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.1727688659.1f3481d5f704

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4f5f778b161cc3480dc4a5454ce4d828c35a32f238b439b013accaf1a8cbda
+size 219722

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: 10.24 +/- 5.06
+      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 apple9855/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_000000961_3936256_reward_23.986.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d640b56100b4ec11a063f8b5cffb3d0ce075bbada724589451191e3991707b1
+size 34929051

checkpoint_p0/checkpoint_000000451_1847296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424b41d2dd7662670080d208dba52d378905a04b860410059436c2dbd581f70d
+size 34929477

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c61b3bb87cc7742118a421bbcd32fef61dcbde454f55c4829f83994ff59e3df
+size 34929541

config.json

@@ -0,0 +1,142 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "doom_health_gathering_supreme",
+  "experiment": "default_experiment",
+  "train_dir": "/content/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:cd8333dca52856b8a7465bf2885c60670779a160baa995a4eeca301f7b277eea
+size 19629916

sf_log.txt

@@ -0,0 +1,843 @@
+[2024-09-30 09:31:04,218][05258] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-09-30 09:31:04,220][05258] Rollout worker 0 uses device cpu
+[2024-09-30 09:31:04,221][05258] Rollout worker 1 uses device cpu
+[2024-09-30 09:31:04,222][05258] Rollout worker 2 uses device cpu
+[2024-09-30 09:31:04,225][05258] Rollout worker 3 uses device cpu
+[2024-09-30 09:31:04,226][05258] Rollout worker 4 uses device cpu
+[2024-09-30 09:31:04,228][05258] Rollout worker 5 uses device cpu
+[2024-09-30 09:31:04,229][05258] Rollout worker 6 uses device cpu
+[2024-09-30 09:31:04,231][05258] Rollout worker 7 uses device cpu
+[2024-09-30 09:31:04,357][05258] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-30 09:31:04,359][05258] InferenceWorker_p0-w0: min num requests: 2
+[2024-09-30 09:31:04,395][05258] Starting all processes...
+[2024-09-30 09:31:04,396][05258] Starting process learner_proc0
+[2024-09-30 09:31:05,086][05258] Starting all processes...
+[2024-09-30 09:31:05,092][05258] Starting process inference_proc0-0
+[2024-09-30 09:31:05,093][05258] Starting process rollout_proc0
+[2024-09-30 09:31:05,094][05258] Starting process rollout_proc1
+[2024-09-30 09:31:05,094][05258] Starting process rollout_proc2
+[2024-09-30 09:31:05,096][05258] Starting process rollout_proc3
+[2024-09-30 09:31:05,096][05258] Starting process rollout_proc4
+[2024-09-30 09:31:05,101][05258] Starting process rollout_proc5
+[2024-09-30 09:31:05,104][05258] Starting process rollout_proc6
+[2024-09-30 09:31:05,107][05258] Starting process rollout_proc7
+[2024-09-30 09:31:07,471][07338] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-30 09:31:07,824][07346] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-30 09:31:07,936][07339] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-30 09:31:08,014][07347] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-30 09:31:08,043][07335] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-30 09:31:08,043][07335] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-09-30 09:31:08,058][07335] Num visible devices: 1
+[2024-09-30 09:31:08,100][07321] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-30 09:31:08,100][07321] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-09-30 09:31:08,115][07321] Num visible devices: 1
+[2024-09-30 09:31:08,118][07336] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-30 09:31:08,142][07321] Starting seed is not provided
+[2024-09-30 09:31:08,142][07321] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-30 09:31:08,142][07321] Initializing actor-critic model on device cuda:0
+[2024-09-30 09:31:08,142][07321] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-30 09:31:08,145][07321] RunningMeanStd input shape: (1,)
+[2024-09-30 09:31:08,158][07321] ConvEncoder: input_channels=3
+[2024-09-30 09:31:08,210][07337] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-30 09:31:08,237][07340] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-30 09:31:08,258][07341] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-30 09:31:08,428][07321] Conv encoder output size: 512
+[2024-09-30 09:31:08,429][07321] Policy head output size: 512
+[2024-09-30 09:31:08,491][07321] Created Actor Critic model with architecture:
+[2024-09-30 09:31:08,491][07321] 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)
+  )
+)
+[2024-09-30 09:31:08,778][07321] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-09-30 09:31:09,470][07321] No checkpoints found
+[2024-09-30 09:31:09,470][07321] Did not load from checkpoint, starting from scratch!
+[2024-09-30 09:31:09,470][07321] Initialized policy 0 weights for model version 0
+[2024-09-30 09:31:09,474][07321] LearnerWorker_p0 finished initialization!
+[2024-09-30 09:31:09,475][07321] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-30 09:31:09,555][07335] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-30 09:31:09,556][07335] RunningMeanStd input shape: (1,)
+[2024-09-30 09:31:09,568][07335] ConvEncoder: input_channels=3
+[2024-09-30 09:31:09,674][07335] Conv encoder output size: 512
+[2024-09-30 09:31:09,674][07335] Policy head output size: 512
+[2024-09-30 09:31:09,726][05258] Inference worker 0-0 is ready!
+[2024-09-30 09:31:09,727][05258] All inference workers are ready! Signal rollout workers to start!
+[2024-09-30 09:31:09,759][07338] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:31:09,760][07336] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:31:09,779][07341] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:31:09,779][07346] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:31:09,780][07339] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:31:09,780][07347] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:31:09,781][07340] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:31:09,781][07337] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:31:10,081][07337] Decorrelating experience for 0 frames...
+[2024-09-30 09:31:10,081][07346] Decorrelating experience for 0 frames...
+[2024-09-30 09:31:10,081][07338] Decorrelating experience for 0 frames...
+[2024-09-30 09:31:10,081][07341] Decorrelating experience for 0 frames...
+[2024-09-30 09:31:10,091][07340] Decorrelating experience for 0 frames...
+[2024-09-30 09:31:10,127][07347] Decorrelating experience for 0 frames...
+[2024-09-30 09:31:10,322][07341] Decorrelating experience for 32 frames...
+[2024-09-30 09:31:10,324][07337] Decorrelating experience for 32 frames...
+[2024-09-30 09:31:10,331][07340] Decorrelating experience for 32 frames...
+[2024-09-30 09:31:10,368][07346] Decorrelating experience for 32 frames...
+[2024-09-30 09:31:10,576][07339] Decorrelating experience for 0 frames...
+[2024-09-30 09:31:10,616][07347] Decorrelating experience for 32 frames...
+[2024-09-30 09:31:10,626][07338] Decorrelating experience for 32 frames...
+[2024-09-30 09:31:10,646][07340] Decorrelating experience for 64 frames...
+[2024-09-30 09:31:10,687][07337] Decorrelating experience for 64 frames...
+[2024-09-30 09:31:10,690][07341] Decorrelating experience for 64 frames...
+[2024-09-30 09:31:10,905][07346] Decorrelating experience for 64 frames...
+[2024-09-30 09:31:10,938][07347] Decorrelating experience for 64 frames...
+[2024-09-30 09:31:10,946][07340] Decorrelating experience for 96 frames...
+[2024-09-30 09:31:10,977][07339] Decorrelating experience for 32 frames...
+[2024-09-30 09:31:10,980][07337] Decorrelating experience for 96 frames...
+[2024-09-30 09:31:11,000][07341] Decorrelating experience for 96 frames...
+[2024-09-30 09:31:11,202][07338] Decorrelating experience for 64 frames...
+[2024-09-30 09:31:11,224][07346] Decorrelating experience for 96 frames...
+[2024-09-30 09:31:11,234][07347] Decorrelating experience for 96 frames...
+[2024-09-30 09:31:11,348][07339] Decorrelating experience for 64 frames...
+[2024-09-30 09:31:11,484][07338] Decorrelating experience for 96 frames...
+[2024-09-30 09:31:11,613][07339] Decorrelating experience for 96 frames...
+[2024-09-30 09:31:13,550][07321] Signal inference workers to stop experience collection...
+[2024-09-30 09:31:13,555][07335] InferenceWorker_p0-w0: stopping experience collection
+[2024-09-30 09:31:14,183][05258] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 60. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-09-30 09:31:14,184][05258] Avg episode reward: [(0, '2.803')]
+[2024-09-30 09:31:16,133][07321] Signal inference workers to resume experience collection...
+[2024-09-30 09:31:16,134][07335] InferenceWorker_p0-w0: resuming experience collection
+[2024-09-30 09:31:18,214][07335] Updated weights for policy 0, policy_version 10 (0.0149)
+[2024-09-30 09:31:19,183][05258] Fps is (10 sec: 11468.6, 60 sec: 11468.6, 300 sec: 11468.6). Total num frames: 57344. Throughput: 0: 2618.8. Samples: 13154. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-30 09:31:19,184][05258] Avg episode reward: [(0, '4.330')]
+[2024-09-30 09:31:20,475][07335] Updated weights for policy 0, policy_version 20 (0.0012)
+[2024-09-30 09:31:22,749][07335] Updated weights for policy 0, policy_version 30 (0.0013)
+[2024-09-30 09:31:24,183][05258] Fps is (10 sec: 14745.6, 60 sec: 14745.6, 300 sec: 14745.6). Total num frames: 147456. Throughput: 0: 2662.0. Samples: 26680. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-30 09:31:24,185][05258] Avg episode reward: [(0, '4.472')]
+[2024-09-30 09:31:24,187][07321] Saving new best policy, reward=4.472!
+[2024-09-30 09:31:24,349][05258] Heartbeat connected on Batcher_0
+[2024-09-30 09:31:24,353][05258] Heartbeat connected on LearnerWorker_p0
+[2024-09-30 09:31:24,362][05258] Heartbeat connected on InferenceWorker_p0-w0
+[2024-09-30 09:31:24,371][05258] Heartbeat connected on RolloutWorker_w1
+[2024-09-30 09:31:24,376][05258] Heartbeat connected on RolloutWorker_w2
+[2024-09-30 09:31:24,379][05258] Heartbeat connected on RolloutWorker_w3
+[2024-09-30 09:31:24,385][05258] Heartbeat connected on RolloutWorker_w4
+[2024-09-30 09:31:24,390][05258] Heartbeat connected on RolloutWorker_w6
+[2024-09-30 09:31:24,395][05258] Heartbeat connected on RolloutWorker_w5
+[2024-09-30 09:31:24,396][05258] Heartbeat connected on RolloutWorker_w7
+[2024-09-30 09:31:25,032][07335] Updated weights for policy 0, policy_version 40 (0.0013)
+[2024-09-30 09:31:27,284][07335] Updated weights for policy 0, policy_version 50 (0.0013)
+[2024-09-30 09:31:29,183][05258] Fps is (10 sec: 17612.9, 60 sec: 15564.7, 300 sec: 15564.7). Total num frames: 233472. Throughput: 0: 3578.9. Samples: 53744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-30 09:31:29,185][05258] Avg episode reward: [(0, '4.525')]
+[2024-09-30 09:31:29,202][07321] Saving new best policy, reward=4.525!
+[2024-09-30 09:31:29,673][07335] Updated weights for policy 0, policy_version 60 (0.0013)
+[2024-09-30 09:31:31,969][07335] Updated weights for policy 0, policy_version 70 (0.0013)
+[2024-09-30 09:31:34,183][05258] Fps is (10 sec: 17612.8, 60 sec: 16179.2, 300 sec: 16179.2). Total num frames: 323584. Throughput: 0: 4011.0. Samples: 80280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-30 09:31:34,184][05258] Avg episode reward: [(0, '4.427')]
+[2024-09-30 09:31:34,219][07335] Updated weights for policy 0, policy_version 80 (0.0013)
+[2024-09-30 09:31:36,461][07335] Updated weights for policy 0, policy_version 90 (0.0012)
+[2024-09-30 09:31:38,724][07335] Updated weights for policy 0, policy_version 100 (0.0012)
+[2024-09-30 09:31:39,183][05258] Fps is (10 sec: 18431.9, 60 sec: 16711.6, 300 sec: 16711.6). Total num frames: 417792. Throughput: 0: 3754.9. Samples: 93934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:31:39,185][05258] Avg episode reward: [(0, '4.554')]
+[2024-09-30 09:31:39,194][07321] Saving new best policy, reward=4.554!
+[2024-09-30 09:31:40,978][07335] Updated weights for policy 0, policy_version 110 (0.0013)
+[2024-09-30 09:31:43,311][07335] Updated weights for policy 0, policy_version 120 (0.0013)
+[2024-09-30 09:31:44,183][05258] Fps is (10 sec: 18022.4, 60 sec: 16793.6, 300 sec: 16793.6). Total num frames: 503808. Throughput: 0: 4027.8. Samples: 120894. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:31:44,185][05258] Avg episode reward: [(0, '4.481')]
+[2024-09-30 09:31:45,601][07335] Updated weights for policy 0, policy_version 130 (0.0013)
+[2024-09-30 09:31:47,851][07335] Updated weights for policy 0, policy_version 140 (0.0013)
+[2024-09-30 09:31:49,183][05258] Fps is (10 sec: 17612.7, 60 sec: 16969.1, 300 sec: 16969.1). Total num frames: 593920. Throughput: 0: 4222.7. Samples: 147854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-30 09:31:49,185][05258] Avg episode reward: [(0, '4.523')]
+[2024-09-30 09:31:50,113][07335] Updated weights for policy 0, policy_version 150 (0.0013)
+[2024-09-30 09:31:52,350][07335] Updated weights for policy 0, policy_version 160 (0.0013)
+[2024-09-30 09:31:54,183][05258] Fps is (10 sec: 18431.9, 60 sec: 17203.2, 300 sec: 17203.2). Total num frames: 688128. Throughput: 0: 4037.6. Samples: 161564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:31:54,185][05258] Avg episode reward: [(0, '4.838')]
+[2024-09-30 09:31:54,188][07321] Saving new best policy, reward=4.838!
+[2024-09-30 09:31:54,617][07335] Updated weights for policy 0, policy_version 170 (0.0012)
+[2024-09-30 09:31:57,021][07335] Updated weights for policy 0, policy_version 180 (0.0014)
+[2024-09-30 09:31:59,183][05258] Fps is (10 sec: 18022.6, 60 sec: 17203.2, 300 sec: 17203.2). Total num frames: 774144. Throughput: 0: 4176.5. Samples: 188004. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-30 09:31:59,185][05258] Avg episode reward: [(0, '4.933')]
+[2024-09-30 09:31:59,192][07321] Saving new best policy, reward=4.933!
+[2024-09-30 09:31:59,348][07335] Updated weights for policy 0, policy_version 190 (0.0013)
+[2024-09-30 09:32:01,587][07335] Updated weights for policy 0, policy_version 200 (0.0012)
+[2024-09-30 09:32:03,795][07335] Updated weights for policy 0, policy_version 210 (0.0012)
+[2024-09-30 09:32:04,183][05258] Fps is (10 sec: 17612.9, 60 sec: 17285.1, 300 sec: 17285.1). Total num frames: 864256. Throughput: 0: 4491.9. Samples: 215290. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:32:04,185][05258] Avg episode reward: [(0, '4.762')]
+[2024-09-30 09:32:06,067][07335] Updated weights for policy 0, policy_version 220 (0.0012)
+[2024-09-30 09:32:08,320][07335] Updated weights for policy 0, policy_version 230 (0.0013)
+[2024-09-30 09:32:09,183][05258] Fps is (10 sec: 18022.3, 60 sec: 17352.1, 300 sec: 17352.1). Total num frames: 954368. Throughput: 0: 4493.1. Samples: 228868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:32:09,185][05258] Avg episode reward: [(0, '5.153')]
+[2024-09-30 09:32:09,192][07321] Saving new best policy, reward=5.153!
+[2024-09-30 09:32:10,673][07335] Updated weights for policy 0, policy_version 240 (0.0013)
+[2024-09-30 09:32:13,008][07335] Updated weights for policy 0, policy_version 250 (0.0012)
+[2024-09-30 09:32:14,183][05258] Fps is (10 sec: 18022.4, 60 sec: 17408.0, 300 sec: 17408.0). Total num frames: 1044480. Throughput: 0: 4481.8. Samples: 255424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:32:14,185][05258] Avg episode reward: [(0, '4.899')]
+[2024-09-30 09:32:15,286][07335] Updated weights for policy 0, policy_version 260 (0.0012)
+[2024-09-30 09:32:17,578][07335] Updated weights for policy 0, policy_version 270 (0.0012)
+[2024-09-30 09:32:19,183][05258] Fps is (10 sec: 18022.4, 60 sec: 17954.1, 300 sec: 17455.2). Total num frames: 1134592. Throughput: 0: 4488.4. Samples: 282256. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:32:19,185][05258] Avg episode reward: [(0, '5.187')]
+[2024-09-30 09:32:19,192][07321] Saving new best policy, reward=5.187!
+[2024-09-30 09:32:19,859][07335] Updated weights for policy 0, policy_version 280 (0.0013)
+[2024-09-30 09:32:22,107][07335] Updated weights for policy 0, policy_version 290 (0.0013)
+[2024-09-30 09:32:24,183][05258] Fps is (10 sec: 17612.8, 60 sec: 17885.9, 300 sec: 17437.3). Total num frames: 1220608. Throughput: 0: 4485.0. Samples: 295758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:32:24,184][05258] Avg episode reward: [(0, '5.551')]
+[2024-09-30 09:32:24,186][07321] Saving new best policy, reward=5.551!
+[2024-09-30 09:32:24,479][07335] Updated weights for policy 0, policy_version 300 (0.0013)
+[2024-09-30 09:32:26,737][07335] Updated weights for policy 0, policy_version 310 (0.0013)
+[2024-09-30 09:32:29,042][07335] Updated weights for policy 0, policy_version 320 (0.0012)
+[2024-09-30 09:32:29,183][05258] Fps is (10 sec: 17612.8, 60 sec: 17954.1, 300 sec: 17476.3). Total num frames: 1310720. Throughput: 0: 4478.5. Samples: 322428. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-30 09:32:29,185][05258] Avg episode reward: [(0, '5.554')]
+[2024-09-30 09:32:29,192][07321] Saving new best policy, reward=5.554!
+[2024-09-30 09:32:31,285][07335] Updated weights for policy 0, policy_version 330 (0.0013)
+[2024-09-30 09:32:33,530][07335] Updated weights for policy 0, policy_version 340 (0.0013)
+[2024-09-30 09:32:34,183][05258] Fps is (10 sec: 18022.4, 60 sec: 17954.2, 300 sec: 17510.4). Total num frames: 1400832. Throughput: 0: 4484.4. Samples: 349650. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:32:34,185][05258] Avg episode reward: [(0, '5.448')]
+[2024-09-30 09:32:35,815][07335] Updated weights for policy 0, policy_version 350 (0.0012)
+[2024-09-30 09:32:38,142][07335] Updated weights for policy 0, policy_version 360 (0.0013)
+[2024-09-30 09:32:39,183][05258] Fps is (10 sec: 18022.3, 60 sec: 17885.9, 300 sec: 17540.5). Total num frames: 1490944. Throughput: 0: 4477.4. Samples: 363048. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:32:39,185][05258] Avg episode reward: [(0, '5.689')]
+[2024-09-30 09:32:39,192][07321] Saving new best policy, reward=5.689!
+[2024-09-30 09:32:40,443][07335] Updated weights for policy 0, policy_version 370 (0.0013)
+[2024-09-30 09:32:42,682][07335] Updated weights for policy 0, policy_version 380 (0.0012)
+[2024-09-30 09:32:44,183][05258] Fps is (10 sec: 18022.3, 60 sec: 17954.1, 300 sec: 17567.3). Total num frames: 1581056. Throughput: 0: 4484.0. Samples: 389784. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:32:44,185][05258] Avg episode reward: [(0, '6.351')]
+[2024-09-30 09:32:44,188][07321] Saving new best policy, reward=6.351!
+[2024-09-30 09:32:45,062][07335] Updated weights for policy 0, policy_version 390 (0.0013)
+[2024-09-30 09:32:47,343][07335] Updated weights for policy 0, policy_version 400 (0.0013)
+[2024-09-30 09:32:49,183][05258] Fps is (10 sec: 18022.5, 60 sec: 17954.2, 300 sec: 17591.2). Total num frames: 1671168. Throughput: 0: 4468.3. Samples: 416364. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-30 09:32:49,185][05258] Avg episode reward: [(0, '6.899')]
+[2024-09-30 09:32:49,193][07321] Saving new best policy, reward=6.899!
+[2024-09-30 09:32:49,650][07335] Updated weights for policy 0, policy_version 410 (0.0013)
+[2024-09-30 09:32:51,986][07335] Updated weights for policy 0, policy_version 420 (0.0013)
+[2024-09-30 09:32:54,183][05258] Fps is (10 sec: 17612.8, 60 sec: 17817.6, 300 sec: 17571.8). Total num frames: 1757184. Throughput: 0: 4459.4. Samples: 429542. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:32:54,185][05258] Avg episode reward: [(0, '8.499')]
+[2024-09-30 09:32:54,188][07321] Saving new best policy, reward=8.499!
+[2024-09-30 09:32:54,287][07335] Updated weights for policy 0, policy_version 430 (0.0012)
+[2024-09-30 09:32:56,481][07335] Updated weights for policy 0, policy_version 440 (0.0012)
+[2024-09-30 09:32:58,747][07335] Updated weights for policy 0, policy_version 450 (0.0012)
+[2024-09-30 09:32:59,183][05258] Fps is (10 sec: 17612.6, 60 sec: 17885.8, 300 sec: 17593.3). Total num frames: 1847296. Throughput: 0: 4472.7. Samples: 456694. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-30 09:32:59,185][05258] Avg episode reward: [(0, '9.979')]
+[2024-09-30 09:32:59,194][07321] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000451_1847296.pth...
+[2024-09-30 09:32:59,266][07321] Saving new best policy, reward=9.979!
+[2024-09-30 09:33:01,003][07335] Updated weights for policy 0, policy_version 460 (0.0012)
+[2024-09-30 09:33:03,214][07335] Updated weights for policy 0, policy_version 470 (0.0013)
+[2024-09-30 09:33:04,183][05258] Fps is (10 sec: 18432.1, 60 sec: 17954.1, 300 sec: 17650.0). Total num frames: 1941504. Throughput: 0: 4485.2. Samples: 484090. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:33:04,185][05258] Avg episode reward: [(0, '10.057')]
+[2024-09-30 09:33:04,188][07321] Saving new best policy, reward=10.057!
+[2024-09-30 09:33:05,571][07335] Updated weights for policy 0, policy_version 480 (0.0013)
+[2024-09-30 09:33:07,815][07335] Updated weights for policy 0, policy_version 490 (0.0013)
+[2024-09-30 09:33:09,183][05258] Fps is (10 sec: 18432.1, 60 sec: 17954.1, 300 sec: 17666.2). Total num frames: 2031616. Throughput: 0: 4480.3. Samples: 497374. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-30 09:33:09,185][05258] Avg episode reward: [(0, '11.287')]
+[2024-09-30 09:33:09,192][07321] Saving new best policy, reward=11.287!
+[2024-09-30 09:33:10,069][07335] Updated weights for policy 0, policy_version 500 (0.0013)
+[2024-09-30 09:33:12,323][07335] Updated weights for policy 0, policy_version 510 (0.0012)
+[2024-09-30 09:33:14,183][05258] Fps is (10 sec: 18022.3, 60 sec: 17954.1, 300 sec: 17681.1). Total num frames: 2121728. Throughput: 0: 4496.2. Samples: 524758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:33:14,184][05258] Avg episode reward: [(0, '12.018')]
+[2024-09-30 09:33:14,187][07321] Saving new best policy, reward=12.018!
+[2024-09-30 09:33:14,504][07335] Updated weights for policy 0, policy_version 520 (0.0012)
+[2024-09-30 09:33:16,772][07335] Updated weights for policy 0, policy_version 530 (0.0013)
+[2024-09-30 09:33:19,049][07335] Updated weights for policy 0, policy_version 540 (0.0013)
+[2024-09-30 09:33:19,183][05258] Fps is (10 sec: 18022.4, 60 sec: 17954.1, 300 sec: 17694.7). Total num frames: 2211840. Throughput: 0: 4497.3. Samples: 552030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:33:19,185][05258] Avg episode reward: [(0, '11.033')]
+[2024-09-30 09:33:21,324][07335] Updated weights for policy 0, policy_version 550 (0.0012)
+[2024-09-30 09:33:23,557][07335] Updated weights for policy 0, policy_version 560 (0.0013)
+[2024-09-30 09:33:24,183][05258] Fps is (10 sec: 18022.5, 60 sec: 18022.4, 300 sec: 17707.3). Total num frames: 2301952. Throughput: 0: 4502.7. Samples: 565670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:33:24,184][05258] Avg episode reward: [(0, '13.421')]
+[2024-09-30 09:33:24,186][07321] Saving new best policy, reward=13.421!
+[2024-09-30 09:33:25,779][07335] Updated weights for policy 0, policy_version 570 (0.0012)
+[2024-09-30 09:33:27,977][07335] Updated weights for policy 0, policy_version 580 (0.0012)
+[2024-09-30 09:33:29,183][05258] Fps is (10 sec: 18432.2, 60 sec: 18090.7, 300 sec: 17749.3). Total num frames: 2396160. Throughput: 0: 4523.8. Samples: 593354. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:33:29,185][05258] Avg episode reward: [(0, '15.187')]
+[2024-09-30 09:33:29,192][07321] Saving new best policy, reward=15.187!
+[2024-09-30 09:33:30,197][07335] Updated weights for policy 0, policy_version 590 (0.0012)
+[2024-09-30 09:33:32,545][07335] Updated weights for policy 0, policy_version 600 (0.0013)
+[2024-09-30 09:33:34,183][05258] Fps is (10 sec: 18432.0, 60 sec: 18090.7, 300 sec: 17759.1). Total num frames: 2486272. Throughput: 0: 4534.3. Samples: 620406. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:33:34,185][05258] Avg episode reward: [(0, '15.240')]
+[2024-09-30 09:33:34,187][07321] Saving new best policy, reward=15.240!
+[2024-09-30 09:33:34,758][07335] Updated weights for policy 0, policy_version 610 (0.0013)
+[2024-09-30 09:33:37,030][07335] Updated weights for policy 0, policy_version 620 (0.0013)
+[2024-09-30 09:33:39,183][05258] Fps is (10 sec: 18022.2, 60 sec: 18090.7, 300 sec: 17768.2). Total num frames: 2576384. Throughput: 0: 4547.2. Samples: 634164. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-30 09:33:39,185][05258] Avg episode reward: [(0, '16.221')]
+[2024-09-30 09:33:39,192][07321] Saving new best policy, reward=16.221!
+[2024-09-30 09:33:39,297][07335] Updated weights for policy 0, policy_version 630 (0.0012)
+[2024-09-30 09:33:41,481][07335] Updated weights for policy 0, policy_version 640 (0.0012)
+[2024-09-30 09:33:43,710][07335] Updated weights for policy 0, policy_version 650 (0.0012)
+[2024-09-30 09:33:44,183][05258] Fps is (10 sec: 18432.0, 60 sec: 18158.9, 300 sec: 17803.9). Total num frames: 2670592. Throughput: 0: 4556.5. Samples: 661738. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-30 09:33:44,185][05258] Avg episode reward: [(0, '16.682')]
+[2024-09-30 09:33:44,188][07321] Saving new best policy, reward=16.682!
+[2024-09-30 09:33:45,984][07335] Updated weights for policy 0, policy_version 660 (0.0013)
+[2024-09-30 09:33:48,294][07335] Updated weights for policy 0, policy_version 670 (0.0013)
+[2024-09-30 09:33:49,183][05258] Fps is (10 sec: 18432.0, 60 sec: 18158.9, 300 sec: 17811.0). Total num frames: 2760704. Throughput: 0: 4545.7. Samples: 688648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:33:49,185][05258] Avg episode reward: [(0, '16.740')]
+[2024-09-30 09:33:49,193][07321] Saving new best policy, reward=16.740!
+[2024-09-30 09:33:50,518][07335] Updated weights for policy 0, policy_version 680 (0.0013)
+[2024-09-30 09:33:52,791][07335] Updated weights for policy 0, policy_version 690 (0.0012)
+[2024-09-30 09:33:54,183][05258] Fps is (10 sec: 18022.3, 60 sec: 18227.2, 300 sec: 17817.6). Total num frames: 2850816. Throughput: 0: 4555.1. Samples: 702354. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:33:54,184][05258] Avg episode reward: [(0, '20.414')]
+[2024-09-30 09:33:54,187][07321] Saving new best policy, reward=20.414!
+[2024-09-30 09:33:55,011][07335] Updated weights for policy 0, policy_version 700 (0.0012)
+[2024-09-30 09:33:57,268][07335] Updated weights for policy 0, policy_version 710 (0.0013)
+[2024-09-30 09:33:59,183][05258] Fps is (10 sec: 18022.5, 60 sec: 18227.2, 300 sec: 17823.8). Total num frames: 2940928. Throughput: 0: 4554.0. Samples: 729686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:33:59,185][05258] Avg episode reward: [(0, '16.750')]
+[2024-09-30 09:33:59,635][07335] Updated weights for policy 0, policy_version 720 (0.0013)
+[2024-09-30 09:34:01,886][07335] Updated weights for policy 0, policy_version 730 (0.0012)
+[2024-09-30 09:34:04,129][07335] Updated weights for policy 0, policy_version 740 (0.0012)
+[2024-09-30 09:34:04,183][05258] Fps is (10 sec: 18022.5, 60 sec: 18158.9, 300 sec: 17829.7). Total num frames: 3031040. Throughput: 0: 4542.6. Samples: 756446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:34:04,184][05258] Avg episode reward: [(0, '20.115')]
+[2024-09-30 09:34:06,378][07335] Updated weights for policy 0, policy_version 750 (0.0013)
+[2024-09-30 09:34:08,612][07335] Updated weights for policy 0, policy_version 760 (0.0013)
+[2024-09-30 09:34:09,183][05258] Fps is (10 sec: 18022.4, 60 sec: 18158.9, 300 sec: 17835.1). Total num frames: 3121152. Throughput: 0: 4545.4. Samples: 770214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-30 09:34:09,185][05258] Avg episode reward: [(0, '17.857')]
+[2024-09-30 09:34:10,950][07335] Updated weights for policy 0, policy_version 770 (0.0013)
+[2024-09-30 09:34:13,390][07335] Updated weights for policy 0, policy_version 780 (0.0013)
+[2024-09-30 09:34:14,183][05258] Fps is (10 sec: 17612.7, 60 sec: 18090.7, 300 sec: 17817.6). Total num frames: 3207168. Throughput: 0: 4514.1. Samples: 796488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:34:14,186][05258] Avg episode reward: [(0, '19.764')]
+[2024-09-30 09:34:15,627][07335] Updated weights for policy 0, policy_version 790 (0.0013)
+[2024-09-30 09:34:17,856][07335] Updated weights for policy 0, policy_version 800 (0.0013)
+[2024-09-30 09:34:19,183][05258] Fps is (10 sec: 18022.5, 60 sec: 18159.0, 300 sec: 17845.3). Total num frames: 3301376. Throughput: 0: 4519.4. Samples: 823780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-30 09:34:19,185][05258] Avg episode reward: [(0, '20.421')]
+[2024-09-30 09:34:19,191][07321] Saving new best policy, reward=20.421!
+[2024-09-30 09:34:20,090][07335] Updated weights for policy 0, policy_version 810 (0.0012)
+[2024-09-30 09:34:22,307][07335] Updated weights for policy 0, policy_version 820 (0.0013)
+[2024-09-30 09:34:24,183][05258] Fps is (10 sec: 18431.9, 60 sec: 18158.9, 300 sec: 17849.9). Total num frames: 3391488. Throughput: 0: 4521.2. Samples: 837618. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-30 09:34:24,185][05258] Avg episode reward: [(0, '20.875')]
+[2024-09-30 09:34:24,188][07321] Saving new best policy, reward=20.875!
+[2024-09-30 09:34:24,529][07335] Updated weights for policy 0, policy_version 830 (0.0012)
+[2024-09-30 09:34:26,843][07335] Updated weights for policy 0, policy_version 840 (0.0013)
+[2024-09-30 09:34:29,111][07335] Updated weights for policy 0, policy_version 850 (0.0013)
+[2024-09-30 09:34:29,183][05258] Fps is (10 sec: 18022.3, 60 sec: 18090.6, 300 sec: 17854.4). Total num frames: 3481600. Throughput: 0: 4510.7. Samples: 864720. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:34:29,185][05258] Avg episode reward: [(0, '19.357')]
+[2024-09-30 09:34:31,306][07335] Updated weights for policy 0, policy_version 860 (0.0012)
+[2024-09-30 09:34:33,527][07335] Updated weights for policy 0, policy_version 870 (0.0013)
+[2024-09-30 09:34:34,183][05258] Fps is (10 sec: 18022.6, 60 sec: 18090.7, 300 sec: 17858.6). Total num frames: 3571712. Throughput: 0: 4527.6. Samples: 892388. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:34:34,185][05258] Avg episode reward: [(0, '23.261')]
+[2024-09-30 09:34:34,201][07321] Saving new best policy, reward=23.261!
+[2024-09-30 09:34:35,761][07335] Updated weights for policy 0, policy_version 880 (0.0013)
+[2024-09-30 09:34:38,014][07335] Updated weights for policy 0, policy_version 890 (0.0013)
+[2024-09-30 09:34:39,183][05258] Fps is (10 sec: 18431.9, 60 sec: 18158.9, 300 sec: 17882.5). Total num frames: 3665920. Throughput: 0: 4527.8. Samples: 906104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:34:39,185][05258] Avg episode reward: [(0, '19.074')]
+[2024-09-30 09:34:40,344][07335] Updated weights for policy 0, policy_version 900 (0.0014)
+[2024-09-30 09:34:42,605][07335] Updated weights for policy 0, policy_version 910 (0.0013)
+[2024-09-30 09:34:44,183][05258] Fps is (10 sec: 18431.9, 60 sec: 18090.6, 300 sec: 17885.9). Total num frames: 3756032. Throughput: 0: 4519.6. Samples: 933068. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-30 09:34:44,185][05258] Avg episode reward: [(0, '22.192')]
+[2024-09-30 09:34:44,837][07335] Updated weights for policy 0, policy_version 920 (0.0013)
+[2024-09-30 09:34:47,057][07335] Updated weights for policy 0, policy_version 930 (0.0013)
+[2024-09-30 09:34:49,183][05258] Fps is (10 sec: 18022.4, 60 sec: 18090.7, 300 sec: 17889.0). Total num frames: 3846144. Throughput: 0: 4535.8. Samples: 960556. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-30 09:34:49,185][05258] Avg episode reward: [(0, '20.340')]
+[2024-09-30 09:34:49,286][07335] Updated weights for policy 0, policy_version 940 (0.0013)
+[2024-09-30 09:34:51,542][07335] Updated weights for policy 0, policy_version 950 (0.0012)
+[2024-09-30 09:34:53,827][07335] Updated weights for policy 0, policy_version 960 (0.0012)
+[2024-09-30 09:34:54,183][05258] Fps is (10 sec: 18022.4, 60 sec: 18090.7, 300 sec: 17892.1). Total num frames: 3936256. Throughput: 0: 4534.7. Samples: 974274. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-30 09:34:54,185][05258] Avg episode reward: [(0, '23.986')]
+[2024-09-30 09:34:54,188][07321] Saving new best policy, reward=23.986!
+[2024-09-30 09:34:56,103][07335] Updated weights for policy 0, policy_version 970 (0.0013)
+[2024-09-30 09:34:57,880][07321] Stopping Batcher_0...
+[2024-09-30 09:34:57,881][07321] Loop batcher_evt_loop terminating...
+[2024-09-30 09:34:57,880][05258] Component Batcher_0 stopped!
+[2024-09-30 09:34:57,881][07321] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-30 09:34:57,883][05258] Component RolloutWorker_w0 process died already! Don't wait for it.
+[2024-09-30 09:34:57,905][07335] Weights refcount: 2 0
+[2024-09-30 09:34:57,907][07335] Stopping InferenceWorker_p0-w0...
+[2024-09-30 09:34:57,907][07335] Loop inference_proc0-0_evt_loop terminating...
+[2024-09-30 09:34:57,907][05258] Component InferenceWorker_p0-w0 stopped!
+[2024-09-30 09:34:57,927][07347] Stopping RolloutWorker_w7...
+[2024-09-30 09:34:57,927][07347] Loop rollout_proc7_evt_loop terminating...
+[2024-09-30 09:34:57,927][07339] Stopping RolloutWorker_w3...
+[2024-09-30 09:34:57,928][07339] Loop rollout_proc3_evt_loop terminating...
+[2024-09-30 09:34:57,928][07338] Stopping RolloutWorker_w2...
+[2024-09-30 09:34:57,928][07338] Loop rollout_proc2_evt_loop terminating...
+[2024-09-30 09:34:57,927][05258] Component RolloutWorker_w7 stopped!
+[2024-09-30 09:34:57,929][05258] Component RolloutWorker_w3 stopped!
+[2024-09-30 09:34:57,931][07346] Stopping RolloutWorker_w6...
+[2024-09-30 09:34:57,931][07337] Stopping RolloutWorker_w1...
+[2024-09-30 09:34:57,931][05258] Component RolloutWorker_w2 stopped!
+[2024-09-30 09:34:57,932][07346] Loop rollout_proc6_evt_loop terminating...
+[2024-09-30 09:34:57,932][07337] Loop rollout_proc1_evt_loop terminating...
+[2024-09-30 09:34:57,934][07341] Stopping RolloutWorker_w5...
+[2024-09-30 09:34:57,934][07340] Stopping RolloutWorker_w4...
+[2024-09-30 09:34:57,933][05258] Component RolloutWorker_w6 stopped!
+[2024-09-30 09:34:57,934][07341] Loop rollout_proc5_evt_loop terminating...
+[2024-09-30 09:34:57,934][07340] Loop rollout_proc4_evt_loop terminating...
+[2024-09-30 09:34:57,934][05258] Component RolloutWorker_w1 stopped!
+[2024-09-30 09:34:57,936][05258] Component RolloutWorker_w5 stopped!
+[2024-09-30 09:34:57,939][05258] Component RolloutWorker_w4 stopped!
+[2024-09-30 09:34:57,961][07321] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-30 09:34:58,083][07321] Stopping LearnerWorker_p0...
+[2024-09-30 09:34:58,084][07321] Loop learner_proc0_evt_loop terminating...
+[2024-09-30 09:34:58,085][05258] Component LearnerWorker_p0 stopped!
+[2024-09-30 09:34:58,087][05258] Waiting for process learner_proc0 to stop...
+[2024-09-30 09:34:58,838][05258] Waiting for process inference_proc0-0 to join...
+[2024-09-30 09:34:58,840][05258] Waiting for process rollout_proc0 to join...
+[2024-09-30 09:34:58,841][05258] Waiting for process rollout_proc1 to join...
+[2024-09-30 09:34:58,843][05258] Waiting for process rollout_proc2 to join...
+[2024-09-30 09:34:58,845][05258] Waiting for process rollout_proc3 to join...
+[2024-09-30 09:34:58,847][05258] Waiting for process rollout_proc4 to join...
+[2024-09-30 09:34:58,849][05258] Waiting for process rollout_proc5 to join...
+[2024-09-30 09:34:58,852][05258] Waiting for process rollout_proc6 to join...
+[2024-09-30 09:34:58,854][05258] Waiting for process rollout_proc7 to join...
+[2024-09-30 09:34:58,856][05258] Batcher 0 profile tree view:
+batching: 15.5652, releasing_batches: 0.0228
+[2024-09-30 09:34:58,857][05258] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0001
+  wait_policy_total: 3.8065
+update_model: 3.5393
+  weight_update: 0.0013
+one_step: 0.0031
+  handle_policy_step: 208.2309
+    deserialize: 7.8526, stack: 1.3762, obs_to_device_normalize: 48.9075, forward: 104.1723, send_messages: 13.5344
+    prepare_outputs: 23.1199
+      to_cpu: 14.0254
+[2024-09-30 09:34:58,860][05258] Learner 0 profile tree view:
+misc: 0.0056, prepare_batch: 6.5882
+train: 18.4017
+  epoch_init: 0.0056, minibatch_init: 0.0064, losses_postprocess: 0.5398, kl_divergence: 0.3534, after_optimizer: 2.1531
+  calculate_losses: 8.1994
+    losses_init: 0.0033, forward_head: 0.6300, bptt_initial: 4.4622, tail: 0.6055, advantages_returns: 0.1470, losses: 1.1248
+    bptt: 1.0649
+      bptt_forward_core: 1.0139
+  update: 6.8221
+    clip: 0.6925
+[2024-09-30 09:34:58,861][05258] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.1643, enqueue_policy_requests: 8.3633, env_step: 136.5715, overhead: 6.9259, complete_rollouts: 0.2607
+save_policy_outputs: 9.7644
+  split_output_tensors: 3.9109
+[2024-09-30 09:34:58,863][05258] Loop Runner_EvtLoop terminating...
+[2024-09-30 09:34:58,864][05258] Runner profile tree view:
+main_loop: 234.4698
+[2024-09-30 09:34:58,865][05258] Collected {0: 4005888}, FPS: 17084.9
+[2024-09-30 09:35:07,691][05258] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-30 09:35:07,693][05258] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-30 09:35:07,694][05258] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-30 09:35:07,696][05258] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-30 09:35:07,697][05258] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-30 09:35:07,698][05258] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-30 09:35:07,700][05258] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-30 09:35:07,701][05258] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-30 09:35:07,702][05258] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-09-30 09:35:07,703][05258] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-09-30 09:35:07,705][05258] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-30 09:35:07,706][05258] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-30 09:35:07,707][05258] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-30 09:35:07,709][05258] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-30 09:35:07,710][05258] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-30 09:35:07,738][05258] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-30 09:35:07,741][05258] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-30 09:35:07,744][05258] RunningMeanStd input shape: (1,)
+[2024-09-30 09:35:07,757][05258] ConvEncoder: input_channels=3
+[2024-09-30 09:35:07,870][05258] Conv encoder output size: 512
+[2024-09-30 09:35:07,872][05258] Policy head output size: 512
+[2024-09-30 09:35:08,028][05258] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-30 09:35:08,812][05258] Num frames 100...
+[2024-09-30 09:35:08,929][05258] Num frames 200...
+[2024-09-30 09:35:09,049][05258] Num frames 300...
+[2024-09-30 09:35:09,167][05258] Num frames 400...
+[2024-09-30 09:35:09,288][05258] Num frames 500...
+[2024-09-30 09:35:09,407][05258] Num frames 600...
+[2024-09-30 09:35:09,527][05258] Num frames 700...
+[2024-09-30 09:35:09,644][05258] Num frames 800...
+[2024-09-30 09:35:09,762][05258] Num frames 900...
+[2024-09-30 09:35:09,879][05258] Num frames 1000...
+[2024-09-30 09:35:09,999][05258] Num frames 1100...
+[2024-09-30 09:35:10,120][05258] Num frames 1200...
+[2024-09-30 09:35:10,240][05258] Num frames 1300...
+[2024-09-30 09:35:10,359][05258] Num frames 1400...
+[2024-09-30 09:35:10,478][05258] Num frames 1500...
+[2024-09-30 09:35:10,600][05258] Num frames 1600...
+[2024-09-30 09:35:10,721][05258] Num frames 1700...
+[2024-09-30 09:35:10,840][05258] Num frames 1800...
+[2024-09-30 09:35:10,961][05258] Num frames 1900...
+[2024-09-30 09:35:11,081][05258] Num frames 2000...
+[2024-09-30 09:35:11,205][05258] Num frames 2100...
+[2024-09-30 09:35:11,258][05258] Avg episode rewards: #0: 54.999, true rewards: #0: 21.000
+[2024-09-30 09:35:11,260][05258] Avg episode reward: 54.999, avg true_objective: 21.000
+[2024-09-30 09:35:11,383][05258] Num frames 2200...
+[2024-09-30 09:35:11,504][05258] Num frames 2300...
+[2024-09-30 09:35:11,623][05258] Num frames 2400...
+[2024-09-30 09:35:11,740][05258] Num frames 2500...
+[2024-09-30 09:35:11,858][05258] Num frames 2600...
+[2024-09-30 09:35:11,977][05258] Num frames 2700...
+[2024-09-30 09:35:12,098][05258] Num frames 2800...
+[2024-09-30 09:35:12,220][05258] Num frames 2900...
+[2024-09-30 09:35:12,339][05258] Num frames 3000...
+[2024-09-30 09:35:12,458][05258] Num frames 3100...
+[2024-09-30 09:35:12,574][05258] Num frames 3200...
+[2024-09-30 09:35:12,692][05258] Num frames 3300...
+[2024-09-30 09:35:12,845][05258] Avg episode rewards: #0: 41.915, true rewards: #0: 16.915
+[2024-09-30 09:35:12,847][05258] Avg episode reward: 41.915, avg true_objective: 16.915
+[2024-09-30 09:35:12,870][05258] Num frames 3400...
+[2024-09-30 09:35:12,987][05258] Num frames 3500...
+[2024-09-30 09:35:13,108][05258] Num frames 3600...
+[2024-09-30 09:35:13,229][05258] Num frames 3700...
+[2024-09-30 09:35:13,351][05258] Num frames 3800...
+[2024-09-30 09:35:13,470][05258] Num frames 3900...
+[2024-09-30 09:35:13,590][05258] Num frames 4000...
+[2024-09-30 09:35:13,707][05258] Num frames 4100...
+[2024-09-30 09:35:13,825][05258] Num frames 4200...
+[2024-09-30 09:35:13,945][05258] Num frames 4300...
+[2024-09-30 09:35:14,062][05258] Num frames 4400...
+[2024-09-30 09:35:14,178][05258] Num frames 4500...
+[2024-09-30 09:35:14,300][05258] Num frames 4600...
+[2024-09-30 09:35:14,423][05258] Num frames 4700...
+[2024-09-30 09:35:14,543][05258] Num frames 4800...
+[2024-09-30 09:35:14,662][05258] Num frames 4900...
+[2024-09-30 09:35:14,784][05258] Num frames 5000...
+[2024-09-30 09:35:14,906][05258] Num frames 5100...
+[2024-09-30 09:35:15,027][05258] Num frames 5200...
+[2024-09-30 09:35:15,150][05258] Num frames 5300...
+[2024-09-30 09:35:15,321][05258] Avg episode rewards: #0: 45.653, true rewards: #0: 17.987
+[2024-09-30 09:35:15,323][05258] Avg episode reward: 45.653, avg true_objective: 17.987
+[2024-09-30 09:35:15,331][05258] Num frames 5400...
+[2024-09-30 09:35:15,452][05258] Num frames 5500...
+[2024-09-30 09:35:15,570][05258] Num frames 5600...
+[2024-09-30 09:35:15,689][05258] Num frames 5700...
+[2024-09-30 09:35:15,808][05258] Num frames 5800...
+[2024-09-30 09:35:15,952][05258] Avg episode rewards: #0: 36.940, true rewards: #0: 14.690
+[2024-09-30 09:35:15,954][05258] Avg episode reward: 36.940, avg true_objective: 14.690
+[2024-09-30 09:35:15,985][05258] Num frames 5900...
+[2024-09-30 09:35:16,106][05258] Num frames 6000...
+[2024-09-30 09:35:16,226][05258] Num frames 6100...
+[2024-09-30 09:35:16,348][05258] Num frames 6200...
+[2024-09-30 09:35:16,468][05258] Num frames 6300...
+[2024-09-30 09:35:16,589][05258] Num frames 6400...
+[2024-09-30 09:35:16,718][05258] Num frames 6500...
+[2024-09-30 09:35:16,842][05258] Num frames 6600...
+[2024-09-30 09:35:16,967][05258] Num frames 6700...
+[2024-09-30 09:35:17,032][05258] Avg episode rewards: #0: 33.216, true rewards: #0: 13.416
+[2024-09-30 09:35:17,034][05258] Avg episode reward: 33.216, avg true_objective: 13.416
+[2024-09-30 09:35:17,149][05258] Num frames 6800...
+[2024-09-30 09:35:17,273][05258] Num frames 6900...
+[2024-09-30 09:35:17,396][05258] Num frames 7000...
+[2024-09-30 09:35:17,522][05258] Num frames 7100...
+[2024-09-30 09:35:17,647][05258] Num frames 7200...
+[2024-09-30 09:35:17,769][05258] Num frames 7300...
+[2024-09-30 09:35:17,891][05258] Num frames 7400...
+[2024-09-30 09:35:18,013][05258] Num frames 7500...
+[2024-09-30 09:35:18,081][05258] Avg episode rewards: #0: 30.680, true rewards: #0: 12.513
+[2024-09-30 09:35:18,083][05258] Avg episode reward: 30.680, avg true_objective: 12.513
+[2024-09-30 09:35:18,193][05258] Num frames 7600...
+[2024-09-30 09:35:18,315][05258] Num frames 7700...
+[2024-09-30 09:35:18,432][05258] Num frames 7800...
+[2024-09-30 09:35:18,550][05258] Num frames 7900...
+[2024-09-30 09:35:18,670][05258] Num frames 8000...
+[2024-09-30 09:35:18,734][05258] Avg episode rewards: #0: 27.296, true rewards: #0: 11.439
+[2024-09-30 09:35:18,736][05258] Avg episode reward: 27.296, avg true_objective: 11.439
+[2024-09-30 09:35:18,847][05258] Num frames 8100...
+[2024-09-30 09:35:18,964][05258] Num frames 8200...
+[2024-09-30 09:35:19,095][05258] Avg episode rewards: #0: 24.204, true rewards: #0: 10.329
+[2024-09-30 09:35:19,097][05258] Avg episode reward: 24.204, avg true_objective: 10.329
+[2024-09-30 09:35:19,142][05258] Num frames 8300...
+[2024-09-30 09:35:19,261][05258] Num frames 8400...
+[2024-09-30 09:35:19,380][05258] Num frames 8500...
+[2024-09-30 09:35:19,498][05258] Num frames 8600...
+[2024-09-30 09:35:19,617][05258] Num frames 8700...
+[2024-09-30 09:35:19,735][05258] Num frames 8800...
+[2024-09-30 09:35:19,853][05258] Num frames 8900...
+[2024-09-30 09:35:19,972][05258] Num frames 9000...
+[2024-09-30 09:35:20,093][05258] Num frames 9100...
+[2024-09-30 09:35:20,257][05258] Avg episode rewards: #0: 23.990, true rewards: #0: 10.212
+[2024-09-30 09:35:20,259][05258] Avg episode reward: 23.990, avg true_objective: 10.212
+[2024-09-30 09:35:20,272][05258] Num frames 9200...
+[2024-09-30 09:35:20,387][05258] Num frames 9300...
+[2024-09-30 09:35:20,505][05258] Num frames 9400...
+[2024-09-30 09:35:20,624][05258] Num frames 9500...
+[2024-09-30 09:35:20,741][05258] Num frames 9600...
+[2024-09-30 09:35:20,859][05258] Num frames 9700...
+[2024-09-30 09:35:20,978][05258] Num frames 9800...
+[2024-09-30 09:35:21,095][05258] Num frames 9900...
+[2024-09-30 09:35:21,216][05258] Num frames 10000...
+[2024-09-30 09:35:21,342][05258] Avg episode rewards: #0: 23.460, true rewards: #0: 10.060
+[2024-09-30 09:35:21,344][05258] Avg episode reward: 23.460, avg true_objective: 10.060
+[2024-09-30 09:35:45,264][05258] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-09-30 09:36:23,816][05258] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-30 09:36:23,817][05258] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-30 09:36:23,819][05258] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-30 09:36:23,820][05258] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-30 09:36:23,822][05258] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-30 09:36:23,824][05258] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-30 09:36:23,825][05258] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-09-30 09:36:23,827][05258] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-30 09:36:23,828][05258] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-09-30 09:36:23,830][05258] Adding new argument 'hf_repository'='ThomasSimonini/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-09-30 09:36:23,831][05258] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-30 09:36:23,833][05258] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-30 09:36:23,834][05258] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-30 09:36:23,836][05258] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-30 09:36:23,837][05258] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-30 09:36:23,861][05258] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-30 09:36:23,863][05258] RunningMeanStd input shape: (1,)
+[2024-09-30 09:36:23,875][05258] ConvEncoder: input_channels=3
+[2024-09-30 09:36:23,915][05258] Conv encoder output size: 512
+[2024-09-30 09:36:23,916][05258] Policy head output size: 512
+[2024-09-30 09:36:23,937][05258] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-30 09:36:24,355][05258] Num frames 100...
+[2024-09-30 09:36:24,473][05258] Num frames 200...
+[2024-09-30 09:36:24,592][05258] Num frames 300...
+[2024-09-30 09:36:24,711][05258] Num frames 400...
+[2024-09-30 09:36:24,825][05258] Num frames 500...
+[2024-09-30 09:36:24,946][05258] Num frames 600...
+[2024-09-30 09:36:25,062][05258] Num frames 700...
+[2024-09-30 09:36:25,183][05258] Num frames 800...
+[2024-09-30 09:36:25,301][05258] Num frames 900...
+[2024-09-30 09:36:25,415][05258] Num frames 1000...
+[2024-09-30 09:36:25,531][05258] Num frames 1100...
+[2024-09-30 09:36:25,684][05258] Avg episode rewards: #0: 28.840, true rewards: #0: 11.840
+[2024-09-30 09:36:25,686][05258] Avg episode reward: 28.840, avg true_objective: 11.840
+[2024-09-30 09:36:25,707][05258] Num frames 1200...
+[2024-09-30 09:36:25,822][05258] Num frames 1300...
+[2024-09-30 09:36:25,941][05258] Num frames 1400...
+[2024-09-30 09:36:26,057][05258] Num frames 1500...
+[2024-09-30 09:36:26,176][05258] Num frames 1600...
+[2024-09-30 09:36:26,269][05258] Avg episode rewards: #0: 17.160, true rewards: #0: 8.160
+[2024-09-30 09:36:26,270][05258] Avg episode reward: 17.160, avg true_objective: 8.160
+[2024-09-30 09:36:26,355][05258] Num frames 1700...
+[2024-09-30 09:36:26,475][05258] Num frames 1800...
+[2024-09-30 09:36:26,596][05258] Num frames 1900...
+[2024-09-30 09:36:26,714][05258] Num frames 2000...
+[2024-09-30 09:36:26,834][05258] Num frames 2100...
+[2024-09-30 09:36:26,952][05258] Num frames 2200...
+[2024-09-30 09:36:27,016][05258] Avg episode rewards: #0: 15.027, true rewards: #0: 7.360
+[2024-09-30 09:36:27,017][05258] Avg episode reward: 15.027, avg true_objective: 7.360
+[2024-09-30 09:36:27,131][05258] Num frames 2300...
+[2024-09-30 09:36:27,256][05258] Num frames 2400...
+[2024-09-30 09:36:27,378][05258] Num frames 2500...
+[2024-09-30 09:36:27,504][05258] Num frames 2600...
+[2024-09-30 09:36:27,625][05258] Num frames 2700...
+[2024-09-30 09:36:27,749][05258] Num frames 2800...
+[2024-09-30 09:36:27,871][05258] Num frames 2900...
+[2024-09-30 09:36:27,996][05258] Num frames 3000...
+[2024-09-30 09:36:28,116][05258] Num frames 3100...
+[2024-09-30 09:36:28,253][05258] Avg episode rewards: #0: 15.670, true rewards: #0: 7.920
+[2024-09-30 09:36:28,255][05258] Avg episode reward: 15.670, avg true_objective: 7.920
+[2024-09-30 09:36:28,294][05258] Num frames 3200...
+[2024-09-30 09:36:28,409][05258] Num frames 3300...
+[2024-09-30 09:36:28,528][05258] Num frames 3400...
+[2024-09-30 09:36:28,646][05258] Num frames 3500...
+[2024-09-30 09:36:28,764][05258] Num frames 3600...
+[2024-09-30 09:36:28,882][05258] Num frames 3700...
+[2024-09-30 09:36:29,001][05258] Num frames 3800...
+[2024-09-30 09:36:29,120][05258] Num frames 3900...
+[2024-09-30 09:36:29,180][05258] Avg episode rewards: #0: 15.608, true rewards: #0: 7.808
+[2024-09-30 09:36:29,182][05258] Avg episode reward: 15.608, avg true_objective: 7.808
+[2024-09-30 09:36:29,294][05258] Num frames 4000...
+[2024-09-30 09:36:29,411][05258] Num frames 4100...
+[2024-09-30 09:36:29,529][05258] Num frames 4200...
+[2024-09-30 09:36:29,692][05258] Avg episode rewards: #0: 13.647, true rewards: #0: 7.147
+[2024-09-30 09:36:29,694][05258] Avg episode reward: 13.647, avg true_objective: 7.147
+[2024-09-30 09:36:29,710][05258] Num frames 4300...
+[2024-09-30 09:36:29,827][05258] Num frames 4400...
+[2024-09-30 09:36:29,942][05258] Num frames 4500...
+[2024-09-30 09:36:30,064][05258] Num frames 4600...
+[2024-09-30 09:36:30,190][05258] Num frames 4700...
+[2024-09-30 09:36:30,305][05258] Num frames 4800...
+[2024-09-30 09:36:30,422][05258] Num frames 4900...
+[2024-09-30 09:36:30,539][05258] Num frames 5000...
+[2024-09-30 09:36:30,657][05258] Num frames 5100...
+[2024-09-30 09:36:30,715][05258] Avg episode rewards: #0: 13.719, true rewards: #0: 7.290
+[2024-09-30 09:36:30,716][05258] Avg episode reward: 13.719, avg true_objective: 7.290
+[2024-09-30 09:36:30,833][05258] Num frames 5200...
+[2024-09-30 09:36:30,949][05258] Num frames 5300...
+[2024-09-30 09:36:31,066][05258] Num frames 5400...
+[2024-09-30 09:36:31,186][05258] Num frames 5500...
+[2024-09-30 09:36:31,263][05258] Avg episode rewards: #0: 12.774, true rewards: #0: 6.899
+[2024-09-30 09:36:31,264][05258] Avg episode reward: 12.774, avg true_objective: 6.899
+[2024-09-30 09:36:31,357][05258] Num frames 5600...
+[2024-09-30 09:36:31,474][05258] Num frames 5700...
+[2024-09-30 09:36:31,594][05258] Num frames 5800...
+[2024-09-30 09:36:31,713][05258] Num frames 5900...
+[2024-09-30 09:36:31,832][05258] Num frames 6000...
+[2024-09-30 09:36:31,949][05258] Num frames 6100...
+[2024-09-30 09:36:32,066][05258] Num frames 6200...
+[2024-09-30 09:36:32,194][05258] Num frames 6300...
+[2024-09-30 09:36:32,310][05258] Num frames 6400...
+[2024-09-30 09:36:32,382][05258] Avg episode rewards: #0: 13.459, true rewards: #0: 7.126
+[2024-09-30 09:36:32,383][05258] Avg episode reward: 13.459, avg true_objective: 7.126
+[2024-09-30 09:36:32,481][05258] Num frames 6500...
+[2024-09-30 09:36:32,600][05258] Num frames 6600...
+[2024-09-30 09:36:32,715][05258] Num frames 6700...
+[2024-09-30 09:36:32,832][05258] Num frames 6800...
+[2024-09-30 09:36:32,951][05258] Num frames 6900...
+[2024-09-30 09:36:33,072][05258] Num frames 7000...
+[2024-09-30 09:36:33,194][05258] Num frames 7100...
+[2024-09-30 09:36:33,314][05258] Num frames 7200...
+[2024-09-30 09:36:33,431][05258] Num frames 7300...
+[2024-09-30 09:36:33,550][05258] Num frames 7400...
+[2024-09-30 09:36:33,686][05258] Avg episode rewards: #0: 14.469, true rewards: #0: 7.469
+[2024-09-30 09:36:33,687][05258] Avg episode reward: 14.469, avg true_objective: 7.469
+[2024-09-30 09:36:41,568][05258] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-09-30 09:36:45,199][05258] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-30 09:36:45,200][05258] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-30 09:36:45,203][05258] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-30 09:36:45,204][05258] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-30 09:36:45,205][05258] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-30 09:36:45,207][05258] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-30 09:36:45,207][05258] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-09-30 09:36:45,210][05258] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-30 09:36:45,211][05258] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-09-30 09:36:45,212][05258] Adding new argument 'hf_repository'='apple9855/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-09-30 09:36:45,214][05258] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-30 09:36:45,215][05258] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-30 09:36:45,217][05258] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-30 09:36:45,219][05258] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-30 09:36:45,220][05258] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-30 09:36:45,248][05258] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-30 09:36:45,249][05258] RunningMeanStd input shape: (1,)
+[2024-09-30 09:36:45,261][05258] ConvEncoder: input_channels=3
+[2024-09-30 09:36:45,302][05258] Conv encoder output size: 512
+[2024-09-30 09:36:45,304][05258] Policy head output size: 512
+[2024-09-30 09:36:45,322][05258] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-30 09:36:45,732][05258] Num frames 100...
+[2024-09-30 09:36:45,848][05258] Num frames 200...
+[2024-09-30 09:36:45,967][05258] Num frames 300...
+[2024-09-30 09:36:46,089][05258] Num frames 400...
+[2024-09-30 09:36:46,211][05258] Num frames 500...
+[2024-09-30 09:36:46,334][05258] Num frames 600...
+[2024-09-30 09:36:46,462][05258] Num frames 700...
+[2024-09-30 09:36:46,590][05258] Num frames 800...
+[2024-09-30 09:36:46,709][05258] Num frames 900...
+[2024-09-30 09:36:46,826][05258] Num frames 1000...
+[2024-09-30 09:36:46,946][05258] Num frames 1100...
+[2024-09-30 09:36:47,063][05258] Num frames 1200...
+[2024-09-30 09:36:47,185][05258] Num frames 1300...
+[2024-09-30 09:36:47,307][05258] Num frames 1400...
+[2024-09-30 09:36:47,425][05258] Num frames 1500...
+[2024-09-30 09:36:47,547][05258] Num frames 1600...
+[2024-09-30 09:36:47,670][05258] Num frames 1700...
+[2024-09-30 09:36:47,789][05258] Num frames 1800...
+[2024-09-30 09:36:47,909][05258] Num frames 1900...
+[2024-09-30 09:36:47,998][05258] Avg episode rewards: #0: 52.269, true rewards: #0: 19.270
+[2024-09-30 09:36:47,999][05258] Avg episode reward: 52.269, avg true_objective: 19.270
+[2024-09-30 09:36:48,088][05258] Num frames 2000...
+[2024-09-30 09:36:48,210][05258] Num frames 2100...
+[2024-09-30 09:36:48,330][05258] Num frames 2200...
+[2024-09-30 09:36:48,449][05258] Num frames 2300...
+[2024-09-30 09:36:48,570][05258] Num frames 2400...
+[2024-09-30 09:36:48,690][05258] Num frames 2500...
+[2024-09-30 09:36:48,808][05258] Num frames 2600...
+[2024-09-30 09:36:48,976][05258] Avg episode rewards: #0: 34.975, true rewards: #0: 13.475
+[2024-09-30 09:36:48,977][05258] Avg episode reward: 34.975, avg true_objective: 13.475
+[2024-09-30 09:36:48,985][05258] Num frames 2700...
+[2024-09-30 09:36:49,105][05258] Num frames 2800...
+[2024-09-30 09:36:49,226][05258] Num frames 2900...
+[2024-09-30 09:36:49,346][05258] Num frames 3000...
+[2024-09-30 09:36:49,464][05258] Num frames 3100...
+[2024-09-30 09:36:49,585][05258] Num frames 3200...
+[2024-09-30 09:36:49,708][05258] Num frames 3300...
+[2024-09-30 09:36:49,831][05258] Num frames 3400...
+[2024-09-30 09:36:49,951][05258] Num frames 3500...
+[2024-09-30 09:36:50,070][05258] Num frames 3600...
+[2024-09-30 09:36:50,193][05258] Num frames 3700...
+[2024-09-30 09:36:50,313][05258] Num frames 3800...
+[2024-09-30 09:36:50,432][05258] Num frames 3900...
+[2024-09-30 09:36:50,582][05258] Avg episode rewards: #0: 32.250, true rewards: #0: 13.250
+[2024-09-30 09:36:50,584][05258] Avg episode reward: 32.250, avg true_objective: 13.250
+[2024-09-30 09:36:50,617][05258] Num frames 4000...
+[2024-09-30 09:36:50,742][05258] Num frames 4100...
+[2024-09-30 09:36:50,869][05258] Num frames 4200...
+[2024-09-30 09:36:50,994][05258] Num frames 4300...
+[2024-09-30 09:36:51,120][05258] Num frames 4400...
+[2024-09-30 09:36:51,239][05258] Num frames 4500...
+[2024-09-30 09:36:51,357][05258] Num frames 4600...
+[2024-09-30 09:36:51,486][05258] Num frames 4700...
+[2024-09-30 09:36:51,556][05258] Avg episode rewards: #0: 27.527, true rewards: #0: 11.777
+[2024-09-30 09:36:51,557][05258] Avg episode reward: 27.527, avg true_objective: 11.777
+[2024-09-30 09:36:51,664][05258] Num frames 4800...
+[2024-09-30 09:36:51,782][05258] Num frames 4900...
+[2024-09-30 09:36:51,904][05258] Num frames 5000...
+[2024-09-30 09:36:52,023][05258] Num frames 5100...
+[2024-09-30 09:36:52,145][05258] Num frames 5200...
+[2024-09-30 09:36:52,270][05258] Num frames 5300...
+[2024-09-30 09:36:52,396][05258] Num frames 5400...
+[2024-09-30 09:36:52,521][05258] Num frames 5500...
+[2024-09-30 09:36:52,642][05258] Num frames 5600...
+[2024-09-30 09:36:52,759][05258] Num frames 5700...
+[2024-09-30 09:36:52,879][05258] Num frames 5800...
+[2024-09-30 09:36:52,975][05258] Avg episode rewards: #0: 26.262, true rewards: #0: 11.662
+[2024-09-30 09:36:52,976][05258] Avg episode reward: 26.262, avg true_objective: 11.662
+[2024-09-30 09:36:53,061][05258] Num frames 5900...
+[2024-09-30 09:36:53,184][05258] Num frames 6000...
+[2024-09-30 09:36:53,310][05258] Num frames 6100...
+[2024-09-30 09:36:53,427][05258] Avg episode rewards: #0: 22.752, true rewards: #0: 10.252
+[2024-09-30 09:36:53,428][05258] Avg episode reward: 22.752, avg true_objective: 10.252
+[2024-09-30 09:36:53,485][05258] Num frames 6200...
+[2024-09-30 09:36:53,609][05258] Num frames 6300...
+[2024-09-30 09:36:53,735][05258] Num frames 6400...
+[2024-09-30 09:36:53,863][05258] Num frames 6500...
+[2024-09-30 09:36:53,982][05258] Num frames 6600...
+[2024-09-30 09:36:54,102][05258] Num frames 6700...
+[2024-09-30 09:36:54,229][05258] Num frames 6800...
+[2024-09-30 09:36:54,352][05258] Num frames 6900...
+[2024-09-30 09:36:54,473][05258] Num frames 7000...
+[2024-09-30 09:36:54,594][05258] Num frames 7100...
+[2024-09-30 09:36:54,712][05258] Num frames 7200...
+[2024-09-30 09:36:54,832][05258] Num frames 7300...
+[2024-09-30 09:36:54,949][05258] Num frames 7400...
+[2024-09-30 09:36:55,071][05258] Num frames 7500...
+[2024-09-30 09:36:55,194][05258] Num frames 7600...
+[2024-09-30 09:36:55,313][05258] Num frames 7700...
+[2024-09-30 09:36:55,432][05258] Num frames 7800...
+[2024-09-30 09:36:55,553][05258] Num frames 7900...
+[2024-09-30 09:36:55,697][05258] Avg episode rewards: #0: 25.393, true rewards: #0: 11.393
+[2024-09-30 09:36:55,699][05258] Avg episode reward: 25.393, avg true_objective: 11.393
+[2024-09-30 09:36:55,730][05258] Num frames 8000...
+[2024-09-30 09:36:55,849][05258] Num frames 8100...
+[2024-09-30 09:36:55,966][05258] Num frames 8200...
+[2024-09-30 09:36:56,086][05258] Num frames 8300...
+[2024-09-30 09:36:56,206][05258] Num frames 8400...
+[2024-09-30 09:36:56,325][05258] Num frames 8500...
+[2024-09-30 09:36:56,441][05258] Num frames 8600...
+[2024-09-30 09:36:56,559][05258] Num frames 8700...
+[2024-09-30 09:36:56,679][05258] Num frames 8800...
+[2024-09-30 09:36:56,795][05258] Num frames 8900...
+[2024-09-30 09:36:56,967][05258] Avg episode rewards: #0: 24.749, true rewards: #0: 11.249
+[2024-09-30 09:36:56,969][05258] Avg episode reward: 24.749, avg true_objective: 11.249
+[2024-09-30 09:36:56,973][05258] Num frames 9000...
+[2024-09-30 09:36:57,089][05258] Num frames 9100...
+[2024-09-30 09:36:57,212][05258] Num frames 9200...
+[2024-09-30 09:36:57,331][05258] Num frames 9300...
+[2024-09-30 09:36:57,449][05258] Num frames 9400...
+[2024-09-30 09:36:57,561][05258] Avg episode rewards: #0: 22.942, true rewards: #0: 10.498
+[2024-09-30 09:36:57,563][05258] Avg episode reward: 22.942, avg true_objective: 10.498
+[2024-09-30 09:36:57,626][05258] Num frames 9500...
+[2024-09-30 09:36:57,745][05258] Num frames 9600...
+[2024-09-30 09:36:57,864][05258] Num frames 9700...
+[2024-09-30 09:36:57,982][05258] Num frames 9800...
+[2024-09-30 09:36:58,105][05258] Num frames 9900...
+[2024-09-30 09:36:58,229][05258] Num frames 10000...
+[2024-09-30 09:36:58,350][05258] Num frames 10100...
+[2024-09-30 09:36:58,471][05258] Num frames 10200...
+[2024-09-30 09:36:58,577][05258] Avg episode rewards: #0: 22.143, true rewards: #0: 10.243
+[2024-09-30 09:36:58,579][05258] Avg episode reward: 22.143, avg true_objective: 10.243
+[2024-09-30 09:37:22,789][05258] Replay video saved to /content/train_dir/default_experiment/replay.mp4!