Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1716845044.wallenstein

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:675b848754089419efcb77f6bee70a13962780b31510a6ce78dc2250f304dc8f
+size 108302

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 12.63 +/- 5.37
+      value: 11.14 +/- 4.80
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000001779_7286784_reward_25.925.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff07400a3c664f9d50e2c4fcb4e0e73f8ec8fa0ee27ceaf547d8678f1b78d1d
+size 34929243

checkpoint_p0/checkpoint_000001779_7286784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51623b71960451c1fc678c186a6cf68819cbbb290018bd5a4058234b5a3a0026
+size 34929669

checkpoint_p0/checkpoint_000001955_8007680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed26c604f0d18fb4176e513a7cb452d06bd0df83e5791f1c53f6b9203f6dddb
+size 34929669

config.json

@@ -16,7 +16,7 @@
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
   "num_workers": 8,
-  "num_envs_per_worker": 4,
+  "num_envs_per_worker": 8,
   "batch_size": 1024,
   "num_batches_per_epoch": 1,
   "num_epochs": 1,
@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 4000000,
+  "train_for_env_steps": 8000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf2fc33560e2134cac2811ddcf485e499f699112159fdc74a322afb1f7cd002
-size 24006025
+oid sha256:a743a18b22b4d2c0827a27a35b96ef5dc116ec03497abba49cacaf2f3048315a
+size 21230418

sf_log.txt

@@ -781,3 +781,746 @@ main_loop: 204.3645
 [2024-05-27 23:20:02,394][1934158] Avg episode rewards: #0: 30.430, true rewards: #0: 12.630
 [2024-05-27 23:20:02,394][1934158] Avg episode reward: 30.430, avg true_objective: 12.630
 [2024-05-27 23:20:17,697][1934158] Replay video saved to /media/fast/code/learning/train_dir/default_experiment/replay.mp4!
+[2024-05-27 23:20:23,037][1934158] The model has been pushed to https://huggingface.co/DavidPL1/rl_course_vizdoom_health_gathering_supreme
+[2024-05-27 23:24:06,850][1944769] Saving configuration to /media/fast/code/learning/train_dir/default_experiment/config.json...
+[2024-05-27 23:24:06,851][1944769] Rollout worker 0 uses device cpu
+[2024-05-27 23:24:06,851][1944769] Rollout worker 1 uses device cpu
+[2024-05-27 23:24:06,851][1944769] Rollout worker 2 uses device cpu
+[2024-05-27 23:24:06,851][1944769] Rollout worker 3 uses device cpu
+[2024-05-27 23:24:06,851][1944769] Rollout worker 4 uses device cpu
+[2024-05-27 23:24:06,851][1944769] Rollout worker 5 uses device cpu
+[2024-05-27 23:24:06,851][1944769] Rollout worker 6 uses device cpu
+[2024-05-27 23:24:06,851][1944769] Rollout worker 7 uses device cpu
+[2024-05-27 23:24:06,885][1944769] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:24:06,885][1944769] InferenceWorker_p0-w0: min num requests: 2
+[2024-05-27 23:24:06,898][1944769] Starting all processes...
+[2024-05-27 23:24:06,898][1944769] Starting process learner_proc0
+[2024-05-27 23:24:08,668][1944769] Starting all processes...
+[2024-05-27 23:24:08,671][1944769] Starting process inference_proc0-0
+[2024-05-27 23:24:08,671][1944769] Starting process rollout_proc0
+[2024-05-27 23:24:08,672][1944769] Starting process rollout_proc4
+[2024-05-27 23:24:08,672][1944894] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:24:08,672][1944894] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-05-27 23:24:08,671][1944769] Starting process rollout_proc2
+[2024-05-27 23:24:08,672][1944769] Starting process rollout_proc3
+[2024-05-27 23:24:08,671][1944769] Starting process rollout_proc1
+[2024-05-27 23:24:08,672][1944769] Starting process rollout_proc5
+[2024-05-27 23:24:08,672][1944769] Starting process rollout_proc6
+[2024-05-27 23:24:08,682][1944894] Num visible devices: 1
+[2024-05-27 23:24:08,672][1944769] Starting process rollout_proc7
+[2024-05-27 23:24:08,707][1944894] Starting seed is not provided
+[2024-05-27 23:24:08,707][1944894] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:24:08,707][1944894] Initializing actor-critic model on device cuda:0
+[2024-05-27 23:24:08,708][1944894] RunningMeanStd input shape: (3, 72, 128)
+[2024-05-27 23:24:08,708][1944894] RunningMeanStd input shape: (1,)
+[2024-05-27 23:24:08,721][1944894] ConvEncoder: input_channels=3
+[2024-05-27 23:24:08,826][1944894] Conv encoder output size: 512
+[2024-05-27 23:24:08,827][1944894] Policy head output size: 512
+[2024-05-27 23:24:08,840][1944894] Created Actor Critic model with architecture:
+[2024-05-27 23:24:08,840][1944894] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2024-05-27 23:24:08,935][1944894] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-05-27 23:24:09,730][1944894] Loading state from checkpoint /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-05-27 23:24:09,767][1944894] Loading model from checkpoint
+[2024-05-27 23:24:09,769][1944894] Loaded experiment state at self.train_step=978, self.env_steps=4005888
+[2024-05-27 23:24:09,769][1944894] Initialized policy 0 weights for model version 978
+[2024-05-27 23:24:09,771][1944894] LearnerWorker_p0 finished initialization!
+[2024-05-27 23:24:09,771][1944894] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:24:10,329][1944942] Worker 3 uses CPU cores [6, 7]
+[2024-05-27 23:24:10,513][1944941] Worker 2 uses CPU cores [4, 5]
+[2024-05-27 23:24:10,610][1944938] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:24:10,610][1944938] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-05-27 23:24:10,620][1944938] Num visible devices: 1
+[2024-05-27 23:24:10,718][1944940] Worker 4 uses CPU cores [8, 9]
+[2024-05-27 23:24:10,777][1944959] Worker 5 uses CPU cores [10, 11]
+[2024-05-27 23:24:10,791][1944960] Worker 6 uses CPU cores [12, 13]
+[2024-05-27 23:24:10,810][1944939] Worker 0 uses CPU cores [0, 1]
+[2024-05-27 23:24:10,825][1944769] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-05-27 23:24:10,826][1944943] Worker 1 uses CPU cores [2, 3]
+[2024-05-27 23:24:10,829][1944961] Worker 7 uses CPU cores [14, 15]
+[2024-05-27 23:24:10,925][1944938] RunningMeanStd input shape: (3, 72, 128)
+[2024-05-27 23:24:10,926][1944938] RunningMeanStd input shape: (1,)
+[2024-05-27 23:24:10,932][1944938] ConvEncoder: input_channels=3
+[2024-05-27 23:24:10,989][1944938] Conv encoder output size: 512
+[2024-05-27 23:24:10,989][1944938] Policy head output size: 512
+[2024-05-27 23:24:11,020][1944769] Inference worker 0-0 is ready!
+[2024-05-27 23:24:11,020][1944769] All inference workers are ready! Signal rollout workers to start!
+[2024-05-27 23:24:11,031][1944941] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:24:11,033][1944960] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:24:11,035][1944959] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:24:11,036][1944940] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:24:11,036][1944943] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:24:11,036][1944939] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:24:11,036][1944961] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:24:11,036][1944942] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:24:11,635][1944940] Decorrelating experience for 0 frames...
+[2024-05-27 23:24:11,716][1944959] Decorrelating experience for 0 frames...
+[2024-05-27 23:24:11,795][1944943] Decorrelating experience for 0 frames...
+[2024-05-27 23:24:11,796][1944941] Decorrelating experience for 0 frames...
+[2024-05-27 23:24:11,798][1944960] Decorrelating experience for 0 frames...
+[2024-05-27 23:24:12,598][1944940] Decorrelating experience for 32 frames...
+[2024-05-27 23:24:12,600][1944959] Decorrelating experience for 32 frames...
+[2024-05-27 23:24:12,679][1944942] Decorrelating experience for 0 frames...
+[2024-05-27 23:24:12,679][1944961] Decorrelating experience for 0 frames...
+[2024-05-27 23:24:12,681][1944960] Decorrelating experience for 32 frames...
+[2024-05-27 23:24:12,997][1944941] Decorrelating experience for 32 frames...
+[2024-05-27 23:24:13,512][1944940] Decorrelating experience for 64 frames...
+[2024-05-27 23:24:13,592][1944942] Decorrelating experience for 32 frames...
+[2024-05-27 23:24:13,594][1944943] Decorrelating experience for 32 frames...
+[2024-05-27 23:24:13,594][1944959] Decorrelating experience for 64 frames...
+[2024-05-27 23:24:13,997][1944939] Decorrelating experience for 0 frames...
+[2024-05-27 23:24:14,001][1944960] Decorrelating experience for 64 frames...
+[2024-05-27 23:24:14,080][1944941] Decorrelating experience for 64 frames...
+[2024-05-27 23:24:14,331][1944769] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-05-27 23:24:14,411][1944942] Decorrelating experience for 64 frames...
+[2024-05-27 23:24:14,490][1944959] Decorrelating experience for 96 frames...
+[2024-05-27 23:24:14,729][1944940] Decorrelating experience for 96 frames...
+[2024-05-27 23:24:14,811][1944939] Decorrelating experience for 32 frames...
+[2024-05-27 23:24:14,889][1944943] Decorrelating experience for 64 frames...
+[2024-05-27 23:24:15,357][1944942] Decorrelating experience for 96 frames...
+[2024-05-27 23:24:15,358][1944960] Decorrelating experience for 96 frames...
+[2024-05-27 23:24:15,359][1944959] Decorrelating experience for 128 frames...
+[2024-05-27 23:24:15,681][1944961] Decorrelating experience for 32 frames...
+[2024-05-27 23:24:15,765][1944940] Decorrelating experience for 128 frames...
+[2024-05-27 23:24:15,843][1944943] Decorrelating experience for 96 frames...
+[2024-05-27 23:24:16,252][1944939] Decorrelating experience for 64 frames...
+[2024-05-27 23:24:16,419][1944959] Decorrelating experience for 160 frames...
+[2024-05-27 23:24:16,419][1944960] Decorrelating experience for 128 frames...
+[2024-05-27 23:24:16,674][1944942] Decorrelating experience for 128 frames...
+[2024-05-27 23:24:16,759][1944941] Decorrelating experience for 96 frames...
+[2024-05-27 23:24:16,760][1944961] Decorrelating experience for 64 frames...
+[2024-05-27 23:24:17,276][1944939] Decorrelating experience for 96 frames...
+[2024-05-27 23:24:17,359][1944940] Decorrelating experience for 160 frames...
+[2024-05-27 23:24:17,592][1944960] Decorrelating experience for 160 frames...
+[2024-05-27 23:24:17,676][1944959] Decorrelating experience for 192 frames...
+[2024-05-27 23:24:17,764][1944961] Decorrelating experience for 96 frames...
+[2024-05-27 23:24:17,764][1944943] Decorrelating experience for 128 frames...
+[2024-05-27 23:24:18,096][1944939] Decorrelating experience for 128 frames...
+[2024-05-27 23:24:18,410][1944940] Decorrelating experience for 192 frames...
+[2024-05-27 23:24:18,572][1944960] Decorrelating experience for 192 frames...
+[2024-05-27 23:24:18,648][1944959] Decorrelating experience for 224 frames...
+[2024-05-27 23:24:18,649][1944941] Decorrelating experience for 128 frames...
+[2024-05-27 23:24:18,649][1944961] Decorrelating experience for 128 frames...
+[2024-05-27 23:24:19,132][1944942] Decorrelating experience for 160 frames...
+[2024-05-27 23:24:19,288][1944939] Decorrelating experience for 160 frames...
+[2024-05-27 23:24:19,291][1944960] Decorrelating experience for 224 frames...
+[2024-05-27 23:24:19,331][1944769] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-05-27 23:24:19,332][1944769] Avg episode reward: [(0, '0.640')]
+[2024-05-27 23:24:19,460][1944940] Decorrelating experience for 224 frames...
+[2024-05-27 23:24:19,795][1944943] Decorrelating experience for 160 frames...
+[2024-05-27 23:24:19,872][1944961] Decorrelating experience for 160 frames...
+[2024-05-27 23:24:20,033][1944942] Decorrelating experience for 192 frames...
+[2024-05-27 23:24:20,147][1944894] Signal inference workers to stop experience collection...
+[2024-05-27 23:24:20,150][1944938] InferenceWorker_p0-w0: stopping experience collection
+[2024-05-27 23:24:20,353][1944943] Decorrelating experience for 192 frames...
+[2024-05-27 23:24:20,357][1944939] Decorrelating experience for 192 frames...
+[2024-05-27 23:24:20,437][1944961] Decorrelating experience for 192 frames...
+[2024-05-27 23:24:20,795][1944942] Decorrelating experience for 224 frames...
+[2024-05-27 23:24:20,961][1944894] Signal inference workers to resume experience collection...
+[2024-05-27 23:24:20,962][1944938] InferenceWorker_p0-w0: resuming experience collection
+[2024-05-27 23:24:20,962][1944939] Decorrelating experience for 224 frames...
+[2024-05-27 23:24:21,051][1944961] Decorrelating experience for 224 frames...
+[2024-05-27 23:24:21,251][1944941] Decorrelating experience for 160 frames...
+[2024-05-27 23:24:21,685][1944943] Decorrelating experience for 224 frames...
+[2024-05-27 23:24:21,768][1944941] Decorrelating experience for 192 frames...
+[2024-05-27 23:24:22,199][1944941] Decorrelating experience for 224 frames...
+[2024-05-27 23:24:22,633][1944938] Updated weights for policy 0, policy_version 988 (0.0142)
+[2024-05-27 23:24:23,973][1944938] Updated weights for policy 0, policy_version 998 (0.0009)
+[2024-05-27 23:24:24,332][1944769] Fps is (10 sec: 9011.1, 60 sec: 6671.7, 300 sec: 6671.7). Total num frames: 4096000. Throughput: 0: 1034.8. Samples: 13976. Policy #0 lag: (min: 0.0, avg: 1.3, max: 4.0)
+[2024-05-27 23:24:24,332][1944769] Avg episode reward: [(0, '14.106')]
+[2024-05-27 23:24:25,343][1944938] Updated weights for policy 0, policy_version 1008 (0.0008)
+[2024-05-27 23:24:26,541][1944938] Updated weights for policy 0, policy_version 1018 (0.0008)
+[2024-05-27 23:24:26,882][1944769] Heartbeat connected on Batcher_0
+[2024-05-27 23:24:26,883][1944769] Heartbeat connected on LearnerWorker_p0
+[2024-05-27 23:24:26,889][1944769] Heartbeat connected on RolloutWorker_w0
+[2024-05-27 23:24:26,890][1944769] Heartbeat connected on InferenceWorker_p0-w0
+[2024-05-27 23:24:26,892][1944769] Heartbeat connected on RolloutWorker_w3
+[2024-05-27 23:24:26,893][1944769] Heartbeat connected on RolloutWorker_w1
+[2024-05-27 23:24:26,895][1944769] Heartbeat connected on RolloutWorker_w5
+[2024-05-27 23:24:26,896][1944769] Heartbeat connected on RolloutWorker_w2
+[2024-05-27 23:24:26,901][1944769] Heartbeat connected on RolloutWorker_w4
+[2024-05-27 23:24:26,902][1944769] Heartbeat connected on RolloutWorker_w7
+[2024-05-27 23:24:26,902][1944769] Heartbeat connected on RolloutWorker_w6
+[2024-05-27 23:24:27,857][1944938] Updated weights for policy 0, policy_version 1028 (0.0009)
+[2024-05-27 23:24:29,131][1944938] Updated weights for policy 0, policy_version 1038 (0.0008)
+[2024-05-27 23:24:29,331][1944769] Fps is (10 sec: 24985.6, 60 sec: 13501.0, 300 sec: 13501.0). Total num frames: 4255744. Throughput: 0: 3344.3. Samples: 61892. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2024-05-27 23:24:29,332][1944769] Avg episode reward: [(0, '19.936')]
+[2024-05-27 23:24:30,405][1944938] Updated weights for policy 0, policy_version 1048 (0.0008)
+[2024-05-27 23:24:31,658][1944938] Updated weights for policy 0, policy_version 1058 (0.0008)
+[2024-05-27 23:24:32,904][1944938] Updated weights for policy 0, policy_version 1068 (0.0007)
+[2024-05-27 23:24:34,244][1944938] Updated weights for policy 0, policy_version 1078 (0.0007)
+[2024-05-27 23:24:34,331][1944769] Fps is (10 sec: 31949.2, 60 sec: 17425.0, 300 sec: 17425.0). Total num frames: 4415488. Throughput: 0: 3679.0. Samples: 86480. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2024-05-27 23:24:34,332][1944769] Avg episode reward: [(0, '24.717')]
+[2024-05-27 23:24:34,334][1944894] Saving new best policy, reward=24.717!
+[2024-05-27 23:24:35,485][1944938] Updated weights for policy 0, policy_version 1088 (0.0008)
+[2024-05-27 23:24:37,044][1944938] Updated weights for policy 0, policy_version 1098 (0.0014)
+[2024-05-27 23:24:38,236][1944938] Updated weights for policy 0, policy_version 1108 (0.0008)
+[2024-05-27 23:24:39,331][1944769] Fps is (10 sec: 31539.0, 60 sec: 19828.7, 300 sec: 19828.7). Total num frames: 4571136. Throughput: 0: 4656.3. Samples: 132736. Policy #0 lag: (min: 0.0, avg: 1.9, max: 3.0)
+[2024-05-27 23:24:39,332][1944769] Avg episode reward: [(0, '24.188')]
+[2024-05-27 23:24:39,508][1944938] Updated weights for policy 0, policy_version 1118 (0.0012)
+[2024-05-27 23:24:40,818][1944938] Updated weights for policy 0, policy_version 1128 (0.0009)
+[2024-05-27 23:24:42,144][1944938] Updated weights for policy 0, policy_version 1138 (0.0008)
+[2024-05-27 23:24:43,414][1944938] Updated weights for policy 0, policy_version 1148 (0.0008)
+[2024-05-27 23:24:44,332][1944769] Fps is (10 sec: 31538.7, 60 sec: 21637.2, 300 sec: 21637.2). Total num frames: 4730880. Throughput: 0: 5386.4. Samples: 180480. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2024-05-27 23:24:44,332][1944769] Avg episode reward: [(0, '23.123')]
+[2024-05-27 23:24:44,683][1944938] Updated weights for policy 0, policy_version 1158 (0.0010)
+[2024-05-27 23:24:45,942][1944938] Updated weights for policy 0, policy_version 1168 (0.0008)
+[2024-05-27 23:24:47,177][1944938] Updated weights for policy 0, policy_version 1178 (0.0007)
+[2024-05-27 23:24:48,496][1944938] Updated weights for policy 0, policy_version 1188 (0.0007)
+[2024-05-27 23:24:49,332][1944769] Fps is (10 sec: 31948.8, 60 sec: 22976.2, 300 sec: 22976.2). Total num frames: 4890624. Throughput: 0: 5315.0. Samples: 204664. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2024-05-27 23:24:49,332][1944769] Avg episode reward: [(0, '21.083')]
+[2024-05-27 23:24:49,810][1944938] Updated weights for policy 0, policy_version 1198 (0.0008)
+[2024-05-27 23:24:51,091][1944938] Updated weights for policy 0, policy_version 1208 (0.0016)
+[2024-05-27 23:24:52,308][1944938] Updated weights for policy 0, policy_version 1218 (0.0009)
+[2024-05-27 23:24:53,558][1944938] Updated weights for policy 0, policy_version 1228 (0.0008)
+[2024-05-27 23:24:54,331][1944769] Fps is (10 sec: 32358.9, 60 sec: 24101.6, 300 sec: 24101.6). Total num frames: 5054464. Throughput: 0: 5811.0. Samples: 252816. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2024-05-27 23:24:54,332][1944769] Avg episode reward: [(0, '21.497')]
+[2024-05-27 23:24:54,819][1944938] Updated weights for policy 0, policy_version 1238 (0.0008)
+[2024-05-27 23:24:56,059][1944938] Updated weights for policy 0, policy_version 1248 (0.0009)
+[2024-05-27 23:24:57,290][1944938] Updated weights for policy 0, policy_version 1258 (0.0008)
+[2024-05-27 23:24:58,543][1944938] Updated weights for policy 0, policy_version 1268 (0.0008)
+[2024-05-27 23:24:59,331][1944769] Fps is (10 sec: 32768.1, 60 sec: 24994.9, 300 sec: 24994.9). Total num frames: 5218304. Throughput: 0: 6715.3. Samples: 302188. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2024-05-27 23:24:59,332][1944769] Avg episode reward: [(0, '23.600')]
+[2024-05-27 23:24:59,798][1944938] Updated weights for policy 0, policy_version 1278 (0.0010)
+[2024-05-27 23:25:01,050][1944938] Updated weights for policy 0, policy_version 1288 (0.0008)
+[2024-05-27 23:25:02,329][1944938] Updated weights for policy 0, policy_version 1298 (0.0008)
+[2024-05-27 23:25:03,696][1944938] Updated weights for policy 0, policy_version 1308 (0.0014)
+[2024-05-27 23:25:04,332][1944769] Fps is (10 sec: 32357.9, 60 sec: 25644.7, 300 sec: 25644.7). Total num frames: 5378048. Throughput: 0: 7255.6. Samples: 326504. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-05-27 23:25:04,332][1944769] Avg episode reward: [(0, '22.440')]
+[2024-05-27 23:25:04,968][1944938] Updated weights for policy 0, policy_version 1318 (0.0008)
+[2024-05-27 23:25:06,188][1944938] Updated weights for policy 0, policy_version 1328 (0.0008)
+[2024-05-27 23:25:07,478][1944938] Updated weights for policy 0, policy_version 1338 (0.0008)
+[2024-05-27 23:25:08,699][1944938] Updated weights for policy 0, policy_version 1348 (0.0008)
+[2024-05-27 23:25:09,333][1944769] Fps is (10 sec: 32354.4, 60 sec: 26252.9, 300 sec: 26252.9). Total num frames: 5541888. Throughput: 0: 8013.2. Samples: 374580. Policy #0 lag: (min: 1.0, avg: 1.3, max: 3.0)
+[2024-05-27 23:25:09,333][1944769] Avg episode reward: [(0, '22.809')]
+[2024-05-27 23:25:09,969][1944938] Updated weights for policy 0, policy_version 1358 (0.0008)
+[2024-05-27 23:25:11,255][1944938] Updated weights for policy 0, policy_version 1368 (0.0018)
+[2024-05-27 23:25:12,552][1944938] Updated weights for policy 0, policy_version 1378 (0.0007)
+[2024-05-27 23:25:13,813][1944938] Updated weights for policy 0, policy_version 1388 (0.0008)
+[2024-05-27 23:25:14,331][1944769] Fps is (10 sec: 32358.9, 60 sec: 28262.4, 300 sec: 26701.9). Total num frames: 5701632. Throughput: 0: 8021.2. Samples: 422848. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2024-05-27 23:25:14,332][1944769] Avg episode reward: [(0, '24.407')]
+[2024-05-27 23:25:15,063][1944938] Updated weights for policy 0, policy_version 1398 (0.0008)
+[2024-05-27 23:25:16,369][1944938] Updated weights for policy 0, policy_version 1408 (0.0013)
+[2024-05-27 23:25:17,782][1944938] Updated weights for policy 0, policy_version 1418 (0.0011)
+[2024-05-27 23:25:19,073][1944938] Updated weights for policy 0, policy_version 1428 (0.0014)
+[2024-05-27 23:25:19,331][1944769] Fps is (10 sec: 31543.1, 60 sec: 30856.5, 300 sec: 27025.0). Total num frames: 5857280. Throughput: 0: 8008.2. Samples: 446848. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2024-05-27 23:25:19,332][1944769] Avg episode reward: [(0, '23.988')]
+[2024-05-27 23:25:20,331][1944938] Updated weights for policy 0, policy_version 1438 (0.0010)
+[2024-05-27 23:25:21,582][1944938] Updated weights for policy 0, policy_version 1448 (0.0007)
+[2024-05-27 23:25:22,872][1944938] Updated weights for policy 0, policy_version 1458 (0.0009)
+[2024-05-27 23:25:24,142][1944938] Updated weights for policy 0, policy_version 1468 (0.0013)
+[2024-05-27 23:25:24,331][1944769] Fps is (10 sec: 31539.1, 60 sec: 32017.1, 300 sec: 27360.0). Total num frames: 6017024. Throughput: 0: 8028.4. Samples: 494012. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2024-05-27 23:25:24,332][1944769] Avg episode reward: [(0, '24.169')]
+[2024-05-27 23:25:25,527][1944938] Updated weights for policy 0, policy_version 1478 (0.0008)
+[2024-05-27 23:25:26,732][1944938] Updated weights for policy 0, policy_version 1488 (0.0009)
+[2024-05-27 23:25:28,017][1944938] Updated weights for policy 0, policy_version 1498 (0.0008)
+[2024-05-27 23:25:29,185][1944938] Updated weights for policy 0, policy_version 1508 (0.0008)
+[2024-05-27 23:25:29,332][1944769] Fps is (10 sec: 32358.2, 60 sec: 32085.3, 300 sec: 27704.4). Total num frames: 6180864. Throughput: 0: 8043.0. Samples: 542416. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2024-05-27 23:25:29,332][1944769] Avg episode reward: [(0, '21.199')]
+[2024-05-27 23:25:30,420][1944938] Updated weights for policy 0, policy_version 1518 (0.0008)
+[2024-05-27 23:25:31,670][1944938] Updated weights for policy 0, policy_version 1528 (0.0012)
+[2024-05-27 23:25:32,874][1944938] Updated weights for policy 0, policy_version 1538 (0.0008)
+[2024-05-27 23:25:34,228][1944938] Updated weights for policy 0, policy_version 1548 (0.0013)
+[2024-05-27 23:25:34,332][1944769] Fps is (10 sec: 32358.2, 60 sec: 32085.3, 300 sec: 27958.5). Total num frames: 6340608. Throughput: 0: 8061.0. Samples: 567408. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2024-05-27 23:25:34,332][1944769] Avg episode reward: [(0, '25.027')]
+[2024-05-27 23:25:34,335][1944894] Saving new best policy, reward=25.027!
+[2024-05-27 23:25:35,469][1944938] Updated weights for policy 0, policy_version 1558 (0.0008)
+[2024-05-27 23:25:36,758][1944938] Updated weights for policy 0, policy_version 1568 (0.0008)
+[2024-05-27 23:25:38,071][1944938] Updated weights for policy 0, policy_version 1578 (0.0009)
+[2024-05-27 23:25:39,331][1944769] Fps is (10 sec: 31949.0, 60 sec: 32153.6, 300 sec: 28183.9). Total num frames: 6500352. Throughput: 0: 8060.3. Samples: 615528. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2024-05-27 23:25:39,332][1944769] Avg episode reward: [(0, '21.823')]
+[2024-05-27 23:25:39,412][1944938] Updated weights for policy 0, policy_version 1588 (0.0008)
+[2024-05-27 23:25:40,793][1944938] Updated weights for policy 0, policy_version 1598 (0.0014)
+[2024-05-27 23:25:42,055][1944938] Updated weights for policy 0, policy_version 1608 (0.0008)
+[2024-05-27 23:25:43,282][1944938] Updated weights for policy 0, policy_version 1618 (0.0010)
+[2024-05-27 23:25:44,331][1944769] Fps is (10 sec: 31949.1, 60 sec: 32153.7, 300 sec: 28385.3). Total num frames: 6660096. Throughput: 0: 8004.3. Samples: 662380. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2024-05-27 23:25:44,332][1944769] Avg episode reward: [(0, '22.736')]
+[2024-05-27 23:25:44,643][1944938] Updated weights for policy 0, policy_version 1628 (0.0014)
+[2024-05-27 23:25:46,073][1944938] Updated weights for policy 0, policy_version 1638 (0.0007)
+[2024-05-27 23:25:47,425][1944938] Updated weights for policy 0, policy_version 1648 (0.0008)
+[2024-05-27 23:25:48,626][1944938] Updated weights for policy 0, policy_version 1658 (0.0008)
+[2024-05-27 23:25:49,331][1944769] Fps is (10 sec: 31129.8, 60 sec: 32017.1, 300 sec: 28483.0). Total num frames: 6811648. Throughput: 0: 7951.6. Samples: 684324. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2024-05-27 23:25:49,332][1944769] Avg episode reward: [(0, '22.791')]
+[2024-05-27 23:25:49,975][1944938] Updated weights for policy 0, policy_version 1668 (0.0008)
+[2024-05-27 23:25:51,221][1944938] Updated weights for policy 0, policy_version 1678 (0.0009)
+[2024-05-27 23:25:52,458][1944938] Updated weights for policy 0, policy_version 1688 (0.0007)
+[2024-05-27 23:25:53,876][1944938] Updated weights for policy 0, policy_version 1698 (0.0008)
+[2024-05-27 23:25:54,331][1944769] Fps is (10 sec: 30720.0, 60 sec: 31880.5, 300 sec: 28610.8). Total num frames: 6967296. Throughput: 0: 7956.2. Samples: 732600. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2024-05-27 23:25:54,332][1944769] Avg episode reward: [(0, '23.574')]
+[2024-05-27 23:25:55,258][1944938] Updated weights for policy 0, policy_version 1708 (0.0008)
+[2024-05-27 23:25:56,539][1944938] Updated weights for policy 0, policy_version 1718 (0.0012)
+[2024-05-27 23:25:57,767][1944938] Updated weights for policy 0, policy_version 1728 (0.0013)
+[2024-05-27 23:25:59,041][1944938] Updated weights for policy 0, policy_version 1738 (0.0009)
+[2024-05-27 23:25:59,331][1944769] Fps is (10 sec: 31539.1, 60 sec: 31812.3, 300 sec: 28764.6). Total num frames: 7127040. Throughput: 0: 7920.0. Samples: 779248. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2024-05-27 23:25:59,332][1944769] Avg episode reward: [(0, '23.735')]
+[2024-05-27 23:26:00,279][1944938] Updated weights for policy 0, policy_version 1748 (0.0008)
+[2024-05-27 23:26:01,601][1944938] Updated weights for policy 0, policy_version 1758 (0.0010)
+[2024-05-27 23:26:02,916][1944938] Updated weights for policy 0, policy_version 1768 (0.0010)
+[2024-05-27 23:26:04,190][1944938] Updated weights for policy 0, policy_version 1778 (0.0009)
+[2024-05-27 23:26:04,332][1944769] Fps is (10 sec: 31948.3, 60 sec: 31812.3, 300 sec: 28904.9). Total num frames: 7286784. Throughput: 0: 7919.5. Samples: 803224. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2024-05-27 23:26:04,332][1944769] Avg episode reward: [(0, '25.925')]
+[2024-05-27 23:26:04,336][1944894] Saving /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000001779_7286784.pth...
+[2024-05-27 23:26:04,377][1944894] Removing /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000000539_2207744.pth
+[2024-05-27 23:26:04,385][1944894] Saving new best policy, reward=25.925!
+[2024-05-27 23:26:05,437][1944938] Updated weights for policy 0, policy_version 1788 (0.0010)
+[2024-05-27 23:26:06,807][1944938] Updated weights for policy 0, policy_version 1798 (0.0015)
+[2024-05-27 23:26:08,054][1944938] Updated weights for policy 0, policy_version 1808 (0.0016)
+[2024-05-27 23:26:09,297][1944938] Updated weights for policy 0, policy_version 1818 (0.0013)
+[2024-05-27 23:26:09,332][1944769] Fps is (10 sec: 31948.4, 60 sec: 31744.6, 300 sec: 29033.3). Total num frames: 7446528. Throughput: 0: 7928.8. Samples: 850808. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2024-05-27 23:26:09,332][1944769] Avg episode reward: [(0, '25.408')]
+[2024-05-27 23:26:10,740][1944938] Updated weights for policy 0, policy_version 1828 (0.0008)
+[2024-05-27 23:26:12,001][1944938] Updated weights for policy 0, policy_version 1838 (0.0008)
+[2024-05-27 23:26:13,281][1944938] Updated weights for policy 0, policy_version 1848 (0.0007)
+[2024-05-27 23:26:14,334][1944769] Fps is (10 sec: 31530.6, 60 sec: 31674.2, 300 sec: 29117.5). Total num frames: 7602176. Throughput: 0: 7900.8. Samples: 897972. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2024-05-27 23:26:14,335][1944769] Avg episode reward: [(0, '23.550')]
+[2024-05-27 23:26:14,592][1944938] Updated weights for policy 0, policy_version 1858 (0.0008)
+[2024-05-27 23:26:15,901][1944938] Updated weights for policy 0, policy_version 1868 (0.0012)
+[2024-05-27 23:26:17,177][1944938] Updated weights for policy 0, policy_version 1878 (0.0013)
+[2024-05-27 23:26:18,678][1944938] Updated weights for policy 0, policy_version 1888 (0.0014)
+[2024-05-27 23:26:19,332][1944769] Fps is (10 sec: 30720.1, 60 sec: 31607.4, 300 sec: 29164.6). Total num frames: 7753728. Throughput: 0: 7870.1. Samples: 921564. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2024-05-27 23:26:19,332][1944769] Avg episode reward: [(0, '24.534')]
+[2024-05-27 23:26:19,871][1944938] Updated weights for policy 0, policy_version 1898 (0.0008)
+[2024-05-27 23:26:21,197][1944938] Updated weights for policy 0, policy_version 1908 (0.0008)
+[2024-05-27 23:26:22,533][1944938] Updated weights for policy 0, policy_version 1918 (0.0009)
+[2024-05-27 23:26:23,811][1944938] Updated weights for policy 0, policy_version 1928 (0.0008)
+[2024-05-27 23:26:24,331][1944769] Fps is (10 sec: 30728.8, 60 sec: 31539.2, 300 sec: 29238.2). Total num frames: 7909376. Throughput: 0: 7826.9. Samples: 967736. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0)
+[2024-05-27 23:26:24,332][1944769] Avg episode reward: [(0, '23.025')]
+[2024-05-27 23:26:25,114][1944938] Updated weights for policy 0, policy_version 1938 (0.0008)
+[2024-05-27 23:26:26,494][1944938] Updated weights for policy 0, policy_version 1948 (0.0015)
+[2024-05-27 23:26:27,436][1944769] Component Batcher_0 stopped!
+[2024-05-27 23:26:27,436][1944894] Stopping Batcher_0...
+[2024-05-27 23:26:27,436][1944894] Loop batcher_evt_loop terminating...
+[2024-05-27 23:26:27,437][1944894] Saving /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-05-27 23:26:27,450][1944960] Stopping RolloutWorker_w6...
+[2024-05-27 23:26:27,450][1944960] Loop rollout_proc6_evt_loop terminating...
+[2024-05-27 23:26:27,450][1944769] Component RolloutWorker_w6 stopped!
+[2024-05-27 23:26:27,451][1944942] Stopping RolloutWorker_w3...
+[2024-05-27 23:26:27,451][1944769] Component RolloutWorker_w3 stopped!
+[2024-05-27 23:26:27,451][1944939] Stopping RolloutWorker_w0...
+[2024-05-27 23:26:27,452][1944942] Loop rollout_proc3_evt_loop terminating...
+[2024-05-27 23:26:27,452][1944769] Component RolloutWorker_w0 stopped!
+[2024-05-27 23:26:27,452][1944939] Loop rollout_proc0_evt_loop terminating...
+[2024-05-27 23:26:27,452][1944940] Stopping RolloutWorker_w4...
+[2024-05-27 23:26:27,452][1944769] Component RolloutWorker_w4 stopped!
+[2024-05-27 23:26:27,452][1944769] Component RolloutWorker_w7 stopped!
+[2024-05-27 23:26:27,452][1944961] Stopping RolloutWorker_w7...
+[2024-05-27 23:26:27,452][1944940] Loop rollout_proc4_evt_loop terminating...
+[2024-05-27 23:26:27,452][1944961] Loop rollout_proc7_evt_loop terminating...
+[2024-05-27 23:26:27,453][1944769] Component RolloutWorker_w5 stopped!
+[2024-05-27 23:26:27,453][1944959] Stopping RolloutWorker_w5...
+[2024-05-27 23:26:27,452][1944938] Weights refcount: 2 0
+[2024-05-27 23:26:27,453][1944959] Loop rollout_proc5_evt_loop terminating...
+[2024-05-27 23:26:27,470][1944941] Stopping RolloutWorker_w2...
+[2024-05-27 23:26:27,470][1944769] Component RolloutWorker_w2 stopped!
+[2024-05-27 23:26:27,470][1944941] Loop rollout_proc2_evt_loop terminating...
+[2024-05-27 23:26:27,482][1944894] Removing /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
+[2024-05-27 23:26:27,489][1944894] Saving /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-05-27 23:26:27,490][1944943] Stopping RolloutWorker_w1...
+[2024-05-27 23:26:27,490][1944769] Component RolloutWorker_w1 stopped!
+[2024-05-27 23:26:27,491][1944943] Loop rollout_proc1_evt_loop terminating...
+[2024-05-27 23:26:27,536][1944938] Stopping InferenceWorker_p0-w0...
+[2024-05-27 23:26:27,537][1944769] Component InferenceWorker_p0-w0 stopped!
+[2024-05-27 23:26:27,537][1944938] Loop inference_proc0-0_evt_loop terminating...
+[2024-05-27 23:26:27,566][1944894] Stopping LearnerWorker_p0...
+[2024-05-27 23:26:27,567][1944769] Component LearnerWorker_p0 stopped!
+[2024-05-27 23:26:27,567][1944894] Loop learner_proc0_evt_loop terminating...
+[2024-05-27 23:26:27,567][1944769] Waiting for process learner_proc0 to stop...
+[2024-05-27 23:26:28,282][1944769] Waiting for process inference_proc0-0 to join...
+[2024-05-27 23:26:28,282][1944769] Waiting for process rollout_proc0 to join...
+[2024-05-27 23:26:28,282][1944769] Waiting for process rollout_proc1 to join...
+[2024-05-27 23:26:28,282][1944769] Waiting for process rollout_proc2 to join...
+[2024-05-27 23:26:28,282][1944769] Waiting for process rollout_proc3 to join...
+[2024-05-27 23:26:28,283][1944769] Waiting for process rollout_proc4 to join...
+[2024-05-27 23:26:28,283][1944769] Waiting for process rollout_proc5 to join...
+[2024-05-27 23:26:28,283][1944769] Waiting for process rollout_proc6 to join...
+[2024-05-27 23:26:28,283][1944769] Waiting for process rollout_proc7 to join...
+[2024-05-27 23:26:28,283][1944769] Batcher 0 profile tree view:
+batching: 15.3245, releasing_batches: 0.0233
+[2024-05-27 23:26:28,283][1944769] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 9.0043
+update_model: 2.2328
+  weight_update: 0.0020
+one_step: 0.0026
+  handle_policy_step: 119.2006
+    deserialize: 5.5536, stack: 0.5907, obs_to_device_normalize: 28.7723, forward: 62.5003, send_messages: 5.0913
+    prepare_outputs: 12.6494
+      to_cpu: 7.0284
+[2024-05-27 23:26:28,283][1944769] Learner 0 profile tree view:
+misc: 0.0041, prepare_batch: 7.3997
+train: 21.3461
+  epoch_init: 0.0033, minibatch_init: 0.0037, losses_postprocess: 0.3643, kl_divergence: 0.4054, after_optimizer: 0.6822
+  calculate_losses: 8.8365
+    losses_init: 0.0019, forward_head: 0.5491, bptt_initial: 5.4800, tail: 0.5743, advantages_returns: 0.1749, losses: 1.0358
+    bptt: 0.8461
+      bptt_forward_core: 0.8056
+  update: 10.6762
+    clip: 0.5238
+[2024-05-27 23:26:28,283][1944769] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0804, enqueue_policy_requests: 4.6237, env_step: 65.5304, overhead: 7.3248, complete_rollouts: 0.1038
+save_policy_outputs: 5.4512
+  split_output_tensors: 2.5760
+[2024-05-27 23:26:28,283][1944769] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0774, enqueue_policy_requests: 4.4785, env_step: 68.5710, overhead: 7.0470, complete_rollouts: 0.1004
+save_policy_outputs: 5.3293
+  split_output_tensors: 2.4943
+[2024-05-27 23:26:28,283][1944769] Loop Runner_EvtLoop terminating...
+[2024-05-27 23:26:28,283][1944769] Runner profile tree view:
+main_loop: 141.3852
+[2024-05-27 23:26:28,284][1944769] Collected {0: 8007680}, FPS: 28304.2
+[2024-05-27 23:26:28,493][1944769] Loading existing experiment configuration from /media/fast/code/learning/train_dir/default_experiment/config.json
+[2024-05-27 23:26:28,493][1944769] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-05-27 23:26:28,493][1944769] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-05-27 23:26:28,493][1944769] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-05-27 23:26:28,493][1944769] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-05-27 23:26:28,493][1944769] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-05-27 23:26:28,494][1944769] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-05-27 23:26:28,500][1944769] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:26:28,501][1944769] RunningMeanStd input shape: (3, 72, 128)
+[2024-05-27 23:26:28,502][1944769] RunningMeanStd input shape: (1,)
+[2024-05-27 23:26:28,508][1944769] ConvEncoder: input_channels=3
+[2024-05-27 23:26:28,562][1944769] Conv encoder output size: 512
+[2024-05-27 23:26:28,563][1944769] Policy head output size: 512
+[2024-05-27 23:26:28,832][1944769] Loading state from checkpoint /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-05-27 23:26:29,547][1944769] Num frames 100...
+[2024-05-27 23:26:29,608][1944769] Num frames 200...
+[2024-05-27 23:26:29,666][1944769] Num frames 300...
+[2024-05-27 23:26:29,736][1944769] Num frames 400...
+[2024-05-27 23:26:29,810][1944769] Num frames 500...
+[2024-05-27 23:26:29,918][1944769] Avg episode rewards: #0: 12.920, true rewards: #0: 5.920
+[2024-05-27 23:26:29,918][1944769] Avg episode reward: 12.920, avg true_objective: 5.920
+[2024-05-27 23:26:29,923][1944769] Num frames 600...
+[2024-05-27 23:26:29,980][1944769] Num frames 700...
+[2024-05-27 23:26:30,040][1944769] Num frames 800...
+[2024-05-27 23:26:30,094][1944769] Num frames 900...
+[2024-05-27 23:26:30,152][1944769] Num frames 1000...
+[2024-05-27 23:26:30,206][1944769] Num frames 1100...
+[2024-05-27 23:26:30,266][1944769] Num frames 1200...
+[2024-05-27 23:26:30,321][1944769] Num frames 1300...
+[2024-05-27 23:26:30,497][1944769] Avg episode rewards: #0: 14.300, true rewards: #0: 6.800
+[2024-05-27 23:26:30,497][1944769] Avg episode reward: 14.300, avg true_objective: 6.800
+[2024-05-27 23:26:30,522][1944769] Num frames 1400...
+[2024-05-27 23:26:30,580][1944769] Num frames 1500...
+[2024-05-27 23:26:30,637][1944769] Num frames 1600...
+[2024-05-27 23:26:30,696][1944769] Num frames 1700...
+[2024-05-27 23:26:30,760][1944769] Num frames 1800...
+[2024-05-27 23:26:30,825][1944769] Num frames 1900...
+[2024-05-27 23:26:30,884][1944769] Num frames 2000...
+[2024-05-27 23:26:30,980][1944769] Avg episode rewards: #0: 13.897, true rewards: #0: 6.897
+[2024-05-27 23:26:30,980][1944769] Avg episode reward: 13.897, avg true_objective: 6.897
+[2024-05-27 23:26:30,999][1944769] Num frames 2100...
+[2024-05-27 23:26:31,061][1944769] Num frames 2200...
+[2024-05-27 23:26:31,125][1944769] Num frames 2300...
+[2024-05-27 23:26:31,190][1944769] Num frames 2400...
+[2024-05-27 23:26:31,259][1944769] Num frames 2500...
+[2024-05-27 23:26:31,326][1944769] Num frames 2600...
+[2024-05-27 23:26:31,393][1944769] Num frames 2700...
+[2024-05-27 23:26:31,458][1944769] Num frames 2800...
+[2024-05-27 23:26:31,520][1944769] Num frames 2900...
+[2024-05-27 23:26:31,582][1944769] Num frames 3000...
+[2024-05-27 23:26:31,646][1944769] Num frames 3100...
+[2024-05-27 23:26:31,712][1944769] Num frames 3200...
+[2024-05-27 23:26:31,777][1944769] Num frames 3300...
+[2024-05-27 23:26:31,841][1944769] Num frames 3400...
+[2024-05-27 23:26:31,932][1944769] Avg episode rewards: #0: 18.405, true rewards: #0: 8.655
+[2024-05-27 23:26:31,932][1944769] Avg episode reward: 18.405, avg true_objective: 8.655
+[2024-05-27 23:26:31,956][1944769] Num frames 3500...
+[2024-05-27 23:26:32,011][1944769] Num frames 3600...
+[2024-05-27 23:26:32,073][1944769] Num frames 3700...
+[2024-05-27 23:26:32,129][1944769] Num frames 3800...
+[2024-05-27 23:26:32,191][1944769] Num frames 3900...
+[2024-05-27 23:26:32,256][1944769] Num frames 4000...
+[2024-05-27 23:26:32,319][1944769] Num frames 4100...
+[2024-05-27 23:26:32,383][1944769] Num frames 4200...
+[2024-05-27 23:26:32,445][1944769] Num frames 4300...
+[2024-05-27 23:26:32,508][1944769] Num frames 4400...
+[2024-05-27 23:26:32,572][1944769] Num frames 4500...
+[2024-05-27 23:26:32,633][1944769] Num frames 4600...
+[2024-05-27 23:26:32,692][1944769] Num frames 4700...
+[2024-05-27 23:26:32,755][1944769] Num frames 4800...
+[2024-05-27 23:26:32,821][1944769] Num frames 4900...
+[2024-05-27 23:26:32,880][1944769] Num frames 5000...
+[2024-05-27 23:26:32,942][1944769] Num frames 5100...
+[2024-05-27 23:26:33,004][1944769] Num frames 5200...
+[2024-05-27 23:26:33,091][1944769] Avg episode rewards: #0: 24.908, true rewards: #0: 10.508
+[2024-05-27 23:26:33,092][1944769] Avg episode reward: 24.908, avg true_objective: 10.508
+[2024-05-27 23:26:33,119][1944769] Num frames 5300...
+[2024-05-27 23:26:33,183][1944769] Num frames 5400...
+[2024-05-27 23:26:33,243][1944769] Num frames 5500...
+[2024-05-27 23:26:33,300][1944769] Num frames 5600...
+[2024-05-27 23:26:33,363][1944769] Num frames 5700...
+[2024-05-27 23:26:33,424][1944769] Num frames 5800...
+[2024-05-27 23:26:33,486][1944769] Num frames 5900...
+[2024-05-27 23:26:33,553][1944769] Num frames 6000...
+[2024-05-27 23:26:33,617][1944769] Num frames 6100...
+[2024-05-27 23:26:33,681][1944769] Num frames 6200...
+[2024-05-27 23:26:33,755][1944769] Num frames 6300...
+[2024-05-27 23:26:33,827][1944769] Num frames 6400...
+[2024-05-27 23:26:33,939][1944769] Avg episode rewards: #0: 25.983, true rewards: #0: 10.817
+[2024-05-27 23:26:33,939][1944769] Avg episode reward: 25.983, avg true_objective: 10.817
+[2024-05-27 23:26:33,947][1944769] Num frames 6500...
+[2024-05-27 23:26:34,086][1944769] Num frames 6600...
+[2024-05-27 23:26:34,206][1944769] Num frames 6700...
+[2024-05-27 23:26:34,274][1944769] Num frames 6800...
+[2024-05-27 23:26:34,346][1944769] Num frames 6900...
+[2024-05-27 23:26:34,502][1944769] Num frames 7000...
+[2024-05-27 23:26:34,609][1944769] Num frames 7100...
+[2024-05-27 23:26:34,698][1944769] Num frames 7200...
+[2024-05-27 23:26:34,814][1944769] Num frames 7300...
+[2024-05-27 23:26:34,891][1944769] Avg episode rewards: #0: 24.753, true rewards: #0: 10.467
+[2024-05-27 23:26:34,891][1944769] Avg episode reward: 24.753, avg true_objective: 10.467
+[2024-05-27 23:26:34,940][1944769] Num frames 7400...
+[2024-05-27 23:26:35,044][1944769] Num frames 7500...
+[2024-05-27 23:26:35,110][1944769] Num frames 7600...
+[2024-05-27 23:26:35,191][1944769] Num frames 7700...
+[2024-05-27 23:26:35,260][1944769] Num frames 7800...
+[2024-05-27 23:26:35,348][1944769] Num frames 7900...
+[2024-05-27 23:26:35,498][1944769] Avg episode rewards: #0: 22.929, true rewards: #0: 9.929
+[2024-05-27 23:26:35,499][1944769] Avg episode reward: 22.929, avg true_objective: 9.929
+[2024-05-27 23:26:35,538][1944769] Num frames 8000...
+[2024-05-27 23:26:35,630][1944769] Num frames 8100...
+[2024-05-27 23:26:35,731][1944769] Num frames 8200...
+[2024-05-27 23:26:35,882][1944769] Num frames 8300...
+[2024-05-27 23:26:35,971][1944769] Num frames 8400...
+[2024-05-27 23:26:36,041][1944769] Num frames 8500...
+[2024-05-27 23:26:36,140][1944769] Num frames 8600...
+[2024-05-27 23:26:36,295][1944769] Num frames 8700...
+[2024-05-27 23:26:36,377][1944769] Num frames 8800...
+[2024-05-27 23:26:36,446][1944769] Num frames 8900...
+[2024-05-27 23:26:36,514][1944769] Num frames 9000...
+[2024-05-27 23:26:36,602][1944769] Num frames 9100...
+[2024-05-27 23:26:36,670][1944769] Num frames 9200...
+[2024-05-27 23:26:36,737][1944769] Num frames 9300...
+[2024-05-27 23:26:36,826][1944769] Num frames 9400...
+[2024-05-27 23:26:36,926][1944769] Num frames 9500...
+[2024-05-27 23:26:37,023][1944769] Num frames 9600...
+[2024-05-27 23:26:37,092][1944769] Num frames 9700...
+[2024-05-27 23:26:37,160][1944769] Num frames 9800...
+[2024-05-27 23:26:37,295][1944769] Num frames 9900...
+[2024-05-27 23:26:37,435][1944769] Num frames 10000...
+[2024-05-27 23:26:37,516][1944769] Avg episode rewards: #0: 26.492, true rewards: #0: 11.159
+[2024-05-27 23:26:37,516][1944769] Avg episode reward: 26.492, avg true_objective: 11.159
+[2024-05-27 23:26:37,556][1944769] Num frames 10100...
+[2024-05-27 23:26:37,626][1944769] Num frames 10200...
+[2024-05-27 23:26:37,711][1944769] Num frames 10300...
+[2024-05-27 23:26:37,781][1944769] Num frames 10400...
+[2024-05-27 23:26:37,909][1944769] Num frames 10500...
+[2024-05-27 23:26:37,988][1944769] Num frames 10600...
+[2024-05-27 23:26:38,158][1944769] Num frames 10700...
+[2024-05-27 23:26:38,228][1944769] Num frames 10800...
+[2024-05-27 23:26:38,291][1944769] Num frames 10900...
+[2024-05-27 23:26:38,395][1944769] Num frames 11000...
+[2024-05-27 23:26:38,461][1944769] Num frames 11100...
+[2024-05-27 23:26:38,528][1944769] Num frames 11200...
+[2024-05-27 23:26:38,608][1944769] Num frames 11300...
+[2024-05-27 23:26:38,713][1944769] Num frames 11400...
+[2024-05-27 23:26:38,783][1944769] Num frames 11500...
+[2024-05-27 23:26:38,880][1944769] Num frames 11600...
+[2024-05-27 23:26:38,948][1944769] Num frames 11700...
+[2024-05-27 23:26:39,015][1944769] Num frames 11800...
+[2024-05-27 23:26:39,143][1944769] Num frames 11900...
+[2024-05-27 23:26:39,303][1944769] Num frames 12000...
+[2024-05-27 23:26:39,377][1944769] Num frames 12100...
+[2024-05-27 23:26:39,460][1944769] Avg episode rewards: #0: 28.943, true rewards: #0: 12.143
+[2024-05-27 23:26:39,460][1944769] Avg episode reward: 28.943, avg true_objective: 12.143
+[2024-05-27 23:26:54,252][1944769] Replay video saved to /media/fast/code/learning/train_dir/default_experiment/replay.mp4!
+[2024-05-27 23:26:54,444][1944769] Loading existing experiment configuration from /media/fast/code/learning/train_dir/default_experiment/config.json
+[2024-05-27 23:26:54,444][1944769] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-05-27 23:26:54,444][1944769] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-05-27 23:26:54,444][1944769] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'hf_repository'='DavidPL1/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-05-27 23:26:54,445][1944769] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-05-27 23:26:54,450][1944769] RunningMeanStd input shape: (3, 72, 128)
+[2024-05-27 23:26:54,450][1944769] RunningMeanStd input shape: (1,)
+[2024-05-27 23:26:54,459][1944769] ConvEncoder: input_channels=3
+[2024-05-27 23:26:54,489][1944769] Conv encoder output size: 512
+[2024-05-27 23:26:54,489][1944769] Policy head output size: 512
+[2024-05-27 23:26:54,503][1944769] Loading state from checkpoint /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-05-27 23:26:55,013][1944769] Num frames 100...
+[2024-05-27 23:26:55,114][1944769] Num frames 200...
+[2024-05-27 23:26:55,180][1944769] Num frames 300...
+[2024-05-27 23:26:55,321][1944769] Num frames 400...
+[2024-05-27 23:26:55,436][1944769] Num frames 500...
+[2024-05-27 23:26:55,524][1944769] Num frames 600...
+[2024-05-27 23:26:55,592][1944769] Num frames 700...
+[2024-05-27 23:26:55,655][1944769] Num frames 800...
+[2024-05-27 23:26:55,722][1944769] Num frames 900...
+[2024-05-27 23:26:55,787][1944769] Num frames 1000...
+[2024-05-27 23:26:55,855][1944769] Num frames 1100...
+[2024-05-27 23:26:55,999][1944769] Num frames 1200...
+[2024-05-27 23:26:56,088][1944769] Num frames 1300...
+[2024-05-27 23:26:56,195][1944769] Num frames 1400...
+[2024-05-27 23:26:56,273][1944769] Num frames 1500...
+[2024-05-27 23:26:56,339][1944769] Num frames 1600...
+[2024-05-27 23:26:56,449][1944769] Avg episode rewards: #0: 37.320, true rewards: #0: 16.320
+[2024-05-27 23:26:56,449][1944769] Avg episode reward: 37.320, avg true_objective: 16.320
+[2024-05-27 23:26:56,528][1944769] Num frames 1700...
+[2024-05-27 23:26:56,595][1944769] Num frames 1800...
+[2024-05-27 23:26:56,654][1944769] Num frames 1900...
+[2024-05-27 23:26:56,719][1944769] Num frames 2000...
+[2024-05-27 23:26:56,784][1944769] Num frames 2100...
+[2024-05-27 23:26:56,861][1944769] Num frames 2200...
+[2024-05-27 23:26:56,939][1944769] Avg episode rewards: #0: 24.700, true rewards: #0: 11.200
+[2024-05-27 23:26:56,939][1944769] Avg episode reward: 24.700, avg true_objective: 11.200
+[2024-05-27 23:26:56,981][1944769] Num frames 2300...
+[2024-05-27 23:26:57,056][1944769] Num frames 2400...
+[2024-05-27 23:26:57,182][1944769] Num frames 2500...
+[2024-05-27 23:26:57,381][1944769] Num frames 2600...
+[2024-05-27 23:26:57,449][1944769] Num frames 2700...
+[2024-05-27 23:26:57,614][1944769] Num frames 2800...
+[2024-05-27 23:26:57,734][1944769] Num frames 2900...
+[2024-05-27 23:26:57,849][1944769] Avg episode rewards: #0: 21.920, true rewards: #0: 9.920
+[2024-05-27 23:26:57,849][1944769] Avg episode reward: 21.920, avg true_objective: 9.920
+[2024-05-27 23:26:57,865][1944769] Num frames 3000...
+[2024-05-27 23:26:57,971][1944769] Num frames 3100...
+[2024-05-27 23:26:58,045][1944769] Num frames 3200...
+[2024-05-27 23:26:58,122][1944769] Num frames 3300...
+[2024-05-27 23:26:58,234][1944769] Num frames 3400...
+[2024-05-27 23:26:58,368][1944769] Num frames 3500...
+[2024-05-27 23:26:58,458][1944769] Num frames 3600...
+[2024-05-27 23:26:58,529][1944769] Num frames 3700...
+[2024-05-27 23:26:58,579][1944769] Avg episode rewards: #0: 20.500, true rewards: #0: 9.250
+[2024-05-27 23:26:58,580][1944769] Avg episode reward: 20.500, avg true_objective: 9.250
+[2024-05-27 23:26:58,647][1944769] Num frames 3800...
+[2024-05-27 23:26:58,709][1944769] Num frames 3900...
+[2024-05-27 23:26:58,773][1944769] Num frames 4000...
+[2024-05-27 23:26:58,913][1944769] Num frames 4100...
+[2024-05-27 23:26:58,993][1944769] Num frames 4200...
+[2024-05-27 23:26:59,062][1944769] Num frames 4300...
+[2024-05-27 23:26:59,129][1944769] Num frames 4400...
+[2024-05-27 23:26:59,197][1944769] Num frames 4500...
+[2024-05-27 23:26:59,309][1944769] Num frames 4600...
+[2024-05-27 23:26:59,379][1944769] Avg episode rewards: #0: 20.856, true rewards: #0: 9.256
+[2024-05-27 23:26:59,379][1944769] Avg episode reward: 20.856, avg true_objective: 9.256
+[2024-05-27 23:26:59,455][1944769] Num frames 4700...
+[2024-05-27 23:26:59,522][1944769] Num frames 4800...
+[2024-05-27 23:26:59,591][1944769] Num frames 4900...
+[2024-05-27 23:26:59,656][1944769] Num frames 5000...
+[2024-05-27 23:26:59,721][1944769] Num frames 5100...
+[2024-05-27 23:26:59,825][1944769] Num frames 5200...
+[2024-05-27 23:26:59,916][1944769] Num frames 5300...
+[2024-05-27 23:27:00,074][1944769] Num frames 5400...
+[2024-05-27 23:27:00,136][1944769] Num frames 5500...
+[2024-05-27 23:27:00,209][1944769] Num frames 5600...
+[2024-05-27 23:27:00,278][1944769] Num frames 5700...
+[2024-05-27 23:27:00,346][1944769] Num frames 5800...
+[2024-05-27 23:27:00,487][1944769] Num frames 5900...
+[2024-05-27 23:27:00,552][1944769] Num frames 6000...
+[2024-05-27 23:27:00,627][1944769] Num frames 6100...
+[2024-05-27 23:27:00,694][1944769] Num frames 6200...
+[2024-05-27 23:27:00,806][1944769] Avg episode rewards: #0: 23.820, true rewards: #0: 10.487
+[2024-05-27 23:27:00,806][1944769] Avg episode reward: 23.820, avg true_objective: 10.487
+[2024-05-27 23:27:00,812][1944769] Num frames 6300...
+[2024-05-27 23:27:00,902][1944769] Num frames 6400...
+[2024-05-27 23:27:01,011][1944769] Num frames 6500...
+[2024-05-27 23:27:01,075][1944769] Num frames 6600...
+[2024-05-27 23:27:01,198][1944769] Num frames 6700...
+[2024-05-27 23:27:01,263][1944769] Num frames 6800...
+[2024-05-27 23:27:01,353][1944769] Num frames 6900...
+[2024-05-27 23:27:01,615][1944769] Num frames 7000...
+[2024-05-27 23:27:01,684][1944769] Num frames 7100...
+[2024-05-27 23:27:01,753][1944769] Num frames 7200...
+[2024-05-27 23:27:01,840][1944769] Avg episode rewards: #0: 23.074, true rewards: #0: 10.360
+[2024-05-27 23:27:01,840][1944769] Avg episode reward: 23.074, avg true_objective: 10.360
+[2024-05-27 23:27:01,873][1944769] Num frames 7300...
+[2024-05-27 23:27:01,932][1944769] Num frames 7400...
+[2024-05-27 23:27:01,993][1944769] Num frames 7500...
+[2024-05-27 23:27:02,054][1944769] Num frames 7600...
+[2024-05-27 23:27:02,114][1944769] Num frames 7700...
+[2024-05-27 23:27:02,175][1944769] Num frames 7800...
+[2024-05-27 23:27:02,239][1944769] Num frames 7900...
+[2024-05-27 23:27:02,353][1944769] Avg episode rewards: #0: 22.110, true rewards: #0: 9.985
+[2024-05-27 23:27:02,353][1944769] Avg episode reward: 22.110, avg true_objective: 9.985
+[2024-05-27 23:27:02,426][1944769] Num frames 8000...
+[2024-05-27 23:27:02,489][1944769] Num frames 8100...
+[2024-05-27 23:27:02,544][1944769] Num frames 8200...
+[2024-05-27 23:27:02,602][1944769] Num frames 8300...
+[2024-05-27 23:27:02,663][1944769] Num frames 8400...
+[2024-05-27 23:27:02,721][1944769] Num frames 8500...
+[2024-05-27 23:27:02,784][1944769] Num frames 8600...
+[2024-05-27 23:27:02,843][1944769] Num frames 8700...
+[2024-05-27 23:27:02,904][1944769] Num frames 8800...
+[2024-05-27 23:27:02,965][1944769] Num frames 8900...
+[2024-05-27 23:27:03,028][1944769] Num frames 9000...
+[2024-05-27 23:27:03,102][1944769] Avg episode rewards: #0: 22.486, true rewards: #0: 10.041
+[2024-05-27 23:27:03,102][1944769] Avg episode reward: 22.486, avg true_objective: 10.041
+[2024-05-27 23:27:03,141][1944769] Num frames 9100...
+[2024-05-27 23:27:03,204][1944769] Num frames 9200...
+[2024-05-27 23:27:03,267][1944769] Num frames 9300...
+[2024-05-27 23:27:03,328][1944769] Num frames 9400...
+[2024-05-27 23:27:03,387][1944769] Num frames 9500...
+[2024-05-27 23:27:03,447][1944769] Num frames 9600...
+[2024-05-27 23:27:03,506][1944769] Num frames 9700...
+[2024-05-27 23:27:03,565][1944769] Num frames 9800...
+[2024-05-27 23:27:03,626][1944769] Num frames 9900...
+[2024-05-27 23:27:03,682][1944769] Num frames 10000...
+[2024-05-27 23:27:03,739][1944769] Num frames 10100...
+[2024-05-27 23:27:03,799][1944769] Num frames 10200...
+[2024-05-27 23:27:03,864][1944769] Num frames 10300...
+[2024-05-27 23:27:03,928][1944769] Num frames 10400...
+[2024-05-27 23:27:03,990][1944769] Num frames 10500...
+[2024-05-27 23:27:04,054][1944769] Num frames 10600...
+[2024-05-27 23:27:04,116][1944769] Num frames 10700...
+[2024-05-27 23:27:04,179][1944769] Num frames 10800...
+[2024-05-27 23:27:04,238][1944769] Num frames 10900...
+[2024-05-27 23:27:04,305][1944769] Num frames 11000...
+[2024-05-27 23:27:04,369][1944769] Num frames 11100...
+[2024-05-27 23:27:04,446][1944769] Avg episode rewards: #0: 25.637, true rewards: #0: 11.137
+[2024-05-27 23:27:04,446][1944769] Avg episode reward: 25.637, avg true_objective: 11.137
+[2024-05-27 23:27:18,008][1944769] Replay video saved to /media/fast/code/learning/train_dir/default_experiment/replay.mp4!