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.1720116548.3e4cb6262246

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880e00124a428f81a3e8b1c8785ab544957b8f885c6809041fe473eb51eddd50
+size 207920

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: 7.36 +/- 5.32
+      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 Hamze-Hammami/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_000000751_3076096_reward_24.514.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04cfdb14a772fede13f536b82e5ee0033d0b2ee5d5564479c456bdb1efdfd3c
+size 34929051

checkpoint_p0/checkpoint_000000491_2011136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68b0c8fdd0c5726350712728fd43585cd83c443b750b6af9a87ad7cb4f24904
+size 34929477

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c79cdcfb1b049ab5afbed74280f1b4e9cc338c3d448d38bb77d8f39b8ca83a
+size 34929477

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:a8ced743639fc29ef7d78402b1408d51cd9830f3ea6ed03067e3e65045fad74e
+size 14323611

sf_log.txt

@@ -0,0 +1,681 @@
+[2024-07-04 18:09:12,563][02159] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-07-04 18:09:12,565][02159] Rollout worker 0 uses device cpu
+[2024-07-04 18:09:12,566][02159] Rollout worker 1 uses device cpu
+[2024-07-04 18:09:12,567][02159] Rollout worker 2 uses device cpu
+[2024-07-04 18:09:12,568][02159] Rollout worker 3 uses device cpu
+[2024-07-04 18:09:12,571][02159] Rollout worker 4 uses device cpu
+[2024-07-04 18:09:12,571][02159] Rollout worker 5 uses device cpu
+[2024-07-04 18:09:12,573][02159] Rollout worker 6 uses device cpu
+[2024-07-04 18:09:12,574][02159] Rollout worker 7 uses device cpu
+[2024-07-04 18:09:12,672][02159] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-04 18:09:12,673][02159] InferenceWorker_p0-w0: min num requests: 2
+[2024-07-04 18:09:12,706][02159] Starting all processes...
+[2024-07-04 18:09:12,707][02159] Starting process learner_proc0
+[2024-07-04 18:09:14,405][02159] Starting all processes...
+[2024-07-04 18:09:14,411][02159] Starting process inference_proc0-0
+[2024-07-04 18:09:14,411][02159] Starting process rollout_proc0
+[2024-07-04 18:09:14,412][02159] Starting process rollout_proc1
+[2024-07-04 18:09:14,413][02159] Starting process rollout_proc2
+[2024-07-04 18:09:14,413][02159] Starting process rollout_proc3
+[2024-07-04 18:09:14,414][02159] Starting process rollout_proc4
+[2024-07-04 18:09:14,414][02159] Starting process rollout_proc5
+[2024-07-04 18:09:14,416][02159] Starting process rollout_proc6
+[2024-07-04 18:09:14,420][02159] Starting process rollout_proc7
+[2024-07-04 18:09:17,137][04783] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-07-04 18:09:17,169][04785] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-07-04 18:09:17,196][04768] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-04 18:09:17,197][04768] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-07-04 18:09:17,215][04768] Num visible devices: 1
+[2024-07-04 18:09:17,250][04768] Starting seed is not provided
+[2024-07-04 18:09:17,251][04768] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-04 18:09:17,251][04768] Initializing actor-critic model on device cuda:0
+[2024-07-04 18:09:17,252][04768] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-04 18:09:17,254][04768] RunningMeanStd input shape: (1,)
+[2024-07-04 18:09:17,275][04768] ConvEncoder: input_channels=3
+[2024-07-04 18:09:17,375][04786] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-07-04 18:09:17,477][04782] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-07-04 18:09:17,483][04784] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-07-04 18:09:17,532][04789] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-07-04 18:09:17,536][04781] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-04 18:09:17,536][04781] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-07-04 18:09:17,538][04788] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-07-04 18:09:17,552][04781] Num visible devices: 1
+[2024-07-04 18:09:17,563][04768] Conv encoder output size: 512
+[2024-07-04 18:09:17,564][04768] Policy head output size: 512
+[2024-07-04 18:09:17,614][04787] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-07-04 18:09:17,618][04768] Created Actor Critic model with architecture:
+[2024-07-04 18:09:17,618][04768] 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)
+  )
+)
+[2024-07-04 18:09:17,843][04768] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-07-04 18:09:18,814][04768] No checkpoints found
+[2024-07-04 18:09:18,815][04768] Did not load from checkpoint, starting from scratch!
+[2024-07-04 18:09:18,815][04768] Initialized policy 0 weights for model version 0
+[2024-07-04 18:09:18,817][04768] LearnerWorker_p0 finished initialization!
+[2024-07-04 18:09:18,817][04768] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-04 18:09:18,904][04781] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-04 18:09:18,905][04781] RunningMeanStd input shape: (1,)
+[2024-07-04 18:09:18,917][04781] ConvEncoder: input_channels=3
+[2024-07-04 18:09:19,026][04781] Conv encoder output size: 512
+[2024-07-04 18:09:19,027][04781] Policy head output size: 512
+[2024-07-04 18:09:19,085][02159] Inference worker 0-0 is ready!
+[2024-07-04 18:09:19,087][02159] All inference workers are ready! Signal rollout workers to start!
+[2024-07-04 18:09:19,129][04786] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:09:19,134][04789] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:09:19,137][04784] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:09:19,138][04785] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:09:19,141][04783] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:09:19,143][04782] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:09:19,144][04788] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:09:19,148][04787] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:09:19,456][04785] Decorrelating experience for 0 frames...
+[2024-07-04 18:09:19,456][04788] Decorrelating experience for 0 frames...
+[2024-07-04 18:09:19,456][04789] Decorrelating experience for 0 frames...
+[2024-07-04 18:09:19,456][04786] Decorrelating experience for 0 frames...
+[2024-07-04 18:09:19,703][04783] Decorrelating experience for 0 frames...
+[2024-07-04 18:09:19,710][04787] Decorrelating experience for 0 frames...
+[2024-07-04 18:09:19,731][04788] Decorrelating experience for 32 frames...
+[2024-07-04 18:09:19,733][04785] Decorrelating experience for 32 frames...
+[2024-07-04 18:09:19,733][04789] Decorrelating experience for 32 frames...
+[2024-07-04 18:09:19,740][04784] Decorrelating experience for 0 frames...
+[2024-07-04 18:09:19,994][04784] Decorrelating experience for 32 frames...
+[2024-07-04 18:09:20,029][04783] Decorrelating experience for 32 frames...
+[2024-07-04 18:09:20,036][04782] Decorrelating experience for 0 frames...
+[2024-07-04 18:09:20,038][04787] Decorrelating experience for 32 frames...
+[2024-07-04 18:09:20,081][04785] Decorrelating experience for 64 frames...
+[2024-07-04 18:09:20,106][04788] Decorrelating experience for 64 frames...
+[2024-07-04 18:09:20,271][04786] Decorrelating experience for 32 frames...
+[2024-07-04 18:09:20,282][04782] Decorrelating experience for 32 frames...
+[2024-07-04 18:09:20,335][04789] Decorrelating experience for 64 frames...
+[2024-07-04 18:09:20,377][04787] Decorrelating experience for 64 frames...
+[2024-07-04 18:09:20,395][04784] Decorrelating experience for 64 frames...
+[2024-07-04 18:09:20,407][04785] Decorrelating experience for 96 frames...
+[2024-07-04 18:09:20,548][04783] Decorrelating experience for 64 frames...
+[2024-07-04 18:09:20,627][04786] Decorrelating experience for 64 frames...
+[2024-07-04 18:09:20,699][04787] Decorrelating experience for 96 frames...
+[2024-07-04 18:09:20,704][04782] Decorrelating experience for 64 frames...
+[2024-07-04 18:09:20,818][04784] Decorrelating experience for 96 frames...
+[2024-07-04 18:09:20,866][04783] Decorrelating experience for 96 frames...
+[2024-07-04 18:09:20,895][04789] Decorrelating experience for 96 frames...
+[2024-07-04 18:09:20,979][04788] Decorrelating experience for 96 frames...
+[2024-07-04 18:09:21,033][04782] Decorrelating experience for 96 frames...
+[2024-07-04 18:09:21,119][04786] Decorrelating experience for 96 frames...
+[2024-07-04 18:09:22,008][04768] Signal inference workers to stop experience collection...
+[2024-07-04 18:09:22,013][04781] InferenceWorker_p0-w0: stopping experience collection
+[2024-07-04 18:09:23,523][02159] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 2216. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-07-04 18:09:23,525][02159] Avg episode reward: [(0, '1.747')]
+[2024-07-04 18:09:23,826][04768] Signal inference workers to resume experience collection...
+[2024-07-04 18:09:23,827][04781] InferenceWorker_p0-w0: resuming experience collection
+[2024-07-04 18:09:25,945][04781] Updated weights for policy 0, policy_version 10 (0.0194)
+[2024-07-04 18:09:28,220][04781] Updated weights for policy 0, policy_version 20 (0.0013)
+[2024-07-04 18:09:28,524][02159] Fps is (10 sec: 17202.3, 60 sec: 17202.3, 300 sec: 17202.3). Total num frames: 86016. Throughput: 0: 3623.8. Samples: 20336. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-07-04 18:09:28,526][02159] Avg episode reward: [(0, '4.635')]
+[2024-07-04 18:09:30,328][04781] Updated weights for policy 0, policy_version 30 (0.0013)
+[2024-07-04 18:09:32,417][04781] Updated weights for policy 0, policy_version 40 (0.0013)
+[2024-07-04 18:09:32,664][02159] Heartbeat connected on Batcher_0
+[2024-07-04 18:09:32,668][02159] Heartbeat connected on LearnerWorker_p0
+[2024-07-04 18:09:32,677][02159] Heartbeat connected on InferenceWorker_p0-w0
+[2024-07-04 18:09:32,680][02159] Heartbeat connected on RolloutWorker_w0
+[2024-07-04 18:09:32,683][02159] Heartbeat connected on RolloutWorker_w1
+[2024-07-04 18:09:32,688][02159] Heartbeat connected on RolloutWorker_w2
+[2024-07-04 18:09:32,691][02159] Heartbeat connected on RolloutWorker_w3
+[2024-07-04 18:09:32,695][02159] Heartbeat connected on RolloutWorker_w4
+[2024-07-04 18:09:32,698][02159] Heartbeat connected on RolloutWorker_w5
+[2024-07-04 18:09:32,704][02159] Heartbeat connected on RolloutWorker_w6
+[2024-07-04 18:09:32,711][02159] Heartbeat connected on RolloutWorker_w7
+[2024-07-04 18:09:33,523][02159] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 18432.0). Total num frames: 184320. Throughput: 0: 3273.0. Samples: 34946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-04 18:09:33,526][02159] Avg episode reward: [(0, '4.434')]
+[2024-07-04 18:09:33,528][04768] Saving new best policy, reward=4.434!
+[2024-07-04 18:09:34,517][04781] Updated weights for policy 0, policy_version 50 (0.0012)
+[2024-07-04 18:09:36,609][04781] Updated weights for policy 0, policy_version 60 (0.0012)
+[2024-07-04 18:09:38,523][02159] Fps is (10 sec: 19661.1, 60 sec: 18841.4, 300 sec: 18841.4). Total num frames: 282624. Throughput: 0: 4144.0. Samples: 64376. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-04 18:09:38,526][02159] Avg episode reward: [(0, '4.774')]
+[2024-07-04 18:09:38,533][04768] Saving new best policy, reward=4.774!
+[2024-07-04 18:09:38,692][04781] Updated weights for policy 0, policy_version 70 (0.0013)
+[2024-07-04 18:09:41,053][04781] Updated weights for policy 0, policy_version 80 (0.0013)
+[2024-07-04 18:09:43,239][04781] Updated weights for policy 0, policy_version 90 (0.0013)
+[2024-07-04 18:09:43,523][02159] Fps is (10 sec: 18841.6, 60 sec: 18636.8, 300 sec: 18636.8). Total num frames: 372736. Throughput: 0: 4497.4. Samples: 92164. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-07-04 18:09:43,525][02159] Avg episode reward: [(0, '4.653')]
+[2024-07-04 18:09:45,347][04781] Updated weights for policy 0, policy_version 100 (0.0013)
+[2024-07-04 18:09:47,462][04781] Updated weights for policy 0, policy_version 110 (0.0012)
+[2024-07-04 18:09:48,524][02159] Fps is (10 sec: 18841.6, 60 sec: 18841.5, 300 sec: 18841.5). Total num frames: 471040. Throughput: 0: 4185.4. Samples: 106852. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2024-07-04 18:09:48,525][02159] Avg episode reward: [(0, '4.497')]
+[2024-07-04 18:09:49,551][04781] Updated weights for policy 0, policy_version 120 (0.0013)
+[2024-07-04 18:09:51,638][04781] Updated weights for policy 0, policy_version 130 (0.0013)
+[2024-07-04 18:09:53,523][02159] Fps is (10 sec: 19251.0, 60 sec: 18841.5, 300 sec: 18841.5). Total num frames: 565248. Throughput: 0: 4462.7. Samples: 136096. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
+[2024-07-04 18:09:53,526][02159] Avg episode reward: [(0, '4.762')]
+[2024-07-04 18:09:53,791][04781] Updated weights for policy 0, policy_version 140 (0.0012)
+[2024-07-04 18:09:56,018][04781] Updated weights for policy 0, policy_version 150 (0.0013)
+[2024-07-04 18:09:58,139][04781] Updated weights for policy 0, policy_version 160 (0.0013)
+[2024-07-04 18:09:58,523][02159] Fps is (10 sec: 18841.7, 60 sec: 18841.5, 300 sec: 18841.5). Total num frames: 659456. Throughput: 0: 4634.4. Samples: 164422. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:09:58,526][02159] Avg episode reward: [(0, '4.845')]
+[2024-07-04 18:09:58,556][04768] Saving new best policy, reward=4.845!
+[2024-07-04 18:10:00,250][04781] Updated weights for policy 0, policy_version 170 (0.0012)
+[2024-07-04 18:10:02,341][04781] Updated weights for policy 0, policy_version 180 (0.0013)
+[2024-07-04 18:10:03,523][02159] Fps is (10 sec: 19251.2, 60 sec: 18943.9, 300 sec: 18943.9). Total num frames: 757760. Throughput: 0: 4418.0. Samples: 178936. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:10:03,525][02159] Avg episode reward: [(0, '5.081')]
+[2024-07-04 18:10:03,528][04768] Saving new best policy, reward=5.081!
+[2024-07-04 18:10:04,433][04781] Updated weights for policy 0, policy_version 190 (0.0012)
+[2024-07-04 18:10:06,526][04781] Updated weights for policy 0, policy_version 200 (0.0012)
+[2024-07-04 18:10:08,523][02159] Fps is (10 sec: 19660.8, 60 sec: 19023.6, 300 sec: 19023.6). Total num frames: 856064. Throughput: 0: 4576.0. Samples: 208138. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:10:08,525][02159] Avg episode reward: [(0, '5.253')]
+[2024-07-04 18:10:08,533][04768] Saving new best policy, reward=5.253!
+[2024-07-04 18:10:08,725][04781] Updated weights for policy 0, policy_version 210 (0.0012)
+[2024-07-04 18:10:10,926][04781] Updated weights for policy 0, policy_version 220 (0.0012)
+[2024-07-04 18:10:13,010][04781] Updated weights for policy 0, policy_version 230 (0.0012)
+[2024-07-04 18:10:13,523][02159] Fps is (10 sec: 19251.2, 60 sec: 19005.4, 300 sec: 19005.4). Total num frames: 950272. Throughput: 0: 4805.5. Samples: 236584. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:10:13,525][02159] Avg episode reward: [(0, '5.371')]
+[2024-07-04 18:10:13,528][04768] Saving new best policy, reward=5.371!
+[2024-07-04 18:10:15,118][04781] Updated weights for policy 0, policy_version 240 (0.0012)
+[2024-07-04 18:10:17,219][04781] Updated weights for policy 0, policy_version 250 (0.0012)
+[2024-07-04 18:10:18,523][02159] Fps is (10 sec: 18841.6, 60 sec: 18990.5, 300 sec: 18990.5). Total num frames: 1044480. Throughput: 0: 4807.7. Samples: 251294. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2024-07-04 18:10:18,526][02159] Avg episode reward: [(0, '5.741')]
+[2024-07-04 18:10:18,535][04768] Saving new best policy, reward=5.741!
+[2024-07-04 18:10:19,379][04781] Updated weights for policy 0, policy_version 260 (0.0012)
+[2024-07-04 18:10:21,511][04781] Updated weights for policy 0, policy_version 270 (0.0013)
+[2024-07-04 18:10:23,523][02159] Fps is (10 sec: 19251.2, 60 sec: 19046.4, 300 sec: 19046.4). Total num frames: 1142784. Throughput: 0: 4790.5. Samples: 279948. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:10:23,525][02159] Avg episode reward: [(0, '5.533')]
+[2024-07-04 18:10:23,692][04781] Updated weights for policy 0, policy_version 280 (0.0012)
+[2024-07-04 18:10:25,797][04781] Updated weights for policy 0, policy_version 290 (0.0012)
+[2024-07-04 18:10:27,852][04781] Updated weights for policy 0, policy_version 300 (0.0013)
+[2024-07-04 18:10:28,523][02159] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19093.6). Total num frames: 1241088. Throughput: 0: 4816.7. Samples: 308914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-04 18:10:28,526][02159] Avg episode reward: [(0, '6.158')]
+[2024-07-04 18:10:28,533][04768] Saving new best policy, reward=6.158!
+[2024-07-04 18:10:29,948][04781] Updated weights for policy 0, policy_version 310 (0.0013)
+[2024-07-04 18:10:32,065][04781] Updated weights for policy 0, policy_version 320 (0.0012)
+[2024-07-04 18:10:33,523][02159] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19134.1). Total num frames: 1339392. Throughput: 0: 4816.4. Samples: 323590. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-07-04 18:10:33,526][02159] Avg episode reward: [(0, '6.725')]
+[2024-07-04 18:10:33,528][04768] Saving new best policy, reward=6.725!
+[2024-07-04 18:10:34,147][04781] Updated weights for policy 0, policy_version 330 (0.0012)
+[2024-07-04 18:10:36,343][04781] Updated weights for policy 0, policy_version 340 (0.0012)
+[2024-07-04 18:10:38,512][04781] Updated weights for policy 0, policy_version 350 (0.0012)
+[2024-07-04 18:10:38,523][02159] Fps is (10 sec: 19251.2, 60 sec: 19182.9, 300 sec: 19114.6). Total num frames: 1433600. Throughput: 0: 4803.1. Samples: 352236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-07-04 18:10:38,526][02159] Avg episode reward: [(0, '7.359')]
+[2024-07-04 18:10:38,532][04768] Saving new best policy, reward=7.359!
+[2024-07-04 18:10:40,619][04781] Updated weights for policy 0, policy_version 360 (0.0012)
+[2024-07-04 18:10:42,724][04781] Updated weights for policy 0, policy_version 370 (0.0012)
+[2024-07-04 18:10:43,523][02159] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19097.6). Total num frames: 1527808. Throughput: 0: 4823.8. Samples: 381494. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:10:43,526][02159] Avg episode reward: [(0, '7.402')]
+[2024-07-04 18:10:43,529][04768] Saving new best policy, reward=7.402!
+[2024-07-04 18:10:44,833][04781] Updated weights for policy 0, policy_version 380 (0.0013)
+[2024-07-04 18:10:46,918][04781] Updated weights for policy 0, policy_version 390 (0.0012)
+[2024-07-04 18:10:48,524][02159] Fps is (10 sec: 19251.1, 60 sec: 19251.2, 300 sec: 19130.7). Total num frames: 1626112. Throughput: 0: 4825.1. Samples: 396064. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2024-07-04 18:10:48,526][02159] Avg episode reward: [(0, '8.141')]
+[2024-07-04 18:10:48,533][04768] Saving new best policy, reward=8.141!
+[2024-07-04 18:10:49,038][04781] Updated weights for policy 0, policy_version 400 (0.0012)
+[2024-07-04 18:10:51,201][04781] Updated weights for policy 0, policy_version 410 (0.0012)
+[2024-07-04 18:10:53,334][04781] Updated weights for policy 0, policy_version 420 (0.0013)
+[2024-07-04 18:10:53,523][02159] Fps is (10 sec: 19251.3, 60 sec: 19251.2, 300 sec: 19114.6). Total num frames: 1720320. Throughput: 0: 4812.4. Samples: 424696. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:10:53,525][02159] Avg episode reward: [(0, '9.569')]
+[2024-07-04 18:10:53,538][04768] Saving new best policy, reward=9.569!
+[2024-07-04 18:10:55,428][04781] Updated weights for policy 0, policy_version 430 (0.0012)
+[2024-07-04 18:10:57,514][04781] Updated weights for policy 0, policy_version 440 (0.0012)
+[2024-07-04 18:10:58,523][02159] Fps is (10 sec: 19251.4, 60 sec: 19319.5, 300 sec: 19143.4). Total num frames: 1818624. Throughput: 0: 4832.3. Samples: 454038. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-07-04 18:10:58,526][02159] Avg episode reward: [(0, '8.960')]
+[2024-07-04 18:10:59,608][04781] Updated weights for policy 0, policy_version 450 (0.0012)
+[2024-07-04 18:11:01,664][04781] Updated weights for policy 0, policy_version 460 (0.0012)
+[2024-07-04 18:11:03,523][02159] Fps is (10 sec: 19660.7, 60 sec: 19319.5, 300 sec: 19169.3). Total num frames: 1916928. Throughput: 0: 4832.0. Samples: 468736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-04 18:11:03,525][02159] Avg episode reward: [(0, '10.328')]
+[2024-07-04 18:11:03,528][04768] Saving new best policy, reward=10.328!
+[2024-07-04 18:11:03,833][04781] Updated weights for policy 0, policy_version 470 (0.0012)
+[2024-07-04 18:11:06,003][04781] Updated weights for policy 0, policy_version 480 (0.0013)
+[2024-07-04 18:11:08,155][04781] Updated weights for policy 0, policy_version 490 (0.0012)
+[2024-07-04 18:11:08,523][02159] Fps is (10 sec: 19251.1, 60 sec: 19251.2, 300 sec: 19153.6). Total num frames: 2011136. Throughput: 0: 4829.3. Samples: 497268. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-07-04 18:11:08,526][02159] Avg episode reward: [(0, '13.755')]
+[2024-07-04 18:11:08,534][04768] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000491_2011136.pth...
+[2024-07-04 18:11:08,612][04768] Saving new best policy, reward=13.755!
+[2024-07-04 18:11:10,263][04781] Updated weights for policy 0, policy_version 500 (0.0012)
+[2024-07-04 18:11:12,331][04781] Updated weights for policy 0, policy_version 510 (0.0013)
+[2024-07-04 18:11:13,523][02159] Fps is (10 sec: 19251.3, 60 sec: 19319.5, 300 sec: 19176.7). Total num frames: 2109440. Throughput: 0: 4839.0. Samples: 526670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-07-04 18:11:13,526][02159] Avg episode reward: [(0, '14.175')]
+[2024-07-04 18:11:13,528][04768] Saving new best policy, reward=14.175!
+[2024-07-04 18:11:14,398][04781] Updated weights for policy 0, policy_version 520 (0.0013)
+[2024-07-04 18:11:16,508][04781] Updated weights for policy 0, policy_version 530 (0.0012)
+[2024-07-04 18:11:18,523][02159] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19197.8). Total num frames: 2207744. Throughput: 0: 4839.9. Samples: 541384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-07-04 18:11:18,526][02159] Avg episode reward: [(0, '14.465')]
+[2024-07-04 18:11:18,533][04768] Saving new best policy, reward=14.465!
+[2024-07-04 18:11:18,732][04781] Updated weights for policy 0, policy_version 540 (0.0013)
+[2024-07-04 18:11:20,903][04781] Updated weights for policy 0, policy_version 550 (0.0012)
+[2024-07-04 18:11:23,008][04781] Updated weights for policy 0, policy_version 560 (0.0013)
+[2024-07-04 18:11:23,523][02159] Fps is (10 sec: 19251.3, 60 sec: 19319.5, 300 sec: 19182.9). Total num frames: 2301952. Throughput: 0: 4828.5. Samples: 569520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-04 18:11:23,527][02159] Avg episode reward: [(0, '18.393')]
+[2024-07-04 18:11:23,529][04768] Saving new best policy, reward=18.393!
+[2024-07-04 18:11:25,085][04781] Updated weights for policy 0, policy_version 570 (0.0012)
+[2024-07-04 18:11:27,159][04781] Updated weights for policy 0, policy_version 580 (0.0013)
+[2024-07-04 18:11:28,523][02159] Fps is (10 sec: 19251.3, 60 sec: 19319.5, 300 sec: 19202.0). Total num frames: 2400256. Throughput: 0: 4835.6. Samples: 599096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-04 18:11:28,525][02159] Avg episode reward: [(0, '18.739')]
+[2024-07-04 18:11:28,532][04768] Saving new best policy, reward=18.739!
+[2024-07-04 18:11:29,245][04781] Updated weights for policy 0, policy_version 590 (0.0012)
+[2024-07-04 18:11:31,371][04781] Updated weights for policy 0, policy_version 600 (0.0012)
+[2024-07-04 18:11:33,523][02159] Fps is (10 sec: 19251.0, 60 sec: 19251.2, 300 sec: 19188.2). Total num frames: 2494464. Throughput: 0: 4837.0. Samples: 613728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-04 18:11:33,526][02159] Avg episode reward: [(0, '18.011')]
+[2024-07-04 18:11:33,578][04781] Updated weights for policy 0, policy_version 610 (0.0013)
+[2024-07-04 18:11:35,675][04781] Updated weights for policy 0, policy_version 620 (0.0012)
+[2024-07-04 18:11:37,718][04781] Updated weights for policy 0, policy_version 630 (0.0012)
+[2024-07-04 18:11:38,524][02159] Fps is (10 sec: 19250.8, 60 sec: 19319.4, 300 sec: 19205.7). Total num frames: 2592768. Throughput: 0: 4840.0. Samples: 642498. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-04 18:11:38,526][02159] Avg episode reward: [(0, '17.751')]
+[2024-07-04 18:11:39,798][04781] Updated weights for policy 0, policy_version 640 (0.0012)
+[2024-07-04 18:11:41,916][04781] Updated weights for policy 0, policy_version 650 (0.0012)
+[2024-07-04 18:11:43,523][02159] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19221.9). Total num frames: 2691072. Throughput: 0: 4841.8. Samples: 671918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-04 18:11:43,526][02159] Avg episode reward: [(0, '19.244')]
+[2024-07-04 18:11:43,528][04768] Saving new best policy, reward=19.244!
+[2024-07-04 18:11:44,011][04781] Updated weights for policy 0, policy_version 660 (0.0013)
+[2024-07-04 18:11:46,231][04781] Updated weights for policy 0, policy_version 670 (0.0012)
+[2024-07-04 18:11:48,382][04781] Updated weights for policy 0, policy_version 680 (0.0012)
+[2024-07-04 18:11:48,523][02159] Fps is (10 sec: 19251.4, 60 sec: 19319.5, 300 sec: 19208.8). Total num frames: 2785280. Throughput: 0: 4827.6. Samples: 685980. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-04 18:11:48,526][02159] Avg episode reward: [(0, '18.019')]
+[2024-07-04 18:11:50,460][04781] Updated weights for policy 0, policy_version 690 (0.0012)
+[2024-07-04 18:11:52,522][04781] Updated weights for policy 0, policy_version 700 (0.0012)
+[2024-07-04 18:11:53,523][02159] Fps is (10 sec: 19251.2, 60 sec: 19387.7, 300 sec: 19223.9). Total num frames: 2883584. Throughput: 0: 4844.4. Samples: 715264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-07-04 18:11:53,526][02159] Avg episode reward: [(0, '22.378')]
+[2024-07-04 18:11:53,529][04768] Saving new best policy, reward=22.378!
+[2024-07-04 18:11:54,613][04781] Updated weights for policy 0, policy_version 710 (0.0012)
+[2024-07-04 18:11:56,698][04781] Updated weights for policy 0, policy_version 720 (0.0012)
+[2024-07-04 18:11:58,523][02159] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19238.0). Total num frames: 2981888. Throughput: 0: 4848.9. Samples: 744872. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:11:58,525][02159] Avg episode reward: [(0, '22.491')]
+[2024-07-04 18:11:58,533][04768] Saving new best policy, reward=22.491!
+[2024-07-04 18:11:58,838][04781] Updated weights for policy 0, policy_version 730 (0.0013)
+[2024-07-04 18:12:01,053][04781] Updated weights for policy 0, policy_version 740 (0.0012)
+[2024-07-04 18:12:03,191][04781] Updated weights for policy 0, policy_version 750 (0.0012)
+[2024-07-04 18:12:03,523][02159] Fps is (10 sec: 19251.2, 60 sec: 19319.5, 300 sec: 19225.6). Total num frames: 3076096. Throughput: 0: 4830.9. Samples: 758774. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2024-07-04 18:12:03,526][02159] Avg episode reward: [(0, '24.514')]
+[2024-07-04 18:12:03,528][04768] Saving new best policy, reward=24.514!
+[2024-07-04 18:12:05,289][04781] Updated weights for policy 0, policy_version 760 (0.0013)
+[2024-07-04 18:12:07,391][04781] Updated weights for policy 0, policy_version 770 (0.0013)
+[2024-07-04 18:12:08,523][02159] Fps is (10 sec: 19251.2, 60 sec: 19387.7, 300 sec: 19238.8). Total num frames: 3174400. Throughput: 0: 4854.3. Samples: 787962. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2024-07-04 18:12:08,526][02159] Avg episode reward: [(0, '21.793')]
+[2024-07-04 18:12:09,440][04781] Updated weights for policy 0, policy_version 780 (0.0011)
+[2024-07-04 18:12:11,521][04781] Updated weights for policy 0, policy_version 790 (0.0013)
+[2024-07-04 18:12:13,523][02159] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19251.2). Total num frames: 3272704. Throughput: 0: 4844.8. Samples: 817114. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:12:13,526][02159] Avg episode reward: [(0, '21.078')]
+[2024-07-04 18:12:13,714][04781] Updated weights for policy 0, policy_version 800 (0.0013)
+[2024-07-04 18:12:15,906][04781] Updated weights for policy 0, policy_version 810 (0.0012)
+[2024-07-04 18:12:17,984][04781] Updated weights for policy 0, policy_version 820 (0.0012)
+[2024-07-04 18:12:18,523][02159] Fps is (10 sec: 19251.1, 60 sec: 19319.5, 300 sec: 19239.5). Total num frames: 3366912. Throughput: 0: 4830.8. Samples: 831114. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2024-07-04 18:12:18,526][02159] Avg episode reward: [(0, '23.839')]
+[2024-07-04 18:12:20,055][04781] Updated weights for policy 0, policy_version 830 (0.0012)
+[2024-07-04 18:12:22,196][04781] Updated weights for policy 0, policy_version 840 (0.0012)
+[2024-07-04 18:12:23,523][02159] Fps is (10 sec: 19251.3, 60 sec: 19387.7, 300 sec: 19251.2). Total num frames: 3465216. Throughput: 0: 4841.9. Samples: 860384. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:12:23,525][02159] Avg episode reward: [(0, '21.011')]
+[2024-07-04 18:12:24,272][04781] Updated weights for policy 0, policy_version 850 (0.0012)
+[2024-07-04 18:12:26,415][04781] Updated weights for policy 0, policy_version 860 (0.0012)
+[2024-07-04 18:12:28,523][02159] Fps is (10 sec: 19251.3, 60 sec: 19319.5, 300 sec: 19240.1). Total num frames: 3559424. Throughput: 0: 4825.3. Samples: 889056. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:12:28,525][02159] Avg episode reward: [(0, '20.468')]
+[2024-07-04 18:12:28,642][04781] Updated weights for policy 0, policy_version 870 (0.0012)
+[2024-07-04 18:12:30,835][04781] Updated weights for policy 0, policy_version 880 (0.0012)
+[2024-07-04 18:12:32,945][04781] Updated weights for policy 0, policy_version 890 (0.0012)
+[2024-07-04 18:12:33,523][02159] Fps is (10 sec: 18841.5, 60 sec: 19319.5, 300 sec: 19229.6). Total num frames: 3653632. Throughput: 0: 4824.1. Samples: 903066. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:12:33,525][02159] Avg episode reward: [(0, '21.472')]
+[2024-07-04 18:12:35,094][04781] Updated weights for policy 0, policy_version 900 (0.0013)
+[2024-07-04 18:12:37,247][04781] Updated weights for policy 0, policy_version 910 (0.0013)
+[2024-07-04 18:12:38,531][02159] Fps is (10 sec: 19236.8, 60 sec: 19317.1, 300 sec: 19240.0). Total num frames: 3751936. Throughput: 0: 4812.4. Samples: 931858. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:12:38,536][02159] Avg episode reward: [(0, '21.460')]
+[2024-07-04 18:12:39,358][04781] Updated weights for policy 0, policy_version 920 (0.0012)
+[2024-07-04 18:12:41,534][04781] Updated weights for policy 0, policy_version 930 (0.0013)
+[2024-07-04 18:12:43,523][02159] Fps is (10 sec: 18841.6, 60 sec: 19182.9, 300 sec: 19210.2). Total num frames: 3842048. Throughput: 0: 4783.5. Samples: 960130. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-04 18:12:43,526][02159] Avg episode reward: [(0, '22.188')]
+[2024-07-04 18:12:43,788][04781] Updated weights for policy 0, policy_version 940 (0.0013)
+[2024-07-04 18:12:45,848][04781] Updated weights for policy 0, policy_version 950 (0.0012)
+[2024-07-04 18:12:47,986][04781] Updated weights for policy 0, policy_version 960 (0.0012)
+[2024-07-04 18:12:48,524][02159] Fps is (10 sec: 18855.5, 60 sec: 19251.2, 300 sec: 19221.2). Total num frames: 3940352. Throughput: 0: 4797.9. Samples: 974678. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-07-04 18:12:48,526][02159] Avg episode reward: [(0, '19.636')]
+[2024-07-04 18:12:50,105][04781] Updated weights for policy 0, policy_version 970 (0.0013)
+[2024-07-04 18:12:51,811][04768] Stopping Batcher_0...
+[2024-07-04 18:12:51,811][02159] Component Batcher_0 stopped!
+[2024-07-04 18:12:51,811][04768] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-07-04 18:12:51,813][04768] Loop batcher_evt_loop terminating...
+[2024-07-04 18:12:51,829][04785] Stopping RolloutWorker_w2...
+[2024-07-04 18:12:51,829][04785] Loop rollout_proc2_evt_loop terminating...
+[2024-07-04 18:12:51,830][04789] Stopping RolloutWorker_w7...
+[2024-07-04 18:12:51,830][04786] Stopping RolloutWorker_w3...
+[2024-07-04 18:12:51,830][04789] Loop rollout_proc7_evt_loop terminating...
+[2024-07-04 18:12:51,830][04782] Stopping RolloutWorker_w0...
+[2024-07-04 18:12:51,830][04786] Loop rollout_proc3_evt_loop terminating...
+[2024-07-04 18:12:51,831][04787] Stopping RolloutWorker_w5...
+[2024-07-04 18:12:51,829][02159] Component RolloutWorker_w2 stopped!
+[2024-07-04 18:12:51,831][04787] Loop rollout_proc5_evt_loop terminating...
+[2024-07-04 18:12:51,832][04784] Stopping RolloutWorker_w4...
+[2024-07-04 18:12:51,831][04782] Loop rollout_proc0_evt_loop terminating...
+[2024-07-04 18:12:51,832][04784] Loop rollout_proc4_evt_loop terminating...
+[2024-07-04 18:12:51,832][04781] Weights refcount: 2 0
+[2024-07-04 18:12:51,832][04783] Stopping RolloutWorker_w1...
+[2024-07-04 18:12:51,833][04788] Stopping RolloutWorker_w6...
+[2024-07-04 18:12:51,833][04783] Loop rollout_proc1_evt_loop terminating...
+[2024-07-04 18:12:51,833][04788] Loop rollout_proc6_evt_loop terminating...
+[2024-07-04 18:12:51,832][02159] Component RolloutWorker_w7 stopped!
+[2024-07-04 18:12:51,834][04781] Stopping InferenceWorker_p0-w0...
+[2024-07-04 18:12:51,834][04781] Loop inference_proc0-0_evt_loop terminating...
+[2024-07-04 18:12:51,834][02159] Component RolloutWorker_w3 stopped!
+[2024-07-04 18:12:51,835][02159] Component RolloutWorker_w0 stopped!
+[2024-07-04 18:12:51,837][02159] Component RolloutWorker_w5 stopped!
+[2024-07-04 18:12:51,839][02159] Component RolloutWorker_w4 stopped!
+[2024-07-04 18:12:51,840][02159] Component RolloutWorker_w1 stopped!
+[2024-07-04 18:12:51,842][02159] Component RolloutWorker_w6 stopped!
+[2024-07-04 18:12:51,844][02159] Component InferenceWorker_p0-w0 stopped!
+[2024-07-04 18:12:51,891][04768] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-07-04 18:12:52,016][04768] Stopping LearnerWorker_p0...
+[2024-07-04 18:12:52,017][04768] Loop learner_proc0_evt_loop terminating...
+[2024-07-04 18:12:52,017][02159] Component LearnerWorker_p0 stopped!
+[2024-07-04 18:12:52,019][02159] Waiting for process learner_proc0 to stop...
+[2024-07-04 18:12:52,805][02159] Waiting for process inference_proc0-0 to join...
+[2024-07-04 18:12:52,807][02159] Waiting for process rollout_proc0 to join...
+[2024-07-04 18:12:52,809][02159] Waiting for process rollout_proc1 to join...
+[2024-07-04 18:12:52,811][02159] Waiting for process rollout_proc2 to join...
+[2024-07-04 18:12:52,813][02159] Waiting for process rollout_proc3 to join...
+[2024-07-04 18:12:52,815][02159] Waiting for process rollout_proc4 to join...
+[2024-07-04 18:12:52,817][02159] Waiting for process rollout_proc5 to join...
+[2024-07-04 18:12:52,818][02159] Waiting for process rollout_proc6 to join...
+[2024-07-04 18:12:52,820][02159] Waiting for process rollout_proc7 to join...
+[2024-07-04 18:12:52,822][02159] Batcher 0 profile tree view:
+batching: 16.0773, releasing_batches: 0.0238
+[2024-07-04 18:12:52,823][02159] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0001
+  wait_policy_total: 3.8893
+update_model: 3.4935
+  weight_update: 0.0013
+one_step: 0.0030
+  handle_policy_step: 194.0125
+    deserialize: 7.8810, stack: 1.2906, obs_to_device_normalize: 45.2995, forward: 95.6950, send_messages: 13.1087
+    prepare_outputs: 22.0335
+      to_cpu: 13.1896
+[2024-07-04 18:12:52,824][02159] Learner 0 profile tree view:
+misc: 0.0049, prepare_batch: 6.6491
+train: 18.5372
+  epoch_init: 0.0056, minibatch_init: 0.0063, losses_postprocess: 0.4912, kl_divergence: 0.3722, after_optimizer: 2.0643
+  calculate_losses: 8.6103
+    losses_init: 0.0036, forward_head: 0.6840, bptt_initial: 4.5650, tail: 0.6411, advantages_returns: 0.1587, losses: 1.1995
+    bptt: 1.1848
+      bptt_forward_core: 1.1282
+  update: 6.6508
+    clip: 0.7339
+[2024-07-04 18:12:52,826][02159] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.1520, enqueue_policy_requests: 7.1947, env_step: 135.8228, overhead: 6.3251, complete_rollouts: 0.2324
+save_policy_outputs: 8.8245
+  split_output_tensors: 3.5413
+[2024-07-04 18:12:52,828][02159] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.1523, enqueue_policy_requests: 7.1059, env_step: 135.8799, overhead: 6.2706, complete_rollouts: 0.2327
+save_policy_outputs: 8.8091
+  split_output_tensors: 3.5261
+[2024-07-04 18:12:52,829][02159] Loop Runner_EvtLoop terminating...
+[2024-07-04 18:12:52,831][02159] Runner profile tree view:
+main_loop: 220.1254
+[2024-07-04 18:12:52,832][02159] Collected {0: 4005888}, FPS: 18198.2
+[2024-07-04 18:15:16,827][02159] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-07-04 18:15:16,829][02159] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-07-04 18:15:16,830][02159] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-07-04 18:15:16,831][02159] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-07-04 18:15:16,832][02159] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-07-04 18:15:16,835][02159] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-07-04 18:15:16,836][02159] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-07-04 18:15:16,837][02159] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-07-04 18:15:16,838][02159] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-07-04 18:15:16,839][02159] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-07-04 18:15:16,841][02159] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-07-04 18:15:16,842][02159] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-07-04 18:15:16,843][02159] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-07-04 18:15:16,845][02159] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-07-04 18:15:16,845][02159] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-07-04 18:15:16,874][02159] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-04 18:15:16,877][02159] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-04 18:15:16,880][02159] RunningMeanStd input shape: (1,)
+[2024-07-04 18:15:16,895][02159] ConvEncoder: input_channels=3
+[2024-07-04 18:15:17,010][02159] Conv encoder output size: 512
+[2024-07-04 18:15:17,013][02159] Policy head output size: 512
+[2024-07-04 18:15:17,168][02159] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-07-04 18:15:17,926][02159] Num frames 100...
+[2024-07-04 18:15:18,058][02159] Num frames 200...
+[2024-07-04 18:15:18,211][02159] Num frames 300...
+[2024-07-04 18:15:18,341][02159] Num frames 400...
+[2024-07-04 18:15:18,418][02159] Avg episode rewards: #0: 5.160, true rewards: #0: 4.160
+[2024-07-04 18:15:18,420][02159] Avg episode reward: 5.160, avg true_objective: 4.160
+[2024-07-04 18:15:18,528][02159] Num frames 500...
+[2024-07-04 18:15:18,655][02159] Num frames 600...
+[2024-07-04 18:15:18,779][02159] Num frames 700...
+[2024-07-04 18:15:18,907][02159] Num frames 800...
+[2024-07-04 18:15:19,032][02159] Num frames 900...
+[2024-07-04 18:15:19,161][02159] Avg episode rewards: #0: 7.300, true rewards: #0: 4.800
+[2024-07-04 18:15:19,162][02159] Avg episode reward: 7.300, avg true_objective: 4.800
+[2024-07-04 18:15:19,216][02159] Num frames 1000...
+[2024-07-04 18:15:19,342][02159] Num frames 1100...
+[2024-07-04 18:15:19,470][02159] Num frames 1200...
+[2024-07-04 18:15:19,599][02159] Num frames 1300...
+[2024-07-04 18:15:19,728][02159] Num frames 1400...
+[2024-07-04 18:15:19,857][02159] Num frames 1500...
+[2024-07-04 18:15:19,984][02159] Num frames 1600...
+[2024-07-04 18:15:20,112][02159] Num frames 1700...
+[2024-07-04 18:15:20,238][02159] Num frames 1800...
+[2024-07-04 18:15:20,365][02159] Num frames 1900...
+[2024-07-04 18:15:20,493][02159] Num frames 2000...
+[2024-07-04 18:15:20,622][02159] Num frames 2100...
+[2024-07-04 18:15:20,751][02159] Num frames 2200...
+[2024-07-04 18:15:20,879][02159] Num frames 2300...
+[2024-07-04 18:15:20,939][02159] Avg episode rewards: #0: 14.347, true rewards: #0: 7.680
+[2024-07-04 18:15:20,940][02159] Avg episode reward: 14.347, avg true_objective: 7.680
+[2024-07-04 18:15:21,061][02159] Num frames 2400...
+[2024-07-04 18:15:21,188][02159] Num frames 2500...
+[2024-07-04 18:15:21,316][02159] Num frames 2600...
+[2024-07-04 18:15:21,442][02159] Num frames 2700...
+[2024-07-04 18:15:21,571][02159] Num frames 2800...
+[2024-07-04 18:15:21,701][02159] Num frames 2900...
+[2024-07-04 18:15:21,828][02159] Num frames 3000...
+[2024-07-04 18:15:21,954][02159] Num frames 3100...
+[2024-07-04 18:15:22,089][02159] Num frames 3200...
+[2024-07-04 18:15:22,189][02159] Avg episode rewards: #0: 14.830, true rewards: #0: 8.080
+[2024-07-04 18:15:22,190][02159] Avg episode reward: 14.830, avg true_objective: 8.080
+[2024-07-04 18:15:22,281][02159] Num frames 3300...
+[2024-07-04 18:15:22,410][02159] Num frames 3400...
+[2024-07-04 18:15:22,538][02159] Num frames 3500...
+[2024-07-04 18:15:22,666][02159] Num frames 3600...
+[2024-07-04 18:15:22,795][02159] Num frames 3700...
+[2024-07-04 18:15:22,927][02159] Num frames 3800...
+[2024-07-04 18:15:23,057][02159] Num frames 3900...
+[2024-07-04 18:15:23,190][02159] Num frames 4000...
+[2024-07-04 18:15:23,313][02159] Avg episode rewards: #0: 15.902, true rewards: #0: 8.102
+[2024-07-04 18:15:23,314][02159] Avg episode reward: 15.902, avg true_objective: 8.102
+[2024-07-04 18:15:23,385][02159] Num frames 4100...
+[2024-07-04 18:15:23,521][02159] Num frames 4200...
+[2024-07-04 18:15:23,657][02159] Num frames 4300...
+[2024-07-04 18:15:23,791][02159] Num frames 4400...
+[2024-07-04 18:15:23,927][02159] Num frames 4500...
+[2024-07-04 18:15:24,061][02159] Num frames 4600...
+[2024-07-04 18:15:24,195][02159] Num frames 4700...
+[2024-07-04 18:15:24,328][02159] Num frames 4800...
+[2024-07-04 18:15:24,461][02159] Num frames 4900...
+[2024-07-04 18:15:24,595][02159] Num frames 5000...
+[2024-07-04 18:15:24,783][02159] Avg episode rewards: #0: 16.792, true rewards: #0: 8.458
+[2024-07-04 18:15:24,785][02159] Avg episode reward: 16.792, avg true_objective: 8.458
+[2024-07-04 18:15:24,823][02159] Num frames 5100...
+[2024-07-04 18:15:24,948][02159] Num frames 5200...
+[2024-07-04 18:15:25,074][02159] Num frames 5300...
+[2024-07-04 18:15:25,200][02159] Num frames 5400...
+[2024-07-04 18:15:25,325][02159] Num frames 5500...
+[2024-07-04 18:15:25,455][02159] Num frames 5600...
+[2024-07-04 18:15:25,583][02159] Num frames 5700...
+[2024-07-04 18:15:25,710][02159] Num frames 5800...
+[2024-07-04 18:15:25,860][02159] Avg episode rewards: #0: 16.393, true rewards: #0: 8.393
+[2024-07-04 18:15:25,862][02159] Avg episode reward: 16.393, avg true_objective: 8.393
+[2024-07-04 18:15:25,896][02159] Num frames 5900...
+[2024-07-04 18:15:26,024][02159] Num frames 6000...
+[2024-07-04 18:15:26,152][02159] Num frames 6100...
+[2024-07-04 18:15:26,281][02159] Num frames 6200...
+[2024-07-04 18:15:26,408][02159] Num frames 6300...
+[2024-07-04 18:15:26,533][02159] Num frames 6400...
+[2024-07-04 18:15:26,659][02159] Num frames 6500...
+[2024-07-04 18:15:26,786][02159] Num frames 6600...
+[2024-07-04 18:15:26,879][02159] Avg episode rewards: #0: 16.161, true rewards: #0: 8.286
+[2024-07-04 18:15:26,880][02159] Avg episode reward: 16.161, avg true_objective: 8.286
+[2024-07-04 18:15:26,969][02159] Num frames 6700...
+[2024-07-04 18:15:27,096][02159] Num frames 6800...
+[2024-07-04 18:15:27,227][02159] Num frames 6900...
+[2024-07-04 18:15:27,355][02159] Num frames 7000...
+[2024-07-04 18:15:27,480][02159] Num frames 7100...
+[2024-07-04 18:15:27,607][02159] Num frames 7200...
+[2024-07-04 18:15:27,732][02159] Num frames 7300...
+[2024-07-04 18:15:27,790][02159] Avg episode rewards: #0: 15.779, true rewards: #0: 8.112
+[2024-07-04 18:15:27,791][02159] Avg episode reward: 15.779, avg true_objective: 8.112
+[2024-07-04 18:15:27,916][02159] Num frames 7400...
+[2024-07-04 18:15:28,044][02159] Num frames 7500...
+[2024-07-04 18:15:28,168][02159] Num frames 7600...
+[2024-07-04 18:15:28,298][02159] Num frames 7700...
+[2024-07-04 18:15:28,427][02159] Num frames 7800...
+[2024-07-04 18:15:28,559][02159] Num frames 7900...
+[2024-07-04 18:15:28,686][02159] Num frames 8000...
+[2024-07-04 18:15:28,816][02159] Num frames 8100...
+[2024-07-04 18:15:28,946][02159] Num frames 8200...
+[2024-07-04 18:15:29,073][02159] Num frames 8300...
+[2024-07-04 18:15:29,201][02159] Avg episode rewards: #0: 16.757, true rewards: #0: 8.357
+[2024-07-04 18:15:29,202][02159] Avg episode reward: 16.757, avg true_objective: 8.357
+[2024-07-04 18:15:49,147][02159] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-07-04 18:23:54,057][02159] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-07-04 18:23:54,059][02159] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-07-04 18:23:54,059][02159] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-07-04 18:23:54,061][02159] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-07-04 18:23:54,062][02159] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-07-04 18:23:54,064][02159] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-07-04 18:23:54,066][02159] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-07-04 18:23:54,067][02159] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-07-04 18:23:54,069][02159] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-07-04 18:23:54,070][02159] Adding new argument 'hf_repository'='Hamze-Hammami/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-07-04 18:23:54,071][02159] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-07-04 18:23:54,073][02159] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-07-04 18:23:54,075][02159] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-07-04 18:23:54,076][02159] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-07-04 18:23:54,078][02159] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-07-04 18:23:54,103][02159] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-04 18:23:54,105][02159] RunningMeanStd input shape: (1,)
+[2024-07-04 18:23:54,117][02159] ConvEncoder: input_channels=3
+[2024-07-04 18:23:54,156][02159] Conv encoder output size: 512
+[2024-07-04 18:23:54,157][02159] Policy head output size: 512
+[2024-07-04 18:23:54,176][02159] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-07-04 18:23:54,591][02159] Num frames 100...
+[2024-07-04 18:23:54,722][02159] Num frames 200...
+[2024-07-04 18:23:54,849][02159] Num frames 300...
+[2024-07-04 18:23:55,017][02159] Avg episode rewards: #0: 8.900, true rewards: #0: 3.900
+[2024-07-04 18:23:55,018][02159] Avg episode reward: 8.900, avg true_objective: 3.900
+[2024-07-04 18:23:55,033][02159] Num frames 400...
+[2024-07-04 18:23:55,163][02159] Num frames 500...
+[2024-07-04 18:23:55,291][02159] Num frames 600...
+[2024-07-04 18:23:55,420][02159] Num frames 700...
+[2024-07-04 18:23:55,556][02159] Num frames 800...
+[2024-07-04 18:23:55,619][02159] Avg episode rewards: #0: 10.530, true rewards: #0: 4.030
+[2024-07-04 18:23:55,621][02159] Avg episode reward: 10.530, avg true_objective: 4.030
+[2024-07-04 18:23:55,742][02159] Num frames 900...
+[2024-07-04 18:23:55,873][02159] Num frames 1000...
+[2024-07-04 18:23:56,002][02159] Num frames 1100...
+[2024-07-04 18:23:56,175][02159] Avg episode rewards: #0: 9.300, true rewards: #0: 3.967
+[2024-07-04 18:23:56,177][02159] Avg episode reward: 9.300, avg true_objective: 3.967
+[2024-07-04 18:23:56,193][02159] Num frames 1200...
+[2024-07-04 18:23:56,328][02159] Num frames 1300...
+[2024-07-04 18:23:56,463][02159] Num frames 1400...
+[2024-07-04 18:23:56,596][02159] Num frames 1500...
+[2024-07-04 18:23:56,711][02159] Avg episode rewards: #0: 8.868, true rewards: #0: 3.867
+[2024-07-04 18:23:56,712][02159] Avg episode reward: 8.868, avg true_objective: 3.867
+[2024-07-04 18:23:56,787][02159] Num frames 1600...
+[2024-07-04 18:23:56,924][02159] Num frames 1700...
+[2024-07-04 18:23:57,059][02159] Num frames 1800...
+[2024-07-04 18:23:57,194][02159] Num frames 1900...
+[2024-07-04 18:23:57,329][02159] Num frames 2000...
+[2024-07-04 18:23:57,458][02159] Avg episode rewards: #0: 8.910, true rewards: #0: 4.110
+[2024-07-04 18:23:57,460][02159] Avg episode reward: 8.910, avg true_objective: 4.110
+[2024-07-04 18:23:57,521][02159] Num frames 2100...
+[2024-07-04 18:23:57,657][02159] Num frames 2200...
+[2024-07-04 18:23:57,793][02159] Num frames 2300...
+[2024-07-04 18:23:57,923][02159] Num frames 2400...
+[2024-07-04 18:23:58,052][02159] Num frames 2500...
+[2024-07-04 18:23:58,178][02159] Num frames 2600...
+[2024-07-04 18:23:58,305][02159] Num frames 2700...
+[2024-07-04 18:23:58,424][02159] Avg episode rewards: #0: 9.418, true rewards: #0: 4.585
+[2024-07-04 18:23:58,426][02159] Avg episode reward: 9.418, avg true_objective: 4.585
+[2024-07-04 18:23:58,489][02159] Num frames 2800...
+[2024-07-04 18:23:58,616][02159] Num frames 2900...
+[2024-07-04 18:23:58,743][02159] Num frames 3000...
+[2024-07-04 18:23:58,879][02159] Num frames 3100...
+[2024-07-04 18:23:59,008][02159] Num frames 3200...
+[2024-07-04 18:23:59,139][02159] Num frames 3300...
+[2024-07-04 18:23:59,266][02159] Num frames 3400...
+[2024-07-04 18:23:59,393][02159] Num frames 3500...
+[2024-07-04 18:23:59,452][02159] Avg episode rewards: #0: 10.576, true rewards: #0: 5.004
+[2024-07-04 18:23:59,454][02159] Avg episode reward: 10.576, avg true_objective: 5.004
+[2024-07-04 18:23:59,580][02159] Num frames 3600...
+[2024-07-04 18:23:59,706][02159] Num frames 3700...
+[2024-07-04 18:23:59,834][02159] Num frames 3800...
+[2024-07-04 18:23:59,966][02159] Avg episode rewards: #0: 9.825, true rewards: #0: 4.825
+[2024-07-04 18:23:59,968][02159] Avg episode reward: 9.825, avg true_objective: 4.825
+[2024-07-04 18:24:00,022][02159] Num frames 3900...
+[2024-07-04 18:24:00,147][02159] Num frames 4000...
+[2024-07-04 18:24:00,274][02159] Num frames 4100...
+[2024-07-04 18:24:00,404][02159] Num frames 4200...
+[2024-07-04 18:24:00,533][02159] Num frames 4300...
+[2024-07-04 18:24:00,659][02159] Num frames 4400...
+[2024-07-04 18:24:00,786][02159] Num frames 4500...
+[2024-07-04 18:24:00,912][02159] Num frames 4600...
+[2024-07-04 18:24:01,041][02159] Num frames 4700...
+[2024-07-04 18:24:01,168][02159] Num frames 4800...
+[2024-07-04 18:24:01,296][02159] Num frames 4900...
+[2024-07-04 18:24:01,425][02159] Num frames 5000...
+[2024-07-04 18:24:01,550][02159] Num frames 5100...
+[2024-07-04 18:24:01,679][02159] Num frames 5200...
+[2024-07-04 18:24:01,806][02159] Num frames 5300...
+[2024-07-04 18:24:01,935][02159] Num frames 5400...
+[2024-07-04 18:24:02,005][02159] Avg episode rewards: #0: 13.123, true rewards: #0: 6.012
+[2024-07-04 18:24:02,007][02159] Avg episode reward: 13.123, avg true_objective: 6.012
+[2024-07-04 18:24:02,124][02159] Num frames 5500...
+[2024-07-04 18:24:02,255][02159] Num frames 5600...
+[2024-07-04 18:24:02,385][02159] Num frames 5700...
+[2024-07-04 18:24:02,515][02159] Num frames 5800...
+[2024-07-04 18:24:02,641][02159] Num frames 5900...
+[2024-07-04 18:24:02,768][02159] Num frames 6000...
+[2024-07-04 18:24:02,898][02159] Num frames 6100...
+[2024-07-04 18:24:03,030][02159] Num frames 6200...
+[2024-07-04 18:24:03,158][02159] Num frames 6300...
+[2024-07-04 18:24:03,287][02159] Num frames 6400...
+[2024-07-04 18:24:03,413][02159] Num frames 6500...
+[2024-07-04 18:24:03,544][02159] Num frames 6600...
+[2024-07-04 18:24:03,672][02159] Num frames 6700...
+[2024-07-04 18:24:03,799][02159] Num frames 6800...
+[2024-07-04 18:24:03,927][02159] Num frames 6900...
+[2024-07-04 18:24:04,056][02159] Num frames 7000...
+[2024-07-04 18:24:04,183][02159] Num frames 7100...
+[2024-07-04 18:24:04,316][02159] Num frames 7200...
+[2024-07-04 18:24:04,448][02159] Num frames 7300...
+[2024-07-04 18:24:04,587][02159] Avg episode rewards: #0: 16.463, true rewards: #0: 7.363
+[2024-07-04 18:24:04,588][02159] Avg episode reward: 16.463, avg true_objective: 7.363
+[2024-07-04 18:24:22,135][02159] Replay video saved to /content/train_dir/default_experiment/replay.mp4!