-[2023-09-12 13:34:39,523][63590] Decorrelating experience for 32 frames...
-[2023-09-12 13:34:39,525][63553] Decorrelating experience for 0 frames...
-[2023-09-12 13:34:39,533][63593] Decorrelating experience for 64 frames...
-[2023-09-12 13:34:39,788][63553] Decorrelating experience for 32 frames...
-[2023-09-12 13:34:39,838][63595] Decorrelating experience for 64 frames...
-[2023-09-12 13:34:39,843][63586] Decorrelating experience for 64 frames...
-[2023-09-12 13:34:39,849][63593] Decorrelating experience for 96 frames...
-[2023-09-12 13:34:39,863][63587] Decorrelating experience for 64 frames...
-[2023-09-12 13:34:40,155][63595] Decorrelating experience for 96 frames...
-[2023-09-12 13:34:40,176][63587] Decorrelating experience for 96 frames...
-[2023-09-12 13:34:40,218][63553] Decorrelating experience for 64 frames...
-[2023-09-12 13:34:40,221][63594] Decorrelating experience for 64 frames...
-[2023-09-12 13:34:40,247][63586] Decorrelating experience for 96 frames...
-[2023-09-12 13:34:40,499][63590] Decorrelating experience for 64 frames...
-[2023-09-12 13:34:40,609][63594] Decorrelating experience for 96 frames...
-[2023-09-12 13:34:40,618][63553] Decorrelating experience for 96 frames...
-[2023-09-12 13:34:40,838][63596] Decorrelating experience for 64 frames...
-[2023-09-12 13:34:41,027][63590] Decorrelating experience for 96 frames...
-[2023-09-12 13:34:41,229][63596] Decorrelating experience for 96 frames...
-[2023-09-12 13:34:41,428][63361] Signal inference workers to stop experience collection...
-[2023-09-12 13:34:41,432][63552] InferenceWorker_p0-w0: stopping experience collection
-[2023-09-12 13:34:45,435][63361] Signal inference workers to resume experience collection...
-[2023-09-12 13:34:45,436][63552] InferenceWorker_p0-w0: resuming experience collection
-[2023-09-12 13:34:48,988][63552] Updated weights for policy 0, policy_version 10 (0.0376)
-[2023-09-12 13:34:52,732][63552] Updated weights for policy 0, policy_version 20 (0.0010)
-[2023-09-12 13:34:55,247][63361] Saving new best policy, reward=4.631!
-[2023-09-12 13:34:56,268][63552] Updated weights for policy 0, policy_version 30 (0.0009)
-[2023-09-12 13:34:59,869][63552] Updated weights for policy 0, policy_version 40 (0.0009)
-[2023-09-12 13:35:03,454][63552] Updated weights for policy 0, policy_version 50 (0.0009)
-[2023-09-12 13:35:07,103][63552] Updated weights for policy 0, policy_version 60 (0.0009)
-[2023-09-12 13:35:10,657][63552] Updated weights for policy 0, policy_version 70 (0.0009)
-[2023-09-12 13:35:14,191][63552] Updated weights for policy 0, policy_version 80 (0.0009)
-[2023-09-12 13:35:17,722][63552] Updated weights for policy 0, policy_version 90 (0.0009)
-[2023-09-12 13:35:21,228][63552] Updated weights for policy 0, policy_version 100 (0.0008)
-[2023-09-12 13:35:24,812][63552] Updated weights for policy 0, policy_version 110 (0.0009)
-[2023-09-12 13:35:28,361][63552] Updated weights for policy 0, policy_version 120 (0.0008)
-[2023-09-12 13:35:31,821][63552] Updated weights for policy 0, policy_version 130 (0.0009)
-[2023-09-12 13:35:35,276][63552] Updated weights for policy 0, policy_version 140 (0.0008)
-[2023-09-12 13:35:38,747][63552] Updated weights for policy 0, policy_version 150 (0.0008)
-[2023-09-12 13:35:42,301][63552] Updated weights for policy 0, policy_version 160 (0.0008)
-[2023-09-12 13:35:45,805][63552] Updated weights for policy 0, policy_version 170 (0.0008)
-[2023-09-12 13:35:49,340][63552] Updated weights for policy 0, policy_version 180 (0.0008)
-[2023-09-12 13:35:52,925][63552] Updated weights for policy 0, policy_version 190 (0.0008)
-[2023-09-12 13:35:56,545][63552] Updated weights for policy 0, policy_version 200 (0.0008)
-[2023-09-12 13:36:00,090][63552] Updated weights for policy 0, policy_version 210 (0.0009)
-[2023-09-12 13:36:03,599][63552] Updated weights for policy 0, policy_version 220 (0.0009)
-[2023-09-12 13:36:07,145][63552] Updated weights for policy 0, policy_version 230 (0.0008)
-[2023-09-12 13:36:10,690][63552] Updated weights for policy 0, policy_version 240 (0.0008)
-[2023-09-12 13:36:12,775][63361] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000000246_1007616.pth...
-[2023-09-12 13:36:12,789][63593] Stopping RolloutWorker_w4...
-[2023-09-12 13:36:12,789][63593] Loop rollout_proc4_evt_loop terminating...
-[2023-09-12 13:36:12,790][63590] Stopping RolloutWorker_w2...
-[2023-09-12 13:36:12,790][63590] Loop rollout_proc2_evt_loop terminating...
-[2023-09-12 13:36:12,791][63595] Stopping RolloutWorker_w6...
-[2023-09-12 13:36:12,791][63595] Loop rollout_proc6_evt_loop terminating...
-[2023-09-12 13:36:12,792][63587] Stopping RolloutWorker_w0...
-[2023-09-12 13:36:12,792][63596] Stopping RolloutWorker_w7...
-[2023-09-12 13:36:12,793][63587] Loop rollout_proc0_evt_loop terminating...
-[2023-09-12 13:36:12,793][63596] Loop rollout_proc7_evt_loop terminating...
-[2023-09-12 13:36:12,794][63586] Stopping RolloutWorker_w3...
-[2023-09-12 13:36:12,794][63586] Loop rollout_proc3_evt_loop terminating...
-[2023-09-12 13:36:12,786][63361] Stopping Batcher_0...
-[2023-09-12 13:36:12,795][63594] Stopping RolloutWorker_w5...
-[2023-09-12 13:36:12,795][63594] Loop rollout_proc5_evt_loop terminating...
-[2023-09-12 13:36:12,796][63552] Weights refcount: 2 0
-[2023-09-12 13:36:12,797][63552] Stopping InferenceWorker_p0-w0...
-[2023-09-12 13:36:12,798][63552] Loop inference_proc0-0_evt_loop terminating...
-[2023-09-12 13:36:12,807][63553] Stopping RolloutWorker_w1...
-[2023-09-12 13:36:12,807][63553] Loop rollout_proc1_evt_loop terminating...
-[2023-09-12 13:36:12,803][63361] Loop batcher_evt_loop terminating...
-[2023-09-12 13:36:12,828][63361] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000000246_1007616.pth...
-[2023-09-12 13:36:12,891][63361] Stopping LearnerWorker_p0...
-[2023-09-12 13:36:12,891][63361] Loop learner_proc0_evt_loop terminating...
+[2023-09-12 13:50:07,790][122669] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-09-12 13:50:07,791][122669] No checkpoints found
+[2023-09-12 13:50:07,791][122669] Did not load from checkpoint, starting from scratch!
+[2023-09-12 13:50:07,791][122669] Initialized policy 0 weights for model version 0
+[2023-09-12 13:50:07,793][122669] LearnerWorker_p0 finished initialization!
+[2023-09-12 13:50:07,793][122669] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-09-12 13:50:08,116][122838] Worker 2 uses CPU cores [8, 9, 10, 11]
+[2023-09-12 13:50:08,139][122801] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-09-12 13:50:08,139][122801] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-09-12 13:50:08,146][122837] Worker 5 uses CPU cores [20, 21, 22, 23]
+[2023-09-12 13:50:08,178][122801] Num visible devices: 1
+[2023-09-12 13:50:08,179][122803] Worker 1 uses CPU cores [4, 5, 6, 7]
+[2023-09-12 13:50:08,199][122872] Worker 7 uses CPU cores [28, 29, 30, 31]
+[2023-09-12 13:50:08,356][122802] Worker 0 uses CPU cores [0, 1, 2, 3]
+[2023-09-12 13:50:08,398][122805] Worker 4 uses CPU cores [16, 17, 18, 19]
+[2023-09-12 13:50:08,432][122804] Worker 3 uses CPU cores [12, 13, 14, 15]
+[2023-09-12 13:50:08,536][122854] Worker 6 uses CPU cores [24, 25, 26, 27]
+[2023-09-12 13:50:08,895][122801] RunningMeanStd input shape: (3, 72, 128)
+[2023-09-12 13:50:08,895][122801] RunningMeanStd input shape: (1,)
+[2023-09-12 13:50:08,907][122801] ConvEncoder: input_channels=3
+[2023-09-12 13:50:09,014][122801] Conv encoder output size: 512
+[2023-09-12 13:50:09,014][122801] Policy head output size: 512
+[2023-09-12 13:50:09,398][122802] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-09-12 13:50:09,402][122803] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-09-12 13:50:09,403][122805] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-09-12 13:50:09,403][122837] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-09-12 13:50:09,404][122804] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-09-12 13:50:09,404][122872] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-09-12 13:50:09,415][122838] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-09-12 13:50:09,415][122854] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-09-12 13:50:09,701][122802] Decorrelating experience for 0 frames...
+[2023-09-12 13:50:09,703][122804] Decorrelating experience for 0 frames...
+[2023-09-12 13:50:09,705][122837] Decorrelating experience for 0 frames...
+[2023-09-12 13:50:09,711][122872] Decorrelating experience for 0 frames...
+[2023-09-12 13:50:09,716][122805] Decorrelating experience for 0 frames...
+[2023-09-12 13:50:09,754][122854] Decorrelating experience for 0 frames...
+[2023-09-12 13:50:10,036][122837] Decorrelating experience for 32 frames...
+[2023-09-12 13:50:10,040][122805] Decorrelating experience for 32 frames...
+[2023-09-12 13:50:10,040][122802] Decorrelating experience for 32 frames...
+[2023-09-12 13:50:10,041][122804] Decorrelating experience for 32 frames...
+[2023-09-12 13:50:10,053][122838] Decorrelating experience for 0 frames...
+[2023-09-12 13:50:10,132][122854] Decorrelating experience for 32 frames...
+[2023-09-12 13:50:10,328][122803] Decorrelating experience for 0 frames...
+[2023-09-12 13:50:10,394][122838] Decorrelating experience for 32 frames...
+[2023-09-12 13:50:10,411][122837] Decorrelating experience for 64 frames...
+[2023-09-12 13:50:10,427][122802] Decorrelating experience for 64 frames...
+[2023-09-12 13:50:10,514][122804] Decorrelating experience for 64 frames...
+[2023-09-12 13:50:10,620][122803] Decorrelating experience for 32 frames...
+[2023-09-12 13:50:10,693][122805] Decorrelating experience for 64 frames...
+[2023-09-12 13:50:10,754][122838] Decorrelating experience for 64 frames...
+[2023-09-12 13:50:10,806][122872] Decorrelating experience for 32 frames...
+[2023-09-12 13:50:10,811][122854] Decorrelating experience for 64 frames...
+[2023-09-12 13:50:10,974][122803] Decorrelating experience for 64 frames...
+[2023-09-12 13:50:10,989][122837] Decorrelating experience for 96 frames...
+[2023-09-12 13:50:11,078][122838] Decorrelating experience for 96 frames...
+[2023-09-12 13:50:11,081][122805] Decorrelating experience for 96 frames...
+[2023-09-12 13:50:11,218][122802] Decorrelating experience for 96 frames...
+[2023-09-12 13:50:11,218][122854] Decorrelating experience for 96 frames...
+[2023-09-12 13:50:11,226][122804] Decorrelating experience for 96 frames...
+[2023-09-12 13:50:11,362][122803] Decorrelating experience for 96 frames...
+[2023-09-12 13:50:11,385][122872] Decorrelating experience for 64 frames...
+[2023-09-12 13:50:11,793][122872] Decorrelating experience for 96 frames...
+[2023-09-12 13:50:12,506][122669] Signal inference workers to stop experience collection...
+[2023-09-12 13:50:12,515][122801] InferenceWorker_p0-w0: stopping experience collection
+[2023-09-12 13:50:16,545][122669] Signal inference workers to resume experience collection...
+[2023-09-12 13:50:16,546][122801] InferenceWorker_p0-w0: resuming experience collection
+[2023-09-12 13:50:20,179][122801] Updated weights for policy 0, policy_version 10 (0.0375)
+[2023-09-12 13:50:23,796][122801] Updated weights for policy 0, policy_version 20 (0.0010)
+[2023-09-12 13:50:26,298][122669] Saving new best policy, reward=4.557!
+[2023-09-12 13:50:27,374][122801] Updated weights for policy 0, policy_version 30 (0.0009)
+[2023-09-12 13:50:30,961][122801] Updated weights for policy 0, policy_version 40 (0.0008)
+[2023-09-12 13:50:34,564][122801] Updated weights for policy 0, policy_version 50 (0.0009)
+[2023-09-12 13:50:38,125][122801] Updated weights for policy 0, policy_version 60 (0.0009)
+[2023-09-12 13:50:41,618][122801] Updated weights for policy 0, policy_version 70 (0.0008)
+[2023-09-12 13:50:45,242][122801] Updated weights for policy 0, policy_version 80 (0.0007)
+[2023-09-12 13:50:48,864][122801] Updated weights for policy 0, policy_version 90 (0.0008)
+[2023-09-12 13:50:52,436][122801] Updated weights for policy 0, policy_version 100 (0.0009)
+[2023-09-12 13:50:55,901][122801] Updated weights for policy 0, policy_version 110 (0.0008)
+[2023-09-12 13:50:59,479][122801] Updated weights for policy 0, policy_version 120 (0.0009)
+[2023-09-12 13:51:02,984][122801] Updated weights for policy 0, policy_version 130 (0.0008)
+[2023-09-12 13:51:06,588][122801] Updated weights for policy 0, policy_version 140 (0.0008)
+[2023-09-12 13:51:10,071][122801] Updated weights for policy 0, policy_version 150 (0.0008)
+[2023-09-12 13:51:13,647][122801] Updated weights for policy 0, policy_version 160 (0.0008)
+[2023-09-12 13:51:17,251][122801] Updated weights for policy 0, policy_version 170 (0.0008)
+[2023-09-12 13:51:20,775][122801] Updated weights for policy 0, policy_version 180 (0.0008)
+[2023-09-12 13:51:24,366][122801] Updated weights for policy 0, policy_version 190 (0.0009)
+[2023-09-12 13:51:27,870][122801] Updated weights for policy 0, policy_version 200 (0.0009)
+[2023-09-12 13:51:31,409][122801] Updated weights for policy 0, policy_version 210 (0.0008)
+[2023-09-12 13:51:35,008][122801] Updated weights for policy 0, policy_version 220 (0.0009)
+[2023-09-12 13:51:38,438][122801] Updated weights for policy 0, policy_version 230 (0.0008)
+[2023-09-12 13:51:41,135][122801] Updated weights for policy 0, policy_version 240 (0.0008)
+[2023-09-12 13:51:43,644][122801] Updated weights for policy 0, policy_version 250 (0.0008)
+[2023-09-12 13:51:46,148][122801] Updated weights for policy 0, policy_version 260 (0.0008)
+[2023-09-12 13:51:48,639][122801] Updated weights for policy 0, policy_version 270 (0.0008)
+[2023-09-12 13:51:51,116][122801] Updated weights for policy 0, policy_version 280 (0.0009)
+[2023-09-12 13:51:53,668][122801] Updated weights for policy 0, policy_version 290 (0.0009)
+[2023-09-12 13:51:56,175][122801] Updated weights for policy 0, policy_version 300 (0.0009)
+[2023-09-12 13:51:58,675][122801] Updated weights for policy 0, policy_version 310 (0.0008)
+[2023-09-12 13:52:01,156][122801] Updated weights for policy 0, policy_version 320 (0.0008)
+[2023-09-12 13:52:01,221][122669] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000000320_1310720.pth...
+[2023-09-12 13:52:03,617][122801] Updated weights for policy 0, policy_version 330 (0.0008)
+[2023-09-12 13:52:06,104][122801] Updated weights for policy 0, policy_version 340 (0.0008)
+[2023-09-12 13:52:08,659][122801] Updated weights for policy 0, policy_version 350 (0.0010)
+[2023-09-12 13:52:11,141][122801] Updated weights for policy 0, policy_version 360 (0.0009)
+[2023-09-12 13:52:13,612][122801] Updated weights for policy 0, policy_version 370 (0.0009)
+[2023-09-12 13:52:16,156][122801] Updated weights for policy 0, policy_version 380 (0.0009)
+[2023-09-12 13:52:18,801][122801] Updated weights for policy 0, policy_version 390 (0.0009)
+[2023-09-12 13:52:22,331][122801] Updated weights for policy 0, policy_version 400 (0.0009)
+[2023-09-12 13:52:25,874][122801] Updated weights for policy 0, policy_version 410 (0.0009)
+[2023-09-12 13:52:29,455][122801] Updated weights for policy 0, policy_version 420 (0.0008)
+[2023-09-12 13:52:32,978][122801] Updated weights for policy 0, policy_version 430 (0.0008)
+[2023-09-12 13:52:36,552][122801] Updated weights for policy 0, policy_version 440 (0.0009)
+[2023-09-12 13:52:40,030][122801] Updated weights for policy 0, policy_version 450 (0.0008)
+[2023-09-12 13:52:43,608][122801] Updated weights for policy 0, policy_version 460 (0.0009)
+[2023-09-12 13:52:47,075][122801] Updated weights for policy 0, policy_version 470 (0.0008)
+[2023-09-12 13:52:50,608][122801] Updated weights for policy 0, policy_version 480 (0.0008)
+[2023-09-12 13:52:54,158][122801] Updated weights for policy 0, policy_version 490 (0.0009)
+[2023-09-12 13:52:56,280][122669] Saving new best policy, reward=4.924!
+[2023-09-12 13:52:57,660][122801] Updated weights for policy 0, policy_version 500 (0.0009)
+[2023-09-12 13:53:01,204][122801] Updated weights for policy 0, policy_version 510 (0.0008)
+[2023-09-12 13:53:04,750][122801] Updated weights for policy 0, policy_version 520 (0.0008)
+[2023-09-12 13:53:08,208][122801] Updated weights for policy 0, policy_version 530 (0.0008)
+[2023-09-12 13:53:11,784][122801] Updated weights for policy 0, policy_version 540 (0.0009)
+[2023-09-12 13:53:15,279][122801] Updated weights for policy 0, policy_version 550 (0.0008)
+[2023-09-12 13:53:18,872][122801] Updated weights for policy 0, policy_version 560 (0.0009)
+[2023-09-12 13:53:22,378][122801] Updated weights for policy 0, policy_version 570 (0.0008)
+[2023-09-12 13:53:25,918][122801] Updated weights for policy 0, policy_version 580 (0.0008)
+[2023-09-12 13:53:26,271][122669] Saving new best policy, reward=5.105!
+[2023-09-12 13:53:29,480][122801] Updated weights for policy 0, policy_version 590 (0.0009)
+[2023-09-12 13:53:33,014][122801] Updated weights for policy 0, policy_version 600 (0.0009)
+[2023-09-12 13:53:36,250][122669] Saving new best policy, reward=5.315!
+[2023-09-12 13:53:36,638][122801] Updated weights for policy 0, policy_version 610 (0.0008)
+[2023-09-12 13:53:40,183][122801] Updated weights for policy 0, policy_version 620 (0.0009)
+[2023-09-12 13:53:41,228][122669] Saving new best policy, reward=5.387!
+[2023-09-12 13:53:43,793][122801] Updated weights for policy 0, policy_version 630 (0.0008)
+[2023-09-12 13:53:46,219][122669] Saving new best policy, reward=6.129!
+[2023-09-12 13:53:47,307][122801] Updated weights for policy 0, policy_version 640 (0.0008)
+[2023-09-12 13:53:50,868][122801] Updated weights for policy 0, policy_version 650 (0.0009)
+[2023-09-12 13:53:54,354][122801] Updated weights for policy 0, policy_version 660 (0.0009)
+[2023-09-12 13:53:57,983][122801] Updated weights for policy 0, policy_version 670 (0.0009)
+[2023-09-12 13:54:01,239][122669] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000000679_2781184.pth...
+[2023-09-12 13:54:01,597][122801] Updated weights for policy 0, policy_version 680 (0.0009)
+[2023-09-12 13:54:05,147][122801] Updated weights for policy 0, policy_version 690 (0.0009)
+[2023-09-12 13:54:08,668][122801] Updated weights for policy 0, policy_version 700 (0.0009)
+[2023-09-12 13:54:11,222][122669] Saving new best policy, reward=6.507!
+[2023-09-12 13:54:12,225][122801] Updated weights for policy 0, policy_version 710 (0.0009)
+[2023-09-12 13:54:15,831][122801] Updated weights for policy 0, policy_version 720 (0.0008)
+[2023-09-12 13:54:19,308][122801] Updated weights for policy 0, policy_version 730 (0.0008)
+[2023-09-12 13:54:22,924][122801] Updated weights for policy 0, policy_version 740 (0.0009)
+[2023-09-12 13:54:26,467][122801] Updated weights for policy 0, policy_version 750 (0.0008)
+[2023-09-12 13:54:30,032][122801] Updated weights for policy 0, policy_version 760 (0.0008)
+[2023-09-12 13:54:31,222][122669] Saving new best policy, reward=6.614!
+[2023-09-12 13:54:33,602][122801] Updated weights for policy 0, policy_version 770 (0.0008)
+[2023-09-12 13:54:36,220][122669] Saving new best policy, reward=7.715!
+[2023-09-12 13:54:37,120][122801] Updated weights for policy 0, policy_version 780 (0.0009)
+[2023-09-12 13:54:40,719][122801] Updated weights for policy 0, policy_version 790 (0.0008)
+[2023-09-12 13:54:44,230][122801] Updated weights for policy 0, policy_version 800 (0.0009)
+[2023-09-12 13:54:46,282][122669] Saving new best policy, reward=8.526!
+[2023-09-12 13:54:47,740][122801] Updated weights for policy 0, policy_version 810 (0.0009)
+[2023-09-12 13:54:51,332][122801] Updated weights for policy 0, policy_version 820 (0.0009)
+[2023-09-12 13:54:54,902][122801] Updated weights for policy 0, policy_version 830 (0.0009)
+[2023-09-12 13:54:58,451][122801] Updated weights for policy 0, policy_version 840 (0.0009)
+[2023-09-12 13:55:02,061][122801] Updated weights for policy 0, policy_version 850 (0.0008)
+[2023-09-12 13:55:05,638][122801] Updated weights for policy 0, policy_version 860 (0.0008)
+[2023-09-12 13:55:08,332][122801] Updated weights for policy 0, policy_version 870 (0.0008)
+[2023-09-12 13:55:10,824][122801] Updated weights for policy 0, policy_version 880 (0.0008)
+[2023-09-12 13:55:13,335][122801] Updated weights for policy 0, policy_version 890 (0.0009)
+[2023-09-12 13:55:15,781][122801] Updated weights for policy 0, policy_version 900 (0.0008)
+[2023-09-12 13:55:18,327][122801] Updated weights for policy 0, policy_version 910 (0.0008)
+[2023-09-12 13:55:20,838][122801] Updated weights for policy 0, policy_version 920 (0.0008)
+[2023-09-12 13:55:21,222][122669] Saving new best policy, reward=9.517!
+[2023-09-12 13:55:23,418][122801] Updated weights for policy 0, policy_version 930 (0.0008)
+[2023-09-12 13:55:25,924][122801] Updated weights for policy 0, policy_version 940 (0.0009)
+[2023-09-12 13:55:28,376][122801] Updated weights for policy 0, policy_version 950 (0.0008)
+[2023-09-12 13:55:30,871][122801] Updated weights for policy 0, policy_version 960 (0.0008)
+[2023-09-12 13:55:31,223][122669] Saving new best policy, reward=9.645!
+[2023-09-12 13:55:33,460][122801] Updated weights for policy 0, policy_version 970 (0.0008)
+[2023-09-12 13:55:35,994][122801] Updated weights for policy 0, policy_version 980 (0.0008)
+[2023-09-12 13:55:39,009][122801] Updated weights for policy 0, policy_version 990 (0.0011)
+[2023-09-12 13:55:42,020][122801] Updated weights for policy 0, policy_version 1000 (0.0010)
+[2023-09-12 13:55:44,744][122801] Updated weights for policy 0, policy_version 1010 (0.0010)
+[2023-09-12 13:55:46,288][122669] Saving new best policy, reward=12.388!
+[2023-09-12 13:55:47,331][122801] Updated weights for policy 0, policy_version 1020 (0.0008)
+[2023-09-12 13:55:50,658][122801] Updated weights for policy 0, policy_version 1030 (0.0008)
+[2023-09-12 13:55:54,196][122801] Updated weights for policy 0, policy_version 1040 (0.0008)
+[2023-09-12 13:55:57,611][122801] Updated weights for policy 0, policy_version 1050 (0.0008)
+[2023-09-12 13:56:01,046][122801] Updated weights for policy 0, policy_version 1060 (0.0008)
+[2023-09-12 13:56:01,223][122669] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000001060_4341760.pth...
+[2023-09-12 13:56:01,272][122669] Removing /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000000320_1310720.pth
+[2023-09-12 13:56:04,610][122801] Updated weights for policy 0, policy_version 1070 (0.0008)
+[2023-09-12 13:56:08,150][122801] Updated weights for policy 0, policy_version 1080 (0.0008)
+[2023-09-12 13:56:11,688][122801] Updated weights for policy 0, policy_version 1090 (0.0008)
+[2023-09-12 13:56:15,176][122801] Updated weights for policy 0, policy_version 1100 (0.0008)
+[2023-09-12 13:56:18,703][122801] Updated weights for policy 0, policy_version 1110 (0.0008)
+[2023-09-12 13:56:22,205][122801] Updated weights for policy 0, policy_version 1120 (0.0008)
+[2023-09-12 13:56:25,655][122801] Updated weights for policy 0, policy_version 1130 (0.0008)
+[2023-09-12 13:56:29,193][122801] Updated weights for policy 0, policy_version 1140 (0.0008)
+[2023-09-12 13:56:32,718][122801] Updated weights for policy 0, policy_version 1150 (0.0008)
+[2023-09-12 13:56:36,282][122801] Updated weights for policy 0, policy_version 1160 (0.0008)
+[2023-09-12 13:56:39,741][122801] Updated weights for policy 0, policy_version 1170 (0.0008)
+[2023-09-12 13:56:43,260][122801] Updated weights for policy 0, policy_version 1180 (0.0008)
+[2023-09-12 13:56:46,770][122801] Updated weights for policy 0, policy_version 1190 (0.0008)
+[2023-09-12 13:56:50,235][122801] Updated weights for policy 0, policy_version 1200 (0.0008)
+[2023-09-12 13:56:53,812][122801] Updated weights for policy 0, policy_version 1210 (0.0008)
+[2023-09-12 13:56:57,404][122801] Updated weights for policy 0, policy_version 1220 (0.0008)
+[2023-09-12 13:57:00,926][122801] Updated weights for policy 0, policy_version 1230 (0.0009)
+[2023-09-12 13:57:04,472][122801] Updated weights for policy 0, policy_version 1240 (0.0008)
+[2023-09-12 13:57:07,978][122801] Updated weights for policy 0, policy_version 1250 (0.0008)
+[2023-09-12 13:57:11,484][122801] Updated weights for policy 0, policy_version 1260 (0.0008)
+[2023-09-12 13:57:14,980][122801] Updated weights for policy 0, policy_version 1270 (0.0008)
+[2023-09-12 13:57:18,529][122801] Updated weights for policy 0, policy_version 1280 (0.0008)
+[2023-09-12 13:57:22,070][122801] Updated weights for policy 0, policy_version 1290 (0.0008)
+[2023-09-12 13:57:25,561][122801] Updated weights for policy 0, policy_version 1300 (0.0009)
+[2023-09-12 13:57:28,980][122801] Updated weights for policy 0, policy_version 1310 (0.0008)
+[2023-09-12 13:57:32,335][122801] Updated weights for policy 0, policy_version 1320 (0.0009)
+[2023-09-12 13:57:35,885][122801] Updated weights for policy 0, policy_version 1330 (0.0008)
+[2023-09-12 13:57:39,386][122801] Updated weights for policy 0, policy_version 1340 (0.0008)
+[2023-09-12 13:57:42,889][122801] Updated weights for policy 0, policy_version 1350 (0.0008)
+[2023-09-12 13:57:46,371][122801] Updated weights for policy 0, policy_version 1360 (0.0008)
+[2023-09-12 13:57:49,822][122801] Updated weights for policy 0, policy_version 1370 (0.0008)
+[2023-09-12 13:57:53,382][122801] Updated weights for policy 0, policy_version 1380 (0.0008)
+[2023-09-12 13:57:56,938][122801] Updated weights for policy 0, policy_version 1390 (0.0008)
+[2023-09-12 13:58:00,393][122801] Updated weights for policy 0, policy_version 1400 (0.0008)
+[2023-09-12 13:58:01,223][122669] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000001402_5742592.pth...
+[2023-09-12 13:58:01,273][122669] Removing /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000000679_2781184.pth
+[2023-09-12 13:58:03,922][122801] Updated weights for policy 0, policy_version 1410 (0.0008)
+[2023-09-12 13:58:07,415][122801] Updated weights for policy 0, policy_version 1420 (0.0008)
+[2023-09-12 13:58:10,902][122801] Updated weights for policy 0, policy_version 1430 (0.0008)
+[2023-09-12 13:58:14,451][122801] Updated weights for policy 0, policy_version 1440 (0.0008)
+[2023-09-12 13:58:17,972][122801] Updated weights for policy 0, policy_version 1450 (0.0008)
+[2023-09-12 13:58:21,602][122801] Updated weights for policy 0, policy_version 1460 (0.0009)
+[2023-09-12 13:58:25,160][122801] Updated weights for policy 0, policy_version 1470 (0.0008)
+[2023-09-12 13:58:28,662][122801] Updated weights for policy 0, policy_version 1480 (0.0008)
+[2023-09-12 13:58:32,189][122801] Updated weights for policy 0, policy_version 1490 (0.0009)
+[2023-09-12 13:58:35,542][122801] Updated weights for policy 0, policy_version 1500 (0.0008)
+[2023-09-12 13:58:38,007][122801] Updated weights for policy 0, policy_version 1510 (0.0008)
+[2023-09-12 13:58:40,512][122801] Updated weights for policy 0, policy_version 1520 (0.0008)
+[2023-09-12 13:58:42,920][122801] Updated weights for policy 0, policy_version 1530 (0.0008)
+[2023-09-12 13:58:45,421][122801] Updated weights for policy 0, policy_version 1540 (0.0008)
+[2023-09-12 13:58:47,885][122801] Updated weights for policy 0, policy_version 1550 (0.0008)
+[2023-09-12 13:58:50,308][122801] Updated weights for policy 0, policy_version 1560 (0.0009)
+[2023-09-12 13:58:52,793][122801] Updated weights for policy 0, policy_version 1570 (0.0008)
+[2023-09-12 13:58:55,262][122801] Updated weights for policy 0, policy_version 1580 (0.0008)
+[2023-09-12 13:58:57,753][122801] Updated weights for policy 0, policy_version 1590 (0.0008)
+[2023-09-12 13:59:00,249][122801] Updated weights for policy 0, policy_version 1600 (0.0008)
+[2023-09-12 13:59:02,739][122801] Updated weights for policy 0, policy_version 1610 (0.0008)
+[2023-09-12 13:59:05,145][122801] Updated weights for policy 0, policy_version 1620 (0.0008)
+[2023-09-12 13:59:07,614][122801] Updated weights for policy 0, policy_version 1630 (0.0008)
+[2023-09-12 13:59:10,055][122801] Updated weights for policy 0, policy_version 1640 (0.0009)
+[2023-09-12 13:59:12,487][122801] Updated weights for policy 0, policy_version 1650 (0.0009)
+[2023-09-12 13:59:14,915][122801] Updated weights for policy 0, policy_version 1660 (0.0008)
+[2023-09-12 13:59:17,393][122801] Updated weights for policy 0, policy_version 1670 (0.0008)
+[2023-09-12 13:59:19,842][122801] Updated weights for policy 0, policy_version 1680 (0.0008)
+[2023-09-12 13:59:23,360][122801] Updated weights for policy 0, policy_version 1690 (0.0009)
+[2023-09-12 13:59:26,888][122801] Updated weights for policy 0, policy_version 1700 (0.0008)
+[2023-09-12 13:59:30,359][122801] Updated weights for policy 0, policy_version 1710 (0.0010)
+[2023-09-12 13:59:33,894][122801] Updated weights for policy 0, policy_version 1720 (0.0008)
+[2023-09-12 13:59:37,426][122801] Updated weights for policy 0, policy_version 1730 (0.0008)
+[2023-09-12 13:59:40,927][122801] Updated weights for policy 0, policy_version 1740 (0.0008)
+[2023-09-12 13:59:44,445][122801] Updated weights for policy 0, policy_version 1750 (0.0008)
+[2023-09-12 13:59:47,912][122801] Updated weights for policy 0, policy_version 1760 (0.0008)
+[2023-09-12 13:59:51,393][122801] Updated weights for policy 0, policy_version 1770 (0.0009)
+[2023-09-12 13:59:54,924][122801] Updated weights for policy 0, policy_version 1780 (0.0008)
+[2023-09-12 13:59:58,375][122801] Updated weights for policy 0, policy_version 1790 (0.0008)
+[2023-09-12 14:00:01,224][122669] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000001798_7364608.pth...
+[2023-09-12 14:00:01,274][122669] Removing /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000001060_4341760.pth
+[2023-09-12 14:00:01,923][122801] Updated weights for policy 0, policy_version 1800 (0.0008)
+[2023-09-12 14:00:05,513][122801] Updated weights for policy 0, policy_version 1810 (0.0008)
+[2023-09-12 14:00:08,982][122801] Updated weights for policy 0, policy_version 1820 (0.0008)
+[2023-09-12 14:00:12,469][122801] Updated weights for policy 0, policy_version 1830 (0.0009)
+[2023-09-12 14:00:16,029][122801] Updated weights for policy 0, policy_version 1840 (0.0009)
+[2023-09-12 14:00:19,549][122801] Updated weights for policy 0, policy_version 1850 (0.0008)
+[2023-09-12 14:00:23,081][122801] Updated weights for policy 0, policy_version 1860 (0.0008)
+[2023-09-12 14:00:26,628][122801] Updated weights for policy 0, policy_version 1870 (0.0009)
+[2023-09-12 14:00:30,031][122801] Updated weights for policy 0, policy_version 1880 (0.0009)
+[2023-09-12 14:00:33,483][122801] Updated weights for policy 0, policy_version 1890 (0.0008)
+[2023-09-12 14:00:37,012][122801] Updated weights for policy 0, policy_version 1900 (0.0008)
+[2023-09-12 14:00:40,463][122801] Updated weights for policy 0, policy_version 1910 (0.0010)
+[2023-09-12 14:00:44,008][122801] Updated weights for policy 0, policy_version 1920 (0.0008)
+[2023-09-12 14:00:47,561][122801] Updated weights for policy 0, policy_version 1930 (0.0008)
+[2023-09-12 14:00:51,080][122801] Updated weights for policy 0, policy_version 1940 (0.0008)
+[2023-09-12 14:00:54,609][122801] Updated weights for policy 0, policy_version 1950 (0.0008)
+[2023-09-12 14:00:58,084][122801] Updated weights for policy 0, policy_version 1960 (0.0008)
+[2023-09-12 14:01:01,565][122801] Updated weights for policy 0, policy_version 1970 (0.0008)
+[2023-09-12 14:01:05,123][122801] Updated weights for policy 0, policy_version 1980 (0.0010)
+[2023-09-12 14:01:08,610][122801] Updated weights for policy 0, policy_version 1990 (0.0008)
+[2023-09-12 14:01:12,190][122801] Updated weights for policy 0, policy_version 2000 (0.0008)
+[2023-09-12 14:01:15,764][122801] Updated weights for policy 0, policy_version 2010 (0.0008)
+[2023-09-12 14:01:19,242][122801] Updated weights for policy 0, policy_version 2020 (0.0008)
+[2023-09-12 14:01:22,781][122801] Updated weights for policy 0, policy_version 2030 (0.0008)
+[2023-09-12 14:01:26,304][122801] Updated weights for policy 0, policy_version 2040 (0.0008)
+[2023-09-12 14:01:29,822][122801] Updated weights for policy 0, policy_version 2050 (0.0008)
+[2023-09-12 14:01:33,433][122801] Updated weights for policy 0, policy_version 2060 (0.0008)
+[2023-09-12 14:01:36,985][122801] Updated weights for policy 0, policy_version 2070 (0.0009)
+[2023-09-12 14:01:40,542][122801] Updated weights for policy 0, policy_version 2080 (0.0008)
+[2023-09-12 14:01:43,996][122801] Updated weights for policy 0, policy_version 2090 (0.0009)
+[2023-09-12 14:01:47,547][122801] Updated weights for policy 0, policy_version 2100 (0.0008)
+[2023-09-12 14:01:51,096][122801] Updated weights for policy 0, policy_version 2110 (0.0008)
+[2023-09-12 14:01:54,668][122801] Updated weights for policy 0, policy_version 2120 (0.0008)
+[2023-09-12 14:01:58,165][122801] Updated weights for policy 0, policy_version 2130 (0.0008)
+[2023-09-12 14:02:01,223][122669] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000002138_8757248.pth...
+[2023-09-12 14:02:01,275][122669] Removing /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000001402_5742592.pth
+[2023-09-12 14:02:01,691][122801] Updated weights for policy 0, policy_version 2140 (0.0008)
+[2023-09-12 14:02:05,226][122801] Updated weights for policy 0, policy_version 2150 (0.0008)
+[2023-09-12 14:02:06,252][122669] Saving new best policy, reward=12.789!
+[2023-09-12 14:02:08,123][122801] Updated weights for policy 0, policy_version 2160 (0.0008)
+[2023-09-12 14:02:10,787][122801] Updated weights for policy 0, policy_version 2170 (0.0009)
+[2023-09-12 14:02:13,260][122801] Updated weights for policy 0, policy_version 2180 (0.0008)
+[2023-09-12 14:02:15,784][122801] Updated weights for policy 0, policy_version 2190 (0.0009)
+[2023-09-12 14:02:18,397][122801] Updated weights for policy 0, policy_version 2200 (0.0009)
+[2023-09-12 14:02:20,998][122801] Updated weights for policy 0, policy_version 2210 (0.0008)
+[2023-09-12 14:02:23,518][122801] Updated weights for policy 0, policy_version 2220 (0.0008)
+[2023-09-12 14:02:26,013][122801] Updated weights for policy 0, policy_version 2230 (0.0009)
+[2023-09-12 14:02:28,608][122801] Updated weights for policy 0, policy_version 2240 (0.0009)
+[2023-09-12 14:02:31,184][122801] Updated weights for policy 0, policy_version 2250 (0.0009)
+[2023-09-12 14:02:33,913][122801] Updated weights for policy 0, policy_version 2260 (0.0009)
+[2023-09-12 14:02:36,487][122801] Updated weights for policy 0, policy_version 2270 (0.0009)
+[2023-09-12 14:02:38,967][122801] Updated weights for policy 0, policy_version 2280 (0.0009)
+[2023-09-12 14:02:41,534][122801] Updated weights for policy 0, policy_version 2290 (0.0009)
+[2023-09-12 14:02:44,463][122801] Updated weights for policy 0, policy_version 2300 (0.0008)
+[2023-09-12 14:02:48,137][122801] Updated weights for policy 0, policy_version 2310 (0.0009)
+[2023-09-12 14:02:51,597][122801] Updated weights for policy 0, policy_version 2320 (0.0009)
+[2023-09-12 14:02:55,199][122801] Updated weights for policy 0, policy_version 2330 (0.0008)
+[2023-09-12 14:02:58,734][122801] Updated weights for policy 0, policy_version 2340 (0.0008)
+[2023-09-12 14:03:02,473][122801] Updated weights for policy 0, policy_version 2350 (0.0009)
+[2023-09-12 14:03:06,086][122801] Updated weights for policy 0, policy_version 2360 (0.0010)
+[2023-09-12 14:03:09,613][122801] Updated weights for policy 0, policy_version 2370 (0.0009)
+[2023-09-12 14:03:13,353][122801] Updated weights for policy 0, policy_version 2380 (0.0009)
+[2023-09-12 14:03:16,829][122801] Updated weights for policy 0, policy_version 2390 (0.0008)
+[2023-09-12 14:03:20,562][122801] Updated weights for policy 0, policy_version 2400 (0.0008)
+[2023-09-12 14:03:24,116][122801] Updated weights for policy 0, policy_version 2410 (0.0008)
+[2023-09-12 14:03:27,734][122801] Updated weights for policy 0, policy_version 2420 (0.0008)
+[2023-09-12 14:03:31,252][122801] Updated weights for policy 0, policy_version 2430 (0.0008)
+[2023-09-12 14:03:34,867][122801] Updated weights for policy 0, policy_version 2440 (0.0008)
+[2023-09-12 14:03:35,907][122669] Stopping Batcher_0...
+[2023-09-12 14:03:35,907][122669] Loop batcher_evt_loop terminating...
+[2023-09-12 14:03:35,907][122669] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth...
+[2023-09-12 14:03:35,920][122805] Stopping RolloutWorker_w4...
+[2023-09-12 14:03:35,921][122805] Loop rollout_proc4_evt_loop terminating...
+[2023-09-12 14:03:35,922][122804] Stopping RolloutWorker_w3...
+[2023-09-12 14:03:35,922][122804] Loop rollout_proc3_evt_loop terminating...
+[2023-09-12 14:03:35,923][122803] Stopping RolloutWorker_w1...
+[2023-09-12 14:03:35,923][122802] Stopping RolloutWorker_w0...
+[2023-09-12 14:03:35,923][122854] Stopping RolloutWorker_w6...
+[2023-09-12 14:03:35,923][122803] Loop rollout_proc1_evt_loop terminating...
+[2023-09-12 14:03:35,923][122854] Loop rollout_proc6_evt_loop terminating...
+[2023-09-12 14:03:35,923][122802] Loop rollout_proc0_evt_loop terminating...
+[2023-09-12 14:03:35,924][122837] Stopping RolloutWorker_w5...
+[2023-09-12 14:03:35,924][122837] Loop rollout_proc5_evt_loop terminating...
+[2023-09-12 14:03:35,926][122838] Stopping RolloutWorker_w2...
+[2023-09-12 14:03:35,926][122838] Loop rollout_proc2_evt_loop terminating...
+[2023-09-12 14:03:35,927][122872] Stopping RolloutWorker_w7...
+[2023-09-12 14:03:35,927][122872] Loop rollout_proc7_evt_loop terminating...
+[2023-09-12 14:03:35,931][122801] Weights refcount: 2 0
+[2023-09-12 14:03:35,933][122801] Stopping InferenceWorker_p0-w0...
+[2023-09-12 14:03:35,933][122801] Loop inference_proc0-0_evt_loop terminating...
+[2023-09-12 14:03:35,962][122669] Removing /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000001798_7364608.pth
+[2023-09-12 14:03:35,970][122669] Saving /home/cogstack/Documents/optuna/environments/sample_factory/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth...
+[2023-09-12 14:03:36,035][122669] Stopping LearnerWorker_p0...
+[2023-09-12 14:03:36,035][122669] Loop learner_proc0_evt_loop terminating...