Upload . with huggingface_hub

.summary/0/events.out.tfevents.1677320001.groot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed08f7db667cbe00f5172da28c8a8119bc68eadeef9ed1599e3e82adcd4e0e80
+size 40

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 12.83 +/- 5.79
+      value: 14.27 +/- 5.47
       name: mean_reward
       verified: false
 ---

config.json

@@ -1,7 +1,7 @@
 {
   "help": false,
   "algo": "APPO",
-  "env": "doom_health_gathering_supreme",
+  "env": "doom_deathmatch_bots",
   "experiment": "default_experiment",
   "train_dir": "/home/sebas/research/hugging-face-course/vizdoom/train_dir",
   "restart_behavior": "resume",
@@ -15,8 +15,8 @@
   "worker_num_splits": 2,
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
-  "num_workers": 16,
-  "num_envs_per_worker": 6,
+  "num_workers": 32,
+  "num_envs_per_worker": 24,
   "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": 20000000,
+  "train_for_env_steps": 100000000,
   "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 sha256:9cf58ae42597207ce5c99f41b3d124ec0325bb4240a29954b4674bf2c479acb8
-size 25052505
+oid sha256:26aa549c10a821373437bc33149a39306ed43a3b9e8483b18369874ddd6b071b
+size 28271956

sf_log.txt

@@ -1516,3 +1516,558 @@ main_loop: 398.6762
 [2023-02-24 17:39:23,433][2364708] Avg episode rewards: #0: 33.229, true rewards: #0: 12.829
 [2023-02-24 17:39:23,433][2364708] Avg episode reward: 33.229, avg true_objective: 12.829
 [2023-02-24 17:39:39,087][2364708] Replay video saved to train_dir/default_experiment/replay.mp4!
+[2023-02-24 17:39:45,076][2364708] The model has been pushed to https://huggingface.co/eldraco/rl_course_vizdoom_health_gathering_supreme
+[2023-02-25 11:13:23,382][2391555] Saving configuration to /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/config.json...
+[2023-02-25 11:13:23,382][2391555] Rollout worker 0 uses device cpu
+[2023-02-25 11:13:23,382][2391555] Rollout worker 1 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 2 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 3 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 4 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 5 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 6 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 7 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 8 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 9 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 10 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 11 uses device cpu
+[2023-02-25 11:13:23,383][2391555] Rollout worker 12 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 13 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 14 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 15 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 16 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 17 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 18 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 19 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 20 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 21 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 22 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 23 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 24 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 25 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 26 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 27 uses device cpu
+[2023-02-25 11:13:23,384][2391555] Rollout worker 28 uses device cpu
+[2023-02-25 11:13:23,385][2391555] Rollout worker 29 uses device cpu
+[2023-02-25 11:13:23,385][2391555] Rollout worker 30 uses device cpu
+[2023-02-25 11:13:23,385][2391555] Rollout worker 31 uses device cpu
+[2023-02-25 11:13:23,820][2391555] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 11:13:23,821][2391555] InferenceWorker_p0-w0: min num requests: 10
+[2023-02-25 11:13:23,889][2391555] Starting all processes...
+[2023-02-25 11:13:23,889][2391555] Starting process learner_proc0
+[2023-02-25 11:13:24,631][2391555] Starting all processes...
+[2023-02-25 11:13:24,637][2391555] Starting process inference_proc0-0
+[2023-02-25 11:13:24,638][2391646] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 11:13:24,638][2391646] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-02-25 11:13:24,639][2391555] Starting process rollout_proc0
+[2023-02-25 11:13:24,639][2391555] Starting process rollout_proc1
+[2023-02-25 11:13:24,639][2391555] Starting process rollout_proc2
+[2023-02-25 11:13:24,640][2391555] Starting process rollout_proc3
+[2023-02-25 11:13:24,641][2391555] Starting process rollout_proc4
+[2023-02-25 11:13:24,642][2391555] Starting process rollout_proc5
+[2023-02-25 11:13:24,643][2391555] Starting process rollout_proc6
+[2023-02-25 11:13:24,645][2391555] Starting process rollout_proc7
+[2023-02-25 11:13:24,648][2391555] Starting process rollout_proc8
+[2023-02-25 11:13:24,654][2391646] Num visible devices: 1
+[2023-02-25 11:13:24,649][2391555] Starting process rollout_proc9
+[2023-02-25 11:13:24,687][2391646] Starting seed is not provided
+[2023-02-25 11:13:24,687][2391646] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 11:13:24,688][2391646] Initializing actor-critic model on device cuda:0
+[2023-02-25 11:13:24,688][2391646] RunningMeanStd input shape: (23,)
+[2023-02-25 11:13:24,688][2391646] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-25 11:13:24,650][2391555] Starting process rollout_proc10
+[2023-02-25 11:13:24,689][2391646] RunningMeanStd input shape: (1,)
+[2023-02-25 11:13:24,650][2391555] Starting process rollout_proc11
+[2023-02-25 11:13:24,650][2391555] Starting process rollout_proc12
+[2023-02-25 11:13:24,651][2391555] Starting process rollout_proc13
+[2023-02-25 11:13:24,653][2391555] Starting process rollout_proc14
+[2023-02-25 11:13:24,704][2391646] ConvEncoder: input_channels=3
+[2023-02-25 11:13:24,853][2391646] Conv encoder output size: 512
+[2023-02-25 11:13:24,854][2391646] Policy head output size: 512
+[2023-02-25 11:13:24,870][2391646] Created Actor Critic model with architecture:
+[2023-02-25 11:13:24,870][2391646] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (measurements): RunningMeanStdInPlace()
+        (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=39, bias=True)
+  )
+)
+[2023-02-25 11:13:26,317][2391555] Starting process rollout_proc15
+[2023-02-25 11:13:26,327][2391692] Worker 0 uses CPU cores [0]
+[2023-02-25 11:13:26,341][2391555] Starting process rollout_proc16
+[2023-02-25 11:13:26,352][2391691] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 11:13:26,353][2391691] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-02-25 11:13:26,370][2391555] Starting process rollout_proc17
+[2023-02-25 11:13:26,376][2391691] Num visible devices: 1
+[2023-02-25 11:13:26,377][2391696] Worker 5 uses CPU cores [5]
+[2023-02-25 11:13:26,413][2391555] Starting process rollout_proc18
+[2023-02-25 11:13:26,422][2391694] Worker 3 uses CPU cores [3]
+[2023-02-25 11:13:26,423][2391555] Starting process rollout_proc19
+[2023-02-25 11:13:26,434][2391695] Worker 1 uses CPU cores [1]
+[2023-02-25 11:13:26,437][2391555] Starting process rollout_proc20
+[2023-02-25 11:13:26,457][2391722] Worker 12 uses CPU cores [12]
+[2023-02-25 11:13:26,457][2391555] Starting process rollout_proc21
+[2023-02-25 11:13:26,459][2391555] Starting process rollout_proc22
+[2023-02-25 11:13:26,466][2391555] Starting process rollout_proc23
+[2023-02-25 11:13:26,469][2391721] Worker 14 uses CPU cores [14]
+[2023-02-25 11:13:26,474][2391712] Worker 4 uses CPU cores [4]
+[2023-02-25 11:13:26,486][2391718] Worker 11 uses CPU cores [11]
+[2023-02-25 11:13:26,491][2391555] Starting process rollout_proc24
+[2023-02-25 11:13:26,502][2391720] Worker 13 uses CPU cores [13]
+[2023-02-25 11:13:26,523][2391555] Starting process rollout_proc25
+[2023-02-25 11:13:26,536][2391555] Starting process rollout_proc26
+[2023-02-25 11:13:26,546][2391715] Worker 7 uses CPU cores [7]
+[2023-02-25 11:13:26,550][2391719] Worker 8 uses CPU cores [8]
+[2023-02-25 11:13:26,558][2391555] Starting process rollout_proc27
+[2023-02-25 11:13:26,570][2391693] Worker 2 uses CPU cores [2]
+[2023-02-25 11:13:26,583][2391555] Starting process rollout_proc28
+[2023-02-25 11:13:26,602][2391717] Worker 10 uses CPU cores [10]
+[2023-02-25 11:13:26,638][2391555] Starting process rollout_proc29
+[2023-02-25 11:13:26,646][2391716] Worker 9 uses CPU cores [9]
+[2023-02-25 11:13:26,655][2391555] Starting process rollout_proc30
+[2023-02-25 11:13:26,670][2391713] Worker 6 uses CPU cores [6]
+[2023-02-25 11:13:27,941][2391646] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-02-25 11:13:27,942][2391646] Loading state from checkpoint /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
+[2023-02-25 11:13:27,976][2391646] Loading model from checkpoint
+[2023-02-25 11:13:27,978][2391646] EvtLoop [learner_proc0_evt_loop, process=learner_proc0] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Runner_EvtLoop', signal_name='start'), args=()
+Traceback (most recent call last):
+  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
+    slot_callable(*args)
+  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/sample_factory/algo/learning/learner_worker.py", line 139, in init
+    init_model_data = self.learner.init()
+  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/sample_factory/algo/learning/learner.py", line 243, in init
+    self.load_from_checkpoint(self.policy_id)
+  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/sample_factory/algo/learning/learner.py", line 305, in load_from_checkpoint
+    self._load_state(checkpoint_dict, load_progress=load_progress)
+  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/sample_factory/algo/learning/learner.py", line 289, in _load_state
+    self.actor_critic.load_state_dict(checkpoint_dict["model"])
+  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1671, in load_state_dict
+    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
+RuntimeError: Error(s) in loading state_dict for ActorCriticSharedWeights:
+	Missing key(s) in state_dict: "obs_normalizer.running_mean_std.running_mean_std.measurements.running_mean", "obs_normalizer.running_mean_std.running_mean_std.measurements.running_var", "obs_normalizer.running_mean_std.running_mean_std.measurements.count". 
+	size mismatch for action_parameterization.distribution_linear.weight: copying a param with shape torch.Size([5, 512]) from checkpoint, the shape in current model is torch.Size([39, 512]).
+	size mismatch for action_parameterization.distribution_linear.bias: copying a param with shape torch.Size([5]) from checkpoint, the shape in current model is torch.Size([39]).
+[2023-02-25 11:13:27,980][2391646] Unhandled exception Error(s) in loading state_dict for ActorCriticSharedWeights:
+	Missing key(s) in state_dict: "obs_normalizer.running_mean_std.running_mean_std.measurements.running_mean", "obs_normalizer.running_mean_std.running_mean_std.measurements.running_var", "obs_normalizer.running_mean_std.running_mean_std.measurements.count". 
+	size mismatch for action_parameterization.distribution_linear.weight: copying a param with shape torch.Size([5, 512]) from checkpoint, the shape in current model is torch.Size([39, 512]).
+	size mismatch for action_parameterization.distribution_linear.bias: copying a param with shape torch.Size([5]) from checkpoint, the shape in current model is torch.Size([39]). in evt loop learner_proc0_evt_loop
+[2023-02-25 11:13:28,110][2391555] Starting process rollout_proc31
+[2023-02-25 11:13:28,126][2391996] Worker 17 uses CPU cores [1]
+[2023-02-25 11:13:28,242][2392076] Worker 23 uses CPU cores [7]
+[2023-02-25 11:13:28,314][2392027] Worker 18 uses CPU cores [2]
+[2023-02-25 11:13:28,330][2392044] Worker 20 uses CPU cores [4]
+[2023-02-25 11:13:28,350][2391995] Worker 16 uses CPU cores [0]
+[2023-02-25 11:13:28,378][2392028] Worker 19 uses CPU cores [3]
+[2023-02-25 11:13:28,394][2392139] Worker 25 uses CPU cores [9]
+[2023-02-25 11:13:28,394][2391979] Worker 15 uses CPU cores [15]
+[2023-02-25 11:13:28,397][2392123] Worker 24 uses CPU cores [8]
+[2023-02-25 11:13:28,407][2392171] Worker 27 uses CPU cores [11]
+[2023-02-25 11:13:28,410][2392107] Worker 22 uses CPU cores [6]
+[2023-02-25 11:13:28,446][2392140] Worker 26 uses CPU cores [10]
+[2023-02-25 11:13:28,458][2392075] Worker 21 uses CPU cores [5]
+[2023-02-25 11:13:28,490][2392203] Worker 29 uses CPU cores [13]
+[2023-02-25 11:13:28,547][2392187] Worker 28 uses CPU cores [12]
+[2023-02-25 11:13:28,562][2392219] Worker 30 uses CPU cores [14]
+[2023-02-25 11:13:29,110][2392478] Worker 31 uses CPU cores [15]
+[2023-02-25 11:13:43,817][2391555] Heartbeat connected on Batcher_0
+[2023-02-25 11:13:43,822][2391555] Heartbeat connected on InferenceWorker_p0-w0
+[2023-02-25 11:13:43,824][2391555] Heartbeat connected on RolloutWorker_w0
+[2023-02-25 11:13:43,826][2391555] Heartbeat connected on RolloutWorker_w1
+[2023-02-25 11:13:43,829][2391555] Heartbeat connected on RolloutWorker_w2
+[2023-02-25 11:13:43,831][2391555] Heartbeat connected on RolloutWorker_w3
+[2023-02-25 11:13:43,833][2391555] Heartbeat connected on RolloutWorker_w4
+[2023-02-25 11:13:43,835][2391555] Heartbeat connected on RolloutWorker_w5
+[2023-02-25 11:13:43,837][2391555] Heartbeat connected on RolloutWorker_w6
+[2023-02-25 11:13:43,839][2391555] Heartbeat connected on RolloutWorker_w7
+[2023-02-25 11:13:43,841][2391555] Heartbeat connected on RolloutWorker_w8
+[2023-02-25 11:13:43,843][2391555] Heartbeat connected on RolloutWorker_w9
+[2023-02-25 11:13:43,845][2391555] Heartbeat connected on RolloutWorker_w10
+[2023-02-25 11:13:43,847][2391555] Heartbeat connected on RolloutWorker_w11
+[2023-02-25 11:13:43,849][2391555] Heartbeat connected on RolloutWorker_w12
+[2023-02-25 11:13:43,852][2391555] Heartbeat connected on RolloutWorker_w13
+[2023-02-25 11:13:43,854][2391555] Heartbeat connected on RolloutWorker_w14
+[2023-02-25 11:13:43,856][2391555] Heartbeat connected on RolloutWorker_w15
+[2023-02-25 11:13:43,858][2391555] Heartbeat connected on RolloutWorker_w16
+[2023-02-25 11:13:43,860][2391555] Heartbeat connected on RolloutWorker_w17
+[2023-02-25 11:13:43,861][2391555] Heartbeat connected on RolloutWorker_w18
+[2023-02-25 11:13:43,863][2391555] Heartbeat connected on RolloutWorker_w19
+[2023-02-25 11:13:43,865][2391555] Heartbeat connected on RolloutWorker_w20
+[2023-02-25 11:13:43,867][2391555] Heartbeat connected on RolloutWorker_w21
+[2023-02-25 11:13:43,870][2391555] Heartbeat connected on RolloutWorker_w22
+[2023-02-25 11:13:43,872][2391555] Heartbeat connected on RolloutWorker_w23
+[2023-02-25 11:13:43,874][2391555] Heartbeat connected on RolloutWorker_w24
+[2023-02-25 11:13:43,876][2391555] Heartbeat connected on RolloutWorker_w25
+[2023-02-25 11:13:43,878][2391555] Heartbeat connected on RolloutWorker_w26
+[2023-02-25 11:13:43,880][2391555] Heartbeat connected on RolloutWorker_w27
+[2023-02-25 11:13:43,882][2391555] Heartbeat connected on RolloutWorker_w28
+[2023-02-25 11:13:43,884][2391555] Heartbeat connected on RolloutWorker_w29
+[2023-02-25 11:13:43,886][2391555] Heartbeat connected on RolloutWorker_w30
+[2023-02-25 11:13:43,888][2391555] Heartbeat connected on RolloutWorker_w31
+[2023-02-25 11:23:21,760][2391555] Components not started: LearnerWorker_p0, wait_time=600.0 seconds
+[2023-02-25 11:33:21,760][2391555] Components not started: LearnerWorker_p0, wait_time=1200.0 seconds
+[2023-02-25 11:43:21,761][2391555] Components not started: LearnerWorker_p0, wait_time=1800.0 seconds
+[2023-02-25 11:43:21,762][2391555] Components take too long to start: LearnerWorker_p0. Aborting the experiment!
+
+
+
+[2023-02-25 11:43:21,763][2391694] Stopping RolloutWorker_w3...
+[2023-02-25 11:43:21,764][2391555] Component RolloutWorker_w3 stopped!
+[2023-02-25 11:43:21,763][2391716] Stopping RolloutWorker_w9...
+[2023-02-25 11:43:21,763][2392140] Stopping RolloutWorker_w26...
+[2023-02-25 11:43:21,764][2391691] Stopping InferenceWorker_p0-w0...
+[2023-02-25 11:43:21,764][2392187] Stopping RolloutWorker_w28...
+[2023-02-25 11:43:21,764][2391712] Stopping RolloutWorker_w4...
+[2023-02-25 11:43:21,764][2391721] Stopping RolloutWorker_w14...
+[2023-02-25 11:43:21,764][2391646] Stopping Batcher_0...
+[2023-02-25 11:43:21,764][2392027] Stopping RolloutWorker_w18...
+[2023-02-25 11:43:21,764][2391719] Stopping RolloutWorker_w8...
+[2023-02-25 11:43:21,764][2391720] Stopping RolloutWorker_w13...
+[2023-02-25 11:43:21,764][2391715] Stopping RolloutWorker_w7...
+[2023-02-25 11:43:21,764][2392028] Stopping RolloutWorker_w19...
+[2023-02-25 11:43:21,764][2391695] Stopping RolloutWorker_w1...
+[2023-02-25 11:43:21,764][2392187] Loop rollout_proc28_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391716] Loop rollout_proc9_evt_loop terminating...
+[2023-02-25 11:43:21,764][2392140] Loop rollout_proc26_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391646] Loop batcher_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391721] Loop rollout_proc14_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w6', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w9', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w20', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w26', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,764][2392027] Loop rollout_proc18_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391719] Loop rollout_proc8_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391715] Loop rollout_proc7_evt_loop terminating...
+[2023-02-25 11:43:21,764][2392028] Loop rollout_proc19_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391718] Stopping RolloutWorker_w11...
+[2023-02-25 11:43:21,764][2391555] Component RolloutWorker_w26 stopped!
+[2023-02-25 11:43:21,764][2392075] Stopping RolloutWorker_w21...
+[2023-02-25 11:43:21,764][2391995] Stopping RolloutWorker_w16...
+[2023-02-25 11:43:21,764][2392107] Stopping RolloutWorker_w22...
+[2023-02-25 11:43:21,764][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w6', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w9', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w20', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,764][2391718] Loop rollout_proc11_evt_loop terminating...
+[2023-02-25 11:43:21,765][2391995] Loop rollout_proc16_evt_loop terminating...
+[2023-02-25 11:43:21,765][2391555] Component RolloutWorker_w9 stopped!
+[2023-02-25 11:43:21,765][2392075] Loop rollout_proc21_evt_loop terminating...
+[2023-02-25 11:43:21,763][2391713] Stopping RolloutWorker_w6...
+[2023-02-25 11:43:21,763][2392044] Stopping RolloutWorker_w20...
+[2023-02-25 11:43:21,765][2391713] Loop rollout_proc6_evt_loop terminating...
+[2023-02-25 11:43:21,765][2391979] Stopping RolloutWorker_w15...
+[2023-02-25 11:43:21,765][2392044] Loop rollout_proc20_evt_loop terminating...
+[2023-02-25 11:43:21,766][2391979] Loop rollout_proc15_evt_loop terminating...
+[2023-02-25 11:43:21,763][2391722] Stopping RolloutWorker_w12...
+[2023-02-25 11:43:21,771][2392076] Stopping RolloutWorker_w23...
+[2023-02-25 11:43:21,771][2391722] Loop rollout_proc12_evt_loop terminating...
+[2023-02-25 11:43:21,771][2392478] Stopping RolloutWorker_w31...
+[2023-02-25 11:43:21,771][2392076] Loop rollout_proc23_evt_loop terminating...
+[2023-02-25 11:43:21,771][2392478] Loop rollout_proc31_evt_loop terminating...
+[2023-02-25 11:43:21,763][2392219] Stopping RolloutWorker_w30...
+[2023-02-25 11:43:21,775][2392219] Loop rollout_proc30_evt_loop terminating...
+[2023-02-25 11:43:21,763][2391693] Stopping RolloutWorker_w2...
+[2023-02-25 11:43:21,779][2391693] Loop rollout_proc2_evt_loop terminating...
+[2023-02-25 11:43:21,763][2392123] Stopping RolloutWorker_w24...
+[2023-02-25 11:43:21,783][2392123] Loop rollout_proc24_evt_loop terminating...
+[2023-02-25 11:43:21,763][2392203] Stopping RolloutWorker_w29...
+[2023-02-25 11:43:21,787][2392203] Loop rollout_proc29_evt_loop terminating...
+[2023-02-25 11:43:21,763][2391694] Loop rollout_proc3_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391720] Loop rollout_proc13_evt_loop terminating...
+[2023-02-25 11:43:21,763][2391996] Stopping RolloutWorker_w17...
+[2023-02-25 11:43:21,791][2391996] Loop rollout_proc17_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391717] Stopping RolloutWorker_w10...
+[2023-02-25 11:43:21,795][2391717] Loop rollout_proc10_evt_loop terminating...
+[2023-02-25 11:43:21,764][2392139] Stopping RolloutWorker_w25...
+[2023-02-25 11:43:21,799][2392139] Loop rollout_proc25_evt_loop terminating...
+[2023-02-25 11:43:21,764][2392171] Stopping RolloutWorker_w27...
+[2023-02-25 11:43:21,764][2391691] Loop inference_proc0-0_evt_loop terminating...
+[2023-02-25 11:43:21,803][2392171] Loop rollout_proc27_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391712] Loop rollout_proc4_evt_loop terminating...
+[2023-02-25 11:43:21,764][2391695] Loop rollout_proc1_evt_loop terminating...
+[2023-02-25 11:43:21,765][2392107] Loop rollout_proc22_evt_loop terminating...
+[2023-02-25 11:43:21,763][2391696] Stopping RolloutWorker_w5...
+[2023-02-25 11:43:21,765][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w6', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w20', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,815][2391555] Component RolloutWorker_w20 stopped!
+[2023-02-25 11:43:21,815][2391696] Loop rollout_proc5_evt_loop terminating...
+[2023-02-25 11:43:21,815][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w6', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,816][2391555] Component RolloutWorker_w6 stopped!
+[2023-02-25 11:43:21,816][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,816][2391555] Component RolloutWorker_w12 stopped!
+[2023-02-25 11:43:21,816][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,816][2391555] Component RolloutWorker_w30 stopped!
+[2023-02-25 11:43:21,816][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,817][2391555] Component RolloutWorker_w2 stopped!
+[2023-02-25 11:43:21,817][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,817][2391555] Component RolloutWorker_w5 stopped!
+[2023-02-25 11:43:21,817][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,817][2391555] Component RolloutWorker_w29 stopped!
+[2023-02-25 11:43:21,817][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,818][2391555] Component RolloutWorker_w24 stopped!
+[2023-02-25 11:43:21,818][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,818][2391555] Component RolloutWorker_w11 stopped!
+[2023-02-25 11:43:21,818][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,818][2391555] Component RolloutWorker_w17 stopped!
+[2023-02-25 11:43:21,771][2391692] Stopping RolloutWorker_w0...
+[2023-02-25 11:43:21,818][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,819][2391555] Component RolloutWorker_w10 stopped!
+[2023-02-25 11:43:21,819][2391692] Loop rollout_proc0_evt_loop terminating...
+[2023-02-25 11:43:21,819][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,819][2391555] Component RolloutWorker_w25 stopped!
+[2023-02-25 11:43:21,819][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,819][2391555] Component InferenceWorker_p0-w0 stopped!
+[2023-02-25 11:43:21,819][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,820][2391555] Component RolloutWorker_w27 stopped!
+[2023-02-25 11:43:21,820][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,820][2391555] Component RolloutWorker_w28 stopped!
+[2023-02-25 11:43:21,820][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,820][2391555] Component RolloutWorker_w4 stopped!
+[2023-02-25 11:43:21,820][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,820][2391555] Component RolloutWorker_w21 stopped!
+[2023-02-25 11:43:21,821][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,821][2391555] Component RolloutWorker_w22 stopped!
+[2023-02-25 11:43:21,821][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,821][2391555] Component RolloutWorker_w14 stopped!
+[2023-02-25 11:43:21,821][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,821][2391555] Component Batcher_0 stopped!
+[2023-02-25 11:43:21,821][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,821][2391555] Component RolloutWorker_w18 stopped!
+[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,822][2391555] Component RolloutWorker_w13 stopped!
+[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,822][2391555] Component RolloutWorker_w8 stopped!
+[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,822][2391555] Component RolloutWorker_w7 stopped!
+[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,822][2391555] Component RolloutWorker_w19 stopped!
+[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w1 stopped!
+[2023-02-25 11:43:21,823][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w16 stopped!
+[2023-02-25 11:43:21,823][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w15', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w15 stopped!
+[2023-02-25 11:43:21,823][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w23 stopped!
+[2023-02-25 11:43:21,823][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w0 stopped!
+[2023-02-25 11:43:21,824][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w31'] to stop...
+[2023-02-25 11:43:21,824][2391555] Component RolloutWorker_w31 stopped!
+[2023-02-25 11:43:21,824][2391555] Waiting for ['LearnerWorker_p0'] to stop...
+[2023-02-25 12:10:30,585][2391555] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 2391555], exiting...
+[2023-02-25 12:10:30,588][2391555] Runner profile tree view:
+main_loop: 3426.6990
+[2023-02-25 12:10:30,588][2391555] Collected {}, FPS: 0.0
+[2023-02-25 12:10:30,595][2391555] Loading existing experiment configuration from train_dir/default_experiment/config.json
+[2023-02-25 12:10:30,595][2391555] Overriding arg 'env' with value 'doom_health_gathering_supreme' passed from command line
+[2023-02-25 12:10:30,596][2391555] Overriding arg 'train_dir' with value 'train_dir' passed from command line
+[2023-02-25 12:10:30,596][2391555] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'hf_repository'='eldraco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-25 12:10:30,596][2391555] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-25 12:10:30,597][2391555] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-25 12:10:30,597][2391555] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-25 12:10:30,602][2391555] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 12:10:30,603][2391555] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-25 12:10:30,603][2391555] RunningMeanStd input shape: (1,)
+[2023-02-25 12:10:30,610][2391555] ConvEncoder: input_channels=3
+[2023-02-25 12:10:30,753][2391555] Conv encoder output size: 512
+[2023-02-25 12:10:30,753][2391555] Policy head output size: 512
+[2023-02-25 12:10:32,086][2391555] Loading state from checkpoint train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
+[2023-02-25 12:10:32,762][2391555] Num frames 100...
+[2023-02-25 12:10:32,829][2391555] Num frames 200...
+[2023-02-25 12:10:32,896][2391555] Num frames 300...
+[2023-02-25 12:10:32,964][2391555] Num frames 400...
+[2023-02-25 12:10:33,034][2391555] Num frames 500...
+[2023-02-25 12:10:33,121][2391555] Num frames 600...
+[2023-02-25 12:10:33,191][2391555] Num frames 700...
+[2023-02-25 12:10:33,261][2391555] Num frames 800...
+[2023-02-25 12:10:33,330][2391555] Num frames 900...
+[2023-02-25 12:10:33,398][2391555] Num frames 1000...
+[2023-02-25 12:10:33,466][2391555] Num frames 1100...
+[2023-02-25 12:10:33,536][2391555] Num frames 1200...
+[2023-02-25 12:10:33,605][2391555] Num frames 1300...
+[2023-02-25 12:10:33,673][2391555] Num frames 1400...
+[2023-02-25 12:10:33,741][2391555] Num frames 1500...
+[2023-02-25 12:10:33,796][2391555] Avg episode rewards: #0: 40.040, true rewards: #0: 15.040
+[2023-02-25 12:10:33,796][2391555] Avg episode reward: 40.040, avg true_objective: 15.040
+[2023-02-25 12:10:33,886][2391555] Num frames 1600...
+[2023-02-25 12:10:33,955][2391555] Num frames 1700...
+[2023-02-25 12:10:34,023][2391555] Num frames 1800...
+[2023-02-25 12:10:34,091][2391555] Num frames 1900...
+[2023-02-25 12:10:34,158][2391555] Num frames 2000...
+[2023-02-25 12:10:34,226][2391555] Num frames 2100...
+[2023-02-25 12:10:34,286][2391555] Avg episode rewards: #0: 25.560, true rewards: #0: 10.560
+[2023-02-25 12:10:34,287][2391555] Avg episode reward: 25.560, avg true_objective: 10.560
+[2023-02-25 12:10:34,371][2391555] Num frames 2200...
+[2023-02-25 12:10:34,439][2391555] Num frames 2300...
+[2023-02-25 12:10:34,506][2391555] Num frames 2400...
+[2023-02-25 12:10:34,573][2391555] Num frames 2500...
+[2023-02-25 12:10:34,642][2391555] Num frames 2600...
+[2023-02-25 12:10:34,711][2391555] Num frames 2700...
+[2023-02-25 12:10:34,780][2391555] Num frames 2800...
+[2023-02-25 12:10:34,842][2391555] Avg episode rewards: #0: 22.043, true rewards: #0: 9.377
+[2023-02-25 12:10:34,842][2391555] Avg episode reward: 22.043, avg true_objective: 9.377
+[2023-02-25 12:10:34,928][2391555] Num frames 2900...
+[2023-02-25 12:10:34,995][2391555] Num frames 3000...
+[2023-02-25 12:10:35,062][2391555] Num frames 3100...
+[2023-02-25 12:10:35,133][2391555] Num frames 3200...
+[2023-02-25 12:10:35,203][2391555] Num frames 3300...
+[2023-02-25 12:10:35,271][2391555] Num frames 3400...
+[2023-02-25 12:10:35,339][2391555] Num frames 3500...
+[2023-02-25 12:10:35,408][2391555] Num frames 3600...
+[2023-02-25 12:10:35,475][2391555] Num frames 3700...
+[2023-02-25 12:10:35,545][2391555] Num frames 3800...
+[2023-02-25 12:10:35,613][2391555] Num frames 3900...
+[2023-02-25 12:10:35,680][2391555] Num frames 4000...
+[2023-02-25 12:10:35,749][2391555] Num frames 4100...
+[2023-02-25 12:10:35,819][2391555] Num frames 4200...
+[2023-02-25 12:10:35,889][2391555] Num frames 4300...
+[2023-02-25 12:10:35,957][2391555] Num frames 4400...
+[2023-02-25 12:10:36,024][2391555] Num frames 4500...
+[2023-02-25 12:10:36,093][2391555] Num frames 4600...
+[2023-02-25 12:10:36,163][2391555] Num frames 4700...
+[2023-02-25 12:10:36,231][2391555] Num frames 4800...
+[2023-02-25 12:10:36,299][2391555] Num frames 4900...
+[2023-02-25 12:10:36,361][2391555] Avg episode rewards: #0: 31.282, true rewards: #0: 12.283
+[2023-02-25 12:10:36,361][2391555] Avg episode reward: 31.282, avg true_objective: 12.283
+[2023-02-25 12:10:36,443][2391555] Num frames 5000...
+[2023-02-25 12:10:36,511][2391555] Num frames 5100...
+[2023-02-25 12:10:36,580][2391555] Num frames 5200...
+[2023-02-25 12:10:36,647][2391555] Num frames 5300...
+[2023-02-25 12:10:36,716][2391555] Num frames 5400...
+[2023-02-25 12:10:36,786][2391555] Num frames 5500...
+[2023-02-25 12:10:36,854][2391555] Num frames 5600...
+[2023-02-25 12:10:36,923][2391555] Num frames 5700...
+[2023-02-25 12:10:36,991][2391555] Num frames 5800...
+[2023-02-25 12:10:37,060][2391555] Num frames 5900...
+[2023-02-25 12:10:37,128][2391555] Num frames 6000...
+[2023-02-25 12:10:37,198][2391555] Num frames 6100...
+[2023-02-25 12:10:37,280][2391555] Num frames 6200...
+[2023-02-25 12:10:37,350][2391555] Num frames 6300...
+[2023-02-25 12:10:37,418][2391555] Num frames 6400...
+[2023-02-25 12:10:37,488][2391555] Num frames 6500...
+[2023-02-25 12:10:37,557][2391555] Num frames 6600...
+[2023-02-25 12:10:37,625][2391555] Num frames 6700...
+[2023-02-25 12:10:37,696][2391555] Num frames 6800...
+[2023-02-25 12:10:37,765][2391555] Num frames 6900...
+[2023-02-25 12:10:37,834][2391555] Num frames 7000...
+[2023-02-25 12:10:37,895][2391555] Avg episode rewards: #0: 36.425, true rewards: #0: 14.026
+[2023-02-25 12:10:37,896][2391555] Avg episode reward: 36.425, avg true_objective: 14.026
+[2023-02-25 12:10:37,979][2391555] Num frames 7100...
+[2023-02-25 12:10:38,045][2391555] Num frames 7200...
+[2023-02-25 12:10:38,113][2391555] Num frames 7300...
+[2023-02-25 12:10:38,182][2391555] Num frames 7400...
+[2023-02-25 12:10:38,251][2391555] Num frames 7500...
+[2023-02-25 12:10:38,318][2391555] Num frames 7600...
+[2023-02-25 12:10:38,386][2391555] Num frames 7700...
+[2023-02-25 12:10:38,455][2391555] Num frames 7800...
+[2023-02-25 12:10:38,522][2391555] Num frames 7900...
+[2023-02-25 12:10:38,591][2391555] Num frames 8000...
+[2023-02-25 12:10:38,659][2391555] Num frames 8100...
+[2023-02-25 12:10:38,729][2391555] Num frames 8200...
+[2023-02-25 12:10:38,798][2391555] Num frames 8300...
+[2023-02-25 12:10:38,866][2391555] Num frames 8400...
+[2023-02-25 12:10:38,936][2391555] Num frames 8500...
+[2023-02-25 12:10:39,004][2391555] Num frames 8600...
+[2023-02-25 12:10:39,072][2391555] Num frames 8700...
+[2023-02-25 12:10:39,131][2391555] Avg episode rewards: #0: 38.514, true rewards: #0: 14.515
+[2023-02-25 12:10:39,131][2391555] Avg episode reward: 38.514, avg true_objective: 14.515
+[2023-02-25 12:10:39,218][2391555] Num frames 8800...
+[2023-02-25 12:10:39,287][2391555] Num frames 8900...
+[2023-02-25 12:10:39,364][2391555] Num frames 9000...
+[2023-02-25 12:10:39,433][2391555] Num frames 9100...
+[2023-02-25 12:10:39,502][2391555] Num frames 9200...
+[2023-02-25 12:10:39,570][2391555] Num frames 9300...
+[2023-02-25 12:10:39,638][2391555] Num frames 9400...
+[2023-02-25 12:10:39,706][2391555] Num frames 9500...
+[2023-02-25 12:10:39,774][2391555] Num frames 9600...
+[2023-02-25 12:10:39,842][2391555] Num frames 9700...
+[2023-02-25 12:10:39,934][2391555] Avg episode rewards: #0: 36.367, true rewards: #0: 13.939
+[2023-02-25 12:10:39,935][2391555] Avg episode reward: 36.367, avg true_objective: 13.939
+[2023-02-25 12:10:40,022][2391555] Num frames 9800...
+[2023-02-25 12:10:40,090][2391555] Num frames 9900...
+[2023-02-25 12:10:40,159][2391555] Num frames 10000...
+[2023-02-25 12:10:40,227][2391555] Num frames 10100...
+[2023-02-25 12:10:40,296][2391555] Num frames 10200...
+[2023-02-25 12:10:40,365][2391555] Num frames 10300...
+[2023-02-25 12:10:40,434][2391555] Num frames 10400...
+[2023-02-25 12:10:40,503][2391555] Num frames 10500...
+[2023-02-25 12:10:40,571][2391555] Num frames 10600...
+[2023-02-25 12:10:40,641][2391555] Num frames 10700...
+[2023-02-25 12:10:40,712][2391555] Num frames 10800...
+[2023-02-25 12:10:40,783][2391555] Num frames 10900...
+[2023-02-25 12:10:40,852][2391555] Num frames 11000...
+[2023-02-25 12:10:40,922][2391555] Num frames 11100...
+[2023-02-25 12:10:40,991][2391555] Num frames 11200...
+[2023-02-25 12:10:41,048][2391555] Avg episode rewards: #0: 36.757, true rewards: #0: 14.007
+[2023-02-25 12:10:41,048][2391555] Avg episode reward: 36.757, avg true_objective: 14.007
+[2023-02-25 12:10:41,141][2391555] Num frames 11300...
+[2023-02-25 12:10:41,209][2391555] Num frames 11400...
+[2023-02-25 12:10:41,278][2391555] Num frames 11500...
+[2023-02-25 12:10:41,347][2391555] Num frames 11600...
+[2023-02-25 12:10:41,419][2391555] Num frames 11700...
+[2023-02-25 12:10:41,489][2391555] Num frames 11800...
+[2023-02-25 12:10:41,559][2391555] Num frames 11900...
+[2023-02-25 12:10:41,626][2391555] Num frames 12000...
+[2023-02-25 12:10:41,694][2391555] Num frames 12100...
+[2023-02-25 12:10:41,793][2391555] Avg episode rewards: #0: 34.740, true rewards: #0: 13.518
+[2023-02-25 12:10:41,793][2391555] Avg episode reward: 34.740, avg true_objective: 13.518
+[2023-02-25 12:10:41,834][2391555] Num frames 12200...
+[2023-02-25 12:10:41,911][2391555] Num frames 12300...
+[2023-02-25 12:10:41,981][2391555] Num frames 12400...
+[2023-02-25 12:10:42,050][2391555] Num frames 12500...
+[2023-02-25 12:10:42,121][2391555] Num frames 12600...
+[2023-02-25 12:10:42,192][2391555] Num frames 12700...
+[2023-02-25 12:10:42,261][2391555] Num frames 12800...
+[2023-02-25 12:10:42,330][2391555] Num frames 12900...
+[2023-02-25 12:10:42,399][2391555] Num frames 13000...
+[2023-02-25 12:10:42,468][2391555] Num frames 13100...
+[2023-02-25 12:10:42,538][2391555] Num frames 13200...
+[2023-02-25 12:10:42,607][2391555] Num frames 13300...
+[2023-02-25 12:10:42,675][2391555] Num frames 13400...
+[2023-02-25 12:10:42,748][2391555] Num frames 13500...
+[2023-02-25 12:10:42,820][2391555] Num frames 13600...
+[2023-02-25 12:10:42,891][2391555] Num frames 13700...
+[2023-02-25 12:10:42,964][2391555] Num frames 13800...
+[2023-02-25 12:10:43,037][2391555] Num frames 13900...
+[2023-02-25 12:10:43,108][2391555] Num frames 14000...
+[2023-02-25 12:10:43,178][2391555] Num frames 14100...
+[2023-02-25 12:10:43,251][2391555] Num frames 14200...
+[2023-02-25 12:10:43,351][2391555] Avg episode rewards: #0: 37.566, true rewards: #0: 14.266
+[2023-02-25 12:10:43,351][2391555] Avg episode reward: 37.566, avg true_objective: 14.266
+[2023-02-25 12:11:00,944][2391555] Replay video saved to train_dir/default_experiment/replay.mp4!