Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1716844378.wallenstein

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5fac2f6fdf8da55fcd08f5962271e53448952a2b19b7fe3a3a20ad0e010ac7
+size 40

.summary/0/events.out.tfevents.1716844380.wallenstein

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dca2203279a7f44831d6c53e50816c3aa422e48830717cb3fb5d530ba6d5c70
+size 40

.summary/0/events.out.tfevents.1716844561.wallenstein

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6937791aacd071136e1669e32d17578206f5b57f58127c57427e10ddc39e7a16
+size 193055

README.md

@@ -0,0 +1,56 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: doom_health_gathering_supreme
+      type: doom_health_gathering_supreme
+    metrics:
+    - type: mean_reward
+      value: 12.63 +/- 5.37
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
+
+This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
+Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+
+
+## Downloading the model
+
+After installing Sample-Factory, download the model with:
+```
+python -m sample_factory.huggingface.load_from_hub -r DavidPL1/rl_course_vizdoom_health_gathering_supreme
+```
+
+    
+## Using the model
+
+To run the model after download, use the `enjoy` script corresponding to this environment:
+```
+python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
+```
+
+
+You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
+See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+    
+## Training with this model
+
+To continue training with this model, use the `train` script corresponding to this environment:
+```
+python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_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_000000948_3883008_reward_22.181.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d00c5ba448a65eb52a71d00ba77d75be9665d5ab77d8750dc3abdaee1e55243
+size 34929051

checkpoint_p0/checkpoint_000000539_2207744.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf0f67ca22954ebe0d6a269fb75a942b91f39ae5942297c9326a53b50820efc
+size 34929477

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d1efe718816be8ae75ddb2045798b373dcc940d1a1327f07d503344b5b4a93
+size 34929477

config.json

@@ -0,0 +1,142 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "doom_health_gathering_supreme",
+  "experiment": "default_experiment",
+  "train_dir": "/media/fast/code/learning/train_dir",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": null,
+  "num_policies": 1,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": false,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 2,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 8,
+  "num_envs_per_worker": 4,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 1,
+  "num_epochs": 1,
+  "rollout": 32,
+  "recurrence": 32,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1.0,
+  "reward_clip": 1000.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.001,
+  "value_loss_coeff": 0.5,
+  "kl_loss_coeff": 0.0,
+  "exploration_loss": "symmetric_kl",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.1,
+  "ppo_clip_value": 0.2,
+  "with_vtrace": false,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-06,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 4.0,
+  "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,
+  "normalize_input_keys": null,
+  "decorrelate_experience_max_seconds": 0,
+  "decorrelate_envs_on_one_worker": true,
+  "actor_worker_gpus": [],
+  "set_workers_cpu_affinity": true,
+  "force_envs_single_thread": false,
+  "default_niceness": 0,
+  "log_to_file": true,
+  "experiment_summaries_interval": 10,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": true,
+  "heartbeat_interval": 20,
+  "heartbeat_reporting_interval": 600,
+  "train_for_env_steps": 4000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": -1,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    512,
+    512
+  ],
+  "encoder_conv_architecture": "convnet_simple",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": true,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "elu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": true,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 4,
+  "env_framestack": 1,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": false,
+  "with_wandb": false,
+  "wandb_user": null,
+  "wandb_project": "sample_factory",
+  "wandb_group": null,
+  "wandb_job_type": "SF",
+  "wandb_tags": [],
+  "with_pbt": false,
+  "pbt_mix_policies_in_one_env": true,
+  "pbt_period_env_steps": 5000000,
+  "pbt_start_mutation": 20000000,
+  "pbt_replace_fraction": 0.3,
+  "pbt_mutation_rate": 0.15,
+  "pbt_replace_reward_gap": 0.1,
+  "pbt_replace_reward_gap_absolute": 1e-06,
+  "pbt_optimize_gamma": false,
+  "pbt_target_objective": "true_objective",
+  "pbt_perturb_min": 1.1,
+  "pbt_perturb_max": 1.5,
+  "num_agents": -1,
+  "num_humans": 0,
+  "num_bots": -1,
+  "start_bot_difficulty": null,
+  "timelimit": null,
+  "res_w": 128,
+  "res_h": 72,
+  "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",
+  "cli_args": {
+    "env": "doom_health_gathering_supreme",
+    "num_workers": 8,
+    "num_envs_per_worker": 4,
+    "train_for_env_steps": 4000000
+  },
+  "git_hash": "unknown",
+  "git_repo_name": "not a git repository"
+}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf2fc33560e2134cac2811ddcf485e499f699112159fdc74a322afb1f7cd002
+size 24006025

sf_log.txt

@@ -0,0 +1,783 @@
+[2024-05-27 23:16:03,598][1934158] Saving configuration to /media/fast/code/learning/train_dir/default_experiment/config.json...
+[2024-05-27 23:16:03,599][1934158] Rollout worker 0 uses device cpu
+[2024-05-27 23:16:03,599][1934158] Rollout worker 1 uses device cpu
+[2024-05-27 23:16:03,599][1934158] Rollout worker 2 uses device cpu
+[2024-05-27 23:16:03,599][1934158] Rollout worker 3 uses device cpu
+[2024-05-27 23:16:03,599][1934158] Rollout worker 4 uses device cpu
+[2024-05-27 23:16:03,599][1934158] Rollout worker 5 uses device cpu
+[2024-05-27 23:16:03,599][1934158] Rollout worker 6 uses device cpu
+[2024-05-27 23:16:03,599][1934158] Rollout worker 7 uses device cpu
+[2024-05-27 23:16:03,623][1934158] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:16:03,623][1934158] InferenceWorker_p0-w0: min num requests: 2
+[2024-05-27 23:16:03,635][1934158] Starting all processes...
+[2024-05-27 23:16:03,635][1934158] Starting process learner_proc0
+[2024-05-27 23:16:05,222][1934158] Starting all processes...
+[2024-05-27 23:16:05,225][1934158] Starting process inference_proc0-0
+[2024-05-27 23:16:05,225][1934158] Starting process rollout_proc0
+[2024-05-27 23:16:05,225][1934158] Starting process rollout_proc1
+[2024-05-27 23:16:05,225][1934270] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:16:05,225][1934270] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-05-27 23:16:05,225][1934158] Starting process rollout_proc2
+[2024-05-27 23:16:05,225][1934158] Starting process rollout_proc3
+[2024-05-27 23:16:05,227][1934158] Starting process rollout_proc4
+[2024-05-27 23:16:05,228][1934158] Starting process rollout_proc5
+[2024-05-27 23:16:05,235][1934270] Num visible devices: 1
+[2024-05-27 23:16:05,228][1934158] Starting process rollout_proc6
+[2024-05-27 23:16:05,231][1934158] Starting process rollout_proc7
+[2024-05-27 23:16:05,252][1934270] Starting seed is not provided
+[2024-05-27 23:16:05,252][1934270] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:16:05,252][1934270] Initializing actor-critic model on device cuda:0
+[2024-05-27 23:16:05,252][1934270] RunningMeanStd input shape: (3, 72, 128)
+[2024-05-27 23:16:05,253][1934270] RunningMeanStd input shape: (1,)
+[2024-05-27 23:16:05,265][1934270] ConvEncoder: input_channels=3
+[2024-05-27 23:16:05,383][1934270] Conv encoder output size: 512
+[2024-05-27 23:16:05,383][1934270] Policy head output size: 512
+[2024-05-27 23:16:05,396][1934270] Created Actor Critic model with architecture:
+[2024-05-27 23:16:05,396][1934270] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2024-05-27 23:16:05,572][1934270] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-05-27 23:16:06,494][1934270] No checkpoints found
+[2024-05-27 23:16:06,494][1934270] Did not load from checkpoint, starting from scratch!
+[2024-05-27 23:16:06,497][1934270] Initialized policy 0 weights for model version 0
+[2024-05-27 23:16:06,525][1934270] LearnerWorker_p0 finished initialization!
+[2024-05-27 23:16:06,525][1934270] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:16:09,677][1934319] Worker 3 uses CPU cores [6, 7]
+[2024-05-27 23:16:09,679][1934318] Worker 2 uses CPU cores [4, 5]
+[2024-05-27 23:16:09,679][1934337] Worker 6 uses CPU cores [12, 13]
+[2024-05-27 23:16:09,691][1934315] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-05-27 23:16:09,691][1934315] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-05-27 23:16:09,696][1934316] Worker 0 uses CPU cores [0, 1]
+[2024-05-27 23:16:09,715][1934315] Num visible devices: 1
+[2024-05-27 23:16:09,755][1934320] Worker 4 uses CPU cores [8, 9]
+[2024-05-27 23:16:09,759][1934317] Worker 1 uses CPU cores [2, 3]
+[2024-05-27 23:16:09,760][1934336] Worker 5 uses CPU cores [10, 11]
+[2024-05-27 23:16:09,766][1934158] 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)
+[2024-05-27 23:16:09,769][1934342] Worker 7 uses CPU cores [14, 15]
+[2024-05-27 23:16:09,810][1934315] RunningMeanStd input shape: (3, 72, 128)
+[2024-05-27 23:16:09,811][1934315] RunningMeanStd input shape: (1,)
+[2024-05-27 23:16:09,820][1934315] ConvEncoder: input_channels=3
+[2024-05-27 23:16:09,897][1934315] Conv encoder output size: 512
+[2024-05-27 23:16:09,898][1934315] Policy head output size: 512
+[2024-05-27 23:16:09,948][1934158] Inference worker 0-0 is ready!
+[2024-05-27 23:16:09,948][1934158] All inference workers are ready! Signal rollout workers to start!
+[2024-05-27 23:16:09,966][1934316] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:16:09,966][1934319] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:16:09,966][1934320] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:16:09,966][1934318] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:16:09,966][1934342] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:16:09,966][1934336] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:16:09,966][1934337] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:16:09,966][1934317] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:16:10,026][1934319] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process...
+[2024-05-27 23:16:10,027][1934319] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=()
+Traceback (most recent call last):
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-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 "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
+    slot_callable(*args)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init
+    env_runner.init(self.timing)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init
+    self._reset()
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-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 "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/gymnasium/core.py", line 414, in reset
+    return self.env.reset(seed=seed, options=options)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset
+    return self.env.reset(**kwargs)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/gymnasium/core.py", line 462, in reset
+    obs, info = self.env.reset(seed=seed, options=options)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 82, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/gymnasium/core.py", line 414, in reset
+    return self.env.reset(seed=seed, options=options)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset
+    return self.env.reset(**kwargs)
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset
+    self._ensure_initialized()
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized
+    self.initialize()
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize
+    self._game_init()
+  File "/media/fast/code/learning/venv_learning/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init
+    raise EnvCriticalError()
+sample_factory.envs.env_utils.EnvCriticalError
+[2024-05-27 23:16:10,029][1934319] Unhandled exception  in evt loop rollout_proc3_evt_loop
+[2024-05-27 23:16:10,583][1934337] Decorrelating experience for 0 frames...
+[2024-05-27 23:16:10,583][1934342] Decorrelating experience for 0 frames...
+[2024-05-27 23:16:10,657][1934318] Decorrelating experience for 0 frames...
+[2024-05-27 23:16:10,916][1934342] Decorrelating experience for 32 frames...
+[2024-05-27 23:16:11,000][1934316] Decorrelating experience for 0 frames...
+[2024-05-27 23:16:11,225][1934158] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-05-27 23:16:11,427][1934337] Decorrelating experience for 32 frames...
+[2024-05-27 23:16:11,428][1934316] Decorrelating experience for 32 frames...
+[2024-05-27 23:16:11,606][1934320] Decorrelating experience for 0 frames...
+[2024-05-27 23:16:11,882][1934316] Decorrelating experience for 64 frames...
+[2024-05-27 23:16:12,052][1934342] Decorrelating experience for 64 frames...
+[2024-05-27 23:16:12,155][1934320] Decorrelating experience for 32 frames...
+[2024-05-27 23:16:12,672][1934316] Decorrelating experience for 96 frames...
+[2024-05-27 23:16:12,755][1934337] Decorrelating experience for 64 frames...
+[2024-05-27 23:16:12,756][1934318] Decorrelating experience for 32 frames...
+[2024-05-27 23:16:12,831][1934317] Decorrelating experience for 0 frames...
+[2024-05-27 23:16:13,085][1934342] Decorrelating experience for 96 frames...
+[2024-05-27 23:16:13,412][1934320] Decorrelating experience for 64 frames...
+[2024-05-27 23:16:13,493][1934337] Decorrelating experience for 96 frames...
+[2024-05-27 23:16:13,592][1934318] Decorrelating experience for 64 frames...
+[2024-05-27 23:16:13,763][1934336] Decorrelating experience for 0 frames...
+[2024-05-27 23:16:14,101][1934317] Decorrelating experience for 32 frames...
+[2024-05-27 23:16:14,182][1934318] Decorrelating experience for 96 frames...
+[2024-05-27 23:16:14,425][1934320] Decorrelating experience for 96 frames...
+[2024-05-27 23:16:14,429][1934336] Decorrelating experience for 32 frames...
+[2024-05-27 23:16:14,657][1934317] Decorrelating experience for 64 frames...
+[2024-05-27 23:16:14,666][1934270] Signal inference workers to stop experience collection...
+[2024-05-27 23:16:14,670][1934315] InferenceWorker_p0-w0: stopping experience collection
+[2024-05-27 23:16:14,811][1934336] Decorrelating experience for 64 frames...
+[2024-05-27 23:16:14,967][1934317] Decorrelating experience for 96 frames...
+[2024-05-27 23:16:15,277][1934336] Decorrelating experience for 96 frames...
+[2024-05-27 23:16:15,790][1934270] Signal inference workers to resume experience collection...
+[2024-05-27 23:16:15,790][1934315] InferenceWorker_p0-w0: resuming experience collection
+[2024-05-27 23:16:16,225][1934158] Fps is (10 sec: 1902.6, 60 sec: 1902.6, 300 sec: 1902.6). Total num frames: 12288. Throughput: 0: 379.3. Samples: 2450. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2024-05-27 23:16:16,225][1934158] Avg episode reward: [(0, '3.187')]
+[2024-05-27 23:16:17,981][1934315] Updated weights for policy 0, policy_version 10 (0.0101)
+[2024-05-27 23:16:19,839][1934315] Updated weights for policy 0, policy_version 20 (0.0007)
+[2024-05-27 23:16:21,225][1934158] Fps is (10 sec: 11059.1, 60 sec: 9651.5, 300 sec: 9651.5). Total num frames: 110592. Throughput: 0: 1415.4. Samples: 16218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 3.0)
+[2024-05-27 23:16:21,225][1934158] Avg episode reward: [(0, '4.379')]
+[2024-05-27 23:16:21,228][1934270] Saving new best policy, reward=4.379!
+[2024-05-27 23:16:21,659][1934315] Updated weights for policy 0, policy_version 30 (0.0007)
+[2024-05-27 23:16:23,614][1934315] Updated weights for policy 0, policy_version 40 (0.0008)
+[2024-05-27 23:16:23,619][1934158] Heartbeat connected on Batcher_0
+[2024-05-27 23:16:23,621][1934158] Heartbeat connected on LearnerWorker_p0
+[2024-05-27 23:16:23,625][1934158] Heartbeat connected on RolloutWorker_w0
+[2024-05-27 23:16:23,626][1934158] Heartbeat connected on InferenceWorker_p0-w0
+[2024-05-27 23:16:23,627][1934158] Heartbeat connected on RolloutWorker_w1
+[2024-05-27 23:16:23,632][1934158] Heartbeat connected on RolloutWorker_w4
+[2024-05-27 23:16:23,632][1934158] Heartbeat connected on RolloutWorker_w5
+[2024-05-27 23:16:23,634][1934158] Heartbeat connected on RolloutWorker_w6
+[2024-05-27 23:16:23,635][1934158] Heartbeat connected on RolloutWorker_w2
+[2024-05-27 23:16:23,636][1934158] Heartbeat connected on RolloutWorker_w7
+[2024-05-27 23:16:25,556][1934315] Updated weights for policy 0, policy_version 50 (0.0012)
+[2024-05-27 23:16:26,225][1934158] Fps is (10 sec: 20480.0, 60 sec: 13190.0, 300 sec: 13190.0). Total num frames: 217088. Throughput: 0: 2945.8. Samples: 48484. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-05-27 23:16:26,225][1934158] Avg episode reward: [(0, '4.620')]
+[2024-05-27 23:16:26,225][1934270] Saving new best policy, reward=4.620!
+[2024-05-27 23:16:27,524][1934315] Updated weights for policy 0, policy_version 60 (0.0011)
+[2024-05-27 23:16:29,497][1934315] Updated weights for policy 0, policy_version 70 (0.0007)
+[2024-05-27 23:16:31,225][1934158] Fps is (10 sec: 20889.7, 60 sec: 14888.7, 300 sec: 14888.7). Total num frames: 319488. Throughput: 0: 3703.7. Samples: 79476. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:16:31,225][1934158] Avg episode reward: [(0, '4.594')]
+[2024-05-27 23:16:31,523][1934315] Updated weights for policy 0, policy_version 80 (0.0007)
+[2024-05-27 23:16:33,629][1934315] Updated weights for policy 0, policy_version 90 (0.0007)
+[2024-05-27 23:16:35,621][1934315] Updated weights for policy 0, policy_version 100 (0.0007)
+[2024-05-27 23:16:36,225][1934158] Fps is (10 sec: 20480.0, 60 sec: 15945.3, 300 sec: 15945.3). Total num frames: 421888. Throughput: 0: 3572.4. Samples: 94520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-05-27 23:16:36,225][1934158] Avg episode reward: [(0, '4.672')]
+[2024-05-27 23:16:36,225][1934270] Saving new best policy, reward=4.672!
+[2024-05-27 23:16:37,650][1934315] Updated weights for policy 0, policy_version 110 (0.0007)
+[2024-05-27 23:16:39,626][1934315] Updated weights for policy 0, policy_version 120 (0.0008)
+[2024-05-27 23:16:41,225][1934158] Fps is (10 sec: 20070.3, 60 sec: 16535.8, 300 sec: 16535.8). Total num frames: 520192. Throughput: 0: 3978.1. Samples: 125144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:16:41,225][1934158] Avg episode reward: [(0, '4.368')]
+[2024-05-27 23:16:41,688][1934315] Updated weights for policy 0, policy_version 130 (0.0007)
+[2024-05-27 23:16:43,620][1934315] Updated weights for policy 0, policy_version 140 (0.0007)
+[2024-05-27 23:16:45,415][1934315] Updated weights for policy 0, policy_version 150 (0.0007)
+[2024-05-27 23:16:46,225][1934158] Fps is (10 sec: 20889.6, 60 sec: 17301.4, 300 sec: 17301.4). Total num frames: 630784. Throughput: 0: 4313.8. Samples: 157276. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:16:46,225][1934158] Avg episode reward: [(0, '4.638')]
+[2024-05-27 23:16:47,205][1934315] Updated weights for policy 0, policy_version 160 (0.0007)
+[2024-05-27 23:16:48,998][1934315] Updated weights for policy 0, policy_version 170 (0.0010)
+[2024-05-27 23:16:50,924][1934315] Updated weights for policy 0, policy_version 180 (0.0007)
+[2024-05-27 23:16:51,225][1934158] Fps is (10 sec: 22118.5, 60 sec: 17882.4, 300 sec: 17882.4). Total num frames: 741376. Throughput: 0: 4207.1. Samples: 174418. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:16:51,225][1934158] Avg episode reward: [(0, '4.486')]
+[2024-05-27 23:16:52,935][1934315] Updated weights for policy 0, policy_version 190 (0.0007)
+[2024-05-27 23:16:54,845][1934315] Updated weights for policy 0, policy_version 200 (0.0008)
+[2024-05-27 23:16:56,225][1934158] Fps is (10 sec: 21708.7, 60 sec: 18250.1, 300 sec: 18250.1). Total num frames: 847872. Throughput: 0: 4577.8. Samples: 206002. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-05-27 23:16:56,225][1934158] Avg episode reward: [(0, '4.466')]
+[2024-05-27 23:16:56,781][1934315] Updated weights for policy 0, policy_version 210 (0.0007)
+[2024-05-27 23:16:58,717][1934315] Updated weights for policy 0, policy_version 220 (0.0008)
+[2024-05-27 23:17:00,636][1934315] Updated weights for policy 0, policy_version 230 (0.0007)
+[2024-05-27 23:17:01,225][1934158] Fps is (10 sec: 20889.6, 60 sec: 18466.8, 300 sec: 18466.8). Total num frames: 950272. Throughput: 0: 5229.4. Samples: 237774. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-05-27 23:17:01,225][1934158] Avg episode reward: [(0, '4.450')]
+[2024-05-27 23:17:02,613][1934315] Updated weights for policy 0, policy_version 240 (0.0008)
+[2024-05-27 23:17:04,662][1934315] Updated weights for policy 0, policy_version 250 (0.0007)
+[2024-05-27 23:17:06,225][1934158] Fps is (10 sec: 20480.0, 60 sec: 18645.1, 300 sec: 18645.1). Total num frames: 1052672. Throughput: 0: 5261.9. Samples: 253004. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:17:06,225][1934158] Avg episode reward: [(0, '4.710')]
+[2024-05-27 23:17:06,225][1934270] Saving new best policy, reward=4.710!
+[2024-05-27 23:17:06,803][1934315] Updated weights for policy 0, policy_version 260 (0.0011)
+[2024-05-27 23:17:08,893][1934315] Updated weights for policy 0, policy_version 270 (0.0007)
+[2024-05-27 23:17:10,844][1934315] Updated weights for policy 0, policy_version 280 (0.0012)
+[2024-05-27 23:17:11,225][1934158] Fps is (10 sec: 20070.2, 60 sec: 19182.9, 300 sec: 18727.7). Total num frames: 1150976. Throughput: 0: 5203.4. Samples: 282636. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:17:11,225][1934158] Avg episode reward: [(0, '4.512')]
+[2024-05-27 23:17:12,691][1934315] Updated weights for policy 0, policy_version 290 (0.0007)
+[2024-05-27 23:17:14,604][1934315] Updated weights for policy 0, policy_version 300 (0.0007)
+[2024-05-27 23:17:16,225][1934158] Fps is (10 sec: 21299.1, 60 sec: 20889.6, 300 sec: 19044.4). Total num frames: 1265664. Throughput: 0: 5248.3. Samples: 315650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:17:16,225][1934158] Avg episode reward: [(0, '4.587')]
+[2024-05-27 23:17:16,410][1934315] Updated weights for policy 0, policy_version 310 (0.0007)
+[2024-05-27 23:17:18,299][1934315] Updated weights for policy 0, policy_version 320 (0.0008)
+[2024-05-27 23:17:20,246][1934315] Updated weights for policy 0, policy_version 330 (0.0007)
+[2024-05-27 23:17:21,225][1934158] Fps is (10 sec: 22118.6, 60 sec: 21026.2, 300 sec: 19202.2). Total num frames: 1372160. Throughput: 0: 5274.4. Samples: 331866. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:17:21,225][1934158] Avg episode reward: [(0, '4.428')]
+[2024-05-27 23:17:22,228][1934315] Updated weights for policy 0, policy_version 340 (0.0007)
+[2024-05-27 23:17:24,250][1934315] Updated weights for policy 0, policy_version 350 (0.0007)
+[2024-05-27 23:17:26,216][1934315] Updated weights for policy 0, policy_version 360 (0.0008)
+[2024-05-27 23:17:26,225][1934158] Fps is (10 sec: 20889.8, 60 sec: 20957.9, 300 sec: 19285.8). Total num frames: 1474560. Throughput: 0: 5278.6. Samples: 362680. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:17:26,225][1934158] Avg episode reward: [(0, '4.760')]
+[2024-05-27 23:17:26,225][1934270] Saving new best policy, reward=4.760!
+[2024-05-27 23:17:28,176][1934315] Updated weights for policy 0, policy_version 370 (0.0007)
+[2024-05-27 23:17:30,122][1934315] Updated weights for policy 0, policy_version 380 (0.0007)
+[2024-05-27 23:17:31,225][1934158] Fps is (10 sec: 20480.0, 60 sec: 20957.9, 300 sec: 19359.1). Total num frames: 1576960. Throughput: 0: 5261.3. Samples: 394036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:17:31,225][1934158] Avg episode reward: [(0, '5.042')]
+[2024-05-27 23:17:31,227][1934270] Saving new best policy, reward=5.042!
+[2024-05-27 23:17:32,083][1934315] Updated weights for policy 0, policy_version 390 (0.0007)
+[2024-05-27 23:17:33,997][1934315] Updated weights for policy 0, policy_version 400 (0.0008)
+[2024-05-27 23:17:35,937][1934315] Updated weights for policy 0, policy_version 410 (0.0008)
+[2024-05-27 23:17:36,225][1934158] Fps is (10 sec: 20889.5, 60 sec: 21026.1, 300 sec: 19471.3). Total num frames: 1683456. Throughput: 0: 5235.8. Samples: 410028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-05-27 23:17:36,225][1934158] Avg episode reward: [(0, '4.829')]
+[2024-05-27 23:17:37,913][1934315] Updated weights for policy 0, policy_version 420 (0.0007)
+[2024-05-27 23:17:39,821][1934315] Updated weights for policy 0, policy_version 430 (0.0007)
+[2024-05-27 23:17:41,225][1934158] Fps is (10 sec: 21299.2, 60 sec: 21162.7, 300 sec: 19571.2). Total num frames: 1789952. Throughput: 0: 5239.0. Samples: 441758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 3.0)
+[2024-05-27 23:17:41,225][1934158] Avg episode reward: [(0, '5.811')]
+[2024-05-27 23:17:41,227][1934270] Saving new best policy, reward=5.811!
+[2024-05-27 23:17:41,621][1934315] Updated weights for policy 0, policy_version 440 (0.0007)
+[2024-05-27 23:17:43,431][1934315] Updated weights for policy 0, policy_version 450 (0.0008)
+[2024-05-27 23:17:45,265][1934315] Updated weights for policy 0, policy_version 460 (0.0007)
+[2024-05-27 23:17:46,225][1934158] Fps is (10 sec: 22118.4, 60 sec: 21230.9, 300 sec: 19745.7). Total num frames: 1904640. Throughput: 0: 5286.2. Samples: 475652. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-05-27 23:17:46,225][1934158] Avg episode reward: [(0, '6.064')]
+[2024-05-27 23:17:46,225][1934270] Saving new best policy, reward=6.064!
+[2024-05-27 23:17:47,258][1934315] Updated weights for policy 0, policy_version 470 (0.0007)
+[2024-05-27 23:17:49,311][1934315] Updated weights for policy 0, policy_version 480 (0.0007)
+[2024-05-27 23:17:51,225][1934158] Fps is (10 sec: 21299.0, 60 sec: 21026.1, 300 sec: 19741.5). Total num frames: 2002944. Throughput: 0: 5272.8. Samples: 490282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-05-27 23:17:51,225][1934158] Avg episode reward: [(0, '8.117')]
+[2024-05-27 23:17:51,228][1934270] Saving new best policy, reward=8.117!
+[2024-05-27 23:17:51,309][1934315] Updated weights for policy 0, policy_version 490 (0.0007)
+[2024-05-27 23:17:53,208][1934315] Updated weights for policy 0, policy_version 500 (0.0007)
+[2024-05-27 23:17:55,270][1934315] Updated weights for policy 0, policy_version 510 (0.0007)
+[2024-05-27 23:17:56,225][1934158] Fps is (10 sec: 20070.4, 60 sec: 20957.9, 300 sec: 19776.2). Total num frames: 2105344. Throughput: 0: 5304.0. Samples: 521316. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-05-27 23:17:56,225][1934158] Avg episode reward: [(0, '9.056')]
+[2024-05-27 23:17:56,225][1934270] Saving new best policy, reward=9.056!
+[2024-05-27 23:17:57,265][1934315] Updated weights for policy 0, policy_version 520 (0.0007)
+[2024-05-27 23:17:59,319][1934315] Updated weights for policy 0, policy_version 530 (0.0011)
+[2024-05-27 23:18:01,225][1934158] Fps is (10 sec: 20479.9, 60 sec: 20957.8, 300 sec: 19807.7). Total num frames: 2207744. Throughput: 0: 5240.7. Samples: 551482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:18:01,225][1934158] Avg episode reward: [(0, '11.238')]
+[2024-05-27 23:18:01,228][1934270] Saving /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000000539_2207744.pth...
+[2024-05-27 23:18:01,267][1934270] Saving new best policy, reward=11.238!
+[2024-05-27 23:18:01,335][1934315] Updated weights for policy 0, policy_version 540 (0.0007)
+[2024-05-27 23:18:03,448][1934315] Updated weights for policy 0, policy_version 550 (0.0012)
+[2024-05-27 23:18:05,446][1934315] Updated weights for policy 0, policy_version 560 (0.0007)
+[2024-05-27 23:18:06,225][1934158] Fps is (10 sec: 20070.5, 60 sec: 20889.6, 300 sec: 19801.5). Total num frames: 2306048. Throughput: 0: 5211.2. Samples: 566368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:18:06,225][1934158] Avg episode reward: [(0, '11.336')]
+[2024-05-27 23:18:06,225][1934270] Saving new best policy, reward=11.336!
+[2024-05-27 23:18:07,421][1934315] Updated weights for policy 0, policy_version 570 (0.0007)
+[2024-05-27 23:18:09,239][1934315] Updated weights for policy 0, policy_version 580 (0.0009)
+[2024-05-27 23:18:11,047][1934315] Updated weights for policy 0, policy_version 590 (0.0007)
+[2024-05-27 23:18:11,224][1934158] Fps is (10 sec: 21299.6, 60 sec: 21162.7, 300 sec: 19930.6). Total num frames: 2420736. Throughput: 0: 5245.1. Samples: 598710. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:18:11,225][1934158] Avg episode reward: [(0, '14.662')]
+[2024-05-27 23:18:11,227][1934270] Saving new best policy, reward=14.662!
+[2024-05-27 23:18:12,854][1934315] Updated weights for policy 0, policy_version 600 (0.0009)
+[2024-05-27 23:18:14,740][1934315] Updated weights for policy 0, policy_version 610 (0.0007)
+[2024-05-27 23:18:16,225][1934158] Fps is (10 sec: 22118.2, 60 sec: 21026.1, 300 sec: 19984.7). Total num frames: 2527232. Throughput: 0: 5272.6. Samples: 631302. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-05-27 23:18:16,225][1934158] Avg episode reward: [(0, '15.552')]
+[2024-05-27 23:18:16,225][1934270] Saving new best policy, reward=15.552!
+[2024-05-27 23:18:16,763][1934315] Updated weights for policy 0, policy_version 620 (0.0011)
+[2024-05-27 23:18:18,712][1934315] Updated weights for policy 0, policy_version 630 (0.0012)
+[2024-05-27 23:18:20,722][1934315] Updated weights for policy 0, policy_version 640 (0.0012)
+[2024-05-27 23:18:21,225][1934158] Fps is (10 sec: 20889.2, 60 sec: 20957.8, 300 sec: 20003.5). Total num frames: 2629632. Throughput: 0: 5265.6. Samples: 646982. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:18:21,225][1934158] Avg episode reward: [(0, '15.319')]
+[2024-05-27 23:18:22,704][1934315] Updated weights for policy 0, policy_version 650 (0.0012)
+[2024-05-27 23:18:24,737][1934315] Updated weights for policy 0, policy_version 660 (0.0009)
+[2024-05-27 23:18:26,225][1934158] Fps is (10 sec: 20480.1, 60 sec: 20957.9, 300 sec: 20021.0). Total num frames: 2732032. Throughput: 0: 5239.9. Samples: 677552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:18:26,225][1934158] Avg episode reward: [(0, '18.705')]
+[2024-05-27 23:18:26,225][1934270] Saving new best policy, reward=18.705!
+[2024-05-27 23:18:26,687][1934315] Updated weights for policy 0, policy_version 670 (0.0007)
+[2024-05-27 23:18:28,690][1934315] Updated weights for policy 0, policy_version 680 (0.0007)
+[2024-05-27 23:18:30,666][1934315] Updated weights for policy 0, policy_version 690 (0.0007)
+[2024-05-27 23:18:31,225][1934158] Fps is (10 sec: 20480.2, 60 sec: 20957.9, 300 sec: 20037.2). Total num frames: 2834432. Throughput: 0: 5177.5. Samples: 708638. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-05-27 23:18:31,225][1934158] Avg episode reward: [(0, '19.747')]
+[2024-05-27 23:18:31,228][1934270] Saving new best policy, reward=19.747!
+[2024-05-27 23:18:32,744][1934315] Updated weights for policy 0, policy_version 700 (0.0007)
+[2024-05-27 23:18:34,708][1934315] Updated weights for policy 0, policy_version 710 (0.0008)
+[2024-05-27 23:18:36,225][1934158] Fps is (10 sec: 20479.8, 60 sec: 20889.6, 300 sec: 20052.3). Total num frames: 2936832. Throughput: 0: 5187.1. Samples: 723702. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-05-27 23:18:36,225][1934158] Avg episode reward: [(0, '20.573')]
+[2024-05-27 23:18:36,226][1934270] Saving new best policy, reward=20.573!
+[2024-05-27 23:18:36,748][1934315] Updated weights for policy 0, policy_version 720 (0.0008)
+[2024-05-27 23:18:38,561][1934315] Updated weights for policy 0, policy_version 730 (0.0008)
+[2024-05-27 23:18:40,387][1934315] Updated weights for policy 0, policy_version 740 (0.0008)
+[2024-05-27 23:18:41,225][1934158] Fps is (10 sec: 21299.2, 60 sec: 20957.9, 300 sec: 20120.5). Total num frames: 3047424. Throughput: 0: 5210.7. Samples: 755796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:18:41,225][1934158] Avg episode reward: [(0, '21.032')]
+[2024-05-27 23:18:41,228][1934270] Saving new best policy, reward=21.032!
+[2024-05-27 23:18:42,185][1934315] Updated weights for policy 0, policy_version 750 (0.0007)
+[2024-05-27 23:18:44,027][1934315] Updated weights for policy 0, policy_version 760 (0.0007)
+[2024-05-27 23:18:45,915][1934315] Updated weights for policy 0, policy_version 770 (0.0007)
+[2024-05-27 23:18:46,225][1934158] Fps is (10 sec: 22118.7, 60 sec: 20889.6, 300 sec: 20184.4). Total num frames: 3158016. Throughput: 0: 5280.4. Samples: 789100. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:18:46,225][1934158] Avg episode reward: [(0, '18.887')]
+[2024-05-27 23:18:47,935][1934315] Updated weights for policy 0, policy_version 780 (0.0007)
+[2024-05-27 23:18:49,831][1934315] Updated weights for policy 0, policy_version 790 (0.0007)
+[2024-05-27 23:18:51,225][1934158] Fps is (10 sec: 21708.7, 60 sec: 21026.2, 300 sec: 20218.9). Total num frames: 3264512. Throughput: 0: 5299.6. Samples: 804852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:18:51,225][1934158] Avg episode reward: [(0, '17.324')]
+[2024-05-27 23:18:51,873][1934315] Updated weights for policy 0, policy_version 800 (0.0012)
+[2024-05-27 23:18:53,869][1934315] Updated weights for policy 0, policy_version 810 (0.0008)
+[2024-05-27 23:18:55,945][1934315] Updated weights for policy 0, policy_version 820 (0.0011)
+[2024-05-27 23:18:56,225][1934158] Fps is (10 sec: 20480.0, 60 sec: 20957.9, 300 sec: 20202.1). Total num frames: 3362816. Throughput: 0: 5260.6. Samples: 835438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:18:56,225][1934158] Avg episode reward: [(0, '17.131')]
+[2024-05-27 23:18:57,993][1934315] Updated weights for policy 0, policy_version 830 (0.0016)
+[2024-05-27 23:18:59,990][1934315] Updated weights for policy 0, policy_version 840 (0.0007)
+[2024-05-27 23:19:01,225][1934158] Fps is (10 sec: 20070.4, 60 sec: 20957.9, 300 sec: 20210.2). Total num frames: 3465216. Throughput: 0: 5207.4. Samples: 865636. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-05-27 23:19:01,225][1934158] Avg episode reward: [(0, '20.196')]
+[2024-05-27 23:19:02,004][1934315] Updated weights for policy 0, policy_version 850 (0.0008)
+[2024-05-27 23:19:04,080][1934315] Updated weights for policy 0, policy_version 860 (0.0007)
+[2024-05-27 23:19:05,800][1934315] Updated weights for policy 0, policy_version 870 (0.0007)
+[2024-05-27 23:19:06,225][1934158] Fps is (10 sec: 20889.5, 60 sec: 21094.4, 300 sec: 20241.1). Total num frames: 3571712. Throughput: 0: 5194.5. Samples: 880732. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:19:06,225][1934158] Avg episode reward: [(0, '21.470')]
+[2024-05-27 23:19:06,225][1934270] Saving new best policy, reward=21.470!
+[2024-05-27 23:19:07,672][1934315] Updated weights for policy 0, policy_version 880 (0.0008)
+[2024-05-27 23:19:09,539][1934315] Updated weights for policy 0, policy_version 890 (0.0008)
+[2024-05-27 23:19:11,225][1934158] Fps is (10 sec: 21708.9, 60 sec: 21026.1, 300 sec: 20292.8). Total num frames: 3682304. Throughput: 0: 5259.7. Samples: 914240. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-05-27 23:19:11,225][1934158] Avg episode reward: [(0, '21.748')]
+[2024-05-27 23:19:11,228][1934270] Saving new best policy, reward=21.748!
+[2024-05-27 23:19:11,365][1934315] Updated weights for policy 0, policy_version 900 (0.0007)
+[2024-05-27 23:19:13,481][1934315] Updated weights for policy 0, policy_version 910 (0.0009)
+[2024-05-27 23:19:15,430][1934315] Updated weights for policy 0, policy_version 920 (0.0008)
+[2024-05-27 23:19:16,225][1934158] Fps is (10 sec: 20889.5, 60 sec: 20889.6, 300 sec: 20275.9). Total num frames: 3780608. Throughput: 0: 5263.5. Samples: 945494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-05-27 23:19:16,225][1934158] Avg episode reward: [(0, '20.029')]
+[2024-05-27 23:19:17,514][1934315] Updated weights for policy 0, policy_version 930 (0.0011)
+[2024-05-27 23:19:19,529][1934315] Updated weights for policy 0, policy_version 940 (0.0008)
+[2024-05-27 23:19:21,225][1934158] Fps is (10 sec: 20070.4, 60 sec: 20889.6, 300 sec: 20281.2). Total num frames: 3883008. Throughput: 0: 5255.3. Samples: 960192. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:19:21,225][1934158] Avg episode reward: [(0, '22.181')]
+[2024-05-27 23:19:21,227][1934270] Saving new best policy, reward=22.181!
+[2024-05-27 23:19:21,559][1934315] Updated weights for policy 0, policy_version 950 (0.0007)
+[2024-05-27 23:19:23,512][1934315] Updated weights for policy 0, policy_version 960 (0.0007)
+[2024-05-27 23:19:25,534][1934315] Updated weights for policy 0, policy_version 970 (0.0011)
+[2024-05-27 23:19:26,225][1934158] Fps is (10 sec: 20480.2, 60 sec: 20889.6, 300 sec: 20286.3). Total num frames: 3985408. Throughput: 0: 5222.8. Samples: 990822. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-05-27 23:19:26,225][1934158] Avg episode reward: [(0, '19.642')]
+[2024-05-27 23:19:27,196][1934158] Component Batcher_0 stopped!
+[2024-05-27 23:19:27,196][1934270] Stopping Batcher_0...
+[2024-05-27 23:19:27,196][1934158] Component RolloutWorker_w3 process died already! Don't wait for it.
+[2024-05-27 23:19:27,196][1934270] Loop batcher_evt_loop terminating...
+[2024-05-27 23:19:27,196][1934270] Saving /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-05-27 23:19:27,202][1934317] Stopping RolloutWorker_w1...
+[2024-05-27 23:19:27,202][1934158] Component RolloutWorker_w1 stopped!
+[2024-05-27 23:19:27,202][1934317] Loop rollout_proc1_evt_loop terminating...
+[2024-05-27 23:19:27,202][1934320] Stopping RolloutWorker_w4...
+[2024-05-27 23:19:27,202][1934158] Component RolloutWorker_w4 stopped!
+[2024-05-27 23:19:27,202][1934316] Stopping RolloutWorker_w0...
+[2024-05-27 23:19:27,202][1934336] Stopping RolloutWorker_w5...
+[2024-05-27 23:19:27,203][1934320] Loop rollout_proc4_evt_loop terminating...
+[2024-05-27 23:19:27,203][1934158] Component RolloutWorker_w0 stopped!
+[2024-05-27 23:19:27,203][1934316] Loop rollout_proc0_evt_loop terminating...
+[2024-05-27 23:19:27,203][1934318] Stopping RolloutWorker_w2...
+[2024-05-27 23:19:27,203][1934158] Component RolloutWorker_w5 stopped!
+[2024-05-27 23:19:27,203][1934336] Loop rollout_proc5_evt_loop terminating...
+[2024-05-27 23:19:27,203][1934337] Stopping RolloutWorker_w6...
+[2024-05-27 23:19:27,203][1934158] Component RolloutWorker_w2 stopped!
+[2024-05-27 23:19:27,203][1934158] Component RolloutWorker_w6 stopped!
+[2024-05-27 23:19:27,203][1934318] Loop rollout_proc2_evt_loop terminating...
+[2024-05-27 23:19:27,203][1934337] Loop rollout_proc6_evt_loop terminating...
+[2024-05-27 23:19:27,208][1934342] Stopping RolloutWorker_w7...
+[2024-05-27 23:19:27,208][1934158] Component RolloutWorker_w7 stopped!
+[2024-05-27 23:19:27,208][1934342] Loop rollout_proc7_evt_loop terminating...
+[2024-05-27 23:19:27,210][1934315] Weights refcount: 2 0
+[2024-05-27 23:19:27,250][1934270] Saving /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-05-27 23:19:27,261][1934315] Stopping InferenceWorker_p0-w0...
+[2024-05-27 23:19:27,261][1934315] Loop inference_proc0-0_evt_loop terminating...
+[2024-05-27 23:19:27,261][1934158] Component InferenceWorker_p0-w0 stopped!
+[2024-05-27 23:19:27,311][1934270] Stopping LearnerWorker_p0...
+[2024-05-27 23:19:27,311][1934158] Component LearnerWorker_p0 stopped!
+[2024-05-27 23:19:27,311][1934270] Loop learner_proc0_evt_loop terminating...
+[2024-05-27 23:19:27,312][1934158] Waiting for process learner_proc0 to stop...
+[2024-05-27 23:19:27,998][1934158] Waiting for process inference_proc0-0 to join...
+[2024-05-27 23:19:27,999][1934158] Waiting for process rollout_proc0 to join...
+[2024-05-27 23:19:27,999][1934158] Waiting for process rollout_proc1 to join...
+[2024-05-27 23:19:27,999][1934158] Waiting for process rollout_proc2 to join...
+[2024-05-27 23:19:27,999][1934158] Waiting for process rollout_proc3 to join...
+[2024-05-27 23:19:27,999][1934158] Waiting for process rollout_proc4 to join...
+[2024-05-27 23:19:27,999][1934158] Waiting for process rollout_proc5 to join...
+[2024-05-27 23:19:27,999][1934158] Waiting for process rollout_proc6 to join...
+[2024-05-27 23:19:27,999][1934158] Waiting for process rollout_proc7 to join...
+[2024-05-27 23:19:27,999][1934158] Batcher 0 profile tree view:
+batching: 17.1563, releasing_batches: 0.0218
+[2024-05-27 23:19:27,999][1934158] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 4.5927
+update_model: 2.6467
+  weight_update: 0.0007
+one_step: 0.0025
+  handle_policy_step: 180.1540
+    deserialize: 5.4368, stack: 0.9178, obs_to_device_normalize: 40.7850, forward: 100.2096, send_messages: 7.8527
+    prepare_outputs: 18.8993
+      to_cpu: 11.8170
+[2024-05-27 23:19:27,999][1934158] Learner 0 profile tree view:
+misc: 0.0033, prepare_batch: 6.9298
+train: 19.9916
+  epoch_init: 0.0036, minibatch_init: 0.0045, losses_postprocess: 0.3051, kl_divergence: 0.3106, after_optimizer: 6.7727
+  calculate_losses: 8.3137
+    losses_init: 0.0021, forward_head: 0.5755, bptt_initial: 5.5591, tail: 0.4520, advantages_returns: 0.1178, losses: 0.7330
+    bptt: 0.7343
+      bptt_forward_core: 0.6989
+  update: 3.9895
+    clip: 0.4408
+[2024-05-27 23:19:27,999][1934158] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.1094, enqueue_policy_requests: 6.7447, env_step: 74.1145, overhead: 8.3155, complete_rollouts: 0.2030
+save_policy_outputs: 6.8527
+  split_output_tensors: 3.2861
+[2024-05-27 23:19:27,999][1934158] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.1229, enqueue_policy_requests: 6.7854, env_step: 69.9361, overhead: 8.1086, complete_rollouts: 0.2114
+save_policy_outputs: 6.5377
+  split_output_tensors: 3.1628
+[2024-05-27 23:19:28,000][1934158] Loop Runner_EvtLoop terminating...
+[2024-05-27 23:19:28,000][1934158] Runner profile tree view:
+main_loop: 204.3645
+[2024-05-27 23:19:28,000][1934158] Collected {0: 4005888}, FPS: 19601.7
+[2024-05-27 23:19:28,286][1934158] Loading existing experiment configuration from /media/fast/code/learning/train_dir/default_experiment/config.json
+[2024-05-27 23:19:28,286][1934158] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-05-27 23:19:28,286][1934158] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-05-27 23:19:28,286][1934158] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-05-27 23:19:28,286][1934158] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-05-27 23:19:28,286][1934158] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-05-27 23:19:28,287][1934158] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-05-27 23:19:28,294][1934158] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-05-27 23:19:28,294][1934158] RunningMeanStd input shape: (3, 72, 128)
+[2024-05-27 23:19:28,295][1934158] RunningMeanStd input shape: (1,)
+[2024-05-27 23:19:28,301][1934158] ConvEncoder: input_channels=3
+[2024-05-27 23:19:28,358][1934158] Conv encoder output size: 512
+[2024-05-27 23:19:28,358][1934158] Policy head output size: 512
+[2024-05-27 23:19:28,450][1934158] Loading state from checkpoint /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-05-27 23:19:29,259][1934158] Num frames 100...
+[2024-05-27 23:19:29,371][1934158] Num frames 200...
+[2024-05-27 23:19:29,454][1934158] Num frames 300...
+[2024-05-27 23:19:29,532][1934158] Num frames 400...
+[2024-05-27 23:19:29,631][1934158] Num frames 500...
+[2024-05-27 23:19:29,698][1934158] Num frames 600...
+[2024-05-27 23:19:29,791][1934158] Num frames 700...
+[2024-05-27 23:19:29,862][1934158] Num frames 800...
+[2024-05-27 23:19:29,927][1934158] Num frames 900...
+[2024-05-27 23:19:29,998][1934158] Num frames 1000...
+[2024-05-27 23:19:30,066][1934158] Num frames 1100...
+[2024-05-27 23:19:30,177][1934158] Num frames 1200...
+[2024-05-27 23:19:30,260][1934158] Num frames 1300...
+[2024-05-27 23:19:30,323][1934158] Num frames 1400...
+[2024-05-27 23:19:30,380][1934158] Avg episode rewards: #0: 36.080, true rewards: #0: 14.080
+[2024-05-27 23:19:30,380][1934158] Avg episode reward: 36.080, avg true_objective: 14.080
+[2024-05-27 23:19:30,437][1934158] Num frames 1500...
+[2024-05-27 23:19:30,499][1934158] Num frames 1600...
+[2024-05-27 23:19:30,558][1934158] Num frames 1700...
+[2024-05-27 23:19:30,615][1934158] Num frames 1800...
+[2024-05-27 23:19:30,674][1934158] Num frames 1900...
+[2024-05-27 23:19:30,737][1934158] Num frames 2000...
+[2024-05-27 23:19:30,840][1934158] Avg episode rewards: #0: 24.400, true rewards: #0: 10.400
+[2024-05-27 23:19:30,840][1934158] Avg episode reward: 24.400, avg true_objective: 10.400
+[2024-05-27 23:19:30,853][1934158] Num frames 2100...
+[2024-05-27 23:19:30,916][1934158] Num frames 2200...
+[2024-05-27 23:19:30,975][1934158] Num frames 2300...
+[2024-05-27 23:19:31,035][1934158] Num frames 2400...
+[2024-05-27 23:19:31,097][1934158] Num frames 2500...
+[2024-05-27 23:19:31,155][1934158] Num frames 2600...
+[2024-05-27 23:19:31,213][1934158] Num frames 2700...
+[2024-05-27 23:19:31,271][1934158] Num frames 2800...
+[2024-05-27 23:19:31,330][1934158] Num frames 2900...
+[2024-05-27 23:19:31,392][1934158] Num frames 3000...
+[2024-05-27 23:19:31,450][1934158] Num frames 3100...
+[2024-05-27 23:19:31,505][1934158] Num frames 3200...
+[2024-05-27 23:19:31,561][1934158] Num frames 3300...
+[2024-05-27 23:19:31,668][1934158] Avg episode rewards: #0: 26.640, true rewards: #0: 11.307
+[2024-05-27 23:19:31,668][1934158] Avg episode reward: 26.640, avg true_objective: 11.307
+[2024-05-27 23:19:31,674][1934158] Num frames 3400...
+[2024-05-27 23:19:31,733][1934158] Num frames 3500...
+[2024-05-27 23:19:31,791][1934158] Num frames 3600...
+[2024-05-27 23:19:31,849][1934158] Num frames 3700...
+[2024-05-27 23:19:31,908][1934158] Num frames 3800...
+[2024-05-27 23:19:31,961][1934158] Num frames 3900...
+[2024-05-27 23:19:32,019][1934158] Num frames 4000...
+[2024-05-27 23:19:32,075][1934158] Num frames 4100...
+[2024-05-27 23:19:32,133][1934158] Num frames 4200...
+[2024-05-27 23:19:32,237][1934158] Avg episode rewards: #0: 24.720, true rewards: #0: 10.720
+[2024-05-27 23:19:32,237][1934158] Avg episode reward: 24.720, avg true_objective: 10.720
+[2024-05-27 23:19:32,245][1934158] Num frames 4300...
+[2024-05-27 23:19:32,301][1934158] Num frames 4400...
+[2024-05-27 23:19:32,360][1934158] Num frames 4500...
+[2024-05-27 23:19:32,418][1934158] Num frames 4600...
+[2024-05-27 23:19:32,476][1934158] Num frames 4700...
+[2024-05-27 23:19:32,545][1934158] Num frames 4800...
+[2024-05-27 23:19:32,607][1934158] Num frames 4900...
+[2024-05-27 23:19:32,667][1934158] Num frames 5000...
+[2024-05-27 23:19:32,732][1934158] Num frames 5100...
+[2024-05-27 23:19:32,794][1934158] Num frames 5200...
+[2024-05-27 23:19:32,852][1934158] Num frames 5300...
+[2024-05-27 23:19:32,906][1934158] Avg episode rewards: #0: 24.204, true rewards: #0: 10.604
+[2024-05-27 23:19:32,906][1934158] Avg episode reward: 24.204, avg true_objective: 10.604
+[2024-05-27 23:19:32,970][1934158] Num frames 5400...
+[2024-05-27 23:19:33,037][1934158] Num frames 5500...
+[2024-05-27 23:19:33,102][1934158] Num frames 5600...
+[2024-05-27 23:19:33,165][1934158] Num frames 5700...
+[2024-05-27 23:19:33,222][1934158] Num frames 5800...
+[2024-05-27 23:19:33,310][1934158] Avg episode rewards: #0: 21.607, true rewards: #0: 9.773
+[2024-05-27 23:19:33,310][1934158] Avg episode reward: 21.607, avg true_objective: 9.773
+[2024-05-27 23:19:33,333][1934158] Num frames 5900...
+[2024-05-27 23:19:33,482][1934158] Num frames 6000...
+[2024-05-27 23:19:33,548][1934158] Num frames 6100...
+[2024-05-27 23:19:33,609][1934158] Num frames 6200...
+[2024-05-27 23:19:33,671][1934158] Num frames 6300...
+[2024-05-27 23:19:33,734][1934158] Num frames 6400...
+[2024-05-27 23:19:33,794][1934158] Num frames 6500...
+[2024-05-27 23:19:33,856][1934158] Num frames 6600...
+[2024-05-27 23:19:33,921][1934158] Num frames 6700...
+[2024-05-27 23:19:33,978][1934158] Num frames 6800...
+[2024-05-27 23:19:34,035][1934158] Num frames 6900...
+[2024-05-27 23:19:34,144][1934158] Avg episode rewards: #0: 21.702, true rewards: #0: 9.987
+[2024-05-27 23:19:34,144][1934158] Avg episode reward: 21.702, avg true_objective: 9.987
+[2024-05-27 23:19:34,151][1934158] Num frames 7000...
+[2024-05-27 23:19:34,217][1934158] Num frames 7100...
+[2024-05-27 23:19:34,281][1934158] Num frames 7200...
+[2024-05-27 23:19:34,341][1934158] Num frames 7300...
+[2024-05-27 23:19:34,451][1934158] Num frames 7400...
+[2024-05-27 23:19:34,510][1934158] Num frames 7500...
+[2024-05-27 23:19:34,570][1934158] Num frames 7600...
+[2024-05-27 23:19:34,634][1934158] Num frames 7700...
+[2024-05-27 23:19:34,694][1934158] Num frames 7800...
+[2024-05-27 23:19:34,781][1934158] Num frames 7900...
+[2024-05-27 23:19:34,851][1934158] Num frames 8000...
+[2024-05-27 23:19:34,933][1934158] Num frames 8100...
+[2024-05-27 23:19:35,030][1934158] Num frames 8200...
+[2024-05-27 23:19:35,099][1934158] Num frames 8300...
+[2024-05-27 23:19:35,251][1934158] Num frames 8400...
+[2024-05-27 23:19:35,382][1934158] Num frames 8500...
+[2024-05-27 23:19:35,466][1934158] Num frames 8600...
+[2024-05-27 23:19:35,533][1934158] Num frames 8700...
+[2024-05-27 23:19:35,603][1934158] Num frames 8800...
+[2024-05-27 23:19:35,672][1934158] Num frames 8900...
+[2024-05-27 23:19:35,772][1934158] Num frames 9000...
+[2024-05-27 23:19:35,903][1934158] Avg episode rewards: #0: 25.989, true rewards: #0: 11.364
+[2024-05-27 23:19:35,903][1934158] Avg episode reward: 25.989, avg true_objective: 11.364
+[2024-05-27 23:19:35,910][1934158] Num frames 9100...
+[2024-05-27 23:19:35,989][1934158] Num frames 9200...
+[2024-05-27 23:19:36,090][1934158] Num frames 9300...
+[2024-05-27 23:19:36,194][1934158] Num frames 9400...
+[2024-05-27 23:19:36,262][1934158] Num frames 9500...
+[2024-05-27 23:19:36,364][1934158] Num frames 9600...
+[2024-05-27 23:19:36,441][1934158] Avg episode rewards: #0: 24.039, true rewards: #0: 10.706
+[2024-05-27 23:19:36,441][1934158] Avg episode reward: 24.039, avg true_objective: 10.706
+[2024-05-27 23:19:36,491][1934158] Num frames 9700...
+[2024-05-27 23:19:36,600][1934158] Num frames 9800...
+[2024-05-27 23:19:36,669][1934158] Num frames 9900...
+[2024-05-27 23:19:36,743][1934158] Num frames 10000...
+[2024-05-27 23:19:36,810][1934158] Num frames 10100...
+[2024-05-27 23:19:36,895][1934158] Avg episode rewards: #0: 22.550, true rewards: #0: 10.150
+[2024-05-27 23:19:36,895][1934158] Avg episode reward: 22.550, avg true_objective: 10.150
+[2024-05-27 23:19:49,448][1934158] Replay video saved to /media/fast/code/learning/train_dir/default_experiment/replay.mp4!
+[2024-05-27 23:19:49,685][1934158] Loading existing experiment configuration from /media/fast/code/learning/train_dir/default_experiment/config.json
+[2024-05-27 23:19:49,685][1934158] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'hf_repository'='DavidPL1/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-05-27 23:19:49,685][1934158] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-05-27 23:19:49,688][1934158] RunningMeanStd input shape: (3, 72, 128)
+[2024-05-27 23:19:49,689][1934158] RunningMeanStd input shape: (1,)
+[2024-05-27 23:19:49,694][1934158] ConvEncoder: input_channels=3
+[2024-05-27 23:19:49,712][1934158] Conv encoder output size: 512
+[2024-05-27 23:19:49,712][1934158] Policy head output size: 512
+[2024-05-27 23:19:49,721][1934158] Loading state from checkpoint /media/fast/code/learning/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-05-27 23:19:50,123][1934158] Num frames 100...
+[2024-05-27 23:19:50,179][1934158] Num frames 200...
+[2024-05-27 23:19:50,237][1934158] Num frames 300...
+[2024-05-27 23:19:50,298][1934158] Num frames 400...
+[2024-05-27 23:19:50,364][1934158] Num frames 500...
+[2024-05-27 23:19:50,424][1934158] Num frames 600...
+[2024-05-27 23:19:50,483][1934158] Num frames 700...
+[2024-05-27 23:19:50,544][1934158] Num frames 800...
+[2024-05-27 23:19:50,615][1934158] Avg episode rewards: #0: 15.320, true rewards: #0: 8.320
+[2024-05-27 23:19:50,616][1934158] Avg episode reward: 15.320, avg true_objective: 8.320
+[2024-05-27 23:19:50,657][1934158] Num frames 900...
+[2024-05-27 23:19:50,717][1934158] Num frames 1000...
+[2024-05-27 23:19:50,777][1934158] Num frames 1100...
+[2024-05-27 23:19:50,834][1934158] Num frames 1200...
+[2024-05-27 23:19:50,898][1934158] Num frames 1300...
+[2024-05-27 23:19:51,089][1934158] Num frames 1400...
+[2024-05-27 23:19:51,192][1934158] Num frames 1500...
+[2024-05-27 23:19:51,258][1934158] Num frames 1600...
+[2024-05-27 23:19:51,324][1934158] Num frames 1700...
+[2024-05-27 23:19:51,544][1934158] Num frames 1800...
+[2024-05-27 23:19:51,627][1934158] Num frames 1900...
+[2024-05-27 23:19:51,718][1934158] Num frames 2000...
+[2024-05-27 23:19:51,785][1934158] Num frames 2100...
+[2024-05-27 23:19:51,866][1934158] Avg episode rewards: #0: 23.700, true rewards: #0: 10.700
+[2024-05-27 23:19:51,866][1934158] Avg episode reward: 23.700, avg true_objective: 10.700
+[2024-05-27 23:19:51,915][1934158] Num frames 2200...
+[2024-05-27 23:19:51,983][1934158] Num frames 2300...
+[2024-05-27 23:19:52,098][1934158] Num frames 2400...
+[2024-05-27 23:19:52,189][1934158] Num frames 2500...
+[2024-05-27 23:19:52,259][1934158] Num frames 2600...
+[2024-05-27 23:19:52,432][1934158] Num frames 2700...
+[2024-05-27 23:19:52,507][1934158] Num frames 2800...
+[2024-05-27 23:19:52,571][1934158] Num frames 2900...
+[2024-05-27 23:19:52,754][1934158] Num frames 3000...
+[2024-05-27 23:19:52,874][1934158] Num frames 3100...
+[2024-05-27 23:19:52,940][1934158] Num frames 3200...
+[2024-05-27 23:19:53,007][1934158] Num frames 3300...
+[2024-05-27 23:19:53,074][1934158] Num frames 3400...
+[2024-05-27 23:19:53,180][1934158] Avg episode rewards: #0: 26.280, true rewards: #0: 11.613
+[2024-05-27 23:19:53,180][1934158] Avg episode reward: 26.280, avg true_objective: 11.613
+[2024-05-27 23:19:53,191][1934158] Num frames 3500...
+[2024-05-27 23:19:53,254][1934158] Num frames 3600...
+[2024-05-27 23:19:53,331][1934158] Num frames 3700...
+[2024-05-27 23:19:53,423][1934158] Num frames 3800...
+[2024-05-27 23:19:53,511][1934158] Num frames 3900...
+[2024-05-27 23:19:53,578][1934158] Num frames 4000...
+[2024-05-27 23:19:53,649][1934158] Num frames 4100...
+[2024-05-27 23:19:53,715][1934158] Num frames 4200...
+[2024-05-27 23:19:53,811][1934158] Num frames 4300...
+[2024-05-27 23:19:53,883][1934158] Num frames 4400...
+[2024-05-27 23:19:53,953][1934158] Num frames 4500...
+[2024-05-27 23:19:54,033][1934158] Num frames 4600...
+[2024-05-27 23:19:54,114][1934158] Num frames 4700...
+[2024-05-27 23:19:54,212][1934158] Avg episode rewards: #0: 26.830, true rewards: #0: 11.830
+[2024-05-27 23:19:54,213][1934158] Avg episode reward: 26.830, avg true_objective: 11.830
+[2024-05-27 23:19:54,258][1934158] Num frames 4800...
+[2024-05-27 23:19:54,415][1934158] Num frames 4900...
+[2024-05-27 23:19:54,590][1934158] Num frames 5000...
+[2024-05-27 23:19:54,654][1934158] Num frames 5100...
+[2024-05-27 23:19:54,722][1934158] Num frames 5200...
+[2024-05-27 23:19:54,785][1934158] Num frames 5300...
+[2024-05-27 23:19:54,876][1934158] Num frames 5400...
+[2024-05-27 23:19:55,026][1934158] Num frames 5500...
+[2024-05-27 23:19:55,145][1934158] Num frames 5600...
+[2024-05-27 23:19:55,269][1934158] Num frames 5700...
+[2024-05-27 23:19:55,339][1934158] Num frames 5800...
+[2024-05-27 23:19:55,535][1934158] Num frames 5900...
+[2024-05-27 23:19:55,627][1934158] Num frames 6000...
+[2024-05-27 23:19:55,699][1934158] Num frames 6100...
+[2024-05-27 23:19:55,766][1934158] Num frames 6200...
+[2024-05-27 23:19:55,834][1934158] Num frames 6300...
+[2024-05-27 23:19:55,900][1934158] Num frames 6400...
+[2024-05-27 23:19:56,032][1934158] Num frames 6500...
+[2024-05-27 23:19:56,229][1934158] Num frames 6600...
+[2024-05-27 23:19:56,296][1934158] Num frames 6700...
+[2024-05-27 23:19:56,406][1934158] Num frames 6800...
+[2024-05-27 23:19:56,480][1934158] Avg episode rewards: #0: 33.064, true rewards: #0: 13.664
+[2024-05-27 23:19:56,481][1934158] Avg episode reward: 33.064, avg true_objective: 13.664
+[2024-05-27 23:19:56,526][1934158] Num frames 6900...
+[2024-05-27 23:19:56,763][1934158] Num frames 7000...
+[2024-05-27 23:19:56,865][1934158] Num frames 7100...
+[2024-05-27 23:19:56,932][1934158] Num frames 7200...
+[2024-05-27 23:19:57,014][1934158] Num frames 7300...
+[2024-05-27 23:19:57,145][1934158] Avg episode rewards: #0: 29.163, true rewards: #0: 12.330
+[2024-05-27 23:19:57,145][1934158] Avg episode reward: 29.163, avg true_objective: 12.330
+[2024-05-27 23:19:57,147][1934158] Num frames 7400...
+[2024-05-27 23:19:57,215][1934158] Num frames 7500...
+[2024-05-27 23:19:57,399][1934158] Num frames 7600...
+[2024-05-27 23:19:57,518][1934158] Num frames 7700...
+[2024-05-27 23:19:57,586][1934158] Num frames 7800...
+[2024-05-27 23:19:57,695][1934158] Num frames 7900...
+[2024-05-27 23:19:57,823][1934158] Num frames 8000...
+[2024-05-27 23:19:57,964][1934158] Num frames 8100...
+[2024-05-27 23:19:58,032][1934158] Num frames 8200...
+[2024-05-27 23:19:58,101][1934158] Num frames 8300...
+[2024-05-27 23:19:58,168][1934158] Num frames 8400...
+[2024-05-27 23:19:58,262][1934158] Num frames 8500...
+[2024-05-27 23:19:58,340][1934158] Num frames 8600...
+[2024-05-27 23:19:58,411][1934158] Num frames 8700...
+[2024-05-27 23:19:58,523][1934158] Num frames 8800...
+[2024-05-27 23:19:58,660][1934158] Num frames 8900...
+[2024-05-27 23:19:58,727][1934158] Num frames 9000...
+[2024-05-27 23:19:58,802][1934158] Num frames 9100...
+[2024-05-27 23:19:59,012][1934158] Num frames 9200...
+[2024-05-27 23:19:59,116][1934158] Num frames 9300...
+[2024-05-27 23:19:59,185][1934158] Num frames 9400...
+[2024-05-27 23:19:59,306][1934158] Avg episode rewards: #0: 33.711, true rewards: #0: 13.569
+[2024-05-27 23:19:59,306][1934158] Avg episode reward: 33.711, avg true_objective: 13.569
+[2024-05-27 23:19:59,307][1934158] Num frames 9500...
+[2024-05-27 23:19:59,421][1934158] Num frames 9600...
+[2024-05-27 23:19:59,512][1934158] Num frames 9700...
+[2024-05-27 23:19:59,576][1934158] Num frames 9800...
+[2024-05-27 23:19:59,647][1934158] Num frames 9900...
+[2024-05-27 23:19:59,729][1934158] Avg episode rewards: #0: 30.182, true rewards: #0: 12.433
+[2024-05-27 23:19:59,729][1934158] Avg episode reward: 30.182, avg true_objective: 12.433
+[2024-05-27 23:19:59,775][1934158] Num frames 10000...
+[2024-05-27 23:19:59,844][1934158] Num frames 10100...
+[2024-05-27 23:19:59,909][1934158] Num frames 10200...
+[2024-05-27 23:20:00,028][1934158] Num frames 10300...
+[2024-05-27 23:20:00,151][1934158] Num frames 10400...
+[2024-05-27 23:20:00,252][1934158] Num frames 10500...
+[2024-05-27 23:20:00,320][1934158] Num frames 10600...
+[2024-05-27 23:20:00,496][1934158] Num frames 10700...
+[2024-05-27 23:20:00,583][1934158] Num frames 10800...
+[2024-05-27 23:20:00,669][1934158] Num frames 10900...
+[2024-05-27 23:20:00,763][1934158] Num frames 11000...
+[2024-05-27 23:20:00,883][1934158] Num frames 11100...
+[2024-05-27 23:20:00,972][1934158] Num frames 11200...
+[2024-05-27 23:20:01,045][1934158] Num frames 11300...
+[2024-05-27 23:20:01,140][1934158] Num frames 11400...
+[2024-05-27 23:20:01,322][1934158] Num frames 11500...
+[2024-05-27 23:20:01,404][1934158] Avg episode rewards: #0: 31.269, true rewards: #0: 12.824
+[2024-05-27 23:20:01,404][1934158] Avg episode reward: 31.269, avg true_objective: 12.824
+[2024-05-27 23:20:01,495][1934158] Num frames 11600...
+[2024-05-27 23:20:01,560][1934158] Num frames 11700...
+[2024-05-27 23:20:01,631][1934158] Num frames 11800...
+[2024-05-27 23:20:01,747][1934158] Num frames 11900...
+[2024-05-27 23:20:01,829][1934158] Num frames 12000...
+[2024-05-27 23:20:01,911][1934158] Num frames 12100...
+[2024-05-27 23:20:02,025][1934158] Num frames 12200...
+[2024-05-27 23:20:02,094][1934158] Num frames 12300...
+[2024-05-27 23:20:02,161][1934158] Num frames 12400...
+[2024-05-27 23:20:02,230][1934158] Num frames 12500...
+[2024-05-27 23:20:02,301][1934158] Num frames 12600...
+[2024-05-27 23:20:02,394][1934158] Avg episode rewards: #0: 30.430, true rewards: #0: 12.630
+[2024-05-27 23:20:02,394][1934158] Avg episode reward: 30.430, avg true_objective: 12.630
+[2024-05-27 23:20:17,697][1934158] Replay video saved to /media/fast/code/learning/train_dir/default_experiment/replay.mp4!