Upload folder using huggingface_hub

.gitattributes

@@ -32,3 +32,4 @@ 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.1682648908.CAPTAIN-AMERICA

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b993fd09d818e80b3179fe4de0062329a95ce69e5abb72456a2f2957911d2f04
+size 203043

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: 3.90 +/- 0.60
+      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 ItchyB/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_000000280_1146880_reward_4.759.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcaaf9e66ed8a5018842b94744820c9151474166439b62b504424a4d88d7d11c
+size 34928156

checkpoint_p0/checkpoint_000000517_2117632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0c59bb3cc2ce57a2de7b60b6b68f82fe821daea8347c180125a1c83e633479
+size 34928156

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c041d4c8f7a9b660a19117b7299ccba70cefb4725d2466c1564aad4956ef249
+size 34928156

config.json

@@ -0,0 +1,142 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "doom_health_gathering_supreme",
+  "experiment": "default_experiment",
+  "train_dir": "/home/byron/projects/rl-learning-course/unit-08/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 sha256:2e1acb924a30b27425c5dcc73ae4ba44ec05f28cea902cafff951ef665970113
+size 5397393

sf_log.txt

@@ -0,0 +1,624 @@
+[2023-04-27 22:28:30,298][19320] Saving configuration to /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/config.json...
+[2023-04-27 22:28:30,299][19320] Rollout worker 0 uses device cpu
+[2023-04-27 22:28:30,300][19320] Rollout worker 1 uses device cpu
+[2023-04-27 22:28:30,300][19320] Rollout worker 2 uses device cpu
+[2023-04-27 22:28:30,302][19320] Rollout worker 3 uses device cpu
+[2023-04-27 22:28:30,302][19320] Rollout worker 4 uses device cpu
+[2023-04-27 22:28:30,303][19320] Rollout worker 5 uses device cpu
+[2023-04-27 22:28:30,304][19320] Rollout worker 6 uses device cpu
+[2023-04-27 22:28:30,304][19320] Rollout worker 7 uses device cpu
+[2023-04-27 22:28:30,345][19320] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-04-27 22:28:30,345][19320] InferenceWorker_p0-w0: min num requests: 2
+[2023-04-27 22:28:30,363][19320] Starting all processes...
+[2023-04-27 22:28:30,364][19320] Starting process learner_proc0
+[2023-04-27 22:28:30,489][19320] Starting all processes...
+[2023-04-27 22:28:30,494][19320] Starting process inference_proc0-0
+[2023-04-27 22:28:30,494][19320] Starting process rollout_proc0
+[2023-04-27 22:28:30,495][19320] Starting process rollout_proc1
+[2023-04-27 22:28:30,495][19320] Starting process rollout_proc2
+[2023-04-27 22:28:30,496][19320] Starting process rollout_proc3
+[2023-04-27 22:28:30,496][19320] Starting process rollout_proc4
+[2023-04-27 22:28:30,496][19320] Starting process rollout_proc5
+[2023-04-27 22:28:30,497][19320] Starting process rollout_proc6
+[2023-04-27 22:28:30,497][19320] Starting process rollout_proc7
+[2023-04-27 22:28:31,380][26612] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-04-27 22:28:31,380][26612] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-04-27 22:28:31,403][26612] Num visible devices: 1
+[2023-04-27 22:28:31,424][26630] Worker 3 uses CPU cores [9, 10, 11]
+[2023-04-27 22:28:31,427][26612] Starting seed is not provided
+[2023-04-27 22:28:31,427][26612] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-04-27 22:28:31,427][26612] Initializing actor-critic model on device cuda:0
+[2023-04-27 22:28:31,427][26612] RunningMeanStd input shape: (3, 72, 128)
+[2023-04-27 22:28:31,428][26612] RunningMeanStd input shape: (1,)
+[2023-04-27 22:28:31,430][26629] Worker 2 uses CPU cores [6, 7, 8]
+[2023-04-27 22:28:31,434][26628] Worker 1 uses CPU cores [3, 4, 5]
+[2023-04-27 22:28:31,439][26612] ConvEncoder: input_channels=3
+[2023-04-27 22:28:31,444][26638] Worker 7 uses CPU cores [21, 22, 23]
+[2023-04-27 22:28:31,455][26626] Worker 0 uses CPU cores [0, 1, 2]
+[2023-04-27 22:28:31,457][26632] Worker 5 uses CPU cores [15, 16, 17]
+[2023-04-27 22:28:31,467][26631] Worker 4 uses CPU cores [12, 13, 14]
+[2023-04-27 22:28:31,474][26627] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-04-27 22:28:31,474][26627] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-04-27 22:28:31,481][26657] Worker 6 uses CPU cores [18, 19, 20]
+[2023-04-27 22:28:31,507][26627] Num visible devices: 1
+[2023-04-27 22:28:31,580][26612] Conv encoder output size: 512
+[2023-04-27 22:28:31,581][26612] Policy head output size: 512
+[2023-04-27 22:28:31,603][26612] Created Actor Critic model with architecture:
+[2023-04-27 22:28:31,603][26612] 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)
+  )
+)
+[2023-04-27 22:28:33,372][26612] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-04-27 22:28:33,373][26612] No checkpoints found
+[2023-04-27 22:28:33,373][26612] Did not load from checkpoint, starting from scratch!
+[2023-04-27 22:28:33,373][26612] Initialized policy 0 weights for model version 0
+[2023-04-27 22:28:33,376][26612] LearnerWorker_p0 finished initialization!
+[2023-04-27 22:28:33,376][26612] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-04-27 22:28:33,815][19320] 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)
+[2023-04-27 22:28:34,070][26627] RunningMeanStd input shape: (3, 72, 128)
+[2023-04-27 22:28:34,071][26627] RunningMeanStd input shape: (1,)
+[2023-04-27 22:28:34,079][26627] ConvEncoder: input_channels=3
+[2023-04-27 22:28:34,158][26627] Conv encoder output size: 512
+[2023-04-27 22:28:34,159][26627] Policy head output size: 512
+[2023-04-27 22:28:34,896][19320] Inference worker 0-0 is ready!
+[2023-04-27 22:28:34,897][19320] All inference workers are ready! Signal rollout workers to start!
+[2023-04-27 22:28:34,912][26657] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:28:34,913][26630] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:28:34,914][26638] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:28:34,914][26629] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:28:34,914][26626] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:28:34,915][26632] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:28:34,915][26631] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:28:34,915][26628] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:28:34,949][26628] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process...
+[2023-04-27 22:28:34,950][26628] EvtLoop [rollout_proc1_evt_loop, process=rollout_proc1] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=()
+Traceback (most recent call last):
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/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 "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
+    slot_callable(*args)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init
+    env_runner.init(self.timing)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init
+    self._reset()
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/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 "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/gym/core.py", line 323, in reset
+    return self.env.reset(**kwargs)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset
+    return self.env.reset(**kwargs)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/gym/core.py", line 379, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/gym/core.py", line 323, in reset
+    return self.env.reset(**kwargs)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset
+    return self.env.reset(**kwargs)
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset
+    self._ensure_initialized()
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized
+    self.initialize()
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize
+    self._game_init()
+  File "/home/byron/miniconda3/envs/ml-agents/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init
+    raise EnvCriticalError()
+sample_factory.envs.env_utils.EnvCriticalError
+[2023-04-27 22:28:34,951][26628] Unhandled exception  in evt loop rollout_proc1_evt_loop
+[2023-04-27 22:28:35,135][26629] Decorrelating experience for 0 frames...
+[2023-04-27 22:28:35,135][26630] Decorrelating experience for 0 frames...
+[2023-04-27 22:28:35,135][26657] Decorrelating experience for 0 frames...
+[2023-04-27 22:28:35,141][26631] Decorrelating experience for 0 frames...
+[2023-04-27 22:28:35,326][26629] Decorrelating experience for 32 frames...
+[2023-04-27 22:28:35,327][26631] Decorrelating experience for 32 frames...
+[2023-04-27 22:28:35,361][26630] Decorrelating experience for 32 frames...
+[2023-04-27 22:28:35,399][26632] Decorrelating experience for 0 frames...
+[2023-04-27 22:28:35,410][26626] Decorrelating experience for 0 frames...
+[2023-04-27 22:28:35,566][26631] Decorrelating experience for 64 frames...
+[2023-04-27 22:28:35,567][26657] Decorrelating experience for 32 frames...
+[2023-04-27 22:28:35,596][26632] Decorrelating experience for 32 frames...
+[2023-04-27 22:28:35,596][26629] Decorrelating experience for 64 frames...
+[2023-04-27 22:28:35,597][26630] Decorrelating experience for 64 frames...
+[2023-04-27 22:28:35,783][26631] Decorrelating experience for 96 frames...
+[2023-04-27 22:28:35,784][26657] Decorrelating experience for 64 frames...
+[2023-04-27 22:28:35,825][26626] Decorrelating experience for 32 frames...
+[2023-04-27 22:28:35,826][26629] Decorrelating experience for 96 frames...
+[2023-04-27 22:28:35,860][26630] Decorrelating experience for 96 frames...
+[2023-04-27 22:28:36,028][26626] Decorrelating experience for 64 frames...
+[2023-04-27 22:28:36,029][26638] Decorrelating experience for 0 frames...
+[2023-04-27 22:28:36,236][26638] Decorrelating experience for 32 frames...
+[2023-04-27 22:28:36,278][26626] Decorrelating experience for 96 frames...
+[2023-04-27 22:28:36,483][26638] Decorrelating experience for 64 frames...
+[2023-04-27 22:28:36,526][26657] Decorrelating experience for 96 frames...
+[2023-04-27 22:28:36,742][26638] Decorrelating experience for 96 frames...
+[2023-04-27 22:28:36,763][26632] Decorrelating experience for 64 frames...
+[2023-04-27 22:28:37,009][26632] Decorrelating experience for 96 frames...
+[2023-04-27 22:28:38,609][26612] Signal inference workers to stop experience collection...
+[2023-04-27 22:28:38,611][26627] InferenceWorker_p0-w0: stopping experience collection
+[2023-04-27 22:28:38,815][19320] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 130.4. Samples: 652. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-04-27 22:28:38,816][19320] Avg episode reward: [(0, '2.566')]
+[2023-04-27 22:28:40,413][26612] Signal inference workers to resume experience collection...
+[2023-04-27 22:28:40,414][26627] InferenceWorker_p0-w0: resuming experience collection
+[2023-04-27 22:28:43,469][26627] Updated weights for policy 0, policy_version 10 (0.0582)
+[2023-04-27 22:28:43,815][19320] Fps is (10 sec: 4505.6, 60 sec: 4505.6, 300 sec: 4505.6). Total num frames: 45056. Throughput: 0: 307.2. Samples: 3072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:28:43,816][19320] Avg episode reward: [(0, '4.236')]
+[2023-04-27 22:28:46,007][26627] Updated weights for policy 0, policy_version 20 (0.0008)
+[2023-04-27 22:28:47,944][26627] Updated weights for policy 0, policy_version 30 (0.0012)
+[2023-04-27 22:28:48,815][19320] Fps is (10 sec: 13926.4, 60 sec: 9284.3, 300 sec: 9284.3). Total num frames: 139264. Throughput: 0: 1720.3. Samples: 25804. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
+[2023-04-27 22:28:48,815][19320] Avg episode reward: [(0, '4.246')]
+[2023-04-27 22:28:48,821][26612] Saving new best policy, reward=4.246!
+[2023-04-27 22:28:50,306][26627] Updated weights for policy 0, policy_version 40 (0.0008)
+[2023-04-27 22:28:50,340][19320] Heartbeat connected on Batcher_0
+[2023-04-27 22:28:50,342][19320] Heartbeat connected on LearnerWorker_p0
+[2023-04-27 22:28:50,349][19320] Heartbeat connected on RolloutWorker_w0
+[2023-04-27 22:28:50,350][19320] Heartbeat connected on InferenceWorker_p0-w0
+[2023-04-27 22:28:50,353][19320] Heartbeat connected on RolloutWorker_w2
+[2023-04-27 22:28:50,356][19320] Heartbeat connected on RolloutWorker_w3
+[2023-04-27 22:28:50,358][19320] Heartbeat connected on RolloutWorker_w4
+[2023-04-27 22:28:50,361][19320] Heartbeat connected on RolloutWorker_w5
+[2023-04-27 22:28:50,365][19320] Heartbeat connected on RolloutWorker_w6
+[2023-04-27 22:28:50,366][19320] Heartbeat connected on RolloutWorker_w7
+[2023-04-27 22:28:52,258][26627] Updated weights for policy 0, policy_version 50 (0.0007)
+[2023-04-27 22:28:53,815][19320] Fps is (10 sec: 18432.0, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 229376. Throughput: 0: 2718.3. Samples: 54366. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-04-27 22:28:53,816][19320] Avg episode reward: [(0, '4.546')]
+[2023-04-27 22:28:53,817][26612] Saving new best policy, reward=4.546!
+[2023-04-27 22:28:54,878][26627] Updated weights for policy 0, policy_version 60 (0.0013)
+[2023-04-27 22:28:57,353][26627] Updated weights for policy 0, policy_version 70 (0.0011)
+[2023-04-27 22:28:58,815][19320] Fps is (10 sec: 17612.6, 60 sec: 12615.6, 300 sec: 12615.6). Total num frames: 315392. Throughput: 0: 2677.7. Samples: 66944. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:28:58,816][19320] Avg episode reward: [(0, '4.345')]
+[2023-04-27 22:28:59,354][26627] Updated weights for policy 0, policy_version 80 (0.0009)
+[2023-04-27 22:29:02,010][26627] Updated weights for policy 0, policy_version 90 (0.0014)
+[2023-04-27 22:29:03,815][19320] Fps is (10 sec: 15974.3, 60 sec: 12970.7, 300 sec: 12970.7). Total num frames: 389120. Throughput: 0: 3074.0. Samples: 92220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-04-27 22:29:03,815][19320] Avg episode reward: [(0, '4.536')]
+[2023-04-27 22:29:04,867][26627] Updated weights for policy 0, policy_version 100 (0.0020)
+[2023-04-27 22:29:07,514][26627] Updated weights for policy 0, policy_version 110 (0.0011)
+[2023-04-27 22:29:08,815][19320] Fps is (10 sec: 15974.6, 60 sec: 13575.3, 300 sec: 13575.3). Total num frames: 475136. Throughput: 0: 3287.9. Samples: 115078. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-04-27 22:29:08,816][19320] Avg episode reward: [(0, '4.565')]
+[2023-04-27 22:29:08,829][26612] Saving new best policy, reward=4.565!
+[2023-04-27 22:29:09,550][26627] Updated weights for policy 0, policy_version 120 (0.0007)
+[2023-04-27 22:29:11,733][26627] Updated weights for policy 0, policy_version 130 (0.0009)
+[2023-04-27 22:29:13,474][26627] Updated weights for policy 0, policy_version 140 (0.0009)
+[2023-04-27 22:29:13,815][19320] Fps is (10 sec: 19251.2, 60 sec: 14540.8, 300 sec: 14540.8). Total num frames: 581632. Throughput: 0: 3246.8. Samples: 129872. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-04-27 22:29:13,816][19320] Avg episode reward: [(0, '4.521')]
+[2023-04-27 22:29:15,075][26627] Updated weights for policy 0, policy_version 150 (0.0006)
+[2023-04-27 22:29:16,757][26627] Updated weights for policy 0, policy_version 160 (0.0008)
+[2023-04-27 22:29:18,355][26627] Updated weights for policy 0, policy_version 170 (0.0008)
+[2023-04-27 22:29:18,815][19320] Fps is (10 sec: 22937.4, 60 sec: 15655.8, 300 sec: 15655.8). Total num frames: 704512. Throughput: 0: 3678.4. Samples: 165526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-04-27 22:29:18,816][19320] Avg episode reward: [(0, '4.458')]
+[2023-04-27 22:29:20,047][26627] Updated weights for policy 0, policy_version 180 (0.0008)
+[2023-04-27 22:29:21,736][26627] Updated weights for policy 0, policy_version 190 (0.0009)
+[2023-04-27 22:29:23,376][26627] Updated weights for policy 0, policy_version 200 (0.0009)
+[2023-04-27 22:29:23,815][19320] Fps is (10 sec: 24576.1, 60 sec: 16547.9, 300 sec: 16547.9). Total num frames: 827392. Throughput: 0: 4482.5. Samples: 202364. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-04-27 22:29:23,815][19320] Avg episode reward: [(0, '4.534')]
+[2023-04-27 22:29:25,033][26627] Updated weights for policy 0, policy_version 210 (0.0008)
+[2023-04-27 22:29:26,702][26627] Updated weights for policy 0, policy_version 220 (0.0007)
+[2023-04-27 22:29:28,383][26627] Updated weights for policy 0, policy_version 230 (0.0007)
+[2023-04-27 22:29:28,815][19320] Fps is (10 sec: 24576.2, 60 sec: 17277.7, 300 sec: 17277.7). Total num frames: 950272. Throughput: 0: 4842.8. Samples: 221000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:29:28,816][19320] Avg episode reward: [(0, '4.485')]
+[2023-04-27 22:29:30,029][26627] Updated weights for policy 0, policy_version 240 (0.0008)
+[2023-04-27 22:29:31,795][26627] Updated weights for policy 0, policy_version 250 (0.0008)
+[2023-04-27 22:29:33,815][19320] Fps is (10 sec: 23346.9, 60 sec: 17681.0, 300 sec: 17681.0). Total num frames: 1060864. Throughput: 0: 5146.0. Samples: 257374. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-04-27 22:29:33,816][19320] Avg episode reward: [(0, '4.669')]
+[2023-04-27 22:29:33,818][26612] Saving new best policy, reward=4.669!
+[2023-04-27 22:29:34,002][26627] Updated weights for policy 0, policy_version 260 (0.0008)
+[2023-04-27 22:29:36,837][26627] Updated weights for policy 0, policy_version 270 (0.0010)
+[2023-04-27 22:29:38,730][26627] Updated weights for policy 0, policy_version 280 (0.0007)
+[2023-04-27 22:29:38,815][19320] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 17644.3). Total num frames: 1146880. Throughput: 0: 5076.0. Samples: 282788. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-04-27 22:29:38,816][19320] Avg episode reward: [(0, '4.759')]
+[2023-04-27 22:29:38,821][26612] Saving new best policy, reward=4.759!
+[2023-04-27 22:29:41,483][26627] Updated weights for policy 0, policy_version 290 (0.0013)
+[2023-04-27 22:29:43,815][19320] Fps is (10 sec: 16384.2, 60 sec: 19660.8, 300 sec: 17495.8). Total num frames: 1224704. Throughput: 0: 5061.7. Samples: 294720. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-04-27 22:29:43,817][19320] Avg episode reward: [(0, '4.496')]
+[2023-04-27 22:29:43,996][26627] Updated weights for policy 0, policy_version 300 (0.0009)
+[2023-04-27 22:29:45,921][26627] Updated weights for policy 0, policy_version 310 (0.0009)
+[2023-04-27 22:29:47,745][26627] Updated weights for policy 0, policy_version 320 (0.0007)
+[2023-04-27 22:29:48,815][19320] Fps is (10 sec: 17203.2, 60 sec: 19660.8, 300 sec: 17585.5). Total num frames: 1318912. Throughput: 0: 5135.5. Samples: 323316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:29:48,816][19320] Avg episode reward: [(0, '4.280')]
+[2023-04-27 22:29:50,625][26627] Updated weights for policy 0, policy_version 330 (0.0007)
+[2023-04-27 22:29:52,896][26627] Updated weights for policy 0, policy_version 340 (0.0009)
+[2023-04-27 22:29:53,815][19320] Fps is (10 sec: 17612.0, 60 sec: 19524.1, 300 sec: 17510.3). Total num frames: 1400832. Throughput: 0: 5191.6. Samples: 348700. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-04-27 22:29:53,816][19320] Avg episode reward: [(0, '4.253')]
+[2023-04-27 22:29:56,313][26627] Updated weights for policy 0, policy_version 350 (0.0015)
+[2023-04-27 22:29:58,498][26627] Updated weights for policy 0, policy_version 360 (0.0007)
+[2023-04-27 22:29:58,815][19320] Fps is (10 sec: 15974.4, 60 sec: 19387.8, 300 sec: 17396.0). Total num frames: 1478656. Throughput: 0: 5059.1. Samples: 357532. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-04-27 22:29:58,816][19320] Avg episode reward: [(0, '4.385')]
+[2023-04-27 22:30:01,271][26627] Updated weights for policy 0, policy_version 370 (0.0012)
+[2023-04-27 22:30:03,815][19320] Fps is (10 sec: 14746.0, 60 sec: 19319.4, 300 sec: 17203.2). Total num frames: 1548288. Throughput: 0: 4768.2. Samples: 380094. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:30:03,816][19320] Avg episode reward: [(0, '4.464')]
+[2023-04-27 22:30:04,133][26627] Updated weights for policy 0, policy_version 380 (0.0012)
+[2023-04-27 22:30:06,244][26627] Updated weights for policy 0, policy_version 390 (0.0007)
+[2023-04-27 22:30:07,903][26627] Updated weights for policy 0, policy_version 400 (0.0008)
+[2023-04-27 22:30:08,815][19320] Fps is (10 sec: 18022.4, 60 sec: 19729.1, 300 sec: 17461.9). Total num frames: 1658880. Throughput: 0: 4616.3. Samples: 410098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:30:08,816][19320] Avg episode reward: [(0, '4.384')]
+[2023-04-27 22:30:09,574][26627] Updated weights for policy 0, policy_version 410 (0.0009)
+[2023-04-27 22:30:11,225][26627] Updated weights for policy 0, policy_version 420 (0.0008)
+[2023-04-27 22:30:12,922][26627] Updated weights for policy 0, policy_version 430 (0.0010)
+[2023-04-27 22:30:13,815][19320] Fps is (10 sec: 23347.7, 60 sec: 20002.1, 300 sec: 17817.6). Total num frames: 1781760. Throughput: 0: 4617.6. Samples: 428792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:30:13,816][19320] Avg episode reward: [(0, '4.328')]
+[2023-04-27 22:30:14,554][26627] Updated weights for policy 0, policy_version 440 (0.0007)
+[2023-04-27 22:30:16,206][26627] Updated weights for policy 0, policy_version 450 (0.0007)
+[2023-04-27 22:30:17,871][26627] Updated weights for policy 0, policy_version 460 (0.0009)
+[2023-04-27 22:30:18,815][19320] Fps is (10 sec: 24985.5, 60 sec: 20070.4, 300 sec: 18178.4). Total num frames: 1908736. Throughput: 0: 4631.5. Samples: 465790. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:30:18,816][19320] Avg episode reward: [(0, '4.316')]
+[2023-04-27 22:30:19,460][26627] Updated weights for policy 0, policy_version 470 (0.0008)
+[2023-04-27 22:30:21,046][26627] Updated weights for policy 0, policy_version 480 (0.0009)
+[2023-04-27 22:30:22,710][26627] Updated weights for policy 0, policy_version 490 (0.0009)
+[2023-04-27 22:30:23,815][19320] Fps is (10 sec: 24985.5, 60 sec: 20070.4, 300 sec: 18469.2). Total num frames: 2031616. Throughput: 0: 4906.8. Samples: 503596. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-04-27 22:30:23,816][19320] Avg episode reward: [(0, '4.388')]
+[2023-04-27 22:30:24,368][26627] Updated weights for policy 0, policy_version 500 (0.0007)
+[2023-04-27 22:30:25,982][26627] Updated weights for policy 0, policy_version 510 (0.0009)
+[2023-04-27 22:30:28,815][19320] Fps is (10 sec: 20889.7, 60 sec: 19456.0, 300 sec: 18414.2). Total num frames: 2117632. Throughput: 0: 5056.4. Samples: 522256. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-04-27 22:30:28,816][19320] Avg episode reward: [(0, '4.397')]
+[2023-04-27 22:30:28,820][26612] Saving /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/checkpoint_p0/checkpoint_000000517_2117632.pth...
+[2023-04-27 22:30:29,361][26627] Updated weights for policy 0, policy_version 520 (0.0015)
+[2023-04-27 22:30:31,575][26627] Updated weights for policy 0, policy_version 530 (0.0009)
+[2023-04-27 22:30:33,673][26627] Updated weights for policy 0, policy_version 540 (0.0007)
+[2023-04-27 22:30:33,815][19320] Fps is (10 sec: 18022.5, 60 sec: 19183.0, 300 sec: 18432.0). Total num frames: 2211840. Throughput: 0: 4930.8. Samples: 545200. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-04-27 22:30:33,816][19320] Avg episode reward: [(0, '4.420')]
+[2023-04-27 22:30:35,975][26627] Updated weights for policy 0, policy_version 550 (0.0008)
+[2023-04-27 22:30:38,045][26627] Updated weights for policy 0, policy_version 560 (0.0010)
+[2023-04-27 22:30:38,815][19320] Fps is (10 sec: 18841.5, 60 sec: 19319.5, 300 sec: 18448.4). Total num frames: 2306048. Throughput: 0: 4988.7. Samples: 573190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:30:38,816][19320] Avg episode reward: [(0, '4.549')]
+[2023-04-27 22:30:40,672][26627] Updated weights for policy 0, policy_version 570 (0.0011)
+[2023-04-27 22:30:43,150][26627] Updated weights for policy 0, policy_version 580 (0.0012)
+[2023-04-27 22:30:43,815][19320] Fps is (10 sec: 17612.8, 60 sec: 19387.7, 300 sec: 18369.0). Total num frames: 2387968. Throughput: 0: 5056.8. Samples: 585088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:30:43,816][19320] Avg episode reward: [(0, '4.520')]
+[2023-04-27 22:30:45,278][26627] Updated weights for policy 0, policy_version 590 (0.0007)
+[2023-04-27 22:30:47,790][26627] Updated weights for policy 0, policy_version 600 (0.0007)
+[2023-04-27 22:30:48,815][19320] Fps is (10 sec: 17203.2, 60 sec: 19319.5, 300 sec: 18356.1). Total num frames: 2478080. Throughput: 0: 5159.8. Samples: 612286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:30:48,816][19320] Avg episode reward: [(0, '4.326')]
+[2023-04-27 22:30:50,346][26627] Updated weights for policy 0, policy_version 610 (0.0008)
+[2023-04-27 22:30:53,815][19320] Fps is (10 sec: 14745.6, 60 sec: 18910.0, 300 sec: 18110.2). Total num frames: 2535424. Throughput: 0: 4977.5. Samples: 634084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:30:53,816][19320] Avg episode reward: [(0, '4.424')]
+[2023-04-27 22:30:53,893][26627] Updated weights for policy 0, policy_version 620 (0.0019)
+[2023-04-27 22:30:56,047][26627] Updated weights for policy 0, policy_version 630 (0.0007)
+[2023-04-27 22:30:58,480][26627] Updated weights for policy 0, policy_version 640 (0.0011)
+[2023-04-27 22:30:58,815][19320] Fps is (10 sec: 14745.6, 60 sec: 19114.7, 300 sec: 18107.1). Total num frames: 2625536. Throughput: 0: 4805.1. Samples: 645020. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-04-27 22:30:58,815][19320] Avg episode reward: [(0, '4.450')]
+[2023-04-27 22:31:00,719][26627] Updated weights for policy 0, policy_version 650 (0.0008)
+[2023-04-27 22:31:02,385][26627] Updated weights for policy 0, policy_version 660 (0.0008)
+[2023-04-27 22:31:03,815][19320] Fps is (10 sec: 20070.4, 60 sec: 19797.4, 300 sec: 18240.9). Total num frames: 2736128. Throughput: 0: 4617.8. Samples: 673592. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-04-27 22:31:03,816][19320] Avg episode reward: [(0, '4.602')]
+[2023-04-27 22:31:04,041][26627] Updated weights for policy 0, policy_version 670 (0.0010)
+[2023-04-27 22:31:05,642][26627] Updated weights for policy 0, policy_version 680 (0.0009)
+[2023-04-27 22:31:07,304][26627] Updated weights for policy 0, policy_version 690 (0.0007)
+[2023-04-27 22:31:08,815][19320] Fps is (10 sec: 23756.8, 60 sec: 20070.4, 300 sec: 18471.6). Total num frames: 2863104. Throughput: 0: 4611.2. Samples: 711102. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-04-27 22:31:08,816][19320] Avg episode reward: [(0, '4.465')]
+[2023-04-27 22:31:08,913][26627] Updated weights for policy 0, policy_version 700 (0.0008)
+[2023-04-27 22:31:10,614][26627] Updated weights for policy 0, policy_version 710 (0.0006)
+[2023-04-27 22:31:12,270][26627] Updated weights for policy 0, policy_version 720 (0.0007)
+[2023-04-27 22:31:13,815][19320] Fps is (10 sec: 24985.6, 60 sec: 20070.4, 300 sec: 18662.4). Total num frames: 2985984. Throughput: 0: 4608.2. Samples: 729626. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:31:13,816][19320] Avg episode reward: [(0, '4.396')]
+[2023-04-27 22:31:13,869][26627] Updated weights for policy 0, policy_version 730 (0.0007)
+[2023-04-27 22:31:15,506][26627] Updated weights for policy 0, policy_version 740 (0.0009)
+[2023-04-27 22:31:17,160][26627] Updated weights for policy 0, policy_version 750 (0.0008)
+[2023-04-27 22:31:18,815][19320] Fps is (10 sec: 24576.0, 60 sec: 20002.1, 300 sec: 18841.6). Total num frames: 3108864. Throughput: 0: 4932.6. Samples: 767168. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:31:18,816][19320] Avg episode reward: [(0, '4.364')]
+[2023-04-27 22:31:18,848][26627] Updated weights for policy 0, policy_version 760 (0.0009)
+[2023-04-27 22:31:21,623][26627] Updated weights for policy 0, policy_version 770 (0.0013)
+[2023-04-27 22:31:23,815][19320] Fps is (10 sec: 20070.4, 60 sec: 19251.2, 300 sec: 18745.2). Total num frames: 3186688. Throughput: 0: 4907.6. Samples: 794032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-04-27 22:31:23,816][19320] Avg episode reward: [(0, '4.513')]
+[2023-04-27 22:31:24,158][26627] Updated weights for policy 0, policy_version 780 (0.0013)
+[2023-04-27 22:31:26,913][26627] Updated weights for policy 0, policy_version 790 (0.0012)
+[2023-04-27 22:31:28,815][19320] Fps is (10 sec: 14336.0, 60 sec: 18909.9, 300 sec: 18584.1). Total num frames: 3252224. Throughput: 0: 4932.8. Samples: 807066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:31:28,815][19320] Avg episode reward: [(0, '4.367')]
+[2023-04-27 22:31:30,689][26627] Updated weights for policy 0, policy_version 800 (0.0012)
+[2023-04-27 22:31:33,035][26627] Updated weights for policy 0, policy_version 810 (0.0011)
+[2023-04-27 22:31:33,815][19320] Fps is (10 sec: 14745.6, 60 sec: 18705.1, 300 sec: 18523.0). Total num frames: 3334144. Throughput: 0: 4712.5. Samples: 824348. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:31:33,816][19320] Avg episode reward: [(0, '4.320')]
+[2023-04-27 22:31:35,061][26627] Updated weights for policy 0, policy_version 820 (0.0007)
+[2023-04-27 22:31:37,474][26627] Updated weights for policy 0, policy_version 830 (0.0010)
+[2023-04-27 22:31:38,815][19320] Fps is (10 sec: 16793.5, 60 sec: 18568.5, 300 sec: 18487.4). Total num frames: 3420160. Throughput: 0: 4863.2. Samples: 852926. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-04-27 22:31:38,816][19320] Avg episode reward: [(0, '4.490')]
+[2023-04-27 22:31:40,044][26627] Updated weights for policy 0, policy_version 840 (0.0007)
+[2023-04-27 22:31:42,664][26627] Updated weights for policy 0, policy_version 850 (0.0014)
+[2023-04-27 22:31:43,815][19320] Fps is (10 sec: 15974.4, 60 sec: 18432.0, 300 sec: 18388.9). Total num frames: 3493888. Throughput: 0: 4869.0. Samples: 864126. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-04-27 22:31:43,816][19320] Avg episode reward: [(0, '4.454')]
+[2023-04-27 22:31:45,339][26627] Updated weights for policy 0, policy_version 860 (0.0014)
+[2023-04-27 22:31:47,414][26627] Updated weights for policy 0, policy_version 870 (0.0015)
+[2023-04-27 22:31:48,815][19320] Fps is (10 sec: 16793.2, 60 sec: 18500.2, 300 sec: 18400.5). Total num frames: 3588096. Throughput: 0: 4780.7. Samples: 888726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-04-27 22:31:48,816][19320] Avg episode reward: [(0, '4.718')]
+[2023-04-27 22:31:49,524][26627] Updated weights for policy 0, policy_version 880 (0.0008)
+[2023-04-27 22:31:51,616][26627] Updated weights for policy 0, policy_version 890 (0.0012)
+[2023-04-27 22:31:53,815][19320] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 18411.5). Total num frames: 3682304. Throughput: 0: 4563.8. Samples: 916472. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:31:53,816][19320] Avg episode reward: [(0, '4.287')]
+[2023-04-27 22:31:53,847][26627] Updated weights for policy 0, policy_version 900 (0.0011)
+[2023-04-27 22:31:55,513][26627] Updated weights for policy 0, policy_version 910 (0.0009)
+[2023-04-27 22:31:57,111][26627] Updated weights for policy 0, policy_version 920 (0.0007)
+[2023-04-27 22:31:58,754][26627] Updated weights for policy 0, policy_version 930 (0.0007)
+[2023-04-27 22:31:58,815][19320] Fps is (10 sec: 22118.6, 60 sec: 19729.0, 300 sec: 18581.8). Total num frames: 3809280. Throughput: 0: 4564.9. Samples: 935046. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-04-27 22:31:58,816][19320] Avg episode reward: [(0, '4.318')]
+[2023-04-27 22:32:00,439][26627] Updated weights for policy 0, policy_version 940 (0.0007)
+[2023-04-27 22:32:02,146][26627] Updated weights for policy 0, policy_version 950 (0.0007)
+[2023-04-27 22:32:03,815][19320] Fps is (10 sec: 24576.2, 60 sec: 19865.6, 300 sec: 18705.1). Total num frames: 3928064. Throughput: 0: 4548.2. Samples: 971838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-04-27 22:32:03,816][19320] Avg episode reward: [(0, '4.347')]
+[2023-04-27 22:32:03,837][26627] Updated weights for policy 0, policy_version 960 (0.0008)
+[2023-04-27 22:32:05,497][26627] Updated weights for policy 0, policy_version 970 (0.0008)
+[2023-04-27 22:32:06,763][26612] Stopping Batcher_0...
+[2023-04-27 22:32:06,763][26612] Saving /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-04-27 22:32:06,763][26612] Loop batcher_evt_loop terminating...
+[2023-04-27 22:32:06,763][19320] Component Batcher_0 stopped!
+[2023-04-27 22:32:06,764][19320] Component RolloutWorker_w1 process died already! Don't wait for it.
+[2023-04-27 22:32:06,768][26638] Stopping RolloutWorker_w7...
+[2023-04-27 22:32:06,769][26638] Loop rollout_proc7_evt_loop terminating...
+[2023-04-27 22:32:06,769][26630] Stopping RolloutWorker_w3...
+[2023-04-27 22:32:06,769][26631] Stopping RolloutWorker_w4...
+[2023-04-27 22:32:06,769][26630] Loop rollout_proc3_evt_loop terminating...
+[2023-04-27 22:32:06,769][26631] Loop rollout_proc4_evt_loop terminating...
+[2023-04-27 22:32:06,769][26629] Stopping RolloutWorker_w2...
+[2023-04-27 22:32:06,768][19320] Component RolloutWorker_w7 stopped!
+[2023-04-27 22:32:06,769][26629] Loop rollout_proc2_evt_loop terminating...
+[2023-04-27 22:32:06,770][19320] Component RolloutWorker_w3 stopped!
+[2023-04-27 22:32:06,770][26632] Stopping RolloutWorker_w5...
+[2023-04-27 22:32:06,771][26632] Loop rollout_proc5_evt_loop terminating...
+[2023-04-27 22:32:06,771][19320] Component RolloutWorker_w4 stopped!
+[2023-04-27 22:32:06,772][26657] Stopping RolloutWorker_w6...
+[2023-04-27 22:32:06,773][26657] Loop rollout_proc6_evt_loop terminating...
+[2023-04-27 22:32:06,773][19320] Component RolloutWorker_w2 stopped!
+[2023-04-27 22:32:06,774][19320] Component RolloutWorker_w5 stopped!
+[2023-04-27 22:32:06,775][19320] Component RolloutWorker_w6 stopped!
+[2023-04-27 22:32:06,775][26627] Weights refcount: 2 0
+[2023-04-27 22:32:06,777][26627] Stopping InferenceWorker_p0-w0...
+[2023-04-27 22:32:06,777][26627] Loop inference_proc0-0_evt_loop terminating...
+[2023-04-27 22:32:06,777][19320] Component InferenceWorker_p0-w0 stopped!
+[2023-04-27 22:32:06,786][26626] Stopping RolloutWorker_w0...
+[2023-04-27 22:32:06,787][26626] Loop rollout_proc0_evt_loop terminating...
+[2023-04-27 22:32:06,786][19320] Component RolloutWorker_w0 stopped!
+[2023-04-27 22:32:06,811][26612] Saving /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-04-27 22:32:06,858][26612] Stopping LearnerWorker_p0...
+[2023-04-27 22:32:06,859][26612] Loop learner_proc0_evt_loop terminating...
+[2023-04-27 22:32:06,859][19320] Component LearnerWorker_p0 stopped!
+[2023-04-27 22:32:06,860][19320] Waiting for process learner_proc0 to stop...
+[2023-04-27 22:32:07,560][19320] Waiting for process inference_proc0-0 to join...
+[2023-04-27 22:32:07,561][19320] Waiting for process rollout_proc0 to join...
+[2023-04-27 22:32:07,562][19320] Waiting for process rollout_proc1 to join...
+[2023-04-27 22:32:07,563][19320] Waiting for process rollout_proc2 to join...
+[2023-04-27 22:32:07,564][19320] Waiting for process rollout_proc3 to join...
+[2023-04-27 22:32:07,564][19320] Waiting for process rollout_proc4 to join...
+[2023-04-27 22:32:07,565][19320] Waiting for process rollout_proc5 to join...
+[2023-04-27 22:32:07,566][19320] Waiting for process rollout_proc6 to join...
+[2023-04-27 22:32:07,567][19320] Waiting for process rollout_proc7 to join...
+[2023-04-27 22:32:07,567][19320] Batcher 0 profile tree view:
+batching: 12.7812, releasing_batches: 0.0195
+[2023-04-27 22:32:07,568][19320] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 2.8370
+update_model: 2.8123
+  weight_update: 0.0007
+one_step: 0.0023
+  handle_policy_step: 195.8112
+    deserialize: 5.6395, stack: 0.7269, obs_to_device_normalize: 44.5135, forward: 68.6296, send_messages: 17.9614
+    prepare_outputs: 52.0115
+      to_cpu: 45.1667
+[2023-04-27 22:32:07,569][19320] Learner 0 profile tree view:
+misc: 0.0037, prepare_batch: 9.4485
+train: 22.5017
+  epoch_init: 0.0033, minibatch_init: 0.0045, losses_postprocess: 0.4800, kl_divergence: 0.4893, after_optimizer: 6.8805
+  calculate_losses: 7.1964
+    losses_init: 0.0020, forward_head: 0.5407, bptt_initial: 3.3368, tail: 0.4113, advantages_returns: 0.1193, losses: 1.7274
+    bptt: 0.9502
+      bptt_forward_core: 0.9150
+  update: 7.1922
+    clip: 0.8865
+[2023-04-27 22:32:07,569][19320] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0991, enqueue_policy_requests: 5.1038, env_step: 94.9605, overhead: 6.8366, complete_rollouts: 0.2024
+save_policy_outputs: 6.2491
+  split_output_tensors: 2.9626
+[2023-04-27 22:32:07,570][19320] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0969, enqueue_policy_requests: 5.1019, env_step: 95.1988, overhead: 6.8454, complete_rollouts: 0.2055
+save_policy_outputs: 6.4640
+  split_output_tensors: 3.0653
+[2023-04-27 22:32:07,571][19320] Loop Runner_EvtLoop terminating...
+[2023-04-27 22:32:07,572][19320] Runner profile tree view:
+main_loop: 217.2086
+[2023-04-27 22:32:07,573][19320] Collected {0: 4005888}, FPS: 18442.6
+[2023-04-27 22:33:30,876][19320] Loading existing experiment configuration from /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/config.json
+[2023-04-27 22:33:30,877][19320] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-04-27 22:33:30,878][19320] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-04-27 22:33:30,878][19320] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-04-27 22:33:30,879][19320] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-04-27 22:33:30,879][19320] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-04-27 22:33:30,880][19320] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2023-04-27 22:33:30,881][19320] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-04-27 22:33:30,882][19320] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2023-04-27 22:33:30,882][19320] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2023-04-27 22:33:30,883][19320] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-04-27 22:33:30,883][19320] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-04-27 22:33:30,884][19320] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-04-27 22:33:30,885][19320] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-04-27 22:33:30,885][19320] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-04-27 22:33:30,891][19320] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-04-27 22:33:30,892][19320] RunningMeanStd input shape: (3, 72, 128)
+[2023-04-27 22:33:30,893][19320] RunningMeanStd input shape: (1,)
+[2023-04-27 22:33:30,904][19320] ConvEncoder: input_channels=3
+[2023-04-27 22:33:30,994][19320] Conv encoder output size: 512
+[2023-04-27 22:33:30,995][19320] Policy head output size: 512
+[2023-04-27 22:33:32,427][19320] Loading state from checkpoint /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-04-27 22:33:33,708][19320] Num frames 100...
+[2023-04-27 22:33:33,796][19320] Num frames 200...
+[2023-04-27 22:33:33,876][19320] Num frames 300...
+[2023-04-27 22:33:33,996][19320] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2023-04-27 22:33:33,997][19320] Avg episode reward: 3.840, avg true_objective: 3.840
+[2023-04-27 22:33:34,014][19320] Num frames 400...
+[2023-04-27 22:33:34,096][19320] Num frames 500...
+[2023-04-27 22:33:34,173][19320] Num frames 600...
+[2023-04-27 22:33:34,251][19320] Num frames 700...
+[2023-04-27 22:33:34,358][19320] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2023-04-27 22:33:34,359][19320] Avg episode reward: 3.840, avg true_objective: 3.840
+[2023-04-27 22:33:34,389][19320] Num frames 800...
+[2023-04-27 22:33:34,468][19320] Num frames 900...
+[2023-04-27 22:33:34,542][19320] Num frames 1000...
+[2023-04-27 22:33:34,617][19320] Num frames 1100...
+[2023-04-27 22:33:34,736][19320] Avg episode rewards: #0: 4.280, true rewards: #0: 3.947
+[2023-04-27 22:33:34,737][19320] Avg episode reward: 4.280, avg true_objective: 3.947
+[2023-04-27 22:33:34,752][19320] Num frames 1200...
+[2023-04-27 22:33:34,835][19320] Num frames 1300...
+[2023-04-27 22:33:34,915][19320] Num frames 1400...
+[2023-04-27 22:33:34,997][19320] Num frames 1500...
+[2023-04-27 22:33:35,092][19320] Num frames 1600...
+[2023-04-27 22:33:35,144][19320] Avg episode rewards: #0: 4.500, true rewards: #0: 4.000
+[2023-04-27 22:33:35,145][19320] Avg episode reward: 4.500, avg true_objective: 4.000
+[2023-04-27 22:33:35,229][19320] Num frames 1700...
+[2023-04-27 22:33:35,311][19320] Num frames 1800...
+[2023-04-27 22:33:35,391][19320] Num frames 1900...
+[2023-04-27 22:33:35,474][19320] Num frames 2000...
+[2023-04-27 22:33:35,569][19320] Avg episode rewards: #0: 4.696, true rewards: #0: 4.096
+[2023-04-27 22:33:35,570][19320] Avg episode reward: 4.696, avg true_objective: 4.096
+[2023-04-27 22:33:35,617][19320] Num frames 2100...
+[2023-04-27 22:33:35,698][19320] Num frames 2200...
+[2023-04-27 22:33:35,772][19320] Num frames 2300...
+[2023-04-27 22:33:35,849][19320] Num frames 2400...
+[2023-04-27 22:33:35,932][19320] Avg episode rewards: #0: 4.553, true rewards: #0: 4.053
+[2023-04-27 22:33:35,933][19320] Avg episode reward: 4.553, avg true_objective: 4.053
+[2023-04-27 22:33:35,989][19320] Num frames 2500...
+[2023-04-27 22:33:36,070][19320] Num frames 2600...
+[2023-04-27 22:33:36,157][19320] Num frames 2700...
+[2023-04-27 22:33:36,236][19320] Num frames 2800...
+[2023-04-27 22:33:36,319][19320] Num frames 2900...
+[2023-04-27 22:33:36,396][19320] Num frames 3000...
+[2023-04-27 22:33:36,479][19320] Avg episode rewards: #0: 5.200, true rewards: #0: 4.343
+[2023-04-27 22:33:36,480][19320] Avg episode reward: 5.200, avg true_objective: 4.343
+[2023-04-27 22:33:36,531][19320] Num frames 3100...
+[2023-04-27 22:33:36,612][19320] Num frames 3200...
+[2023-04-27 22:33:36,740][19320] Avg episode rewards: #0: 4.870, true rewards: #0: 4.120
+[2023-04-27 22:33:36,741][19320] Avg episode reward: 4.870, avg true_objective: 4.120
+[2023-04-27 22:33:36,747][19320] Num frames 3300...
+[2023-04-27 22:33:36,839][19320] Num frames 3400...
+[2023-04-27 22:33:36,925][19320] Num frames 3500...
+[2023-04-27 22:33:36,998][19320] Num frames 3600...
+[2023-04-27 22:33:37,114][19320] Avg episode rewards: #0: 4.756, true rewards: #0: 4.089
+[2023-04-27 22:33:37,115][19320] Avg episode reward: 4.756, avg true_objective: 4.089
+[2023-04-27 22:33:37,136][19320] Num frames 3700...
+[2023-04-27 22:33:37,237][19320] Num frames 3800...
+[2023-04-27 22:33:37,323][19320] Num frames 3900...
+[2023-04-27 22:33:37,407][19320] Num frames 4000...
+[2023-04-27 22:33:37,512][19320] Avg episode rewards: #0: 4.664, true rewards: #0: 4.064
+[2023-04-27 22:33:37,513][19320] Avg episode reward: 4.664, avg true_objective: 4.064
+[2023-04-27 22:33:41,947][19320] Replay video saved to /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/replay.mp4!
+[2023-04-27 22:36:21,719][19320] Loading existing experiment configuration from /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/config.json
+[2023-04-27 22:36:21,720][19320] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-04-27 22:36:21,721][19320] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-04-27 22:36:21,722][19320] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-04-27 22:36:21,722][19320] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-04-27 22:36:21,723][19320] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-04-27 22:36:21,724][19320] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-04-27 22:36:21,724][19320] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-04-27 22:36:21,725][19320] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-04-27 22:36:21,726][19320] Adding new argument 'hf_repository'='ItchyB/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-04-27 22:36:21,726][19320] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-04-27 22:36:21,726][19320] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-04-27 22:36:21,727][19320] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-04-27 22:36:21,728][19320] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-04-27 22:36:21,729][19320] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-04-27 22:36:21,732][19320] RunningMeanStd input shape: (3, 72, 128)
+[2023-04-27 22:36:21,733][19320] RunningMeanStd input shape: (1,)
+[2023-04-27 22:36:21,740][19320] ConvEncoder: input_channels=3
+[2023-04-27 22:36:21,763][19320] Conv encoder output size: 512
+[2023-04-27 22:36:21,764][19320] Policy head output size: 512
+[2023-04-27 22:36:21,791][19320] Loading state from checkpoint /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-04-27 22:36:22,219][19320] Num frames 100...
+[2023-04-27 22:36:22,339][19320] Num frames 200...
+[2023-04-27 22:36:22,445][19320] Num frames 300...
+[2023-04-27 22:36:22,572][19320] Num frames 400...
+[2023-04-27 22:36:22,684][19320] Num frames 500...
+[2023-04-27 22:36:22,754][19320] Avg episode rewards: #0: 7.120, true rewards: #0: 5.120
+[2023-04-27 22:36:22,755][19320] Avg episode reward: 7.120, avg true_objective: 5.120
+[2023-04-27 22:36:22,855][19320] Num frames 600...
+[2023-04-27 22:36:22,974][19320] Num frames 700...
+[2023-04-27 22:36:23,101][19320] Num frames 800...
+[2023-04-27 22:36:23,257][19320] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2023-04-27 22:36:23,258][19320] Avg episode reward: 5.480, avg true_objective: 4.480
+[2023-04-27 22:36:23,263][19320] Num frames 900...
+[2023-04-27 22:36:23,371][19320] Num frames 1000...
+[2023-04-27 22:36:23,473][19320] Num frames 1100...
+[2023-04-27 22:36:23,587][19320] Num frames 1200...
+[2023-04-27 22:36:23,727][19320] Avg episode rewards: #0: 4.933, true rewards: #0: 4.267
+[2023-04-27 22:36:23,728][19320] Avg episode reward: 4.933, avg true_objective: 4.267
+[2023-04-27 22:36:23,755][19320] Num frames 1300...
+[2023-04-27 22:36:23,873][19320] Num frames 1400...
+[2023-04-27 22:36:23,991][19320] Num frames 1500...
+[2023-04-27 22:36:24,080][19320] Avg episode rewards: #0: 4.340, true rewards: #0: 3.840
+[2023-04-27 22:36:24,081][19320] Avg episode reward: 4.340, avg true_objective: 3.840
+[2023-04-27 22:36:24,143][19320] Num frames 1600...
+[2023-04-27 22:36:24,240][19320] Num frames 1700...
+[2023-04-27 22:36:24,341][19320] Num frames 1800...
+[2023-04-27 22:36:24,432][19320] Num frames 1900...
+[2023-04-27 22:36:24,562][19320] Avg episode rewards: #0: 4.768, true rewards: #0: 3.968
+[2023-04-27 22:36:24,563][19320] Avg episode reward: 4.768, avg true_objective: 3.968
+[2023-04-27 22:36:24,577][19320] Num frames 2000...
+[2023-04-27 22:36:24,676][19320] Num frames 2100...
+[2023-04-27 22:36:24,778][19320] Num frames 2200...
+[2023-04-27 22:36:24,881][19320] Num frames 2300...
+[2023-04-27 22:36:25,004][19320] Avg episode rewards: #0: 4.613, true rewards: #0: 3.947
+[2023-04-27 22:36:25,005][19320] Avg episode reward: 4.613, avg true_objective: 3.947
+[2023-04-27 22:36:25,036][19320] Num frames 2400...
+[2023-04-27 22:36:25,138][19320] Num frames 2500...
+[2023-04-27 22:36:25,237][19320] Num frames 2600...
+[2023-04-27 22:36:25,340][19320] Num frames 2700...
+[2023-04-27 22:36:25,446][19320] Avg episode rewards: #0: 4.503, true rewards: #0: 3.931
+[2023-04-27 22:36:25,447][19320] Avg episode reward: 4.503, avg true_objective: 3.931
+[2023-04-27 22:36:25,498][19320] Num frames 2800...
+[2023-04-27 22:36:25,598][19320] Num frames 2900...
+[2023-04-27 22:36:25,701][19320] Num frames 3000...
+[2023-04-27 22:36:25,800][19320] Num frames 3100...
+[2023-04-27 22:36:25,888][19320] Avg episode rewards: #0: 4.420, true rewards: #0: 3.920
+[2023-04-27 22:36:25,889][19320] Avg episode reward: 4.420, avg true_objective: 3.920
+[2023-04-27 22:36:25,969][19320] Num frames 3200...
+[2023-04-27 22:36:26,076][19320] Num frames 3300...
+[2023-04-27 22:36:26,181][19320] Num frames 3400...
+[2023-04-27 22:36:26,281][19320] Num frames 3500...
+[2023-04-27 22:36:26,354][19320] Avg episode rewards: #0: 4.356, true rewards: #0: 3.911
+[2023-04-27 22:36:26,355][19320] Avg episode reward: 4.356, avg true_objective: 3.911
+[2023-04-27 22:36:26,446][19320] Num frames 3600...
+[2023-04-27 22:36:26,560][19320] Num frames 3700...
+[2023-04-27 22:36:26,670][19320] Num frames 3800...
+[2023-04-27 22:36:26,784][19320] Num frames 3900...
+[2023-04-27 22:36:26,842][19320] Avg episode rewards: #0: 4.304, true rewards: #0: 3.904
+[2023-04-27 22:36:26,842][19320] Avg episode reward: 4.304, avg true_objective: 3.904
+[2023-04-27 22:36:30,880][19320] Replay video saved to /home/byron/projects/rl-learning-course/unit-08/train_dir/default_experiment/replay.mp4!