Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1690675777.bf83178a6ebb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95ddbccddc16d82c341f18fc42b1c24320f59eab19110ef13f7ce223b06e3d5
+size 167282

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 8.81 +/- 4.72
+      value: 12.76 +/- 7.35
       name: mean_reward
       verified: false
 ---
@@ -38,19 +38,19 @@ python -m sample_factory.huggingface.load_from_hub -r timjwhite/rl_course_vizdoo
 
 To run the model after download, use the `enjoy` script corresponding to this environment:
 ```
-python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
+python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
 ```
 
 
 You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
 See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
-        
+    
 ## Training with this model
 
 To continue training with this model, use the `train` script corresponding to this environment:
 ```
-python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
+python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
 ```
 
 Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
-        
+    

checkpoint_p0/best_000000967_3960832_reward_28.867.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11659dff19234de81d800c86c8b63318f5e75af862dd2493c77c349fe1c73546
+size 34928614

checkpoint_p0/checkpoint_000000546_2236416.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0026cd1acca33ea14cd5674058dda3dac87528525f4393fc08cc6bb272878b20
+size 34929028

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55658880256cf391f1394a9ebcbf94bc8e7db3340c6c7a6cc6dd9f60605e5db
+oid sha256:27749042e16b54626884c00e90c6f52e18461710254d7e2b0837080ec1a7b9eb
 size 34929028

config.json

@@ -15,7 +15,7 @@
   "worker_num_splits": 2,
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
-  "num_workers": 8,
+  "num_workers": 16,
   "num_envs_per_worker": 4,
   "batch_size": 1024,
   "num_batches_per_epoch": 1,
@@ -46,6 +46,8 @@
   "learning_rate": 0.0001,
   "lr_schedule": "constant",
   "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
   "obs_subtract_mean": 0.0,
   "obs_scale": 255.0,
   "normalize_input": true,
@@ -128,14 +130,13 @@
   "wide_aspect_ratio": false,
   "eval_env_frameskip": 1,
   "fps": 35,
-  "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
+  "command_line": "--env=doom_health_gathering_supreme --num_workers=16 --num_envs_per_worker=4 --train_for_env_steps=4000000",
   "cli_args": {
     "env": "doom_health_gathering_supreme",
-    "num_workers": 8,
+    "num_workers": 16,
     "num_envs_per_worker": 4,
     "train_for_env_steps": 4000000
   },
   "git_hash": "unknown",
-  "git_repo_name": "not a git repository",
-  "train_script": ".usr.local.lib.python3.10.dist-packages.ipykernel_launcher"
+  "git_repo_name": "not a git repository"
 }

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f5eb581dfa653bf1614338430fe9a53d031674d7aaf9f29ccc68f88baada04
-size 17077762
+oid sha256:79027abbf16ef6c179f71c3a8b0a0d84c4c64fd4f1319e1737cea4c69c7db2ee
+size 24498656

sf_log.txt

@@ -0,0 +1,870 @@
+[2023-07-30 00:09:42,981][03333] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2023-07-30 00:09:42,983][03333] Rollout worker 0 uses device cpu
+[2023-07-30 00:09:42,984][03333] Rollout worker 1 uses device cpu
+[2023-07-30 00:09:42,986][03333] Rollout worker 2 uses device cpu
+[2023-07-30 00:09:42,987][03333] Rollout worker 3 uses device cpu
+[2023-07-30 00:09:42,988][03333] Rollout worker 4 uses device cpu
+[2023-07-30 00:09:42,990][03333] Rollout worker 5 uses device cpu
+[2023-07-30 00:09:42,991][03333] Rollout worker 6 uses device cpu
+[2023-07-30 00:09:42,992][03333] Rollout worker 7 uses device cpu
+[2023-07-30 00:09:42,993][03333] Rollout worker 8 uses device cpu
+[2023-07-30 00:09:42,994][03333] Rollout worker 9 uses device cpu
+[2023-07-30 00:09:42,996][03333] Rollout worker 10 uses device cpu
+[2023-07-30 00:09:42,997][03333] Rollout worker 11 uses device cpu
+[2023-07-30 00:09:42,998][03333] Rollout worker 12 uses device cpu
+[2023-07-30 00:09:42,999][03333] Rollout worker 13 uses device cpu
+[2023-07-30 00:09:43,000][03333] Rollout worker 14 uses device cpu
+[2023-07-30 00:09:43,001][03333] Rollout worker 15 uses device cpu
+[2023-07-30 00:09:43,121][03333] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-30 00:09:43,122][03333] InferenceWorker_p0-w0: min num requests: 5
+[2023-07-30 00:09:43,180][03333] Starting all processes...
+[2023-07-30 00:09:43,182][03333] Starting process learner_proc0
+[2023-07-30 00:09:43,229][03333] Starting all processes...
+[2023-07-30 00:09:43,234][03333] Starting process inference_proc0-0
+[2023-07-30 00:09:43,235][03333] Starting process rollout_proc0
+[2023-07-30 00:09:43,236][03333] Starting process rollout_proc1
+[2023-07-30 00:09:43,237][03333] Starting process rollout_proc2
+[2023-07-30 00:09:43,238][03333] Starting process rollout_proc3
+[2023-07-30 00:09:43,240][03333] Starting process rollout_proc4
+[2023-07-30 00:09:43,241][03333] Starting process rollout_proc5
+[2023-07-30 00:09:43,242][03333] Starting process rollout_proc6
+[2023-07-30 00:09:43,248][03333] Starting process rollout_proc7
+[2023-07-30 00:09:43,249][03333] Starting process rollout_proc8
+[2023-07-30 00:09:43,253][03333] Starting process rollout_proc9
+[2023-07-30 00:09:43,254][03333] Starting process rollout_proc10
+[2023-07-30 00:09:43,254][03333] Starting process rollout_proc11
+[2023-07-30 00:09:43,255][03333] Starting process rollout_proc12
+[2023-07-30 00:09:43,267][03333] Starting process rollout_proc13
+[2023-07-30 00:09:43,267][03333] Starting process rollout_proc14
+[2023-07-30 00:09:43,297][03333] Starting process rollout_proc15
+[2023-07-30 00:09:46,862][09298] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-30 00:09:46,862][09298] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-07-30 00:09:46,878][09298] Num visible devices: 1
+[2023-07-30 00:09:46,946][09298] Starting seed is not provided
+[2023-07-30 00:09:46,946][09298] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-30 00:09:46,946][09298] Initializing actor-critic model on device cuda:0
+[2023-07-30 00:09:46,947][09298] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-30 00:09:46,949][09298] RunningMeanStd input shape: (1,)
+[2023-07-30 00:09:46,991][09298] ConvEncoder: input_channels=3
+[2023-07-30 00:09:47,339][09324] Worker 6 uses CPU cores [6]
+[2023-07-30 00:09:47,546][09298] Conv encoder output size: 512
+[2023-07-30 00:09:47,546][09298] Policy head output size: 512
+[2023-07-30 00:09:47,628][09298] Created Actor Critic model with architecture:
+[2023-07-30 00:09:47,628][09298] 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)
+  )
+)
+[2023-07-30 00:09:47,806][09328] Worker 9 uses CPU cores [9]
+[2023-07-30 00:09:47,809][09327] Worker 8 uses CPU cores [8]
+[2023-07-30 00:09:47,935][09342] Worker 11 uses CPU cores [11]
+[2023-07-30 00:09:47,992][09318] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-30 00:09:47,992][09318] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-07-30 00:09:48,014][09322] Worker 4 uses CPU cores [4]
+[2023-07-30 00:09:48,018][09318] Num visible devices: 1
+[2023-07-30 00:09:48,036][09320] Worker 0 uses CPU cores [0]
+[2023-07-30 00:09:48,056][09321] Worker 3 uses CPU cores [3]
+[2023-07-30 00:09:48,154][09326] Worker 7 uses CPU cores [7]
+[2023-07-30 00:09:48,156][09323] Worker 5 uses CPU cores [5]
+[2023-07-30 00:09:48,158][09348] Worker 15 uses CPU cores [9, 10, 11]
+[2023-07-30 00:09:48,158][09325] Worker 2 uses CPU cores [2]
+[2023-07-30 00:09:48,296][09341] Worker 10 uses CPU cores [10]
+[2023-07-30 00:09:48,395][09340] Worker 13 uses CPU cores [3, 4, 5]
+[2023-07-30 00:09:48,456][09349] Worker 14 uses CPU cores [6, 7, 8]
+[2023-07-30 00:09:48,493][09319] Worker 1 uses CPU cores [1]
+[2023-07-30 00:09:48,543][09343] Worker 12 uses CPU cores [0, 1, 2]
+[2023-07-30 00:09:55,974][09298] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-07-30 00:09:55,975][09298] No checkpoints found
+[2023-07-30 00:09:55,975][09298] Did not load from checkpoint, starting from scratch!
+[2023-07-30 00:09:55,975][09298] Initialized policy 0 weights for model version 0
+[2023-07-30 00:09:55,978][09298] LearnerWorker_p0 finished initialization!
+[2023-07-30 00:09:55,978][09298] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-30 00:09:56,049][09318] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-30 00:09:56,050][09318] RunningMeanStd input shape: (1,)
+[2023-07-30 00:09:56,062][09318] ConvEncoder: input_channels=3
+[2023-07-30 00:09:56,168][09318] Conv encoder output size: 512
+[2023-07-30 00:09:56,168][09318] Policy head output size: 512
+[2023-07-30 00:09:56,257][03333] Inference worker 0-0 is ready!
+[2023-07-30 00:09:56,259][03333] All inference workers are ready! Signal rollout workers to start!
+[2023-07-30 00:09:56,316][09322] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,316][09328] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,317][09327] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,317][09324] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,317][09319] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,318][09325] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,319][09323] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,320][09342] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,367][09349] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,367][09340] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,368][09348] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,369][09343] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,370][09326] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,370][09321] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,370][09320] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,371][09341] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:09:56,440][09324] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process...
+[2023-07-30 00:09:56,442][09324] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=()
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init
+    self.game.init()
+vizdoom.vizdoom.ViZDoomUnexpectedExitException: Controlled ViZDoom instance exited unexpectedly.
+
+During handling of the above exception, another exception occurred:
+
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
+    slot_callable(*args)
+  File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init
+    env_runner.init(self.timing)
+  File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init
+    self._reset()
+  File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset
+    observations, info = e.reset(seed=seed)  # new way of doing seeding since Gym 0.26.0
+  File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 453, in reset
+    return self.env.reset(seed=seed, options=options)
+  File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 125, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 110, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset
+    return self.env.reset(**kwargs)
+  File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 501, in reset
+    obs, info = self.env.reset(seed=seed, options=options)
+  File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 82, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 453, in reset
+    return self.env.reset(seed=seed, options=options)
+  File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset
+    return self.env.reset(**kwargs)
+  File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset
+    self._ensure_initialized()
+  File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized
+    self.initialize()
+  File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize
+    self._game_init()
+  File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init
+    raise EnvCriticalError()
+sample_factory.envs.env_utils.EnvCriticalError
+[2023-07-30 00:09:56,445][09324] Unhandled exception  in evt loop rollout_proc6_evt_loop
+[2023-07-30 00:09:56,698][09319] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:56,698][09322] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:56,698][09325] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:56,790][09320] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:56,795][09342] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:56,807][09323] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:56,831][09321] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:56,840][09348] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:56,995][09328] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:57,000][09319] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,052][09340] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:57,070][09343] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:57,106][09327] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:57,177][09342] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,227][09326] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:57,318][09343] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,388][09341] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:57,396][09322] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,397][09323] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,408][09319] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:57,508][09340] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,652][09320] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,663][09348] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,700][09349] Decorrelating experience for 0 frames...
+[2023-07-30 00:09:57,763][09326] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,763][09341] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:57,765][09323] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:57,916][03333] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-07-30 00:09:57,937][09319] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:57,944][09349] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:58,021][09327] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:58,069][09322] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,098][09342] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,195][09326] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,199][09323] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:58,277][09341] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,298][09343] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,333][09348] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,478][09349] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,496][09328] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:58,505][09340] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,543][09320] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,580][09327] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:58,619][09322] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:58,683][09348] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:58,717][09325] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:58,727][09341] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:58,864][09343] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:58,889][09321] Decorrelating experience for 32 frames...
+[2023-07-30 00:09:58,901][09326] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:58,989][09340] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:59,013][09327] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:59,126][09328] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:59,223][09342] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:59,231][09325] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:59,410][09349] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:59,413][09321] Decorrelating experience for 64 frames...
+[2023-07-30 00:09:59,507][09320] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:59,573][09328] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:59,597][09325] Decorrelating experience for 96 frames...
+[2023-07-30 00:09:59,861][09321] Decorrelating experience for 96 frames...
+[2023-07-30 00:10:00,503][09298] Signal inference workers to stop experience collection...
+[2023-07-30 00:10:00,510][09318] InferenceWorker_p0-w0: stopping experience collection
+[2023-07-30 00:10:02,916][03333] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 1032.4. Samples: 5162. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-07-30 00:10:02,917][03333] Avg episode reward: [(0, '2.490')]
+[2023-07-30 00:10:03,114][03333] Heartbeat connected on Batcher_0
+[2023-07-30 00:10:03,121][03333] Heartbeat connected on InferenceWorker_p0-w0
+[2023-07-30 00:10:03,128][03333] Heartbeat connected on RolloutWorker_w0
+[2023-07-30 00:10:03,131][03333] Heartbeat connected on RolloutWorker_w1
+[2023-07-30 00:10:03,136][03333] Heartbeat connected on RolloutWorker_w2
+[2023-07-30 00:10:03,139][03333] Heartbeat connected on RolloutWorker_w3
+[2023-07-30 00:10:03,142][03333] Heartbeat connected on RolloutWorker_w4
+[2023-07-30 00:10:03,146][03333] Heartbeat connected on RolloutWorker_w5
+[2023-07-30 00:10:03,152][03333] Heartbeat connected on RolloutWorker_w7
+[2023-07-30 00:10:03,156][03333] Heartbeat connected on RolloutWorker_w8
+[2023-07-30 00:10:03,159][03333] Heartbeat connected on RolloutWorker_w9
+[2023-07-30 00:10:03,162][03333] Heartbeat connected on RolloutWorker_w10
+[2023-07-30 00:10:03,165][03333] Heartbeat connected on RolloutWorker_w11
+[2023-07-30 00:10:03,169][03333] Heartbeat connected on RolloutWorker_w12
+[2023-07-30 00:10:03,172][03333] Heartbeat connected on RolloutWorker_w13
+[2023-07-30 00:10:03,176][03333] Heartbeat connected on RolloutWorker_w14
+[2023-07-30 00:10:03,179][03333] Heartbeat connected on RolloutWorker_w15
+[2023-07-30 00:10:04,786][09298] Signal inference workers to resume experience collection...
+[2023-07-30 00:10:04,787][09318] InferenceWorker_p0-w0: resuming experience collection
+[2023-07-30 00:10:05,673][03333] Heartbeat connected on LearnerWorker_p0
+[2023-07-30 00:10:07,142][09318] Updated weights for policy 0, policy_version 10 (0.0011)
+[2023-07-30 00:10:07,916][03333] Fps is (10 sec: 5324.8, 60 sec: 5324.8, 300 sec: 5324.8). Total num frames: 53248. Throughput: 0: 523.8. Samples: 5238. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2023-07-30 00:10:07,918][03333] Avg episode reward: [(0, '4.400')]
+[2023-07-30 00:10:09,036][09318] Updated weights for policy 0, policy_version 20 (0.0013)
+[2023-07-30 00:10:10,841][09318] Updated weights for policy 0, policy_version 30 (0.0013)
+[2023-07-30 00:10:12,528][09318] Updated weights for policy 0, policy_version 40 (0.0013)
+[2023-07-30 00:10:12,916][03333] Fps is (10 sec: 17202.7, 60 sec: 11468.7, 300 sec: 11468.7). Total num frames: 172032. Throughput: 0: 2314.9. Samples: 34724. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2023-07-30 00:10:12,919][03333] Avg episode reward: [(0, '4.316')]
+[2023-07-30 00:10:12,922][09298] Saving new best policy, reward=4.316!
+[2023-07-30 00:10:14,277][09318] Updated weights for policy 0, policy_version 50 (0.0015)
+[2023-07-30 00:10:15,871][09318] Updated weights for policy 0, policy_version 60 (0.0012)
+[2023-07-30 00:10:17,575][09318] Updated weights for policy 0, policy_version 70 (0.0013)
+[2023-07-30 00:10:17,916][03333] Fps is (10 sec: 24166.4, 60 sec: 14745.7, 300 sec: 14745.7). Total num frames: 294912. Throughput: 0: 3555.7. Samples: 71114. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2023-07-30 00:10:17,918][03333] Avg episode reward: [(0, '4.485')]
+[2023-07-30 00:10:17,926][09298] Saving new best policy, reward=4.485!
+[2023-07-30 00:10:19,186][09318] Updated weights for policy 0, policy_version 80 (0.0013)
+[2023-07-30 00:10:20,861][09318] Updated weights for policy 0, policy_version 90 (0.0012)
+[2023-07-30 00:10:22,459][09318] Updated weights for policy 0, policy_version 100 (0.0013)
+[2023-07-30 00:10:22,916][03333] Fps is (10 sec: 24986.1, 60 sec: 16875.6, 300 sec: 16875.6). Total num frames: 421888. Throughput: 0: 3598.6. Samples: 89964. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2023-07-30 00:10:22,919][03333] Avg episode reward: [(0, '4.432')]
+[2023-07-30 00:10:24,027][09318] Updated weights for policy 0, policy_version 110 (0.0013)
+[2023-07-30 00:10:25,904][09318] Updated weights for policy 0, policy_version 120 (0.0012)
+[2023-07-30 00:10:27,683][09318] Updated weights for policy 0, policy_version 130 (0.0012)
+[2023-07-30 00:10:27,916][03333] Fps is (10 sec: 24166.2, 60 sec: 17885.9, 300 sec: 17885.9). Total num frames: 536576. Throughput: 0: 4203.4. Samples: 126102. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2023-07-30 00:10:27,918][03333] Avg episode reward: [(0, '5.123')]
+[2023-07-30 00:10:27,926][09298] Saving new best policy, reward=5.123!
+[2023-07-30 00:10:29,465][09318] Updated weights for policy 0, policy_version 140 (0.0013)
+[2023-07-30 00:10:31,238][09318] Updated weights for policy 0, policy_version 150 (0.0012)
+[2023-07-30 00:10:32,917][09318] Updated weights for policy 0, policy_version 160 (0.0012)
+[2023-07-30 00:10:32,916][03333] Fps is (10 sec: 23347.3, 60 sec: 18724.6, 300 sec: 18724.6). Total num frames: 655360. Throughput: 0: 4601.3. Samples: 161044. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2023-07-30 00:10:32,918][03333] Avg episode reward: [(0, '4.944')]
+[2023-07-30 00:10:34,643][09318] Updated weights for policy 0, policy_version 170 (0.0014)
+[2023-07-30 00:10:36,272][09318] Updated weights for policy 0, policy_version 180 (0.0013)
+[2023-07-30 00:10:37,847][09318] Updated weights for policy 0, policy_version 190 (0.0013)
+[2023-07-30 00:10:37,916][03333] Fps is (10 sec: 24166.4, 60 sec: 19456.0, 300 sec: 19456.0). Total num frames: 778240. Throughput: 0: 4481.4. Samples: 179256. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2023-07-30 00:10:37,919][03333] Avg episode reward: [(0, '5.436')]
+[2023-07-30 00:10:37,924][09298] Saving new best policy, reward=5.436!
+[2023-07-30 00:10:39,508][09318] Updated weights for policy 0, policy_version 200 (0.0012)
+[2023-07-30 00:10:41,127][09318] Updated weights for policy 0, policy_version 210 (0.0013)
+[2023-07-30 00:10:42,699][09318] Updated weights for policy 0, policy_version 220 (0.0013)
+[2023-07-30 00:10:42,916][03333] Fps is (10 sec: 24575.9, 60 sec: 20024.9, 300 sec: 20024.9). Total num frames: 901120. Throughput: 0: 4825.9. Samples: 217166. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2023-07-30 00:10:42,918][03333] Avg episode reward: [(0, '6.177')]
+[2023-07-30 00:10:42,925][09298] Saving new best policy, reward=6.177!
+[2023-07-30 00:10:44,342][09318] Updated weights for policy 0, policy_version 230 (0.0013)
+[2023-07-30 00:10:46,048][09318] Updated weights for policy 0, policy_version 240 (0.0013)
+[2023-07-30 00:10:47,846][09318] Updated weights for policy 0, policy_version 250 (0.0015)
+[2023-07-30 00:10:47,916][03333] Fps is (10 sec: 24576.0, 60 sec: 20480.0, 300 sec: 20480.0). Total num frames: 1024000. Throughput: 0: 5529.5. Samples: 253992. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2023-07-30 00:10:47,918][03333] Avg episode reward: [(0, '6.797')]
+[2023-07-30 00:10:47,925][09298] Saving new best policy, reward=6.797!
+[2023-07-30 00:10:49,605][09318] Updated weights for policy 0, policy_version 260 (0.0014)
+[2023-07-30 00:10:51,389][09318] Updated weights for policy 0, policy_version 270 (0.0015)
+[2023-07-30 00:10:52,916][03333] Fps is (10 sec: 23755.5, 60 sec: 20703.2, 300 sec: 20703.2). Total num frames: 1138688. Throughput: 0: 5913.3. Samples: 271338. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2023-07-30 00:10:52,919][03333] Avg episode reward: [(0, '7.138')]
+[2023-07-30 00:10:52,921][09298] Saving new best policy, reward=7.138!
+[2023-07-30 00:10:53,179][09318] Updated weights for policy 0, policy_version 280 (0.0012)
+[2023-07-30 00:10:54,844][09318] Updated weights for policy 0, policy_version 290 (0.0012)
+[2023-07-30 00:10:56,459][09318] Updated weights for policy 0, policy_version 300 (0.0012)
+[2023-07-30 00:10:57,916][03333] Fps is (10 sec: 24165.8, 60 sec: 21094.3, 300 sec: 21094.3). Total num frames: 1265664. Throughput: 0: 6054.0. Samples: 307156. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2023-07-30 00:10:57,918][03333] Avg episode reward: [(0, '7.637')]
+[2023-07-30 00:10:57,926][09298] Saving new best policy, reward=7.637!
+[2023-07-30 00:10:58,119][09318] Updated weights for policy 0, policy_version 310 (0.0012)
+[2023-07-30 00:10:59,716][09318] Updated weights for policy 0, policy_version 320 (0.0013)
+[2023-07-30 00:11:01,281][09318] Updated weights for policy 0, policy_version 330 (0.0012)
+[2023-07-30 00:11:02,916][03333] Fps is (10 sec: 24986.8, 60 sec: 23142.3, 300 sec: 21362.2). Total num frames: 1388544. Throughput: 0: 6087.9. Samples: 345070. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2023-07-30 00:11:02,918][03333] Avg episode reward: [(0, '9.192')]
+[2023-07-30 00:11:02,921][09298] Saving new best policy, reward=9.192!
+[2023-07-30 00:11:03,042][09318] Updated weights for policy 0, policy_version 340 (0.0013)
+[2023-07-30 00:11:04,595][09318] Updated weights for policy 0, policy_version 350 (0.0013)
+[2023-07-30 00:11:06,341][09318] Updated weights for policy 0, policy_version 360 (0.0012)
+[2023-07-30 00:11:07,916][03333] Fps is (10 sec: 24576.5, 60 sec: 24302.9, 300 sec: 21591.8). Total num frames: 1511424. Throughput: 0: 6083.3. Samples: 363714. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2023-07-30 00:11:07,919][03333] Avg episode reward: [(0, '11.200')]
+[2023-07-30 00:11:07,925][09298] Saving new best policy, reward=11.200!
+[2023-07-30 00:11:08,084][09318] Updated weights for policy 0, policy_version 370 (0.0012)
+[2023-07-30 00:11:09,830][09318] Updated weights for policy 0, policy_version 380 (0.0013)
+[2023-07-30 00:11:11,572][09318] Updated weights for policy 0, policy_version 390 (0.0012)
+[2023-07-30 00:11:12,916][03333] Fps is (10 sec: 23756.9, 60 sec: 24234.7, 300 sec: 21681.5). Total num frames: 1626112. Throughput: 0: 6058.6. Samples: 398738. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-07-30 00:11:12,919][03333] Avg episode reward: [(0, '13.847')]
+[2023-07-30 00:11:12,922][09298] Saving new best policy, reward=13.847!
+[2023-07-30 00:11:13,364][09318] Updated weights for policy 0, policy_version 400 (0.0014)
+[2023-07-30 00:11:15,048][09318] Updated weights for policy 0, policy_version 410 (0.0013)
+[2023-07-30 00:11:16,723][09318] Updated weights for policy 0, policy_version 420 (0.0013)
+[2023-07-30 00:11:17,916][03333] Fps is (10 sec: 23756.8, 60 sec: 24234.6, 300 sec: 21862.4). Total num frames: 1748992. Throughput: 0: 6078.8. Samples: 434592. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2023-07-30 00:11:17,918][03333] Avg episode reward: [(0, '16.431')]
+[2023-07-30 00:11:17,928][09298] Saving new best policy, reward=16.431!
+[2023-07-30 00:11:18,358][09318] Updated weights for policy 0, policy_version 430 (0.0013)
+[2023-07-30 00:11:20,021][09318] Updated weights for policy 0, policy_version 440 (0.0013)
+[2023-07-30 00:11:21,604][09318] Updated weights for policy 0, policy_version 450 (0.0013)
+[2023-07-30 00:11:22,916][03333] Fps is (10 sec: 24985.7, 60 sec: 24234.7, 300 sec: 22070.2). Total num frames: 1875968. Throughput: 0: 6098.5. Samples: 453690. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2023-07-30 00:11:22,919][03333] Avg episode reward: [(0, '18.854')]
+[2023-07-30 00:11:22,923][09298] Saving new best policy, reward=18.854!
+[2023-07-30 00:11:23,226][09318] Updated weights for policy 0, policy_version 460 (0.0013)
+[2023-07-30 00:11:24,846][09318] Updated weights for policy 0, policy_version 470 (0.0012)
+[2023-07-30 00:11:26,507][09318] Updated weights for policy 0, policy_version 480 (0.0012)
+[2023-07-30 00:11:27,916][03333] Fps is (10 sec: 24985.5, 60 sec: 24371.2, 300 sec: 22209.4). Total num frames: 1998848. Throughput: 0: 6094.8. Samples: 491434. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2023-07-30 00:11:27,918][03333] Avg episode reward: [(0, '19.345')]
+[2023-07-30 00:11:27,925][09298] Saving new best policy, reward=19.345!
+[2023-07-30 00:11:28,253][09318] Updated weights for policy 0, policy_version 490 (0.0013)
+[2023-07-30 00:11:30,039][09318] Updated weights for policy 0, policy_version 500 (0.0014)
+[2023-07-30 00:11:31,782][09318] Updated weights for policy 0, policy_version 510 (0.0013)
+[2023-07-30 00:11:32,916][03333] Fps is (10 sec: 23756.3, 60 sec: 24302.8, 300 sec: 22247.7). Total num frames: 2113536. Throughput: 0: 6053.9. Samples: 526420. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2023-07-30 00:11:32,919][03333] Avg episode reward: [(0, '16.344')]
+[2023-07-30 00:11:33,474][09318] Updated weights for policy 0, policy_version 520 (0.0013)
+[2023-07-30 00:11:35,226][09318] Updated weights for policy 0, policy_version 530 (0.0013)
+[2023-07-30 00:11:36,862][09318] Updated weights for policy 0, policy_version 540 (0.0013)
+[2023-07-30 00:11:37,916][03333] Fps is (10 sec: 23756.7, 60 sec: 24302.9, 300 sec: 22364.1). Total num frames: 2236416. Throughput: 0: 6065.3. Samples: 544274. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2023-07-30 00:11:37,918][03333] Avg episode reward: [(0, '18.867')]
+[2023-07-30 00:11:37,927][09298] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000546_2236416.pth...
+[2023-07-30 00:11:38,448][09318] Updated weights for policy 0, policy_version 550 (0.0013)
+[2023-07-30 00:11:40,076][09318] Updated weights for policy 0, policy_version 560 (0.0013)
+[2023-07-30 00:11:41,688][09318] Updated weights for policy 0, policy_version 570 (0.0013)
+[2023-07-30 00:11:42,916][03333] Fps is (10 sec: 24986.1, 60 sec: 24371.2, 300 sec: 22508.5). Total num frames: 2363392. Throughput: 0: 6115.0. Samples: 582330. Policy #0 lag: (min: 0.0, avg: 1.0, max: 4.0)
+[2023-07-30 00:11:42,918][03333] Avg episode reward: [(0, '20.105')]
+[2023-07-30 00:11:42,926][09298] Saving new best policy, reward=20.105!
+[2023-07-30 00:11:43,319][09318] Updated weights for policy 0, policy_version 580 (0.0013)
+[2023-07-30 00:11:44,935][09318] Updated weights for policy 0, policy_version 590 (0.0013)
+[2023-07-30 00:11:46,598][09318] Updated weights for policy 0, policy_version 600 (0.0012)
+[2023-07-30 00:11:47,916][03333] Fps is (10 sec: 24986.0, 60 sec: 24371.2, 300 sec: 22602.5). Total num frames: 2486272. Throughput: 0: 6101.3. Samples: 619628. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-07-30 00:11:47,918][03333] Avg episode reward: [(0, '19.765')]
+[2023-07-30 00:11:48,369][09318] Updated weights for policy 0, policy_version 610 (0.0012)
+[2023-07-30 00:11:50,128][09318] Updated weights for policy 0, policy_version 620 (0.0012)
+[2023-07-30 00:11:51,789][09318] Updated weights for policy 0, policy_version 630 (0.0012)
+[2023-07-30 00:11:52,916][03333] Fps is (10 sec: 24166.3, 60 sec: 24439.7, 300 sec: 22652.7). Total num frames: 2605056. Throughput: 0: 6074.8. Samples: 637080. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2023-07-30 00:11:52,918][03333] Avg episode reward: [(0, '21.413')]
+[2023-07-30 00:11:52,921][09298] Saving new best policy, reward=21.413!
+[2023-07-30 00:11:53,559][09318] Updated weights for policy 0, policy_version 640 (0.0012)
+[2023-07-30 00:11:55,314][09318] Updated weights for policy 0, policy_version 650 (0.0013)
+[2023-07-30 00:11:56,985][09318] Updated weights for policy 0, policy_version 660 (0.0012)
+[2023-07-30 00:11:57,916][03333] Fps is (10 sec: 23756.3, 60 sec: 24303.0, 300 sec: 22698.6). Total num frames: 2723840. Throughput: 0: 6086.8. Samples: 672644. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2023-07-30 00:11:57,918][03333] Avg episode reward: [(0, '22.144')]
+[2023-07-30 00:11:57,925][09298] Saving new best policy, reward=22.144!
+[2023-07-30 00:11:58,631][09318] Updated weights for policy 0, policy_version 670 (0.0013)
+[2023-07-30 00:12:00,250][09318] Updated weights for policy 0, policy_version 680 (0.0013)
+[2023-07-30 00:12:01,825][09318] Updated weights for policy 0, policy_version 690 (0.0013)
+[2023-07-30 00:12:02,916][03333] Fps is (10 sec: 24576.0, 60 sec: 24371.2, 300 sec: 22806.5). Total num frames: 2850816. Throughput: 0: 6133.8. Samples: 710614. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2023-07-30 00:12:02,919][03333] Avg episode reward: [(0, '24.120')]
+[2023-07-30 00:12:02,921][09298] Saving new best policy, reward=24.120!
+[2023-07-30 00:12:03,453][09318] Updated weights for policy 0, policy_version 700 (0.0012)
+[2023-07-30 00:12:05,094][09318] Updated weights for policy 0, policy_version 710 (0.0013)
+[2023-07-30 00:12:06,741][09318] Updated weights for policy 0, policy_version 720 (0.0012)
+[2023-07-30 00:12:07,916][03333] Fps is (10 sec: 25395.7, 60 sec: 24439.5, 300 sec: 22906.1). Total num frames: 2977792. Throughput: 0: 6127.2. Samples: 729412. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2023-07-30 00:12:07,918][03333] Avg episode reward: [(0, '23.281')]
+[2023-07-30 00:12:08,393][09318] Updated weights for policy 0, policy_version 730 (0.0013)
+[2023-07-30 00:12:10,207][09318] Updated weights for policy 0, policy_version 740 (0.0013)
+[2023-07-30 00:12:11,896][09318] Updated weights for policy 0, policy_version 750 (0.0013)
+[2023-07-30 00:12:12,916][03333] Fps is (10 sec: 24166.5, 60 sec: 24439.5, 300 sec: 22907.3). Total num frames: 3092480. Throughput: 0: 6091.2. Samples: 765536. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2023-07-30 00:12:12,918][03333] Avg episode reward: [(0, '24.386')]
+[2023-07-30 00:12:12,921][09298] Saving new best policy, reward=24.386!
+[2023-07-30 00:12:13,608][09318] Updated weights for policy 0, policy_version 760 (0.0013)
+[2023-07-30 00:12:15,370][09318] Updated weights for policy 0, policy_version 770 (0.0013)
+[2023-07-30 00:12:17,048][09318] Updated weights for policy 0, policy_version 780 (0.0014)
+[2023-07-30 00:12:17,916][03333] Fps is (10 sec: 23756.3, 60 sec: 24439.4, 300 sec: 22966.8). Total num frames: 3215360. Throughput: 0: 6109.8. Samples: 801362. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2023-07-30 00:12:17,918][03333] Avg episode reward: [(0, '22.909')]
+[2023-07-30 00:12:18,653][09318] Updated weights for policy 0, policy_version 790 (0.0013)
+[2023-07-30 00:12:20,270][09318] Updated weights for policy 0, policy_version 800 (0.0012)
+[2023-07-30 00:12:21,876][09318] Updated weights for policy 0, policy_version 810 (0.0013)
+[2023-07-30 00:12:22,916][03333] Fps is (10 sec: 24985.1, 60 sec: 24439.4, 300 sec: 23050.6). Total num frames: 3342336. Throughput: 0: 6136.0. Samples: 820394. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2023-07-30 00:12:22,919][03333] Avg episode reward: [(0, '22.241')]
+[2023-07-30 00:12:23,487][09318] Updated weights for policy 0, policy_version 820 (0.0013)
+[2023-07-30 00:12:25,106][09318] Updated weights for policy 0, policy_version 830 (0.0013)
+[2023-07-30 00:12:26,697][09318] Updated weights for policy 0, policy_version 840 (0.0014)
+[2023-07-30 00:12:27,916][03333] Fps is (10 sec: 25395.5, 60 sec: 24507.8, 300 sec: 23128.7). Total num frames: 3469312. Throughput: 0: 6136.9. Samples: 858490. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0)
+[2023-07-30 00:12:27,919][03333] Avg episode reward: [(0, '23.244')]
+[2023-07-30 00:12:28,418][09318] Updated weights for policy 0, policy_version 850 (0.0012)
+[2023-07-30 00:12:30,118][09318] Updated weights for policy 0, policy_version 860 (0.0012)
+[2023-07-30 00:12:31,935][09318] Updated weights for policy 0, policy_version 870 (0.0012)
+[2023-07-30 00:12:32,916][03333] Fps is (10 sec: 24166.9, 60 sec: 24507.8, 300 sec: 23122.6). Total num frames: 3584000. Throughput: 0: 6100.1. Samples: 894134. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2023-07-30 00:12:32,919][03333] Avg episode reward: [(0, '25.891')]
+[2023-07-30 00:12:32,926][09298] Saving new best policy, reward=25.891!
+[2023-07-30 00:12:33,637][09318] Updated weights for policy 0, policy_version 880 (0.0014)
+[2023-07-30 00:12:35,397][09318] Updated weights for policy 0, policy_version 890 (0.0012)
+[2023-07-30 00:12:37,113][09318] Updated weights for policy 0, policy_version 900 (0.0013)
+[2023-07-30 00:12:37,916][03333] Fps is (10 sec: 23756.5, 60 sec: 24507.7, 300 sec: 23168.0). Total num frames: 3706880. Throughput: 0: 6106.0. Samples: 911850. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2023-07-30 00:12:37,918][03333] Avg episode reward: [(0, '26.956')]
+[2023-07-30 00:12:37,928][09298] Saving new best policy, reward=26.956!
+[2023-07-30 00:12:38,745][09318] Updated weights for policy 0, policy_version 910 (0.0012)
+[2023-07-30 00:12:40,389][09318] Updated weights for policy 0, policy_version 920 (0.0012)
+[2023-07-30 00:12:41,989][09318] Updated weights for policy 0, policy_version 930 (0.0012)
+[2023-07-30 00:12:42,916][03333] Fps is (10 sec: 24576.1, 60 sec: 24439.5, 300 sec: 23210.7). Total num frames: 3829760. Throughput: 0: 6140.6. Samples: 948970. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2023-07-30 00:12:42,919][03333] Avg episode reward: [(0, '22.966')]
+[2023-07-30 00:12:43,555][09318] Updated weights for policy 0, policy_version 940 (0.0012)
+[2023-07-30 00:12:45,178][09318] Updated weights for policy 0, policy_version 950 (0.0013)
+[2023-07-30 00:12:46,807][09318] Updated weights for policy 0, policy_version 960 (0.0013)
+[2023-07-30 00:12:47,916][03333] Fps is (10 sec: 24985.4, 60 sec: 24507.6, 300 sec: 23274.9). Total num frames: 3956736. Throughput: 0: 6148.9. Samples: 987316. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2023-07-30 00:12:47,918][03333] Avg episode reward: [(0, '28.867')]
+[2023-07-30 00:12:47,931][09298] Saving new best policy, reward=28.867!
+[2023-07-30 00:12:48,449][09318] Updated weights for policy 0, policy_version 970 (0.0016)
+[2023-07-30 00:12:49,830][09298] Stopping Batcher_0...
+[2023-07-30 00:12:49,831][09298] Loop batcher_evt_loop terminating...
+[2023-07-30 00:12:49,834][09298] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-07-30 00:12:49,830][03333] Component Batcher_0 stopped!
+[2023-07-30 00:12:49,835][03333] Component RolloutWorker_w6 process died already! Don't wait for it.
+[2023-07-30 00:12:49,845][09341] Stopping RolloutWorker_w10...
+[2023-07-30 00:12:49,846][09341] Loop rollout_proc10_evt_loop terminating...
+[2023-07-30 00:12:49,846][09325] Stopping RolloutWorker_w2...
+[2023-07-30 00:12:49,846][09342] Stopping RolloutWorker_w11...
+[2023-07-30 00:12:49,844][09326] Stopping RolloutWorker_w7...
+[2023-07-30 00:12:49,846][09323] Stopping RolloutWorker_w5...
+[2023-07-30 00:12:49,847][09342] Loop rollout_proc11_evt_loop terminating...
+[2023-07-30 00:12:49,846][09325] Loop rollout_proc2_evt_loop terminating...
+[2023-07-30 00:12:49,844][03333] Component RolloutWorker_w7 stopped!
+[2023-07-30 00:12:49,847][09323] Loop rollout_proc5_evt_loop terminating...
+[2023-07-30 00:12:49,847][09326] Loop rollout_proc7_evt_loop terminating...
+[2023-07-30 00:12:49,848][09320] Stopping RolloutWorker_w0...
+[2023-07-30 00:12:49,848][09320] Loop rollout_proc0_evt_loop terminating...
+[2023-07-30 00:12:49,847][03333] Component RolloutWorker_w10 stopped!
+[2023-07-30 00:12:49,851][09321] Stopping RolloutWorker_w3...
+[2023-07-30 00:12:49,851][09319] Stopping RolloutWorker_w1...
+[2023-07-30 00:12:49,851][09321] Loop rollout_proc3_evt_loop terminating...
+[2023-07-30 00:12:49,853][09319] Loop rollout_proc1_evt_loop terminating...
+[2023-07-30 00:12:49,850][03333] Component RolloutWorker_w2 stopped!
+[2023-07-30 00:12:49,854][09349] Stopping RolloutWorker_w14...
+[2023-07-30 00:12:49,855][09327] Stopping RolloutWorker_w8...
+[2023-07-30 00:12:49,855][09349] Loop rollout_proc14_evt_loop terminating...
+[2023-07-30 00:12:49,854][03333] Component RolloutWorker_w11 stopped!
+[2023-07-30 00:12:49,855][09327] Loop rollout_proc8_evt_loop terminating...
+[2023-07-30 00:12:49,857][03333] Component RolloutWorker_w5 stopped!
+[2023-07-30 00:12:49,860][09318] Weights refcount: 2 0
+[2023-07-30 00:12:49,858][03333] Component RolloutWorker_w0 stopped!
+[2023-07-30 00:12:49,862][09318] Stopping InferenceWorker_p0-w0...
+[2023-07-30 00:12:49,862][09318] Loop inference_proc0-0_evt_loop terminating...
+[2023-07-30 00:12:49,861][03333] Component RolloutWorker_w3 stopped!
+[2023-07-30 00:12:49,864][09348] Stopping RolloutWorker_w15...
+[2023-07-30 00:12:49,864][09343] Stopping RolloutWorker_w12...
+[2023-07-30 00:12:49,864][09348] Loop rollout_proc15_evt_loop terminating...
+[2023-07-30 00:12:49,864][09343] Loop rollout_proc12_evt_loop terminating...
+[2023-07-30 00:12:49,864][03333] Component RolloutWorker_w1 stopped!
+[2023-07-30 00:12:49,866][03333] Component RolloutWorker_w14 stopped!
+[2023-07-30 00:12:49,869][03333] Component RolloutWorker_w8 stopped!
+[2023-07-30 00:12:49,870][09340] Stopping RolloutWorker_w13...
+[2023-07-30 00:12:49,870][09340] Loop rollout_proc13_evt_loop terminating...
+[2023-07-30 00:12:49,870][03333] Component InferenceWorker_p0-w0 stopped!
+[2023-07-30 00:12:49,873][03333] Component RolloutWorker_w15 stopped!
+[2023-07-30 00:12:49,874][03333] Component RolloutWorker_w12 stopped!
+[2023-07-30 00:12:49,877][03333] Component RolloutWorker_w13 stopped!
+[2023-07-30 00:12:49,879][09322] Stopping RolloutWorker_w4...
+[2023-07-30 00:12:49,879][09322] Loop rollout_proc4_evt_loop terminating...
+[2023-07-30 00:12:49,879][03333] Component RolloutWorker_w4 stopped!
+[2023-07-30 00:12:49,886][09328] Stopping RolloutWorker_w9...
+[2023-07-30 00:12:49,887][09328] Loop rollout_proc9_evt_loop terminating...
+[2023-07-30 00:12:49,886][03333] Component RolloutWorker_w9 stopped!
+[2023-07-30 00:12:49,924][09298] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-07-30 00:12:50,039][09298] Stopping LearnerWorker_p0...
+[2023-07-30 00:12:50,040][09298] Loop learner_proc0_evt_loop terminating...
+[2023-07-30 00:12:50,039][03333] Component LearnerWorker_p0 stopped!
+[2023-07-30 00:12:50,042][03333] Waiting for process learner_proc0 to stop...
+[2023-07-30 00:12:51,319][03333] Waiting for process inference_proc0-0 to join...
+[2023-07-30 00:12:51,321][03333] Waiting for process rollout_proc0 to join...
+[2023-07-30 00:12:51,323][03333] Waiting for process rollout_proc1 to join...
+[2023-07-30 00:12:51,325][03333] Waiting for process rollout_proc2 to join...
+[2023-07-30 00:12:51,327][03333] Waiting for process rollout_proc3 to join...
+[2023-07-30 00:12:51,329][03333] Waiting for process rollout_proc4 to join...
+[2023-07-30 00:12:51,330][03333] Waiting for process rollout_proc5 to join...
+[2023-07-30 00:12:51,332][03333] Waiting for process rollout_proc6 to join...
+[2023-07-30 00:12:51,333][03333] Waiting for process rollout_proc7 to join...
+[2023-07-30 00:12:51,336][03333] Waiting for process rollout_proc8 to join...
+[2023-07-30 00:12:51,337][03333] Waiting for process rollout_proc9 to join...
+[2023-07-30 00:12:51,339][03333] Waiting for process rollout_proc10 to join...
+[2023-07-30 00:12:51,340][03333] Waiting for process rollout_proc11 to join...
+[2023-07-30 00:12:51,342][03333] Waiting for process rollout_proc12 to join...
+[2023-07-30 00:12:51,343][03333] Waiting for process rollout_proc13 to join...
+[2023-07-30 00:12:51,345][03333] Waiting for process rollout_proc14 to join...
+[2023-07-30 00:12:51,346][03333] Waiting for process rollout_proc15 to join...
+[2023-07-30 00:12:51,348][03333] Batcher 0 profile tree view:
+batching: 30.6303, releasing_batches: 0.0649
+[2023-07-30 00:12:51,349][03333] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0001
+  wait_policy_total: 4.3616
+update_model: 2.7433
+  weight_update: 0.0012
+one_step: 0.0029
+  handle_policy_step: 153.8284
+    deserialize: 7.6692, stack: 0.8917, obs_to_device_normalize: 34.2510, forward: 74.3801, send_messages: 13.1847
+    prepare_outputs: 17.1719
+      to_cpu: 9.9411
+[2023-07-30 00:12:51,350][03333] Learner 0 profile tree view:
+misc: 0.0056, prepare_batch: 11.6529
+train: 19.4353
+  epoch_init: 0.0060, minibatch_init: 0.0062, losses_postprocess: 0.4999, kl_divergence: 0.3932, after_optimizer: 0.6868
+  calculate_losses: 7.8723
+    losses_init: 0.0037, forward_head: 0.6934, bptt_initial: 3.7548, tail: 0.6575, advantages_returns: 0.1692, losses: 1.1797
+    bptt: 1.2323
+      bptt_forward_core: 1.1786
+  update: 9.6174
+    clip: 2.4035
+[2023-07-30 00:12:51,351][03333] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.1039, enqueue_policy_requests: 5.1811, env_step: 93.2937, overhead: 7.2035, complete_rollouts: 0.3422
+save_policy_outputs: 6.3864
+  split_output_tensors: 2.9567
+[2023-07-30 00:12:51,352][03333] RolloutWorker_w15 profile tree view:
+wait_for_trajectories: 0.0812, enqueue_policy_requests: 3.8036, env_step: 121.5952, overhead: 5.0115, complete_rollouts: 0.1824
+save_policy_outputs: 4.4669
+  split_output_tensors: 2.1261
+[2023-07-30 00:12:51,353][03333] Loop Runner_EvtLoop terminating...
+[2023-07-30 00:12:51,354][03333] Runner profile tree view:
+main_loop: 188.1747
+[2023-07-30 00:12:51,358][03333] Collected {0: 4005888}, FPS: 21288.1
+[2023-07-30 00:15:28,891][03333] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-07-30 00:15:28,892][03333] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-07-30 00:15:28,893][03333] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-07-30 00:15:28,895][03333] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-07-30 00:15:28,896][03333] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-07-30 00:15:28,897][03333] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-07-30 00:15:28,899][03333] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2023-07-30 00:15:28,900][03333] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-07-30 00:15:28,902][03333] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2023-07-30 00:15:28,903][03333] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2023-07-30 00:15:28,905][03333] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-07-30 00:15:28,906][03333] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-07-30 00:15:28,907][03333] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-07-30 00:15:28,908][03333] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-07-30 00:15:28,910][03333] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-07-30 00:15:28,944][03333] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-30 00:15:28,947][03333] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-30 00:15:28,949][03333] RunningMeanStd input shape: (1,)
+[2023-07-30 00:15:28,963][03333] ConvEncoder: input_channels=3
+[2023-07-30 00:15:29,097][03333] Conv encoder output size: 512
+[2023-07-30 00:15:29,099][03333] Policy head output size: 512
+[2023-07-30 00:15:31,896][03333] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-07-30 00:15:33,234][03333] Num frames 100...
+[2023-07-30 00:15:33,356][03333] Num frames 200...
+[2023-07-30 00:15:33,480][03333] Num frames 300...
+[2023-07-30 00:15:33,601][03333] Num frames 400...
+[2023-07-30 00:15:33,726][03333] Num frames 500...
+[2023-07-30 00:15:33,850][03333] Num frames 600...
+[2023-07-30 00:15:33,973][03333] Num frames 700...
+[2023-07-30 00:15:34,098][03333] Num frames 800...
+[2023-07-30 00:15:34,193][03333] Avg episode rewards: #0: 18.320, true rewards: #0: 8.320
+[2023-07-30 00:15:34,194][03333] Avg episode reward: 18.320, avg true_objective: 8.320
+[2023-07-30 00:15:34,278][03333] Num frames 900...
+[2023-07-30 00:15:34,425][03333] Avg episode rewards: #0: 9.870, true rewards: #0: 4.870
+[2023-07-30 00:15:34,427][03333] Avg episode reward: 9.870, avg true_objective: 4.870
+[2023-07-30 00:15:34,459][03333] Num frames 1000...
+[2023-07-30 00:15:34,578][03333] Num frames 1100...
+[2023-07-30 00:15:34,704][03333] Num frames 1200...
+[2023-07-30 00:15:34,827][03333] Num frames 1300...
+[2023-07-30 00:15:34,951][03333] Num frames 1400...
+[2023-07-30 00:15:35,074][03333] Num frames 1500...
+[2023-07-30 00:15:35,204][03333] Num frames 1600...
+[2023-07-30 00:15:35,333][03333] Num frames 1700...
+[2023-07-30 00:15:35,453][03333] Num frames 1800...
+[2023-07-30 00:15:35,580][03333] Num frames 1900...
+[2023-07-30 00:15:35,704][03333] Num frames 2000...
+[2023-07-30 00:15:35,796][03333] Avg episode rewards: #0: 15.100, true rewards: #0: 6.767
+[2023-07-30 00:15:35,797][03333] Avg episode reward: 15.100, avg true_objective: 6.767
+[2023-07-30 00:15:35,883][03333] Num frames 2100...
+[2023-07-30 00:15:36,005][03333] Num frames 2200...
+[2023-07-30 00:15:36,130][03333] Num frames 2300...
+[2023-07-30 00:15:36,253][03333] Num frames 2400...
+[2023-07-30 00:15:36,379][03333] Num frames 2500...
+[2023-07-30 00:15:36,527][03333] Avg episode rewards: #0: 14.185, true rewards: #0: 6.435
+[2023-07-30 00:15:36,529][03333] Avg episode reward: 14.185, avg true_objective: 6.435
+[2023-07-30 00:15:36,563][03333] Num frames 2600...
+[2023-07-30 00:15:36,688][03333] Num frames 2700...
+[2023-07-30 00:15:36,814][03333] Num frames 2800...
+[2023-07-30 00:15:36,940][03333] Num frames 2900...
+[2023-07-30 00:15:37,066][03333] Num frames 3000...
+[2023-07-30 00:15:37,192][03333] Num frames 3100...
+[2023-07-30 00:15:37,318][03333] Num frames 3200...
+[2023-07-30 00:15:37,449][03333] Num frames 3300...
+[2023-07-30 00:15:37,581][03333] Num frames 3400...
+[2023-07-30 00:15:37,715][03333] Num frames 3500...
+[2023-07-30 00:15:37,846][03333] Num frames 3600...
+[2023-07-30 00:15:37,971][03333] Num frames 3700...
+[2023-07-30 00:15:38,093][03333] Num frames 3800...
+[2023-07-30 00:15:38,216][03333] Num frames 3900...
+[2023-07-30 00:15:38,343][03333] Num frames 4000...
+[2023-07-30 00:15:38,469][03333] Num frames 4100...
+[2023-07-30 00:15:38,593][03333] Num frames 4200...
+[2023-07-30 00:15:38,721][03333] Num frames 4300...
+[2023-07-30 00:15:38,819][03333] Avg episode rewards: #0: 21.268, true rewards: #0: 8.668
+[2023-07-30 00:15:38,821][03333] Avg episode reward: 21.268, avg true_objective: 8.668
+[2023-07-30 00:15:38,903][03333] Num frames 4400...
+[2023-07-30 00:15:39,027][03333] Num frames 4500...
+[2023-07-30 00:15:39,153][03333] Num frames 4600...
+[2023-07-30 00:15:39,321][03333] Avg episode rewards: #0: 18.977, true rewards: #0: 7.810
+[2023-07-30 00:15:39,322][03333] Avg episode reward: 18.977, avg true_objective: 7.810
+[2023-07-30 00:15:39,341][03333] Num frames 4700...
+[2023-07-30 00:15:39,471][03333] Num frames 4800...
+[2023-07-30 00:15:39,602][03333] Num frames 4900...
+[2023-07-30 00:15:39,733][03333] Num frames 5000...
+[2023-07-30 00:15:39,864][03333] Num frames 5100...
+[2023-07-30 00:15:39,996][03333] Num frames 5200...
+[2023-07-30 00:15:40,129][03333] Num frames 5300...
+[2023-07-30 00:15:40,262][03333] Num frames 5400...
+[2023-07-30 00:15:40,394][03333] Num frames 5500...
+[2023-07-30 00:15:40,524][03333] Num frames 5600...
+[2023-07-30 00:15:40,656][03333] Num frames 5700...
+[2023-07-30 00:15:40,789][03333] Num frames 5800...
+[2023-07-30 00:15:40,936][03333] Avg episode rewards: #0: 20.243, true rewards: #0: 8.386
+[2023-07-30 00:15:40,937][03333] Avg episode reward: 20.243, avg true_objective: 8.386
+[2023-07-30 00:15:40,976][03333] Num frames 5900...
+[2023-07-30 00:15:41,106][03333] Num frames 6000...
+[2023-07-30 00:15:41,238][03333] Num frames 6100...
+[2023-07-30 00:15:41,358][03333] Num frames 6200...
+[2023-07-30 00:15:41,477][03333] Num frames 6300...
+[2023-07-30 00:15:41,601][03333] Num frames 6400...
+[2023-07-30 00:15:41,726][03333] Num frames 6500...
+[2023-07-30 00:15:41,847][03333] Num frames 6600...
+[2023-07-30 00:15:41,968][03333] Num frames 6700...
+[2023-07-30 00:15:42,091][03333] Num frames 6800...
+[2023-07-30 00:15:42,213][03333] Num frames 6900...
+[2023-07-30 00:15:42,295][03333] Avg episode rewards: #0: 20.901, true rewards: #0: 8.651
+[2023-07-30 00:15:42,296][03333] Avg episode reward: 20.901, avg true_objective: 8.651
+[2023-07-30 00:15:42,392][03333] Num frames 7000...
+[2023-07-30 00:15:42,514][03333] Num frames 7100...
+[2023-07-30 00:15:42,634][03333] Num frames 7200...
+[2023-07-30 00:15:42,755][03333] Num frames 7300...
+[2023-07-30 00:15:42,875][03333] Num frames 7400...
+[2023-07-30 00:15:42,999][03333] Num frames 7500...
+[2023-07-30 00:15:43,123][03333] Num frames 7600...
+[2023-07-30 00:15:43,246][03333] Num frames 7700...
+[2023-07-30 00:15:43,370][03333] Num frames 7800...
+[2023-07-30 00:15:43,494][03333] Num frames 7900...
+[2023-07-30 00:15:43,618][03333] Num frames 8000...
+[2023-07-30 00:15:43,742][03333] Num frames 8100...
+[2023-07-30 00:15:43,863][03333] Num frames 8200...
+[2023-07-30 00:15:43,986][03333] Num frames 8300...
+[2023-07-30 00:15:44,110][03333] Num frames 8400...
+[2023-07-30 00:15:44,235][03333] Avg episode rewards: #0: 22.728, true rewards: #0: 9.394
+[2023-07-30 00:15:44,237][03333] Avg episode reward: 22.728, avg true_objective: 9.394
+[2023-07-30 00:15:44,292][03333] Num frames 8500...
+[2023-07-30 00:15:44,415][03333] Num frames 8600...
+[2023-07-30 00:15:44,537][03333] Num frames 8700...
+[2023-07-30 00:15:44,659][03333] Num frames 8800...
+[2023-07-30 00:15:44,783][03333] Num frames 8900...
+[2023-07-30 00:15:44,905][03333] Num frames 9000...
+[2023-07-30 00:15:45,029][03333] Num frames 9100...
+[2023-07-30 00:15:45,152][03333] Num frames 9200...
+[2023-07-30 00:15:45,278][03333] Num frames 9300...
+[2023-07-30 00:15:45,435][03333] Avg episode rewards: #0: 22.383, true rewards: #0: 9.383
+[2023-07-30 00:15:45,437][03333] Avg episode reward: 22.383, avg true_objective: 9.383
+[2023-07-30 00:16:07,718][03333] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2023-07-30 00:17:55,672][03333] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-07-30 00:17:55,674][03333] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-07-30 00:17:55,675][03333] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-07-30 00:17:55,677][03333] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-07-30 00:17:55,678][03333] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-07-30 00:17:55,680][03333] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-07-30 00:17:55,681][03333] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-07-30 00:17:55,682][03333] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-07-30 00:17:55,683][03333] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-07-30 00:17:55,685][03333] Adding new argument 'hf_repository'='timjwhite/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-07-30 00:17:55,686][03333] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-07-30 00:17:55,687][03333] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-07-30 00:17:55,689][03333] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-07-30 00:17:55,690][03333] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-07-30 00:17:55,691][03333] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-07-30 00:17:55,721][03333] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-30 00:17:55,723][03333] RunningMeanStd input shape: (1,)
+[2023-07-30 00:17:55,734][03333] ConvEncoder: input_channels=3
+[2023-07-30 00:17:55,772][03333] Conv encoder output size: 512
+[2023-07-30 00:17:55,773][03333] Policy head output size: 512
+[2023-07-30 00:17:55,792][03333] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-07-30 00:17:56,256][03333] Num frames 100...
+[2023-07-30 00:17:56,383][03333] Num frames 200...
+[2023-07-30 00:17:56,506][03333] Num frames 300...
+[2023-07-30 00:17:56,630][03333] Num frames 400...
+[2023-07-30 00:17:56,756][03333] Num frames 500...
+[2023-07-30 00:17:56,883][03333] Num frames 600...
+[2023-07-30 00:17:57,008][03333] Num frames 700...
+[2023-07-30 00:17:57,141][03333] Num frames 800...
+[2023-07-30 00:17:57,269][03333] Num frames 900...
+[2023-07-30 00:17:57,396][03333] Num frames 1000...
+[2023-07-30 00:17:57,521][03333] Num frames 1100...
+[2023-07-30 00:17:57,647][03333] Num frames 1200...
+[2023-07-30 00:17:57,775][03333] Num frames 1300...
+[2023-07-30 00:17:57,906][03333] Num frames 1400...
+[2023-07-30 00:17:58,032][03333] Num frames 1500...
+[2023-07-30 00:17:58,162][03333] Num frames 1600...
+[2023-07-30 00:17:58,289][03333] Num frames 1700...
+[2023-07-30 00:17:58,417][03333] Num frames 1800...
+[2023-07-30 00:17:58,541][03333] Num frames 1900...
+[2023-07-30 00:17:58,662][03333] Num frames 2000...
+[2023-07-30 00:17:58,791][03333] Num frames 2100...
+[2023-07-30 00:17:58,844][03333] Avg episode rewards: #0: 58.999, true rewards: #0: 21.000
+[2023-07-30 00:17:58,845][03333] Avg episode reward: 58.999, avg true_objective: 21.000
+[2023-07-30 00:17:58,965][03333] Num frames 2200...
+[2023-07-30 00:17:59,085][03333] Num frames 2300...
+[2023-07-30 00:17:59,209][03333] Num frames 2400...
+[2023-07-30 00:17:59,333][03333] Num frames 2500...
+[2023-07-30 00:17:59,454][03333] Num frames 2600...
+[2023-07-30 00:17:59,524][03333] Avg episode rewards: #0: 33.560, true rewards: #0: 13.060
+[2023-07-30 00:17:59,525][03333] Avg episode reward: 33.560, avg true_objective: 13.060
+[2023-07-30 00:17:59,638][03333] Num frames 2700...
+[2023-07-30 00:17:59,758][03333] Num frames 2800...
+[2023-07-30 00:17:59,876][03333] Num frames 2900...
+[2023-07-30 00:17:59,996][03333] Num frames 3000...
+[2023-07-30 00:18:00,121][03333] Avg episode rewards: #0: 24.200, true rewards: #0: 10.200
+[2023-07-30 00:18:00,122][03333] Avg episode reward: 24.200, avg true_objective: 10.200
+[2023-07-30 00:18:00,171][03333] Num frames 3100...
+[2023-07-30 00:18:00,290][03333] Num frames 3200...
+[2023-07-30 00:18:00,413][03333] Num frames 3300...
+[2023-07-30 00:18:00,533][03333] Num frames 3400...
+[2023-07-30 00:18:00,652][03333] Num frames 3500...
+[2023-07-30 00:18:00,776][03333] Num frames 3600...
+[2023-07-30 00:18:00,897][03333] Num frames 3700...
+[2023-07-30 00:18:01,018][03333] Num frames 3800...
+[2023-07-30 00:18:01,139][03333] Num frames 3900...
+[2023-07-30 00:18:01,260][03333] Num frames 4000...
+[2023-07-30 00:18:01,378][03333] Avg episode rewards: #0: 23.380, true rewards: #0: 10.130
+[2023-07-30 00:18:01,379][03333] Avg episode reward: 23.380, avg true_objective: 10.130
+[2023-07-30 00:18:01,440][03333] Num frames 4100...
+[2023-07-30 00:18:01,561][03333] Num frames 4200...
+[2023-07-30 00:18:01,684][03333] Num frames 4300...
+[2023-07-30 00:18:01,807][03333] Num frames 4400...
+[2023-07-30 00:18:01,931][03333] Num frames 4500...
+[2023-07-30 00:18:02,052][03333] Num frames 4600...
+[2023-07-30 00:18:02,213][03333] Avg episode rewards: #0: 21.574, true rewards: #0: 9.374
+[2023-07-30 00:18:02,215][03333] Avg episode reward: 21.574, avg true_objective: 9.374
+[2023-07-30 00:18:02,233][03333] Num frames 4700...
+[2023-07-30 00:18:02,358][03333] Num frames 4800...
+[2023-07-30 00:18:02,481][03333] Num frames 4900...
+[2023-07-30 00:18:02,603][03333] Num frames 5000...
+[2023-07-30 00:18:02,726][03333] Num frames 5100...
+[2023-07-30 00:18:02,850][03333] Num frames 5200...
+[2023-07-30 00:18:02,974][03333] Num frames 5300...
+[2023-07-30 00:18:03,096][03333] Num frames 5400...
+[2023-07-30 00:18:03,218][03333] Num frames 5500...
+[2023-07-30 00:18:03,343][03333] Num frames 5600...
+[2023-07-30 00:18:03,473][03333] Num frames 5700...
+[2023-07-30 00:18:03,602][03333] Num frames 5800...
+[2023-07-30 00:18:03,724][03333] Num frames 5900...
+[2023-07-30 00:18:03,848][03333] Num frames 6000...
+[2023-07-30 00:18:03,970][03333] Num frames 6100...
+[2023-07-30 00:18:04,095][03333] Num frames 6200...
+[2023-07-30 00:18:04,216][03333] Num frames 6300...
+[2023-07-30 00:18:04,338][03333] Num frames 6400...
+[2023-07-30 00:18:04,464][03333] Num frames 6500...
+[2023-07-30 00:18:04,590][03333] Num frames 6600...
+[2023-07-30 00:18:04,720][03333] Num frames 6700...
+[2023-07-30 00:18:04,881][03333] Avg episode rewards: #0: 28.478, true rewards: #0: 11.312
+[2023-07-30 00:18:04,882][03333] Avg episode reward: 28.478, avg true_objective: 11.312
+[2023-07-30 00:18:04,900][03333] Num frames 6800...
+[2023-07-30 00:18:05,020][03333] Num frames 6900...
+[2023-07-30 00:18:05,141][03333] Num frames 7000...
+[2023-07-30 00:18:05,263][03333] Num frames 7100...
+[2023-07-30 00:18:05,384][03333] Num frames 7200...
+[2023-07-30 00:18:05,506][03333] Num frames 7300...
+[2023-07-30 00:18:05,632][03333] Num frames 7400...
+[2023-07-30 00:18:05,758][03333] Num frames 7500...
+[2023-07-30 00:18:05,882][03333] Num frames 7600...
+[2023-07-30 00:18:06,002][03333] Num frames 7700...
+[2023-07-30 00:18:06,123][03333] Num frames 7800...
+[2023-07-30 00:18:06,244][03333] Num frames 7900...
+[2023-07-30 00:18:06,365][03333] Num frames 8000...
+[2023-07-30 00:18:06,491][03333] Num frames 8100...
+[2023-07-30 00:18:06,615][03333] Num frames 8200...
+[2023-07-30 00:18:06,737][03333] Num frames 8300...
+[2023-07-30 00:18:06,864][03333] Num frames 8400...
+[2023-07-30 00:18:06,985][03333] Num frames 8500...
+[2023-07-30 00:18:07,110][03333] Num frames 8600...
+[2023-07-30 00:18:07,179][03333] Avg episode rewards: #0: 31.301, true rewards: #0: 12.301
+[2023-07-30 00:18:07,180][03333] Avg episode reward: 31.301, avg true_objective: 12.301
+[2023-07-30 00:18:07,292][03333] Num frames 8700...
+[2023-07-30 00:18:07,417][03333] Num frames 8800...
+[2023-07-30 00:18:07,554][03333] Avg episode rewards: #0: 27.708, true rewards: #0: 11.084
+[2023-07-30 00:18:07,555][03333] Avg episode reward: 27.708, avg true_objective: 11.084
+[2023-07-30 00:18:07,598][03333] Num frames 8900...
+[2023-07-30 00:18:07,723][03333] Num frames 9000...
+[2023-07-30 00:18:07,844][03333] Num frames 9100...
+[2023-07-30 00:18:07,965][03333] Num frames 9200...
+[2023-07-30 00:18:08,094][03333] Num frames 9300...
+[2023-07-30 00:18:08,220][03333] Num frames 9400...
+[2023-07-30 00:18:08,349][03333] Num frames 9500...
+[2023-07-30 00:18:08,476][03333] Num frames 9600...
+[2023-07-30 00:18:08,600][03333] Num frames 9700...
+[2023-07-30 00:18:08,729][03333] Num frames 9800...
+[2023-07-30 00:18:08,856][03333] Num frames 9900...
+[2023-07-30 00:18:08,983][03333] Num frames 10000...
+[2023-07-30 00:18:09,110][03333] Num frames 10100...
+[2023-07-30 00:18:09,237][03333] Num frames 10200...
+[2023-07-30 00:18:09,363][03333] Num frames 10300...
+[2023-07-30 00:18:09,491][03333] Num frames 10400...
+[2023-07-30 00:18:09,618][03333] Num frames 10500...
+[2023-07-30 00:18:09,750][03333] Num frames 10600...
+[2023-07-30 00:18:09,884][03333] Avg episode rewards: #0: 29.621, true rewards: #0: 11.843
+[2023-07-30 00:18:09,886][03333] Avg episode reward: 29.621, avg true_objective: 11.843
+[2023-07-30 00:18:09,941][03333] Num frames 10700...
+[2023-07-30 00:18:10,070][03333] Num frames 10800...
+[2023-07-30 00:18:10,199][03333] Num frames 10900...
+[2023-07-30 00:18:10,326][03333] Num frames 11000...
+[2023-07-30 00:18:10,453][03333] Num frames 11100...
+[2023-07-30 00:18:10,579][03333] Num frames 11200...
+[2023-07-30 00:18:10,705][03333] Num frames 11300...
+[2023-07-30 00:18:10,838][03333] Num frames 11400...
+[2023-07-30 00:18:10,962][03333] Num frames 11500...
+[2023-07-30 00:18:11,084][03333] Num frames 11600...
+[2023-07-30 00:18:11,204][03333] Num frames 11700...
+[2023-07-30 00:18:11,331][03333] Num frames 11800...
+[2023-07-30 00:18:11,455][03333] Num frames 11900...
+[2023-07-30 00:18:11,585][03333] Num frames 12000...
+[2023-07-30 00:18:11,712][03333] Num frames 12100...
+[2023-07-30 00:18:11,837][03333] Num frames 12200...
+[2023-07-30 00:18:11,960][03333] Num frames 12300...
+[2023-07-30 00:18:12,086][03333] Num frames 12400...
+[2023-07-30 00:18:12,210][03333] Num frames 12500...
+[2023-07-30 00:18:12,336][03333] Num frames 12600...
+[2023-07-30 00:18:12,462][03333] Num frames 12700...
+[2023-07-30 00:18:12,590][03333] Avg episode rewards: #0: 32.159, true rewards: #0: 12.759
+[2023-07-30 00:18:12,592][03333] Avg episode reward: 32.159, avg true_objective: 12.759
+[2023-07-30 00:18:42,692][03333] Replay video saved to /content/train_dir/default_experiment/replay.mp4!