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.1726414432.49d3274c343a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67120ee05b4af9cd2a3e96139d9f3ada1cfd25287ddd7a48feb39a9d20c830ab
+size 223143

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: 6.05 +/- 2.60
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
+
+This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
+Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+
+
+## Downloading the model
+
+After installing Sample-Factory, download the model with:
+```
+python -m sample_factory.huggingface.load_from_hub -r Vivek-huggingface/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_000000932_3817472_reward_7.084.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749e55fef00b37d162017e0ed5a3eb2c42d2c16f3fb78df4608e8198c8040db3
+size 34929051

checkpoint_p0/checkpoint_000000976_3997696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9681c5fb6925d00ba66825b89cb336baf292a837aa8fb20361ac2674c4950fce
+size 34929541

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d62f07d27427f768cc06f1f621baa9933f31dc0ccdf01867af3aa645a6c1e8
+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 sha256:910ae076c99657c6fcbb0ccbd44cf8d1bba812acf4958d5b8b9e89fbef2b677e
+size 9568434

sf_log.txt

@@ -0,0 +1,619 @@
+[2024-09-15 15:33:57,678][00283] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-09-15 15:33:57,680][00283] Rollout worker 0 uses device cpu
+[2024-09-15 15:33:57,681][00283] Rollout worker 1 uses device cpu
+[2024-09-15 15:33:57,683][00283] Rollout worker 2 uses device cpu
+[2024-09-15 15:33:57,684][00283] Rollout worker 3 uses device cpu
+[2024-09-15 15:33:57,686][00283] Rollout worker 4 uses device cpu
+[2024-09-15 15:33:57,687][00283] Rollout worker 5 uses device cpu
+[2024-09-15 15:33:57,689][00283] Rollout worker 6 uses device cpu
+[2024-09-15 15:33:57,690][00283] Rollout worker 7 uses device cpu
+[2024-09-15 15:33:57,816][00283] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-15 15:33:57,817][00283] InferenceWorker_p0-w0: min num requests: 2
+[2024-09-15 15:33:57,849][00283] Starting all processes...
+[2024-09-15 15:33:57,850][00283] Starting process learner_proc0
+[2024-09-15 15:33:58,582][00283] Starting all processes...
+[2024-09-15 15:33:58,587][00283] Starting process inference_proc0-0
+[2024-09-15 15:33:58,588][00283] Starting process rollout_proc0
+[2024-09-15 15:33:58,588][00283] Starting process rollout_proc1
+[2024-09-15 15:33:58,589][00283] Starting process rollout_proc2
+[2024-09-15 15:33:58,590][00283] Starting process rollout_proc3
+[2024-09-15 15:33:58,602][00283] Starting process rollout_proc4
+[2024-09-15 15:33:58,605][00283] Starting process rollout_proc5
+[2024-09-15 15:33:58,606][00283] Starting process rollout_proc6
+[2024-09-15 15:33:58,607][00283] Starting process rollout_proc7
+[2024-09-15 15:34:00,971][00927] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-15 15:34:01,283][00924] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-15 15:34:01,380][00922] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-15 15:34:01,482][00920] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-15 15:34:01,482][00920] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-09-15 15:34:01,497][00920] Num visible devices: 1
+[2024-09-15 15:34:01,497][00905] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-15 15:34:01,497][00905] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-09-15 15:34:01,515][00905] Num visible devices: 1
+[2024-09-15 15:34:01,516][00925] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-15 15:34:01,539][00905] Starting seed is not provided
+[2024-09-15 15:34:01,540][00905] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-15 15:34:01,540][00905] Initializing actor-critic model on device cuda:0
+[2024-09-15 15:34:01,540][00905] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-15 15:34:01,544][00905] RunningMeanStd input shape: (1,)
+[2024-09-15 15:34:01,565][00905] ConvEncoder: input_channels=3
+[2024-09-15 15:34:01,604][00919] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-15 15:34:01,649][00923] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-15 15:34:01,649][00921] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-15 15:34:01,682][00926] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-09-15 15:34:01,850][00905] Conv encoder output size: 512
+[2024-09-15 15:34:01,851][00905] Policy head output size: 512
+[2024-09-15 15:34:01,915][00905] Created Actor Critic model with architecture:
+[2024-09-15 15:34:01,915][00905] 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)
+  )
+)
+[2024-09-15 15:34:02,226][00905] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-09-15 15:34:02,893][00905] No checkpoints found
+[2024-09-15 15:34:02,893][00905] Did not load from checkpoint, starting from scratch!
+[2024-09-15 15:34:02,893][00905] Initialized policy 0 weights for model version 0
+[2024-09-15 15:34:02,898][00905] LearnerWorker_p0 finished initialization!
+[2024-09-15 15:34:02,898][00905] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-15 15:34:02,973][00920] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-15 15:34:02,974][00920] RunningMeanStd input shape: (1,)
+[2024-09-15 15:34:02,986][00920] ConvEncoder: input_channels=3
+[2024-09-15 15:34:03,094][00920] Conv encoder output size: 512
+[2024-09-15 15:34:03,094][00920] Policy head output size: 512
+[2024-09-15 15:34:03,147][00283] Inference worker 0-0 is ready!
+[2024-09-15 15:34:03,149][00283] All inference workers are ready! Signal rollout workers to start!
+[2024-09-15 15:34:03,181][00919] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:34:03,181][00926] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:34:03,182][00921] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:34:03,182][00922] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:34:03,201][00925] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:34:03,201][00927] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:34:03,202][00923] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:34:03,202][00924] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:34:03,610][00925] Decorrelating experience for 0 frames...
+[2024-09-15 15:34:03,610][00921] Decorrelating experience for 0 frames...
+[2024-09-15 15:34:03,610][00924] Decorrelating experience for 0 frames...
+[2024-09-15 15:34:03,610][00922] Decorrelating experience for 0 frames...
+[2024-09-15 15:34:03,610][00926] Decorrelating experience for 0 frames...
+[2024-09-15 15:34:03,879][00922] Decorrelating experience for 32 frames...
+[2024-09-15 15:34:03,879][00925] Decorrelating experience for 32 frames...
+[2024-09-15 15:34:03,881][00923] Decorrelating experience for 0 frames...
+[2024-09-15 15:34:03,881][00924] Decorrelating experience for 32 frames...
+[2024-09-15 15:34:03,886][00926] Decorrelating experience for 32 frames...
+[2024-09-15 15:34:03,989][00927] Decorrelating experience for 0 frames...
+[2024-09-15 15:34:03,995][00921] Decorrelating experience for 32 frames...
+[2024-09-15 15:34:04,123][00923] Decorrelating experience for 32 frames...
+[2024-09-15 15:34:04,203][00924] Decorrelating experience for 64 frames...
+[2024-09-15 15:34:04,235][00925] Decorrelating experience for 64 frames...
+[2024-09-15 15:34:04,241][00927] Decorrelating experience for 32 frames...
+[2024-09-15 15:34:04,242][00922] Decorrelating experience for 64 frames...
+[2024-09-15 15:34:04,347][00921] Decorrelating experience for 64 frames...
+[2024-09-15 15:34:04,453][00926] Decorrelating experience for 64 frames...
+[2024-09-15 15:34:04,497][00923] Decorrelating experience for 64 frames...
+[2024-09-15 15:34:04,509][00924] Decorrelating experience for 96 frames...
+[2024-09-15 15:34:04,548][00922] Decorrelating experience for 96 frames...
+[2024-09-15 15:34:04,551][00925] Decorrelating experience for 96 frames...
+[2024-09-15 15:34:04,653][00921] Decorrelating experience for 96 frames...
+[2024-09-15 15:34:04,749][00927] Decorrelating experience for 64 frames...
+[2024-09-15 15:34:04,762][00926] Decorrelating experience for 96 frames...
+[2024-09-15 15:34:04,941][00923] Decorrelating experience for 96 frames...
+[2024-09-15 15:34:05,025][00927] Decorrelating experience for 96 frames...
+[2024-09-15 15:34:07,213][00905] Signal inference workers to stop experience collection...
+[2024-09-15 15:34:07,218][00920] InferenceWorker_p0-w0: stopping experience collection
+[2024-09-15 15:34:07,575][00283] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 32. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-09-15 15:34:07,576][00283] Avg episode reward: [(0, '2.837')]
+[2024-09-15 15:34:10,276][00905] Signal inference workers to resume experience collection...
+[2024-09-15 15:34:10,276][00920] InferenceWorker_p0-w0: resuming experience collection
+[2024-09-15 15:34:12,406][00920] Updated weights for policy 0, policy_version 10 (0.0149)
+[2024-09-15 15:34:12,575][00283] Fps is (10 sec: 8191.8, 60 sec: 8191.8, 300 sec: 8191.8). Total num frames: 40960. Throughput: 0: 1940.4. Samples: 9734. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:34:12,578][00283] Avg episode reward: [(0, '4.224')]
+[2024-09-15 15:34:14,647][00920] Updated weights for policy 0, policy_version 20 (0.0013)
+[2024-09-15 15:34:16,934][00920] Updated weights for policy 0, policy_version 30 (0.0013)
+[2024-09-15 15:34:17,575][00283] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13107.2). Total num frames: 131072. Throughput: 0: 2320.8. Samples: 23240. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-15 15:34:17,578][00283] Avg episode reward: [(0, '4.536')]
+[2024-09-15 15:34:17,598][00905] Saving new best policy, reward=4.536!
+[2024-09-15 15:34:17,807][00283] Heartbeat connected on Batcher_0
+[2024-09-15 15:34:17,819][00283] Heartbeat connected on LearnerWorker_p0
+[2024-09-15 15:34:17,823][00283] Heartbeat connected on InferenceWorker_p0-w0
+[2024-09-15 15:34:17,829][00283] Heartbeat connected on RolloutWorker_w1
+[2024-09-15 15:34:17,832][00283] Heartbeat connected on RolloutWorker_w2
+[2024-09-15 15:34:17,835][00283] Heartbeat connected on RolloutWorker_w3
+[2024-09-15 15:34:17,838][00283] Heartbeat connected on RolloutWorker_w4
+[2024-09-15 15:34:17,841][00283] Heartbeat connected on RolloutWorker_w5
+[2024-09-15 15:34:17,847][00283] Heartbeat connected on RolloutWorker_w6
+[2024-09-15 15:34:17,849][00283] Heartbeat connected on RolloutWorker_w7
+[2024-09-15 15:34:19,189][00920] Updated weights for policy 0, policy_version 40 (0.0013)
+[2024-09-15 15:34:21,477][00920] Updated weights for policy 0, policy_version 50 (0.0013)
+[2024-09-15 15:34:22,575][00283] Fps is (10 sec: 18022.3, 60 sec: 14745.4, 300 sec: 14745.4). Total num frames: 221184. Throughput: 0: 3365.6. Samples: 50516. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-15 15:34:22,578][00283] Avg episode reward: [(0, '4.429')]
+[2024-09-15 15:34:23,765][00920] Updated weights for policy 0, policy_version 60 (0.0013)
+[2024-09-15 15:34:26,039][00920] Updated weights for policy 0, policy_version 70 (0.0012)
+[2024-09-15 15:34:27,575][00283] Fps is (10 sec: 18022.4, 60 sec: 15564.8, 300 sec: 15564.8). Total num frames: 311296. Throughput: 0: 3863.1. Samples: 77294. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-15 15:34:27,577][00283] Avg episode reward: [(0, '4.266')]
+[2024-09-15 15:34:28,301][00920] Updated weights for policy 0, policy_version 80 (0.0012)
+[2024-09-15 15:34:30,530][00920] Updated weights for policy 0, policy_version 90 (0.0013)
+[2024-09-15 15:34:32,575][00283] Fps is (10 sec: 18022.4, 60 sec: 16056.2, 300 sec: 16056.2). Total num frames: 401408. Throughput: 0: 3637.3. Samples: 90966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-15 15:34:32,578][00283] Avg episode reward: [(0, '4.535')]
+[2024-09-15 15:34:32,822][00920] Updated weights for policy 0, policy_version 100 (0.0012)
+[2024-09-15 15:34:35,134][00920] Updated weights for policy 0, policy_version 110 (0.0012)
+[2024-09-15 15:34:37,510][00920] Updated weights for policy 0, policy_version 120 (0.0012)
+[2024-09-15 15:34:37,575][00283] Fps is (10 sec: 18022.4, 60 sec: 16384.0, 300 sec: 16384.0). Total num frames: 491520. Throughput: 0: 3920.3. Samples: 117642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:34:37,577][00283] Avg episode reward: [(0, '4.584')]
+[2024-09-15 15:34:37,579][00905] Saving new best policy, reward=4.584!
+[2024-09-15 15:34:39,800][00920] Updated weights for policy 0, policy_version 130 (0.0013)
+[2024-09-15 15:34:42,005][00920] Updated weights for policy 0, policy_version 140 (0.0012)
+[2024-09-15 15:34:42,575][00283] Fps is (10 sec: 18022.6, 60 sec: 16618.0, 300 sec: 16618.0). Total num frames: 581632. Throughput: 0: 4126.6. Samples: 144462. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:34:42,578][00283] Avg episode reward: [(0, '4.717')]
+[2024-09-15 15:34:42,585][00905] Saving new best policy, reward=4.717!
+[2024-09-15 15:34:44,311][00920] Updated weights for policy 0, policy_version 150 (0.0012)
+[2024-09-15 15:34:46,504][00920] Updated weights for policy 0, policy_version 160 (0.0012)
+[2024-09-15 15:34:47,575][00283] Fps is (10 sec: 18022.3, 60 sec: 16793.6, 300 sec: 16793.6). Total num frames: 671744. Throughput: 0: 3951.4. Samples: 158088. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-09-15 15:34:47,577][00283] Avg episode reward: [(0, '4.565')]
+[2024-09-15 15:34:48,821][00920] Updated weights for policy 0, policy_version 170 (0.0012)
+[2024-09-15 15:34:51,101][00920] Updated weights for policy 0, policy_version 180 (0.0013)
+[2024-09-15 15:34:52,575][00283] Fps is (10 sec: 18022.4, 60 sec: 16930.1, 300 sec: 16930.1). Total num frames: 761856. Throughput: 0: 4111.9. Samples: 185068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:34:52,577][00283] Avg episode reward: [(0, '4.478')]
+[2024-09-15 15:34:53,382][00920] Updated weights for policy 0, policy_version 190 (0.0013)
+[2024-09-15 15:34:55,645][00920] Updated weights for policy 0, policy_version 200 (0.0012)
+[2024-09-15 15:34:57,575][00283] Fps is (10 sec: 18022.5, 60 sec: 17039.4, 300 sec: 17039.4). Total num frames: 851968. Throughput: 0: 4500.1. Samples: 212236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:34:57,578][00283] Avg episode reward: [(0, '4.743')]
+[2024-09-15 15:34:57,581][00905] Saving new best policy, reward=4.743!
+[2024-09-15 15:34:57,907][00920] Updated weights for policy 0, policy_version 210 (0.0012)
+[2024-09-15 15:35:00,155][00920] Updated weights for policy 0, policy_version 220 (0.0012)
+[2024-09-15 15:35:02,394][00920] Updated weights for policy 0, policy_version 230 (0.0012)
+[2024-09-15 15:35:02,575][00283] Fps is (10 sec: 18022.3, 60 sec: 17128.7, 300 sec: 17128.7). Total num frames: 942080. Throughput: 0: 4501.2. Samples: 225796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:35:02,578][00283] Avg episode reward: [(0, '4.534')]
+[2024-09-15 15:35:04,706][00920] Updated weights for policy 0, policy_version 240 (0.0013)
+[2024-09-15 15:35:07,015][00920] Updated weights for policy 0, policy_version 250 (0.0013)
+[2024-09-15 15:35:07,575][00283] Fps is (10 sec: 18022.3, 60 sec: 17203.2, 300 sec: 17203.2). Total num frames: 1032192. Throughput: 0: 4493.0. Samples: 252700. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:35:07,578][00283] Avg episode reward: [(0, '4.654')]
+[2024-09-15 15:35:09,271][00920] Updated weights for policy 0, policy_version 260 (0.0012)
+[2024-09-15 15:35:11,563][00920] Updated weights for policy 0, policy_version 270 (0.0013)
+[2024-09-15 15:35:12,575][00283] Fps is (10 sec: 18022.6, 60 sec: 18022.4, 300 sec: 17266.2). Total num frames: 1122304. Throughput: 0: 4500.6. Samples: 279820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:35:12,577][00283] Avg episode reward: [(0, '4.668')]
+[2024-09-15 15:35:13,812][00920] Updated weights for policy 0, policy_version 280 (0.0012)
+[2024-09-15 15:35:16,111][00920] Updated weights for policy 0, policy_version 290 (0.0013)
+[2024-09-15 15:35:17,575][00283] Fps is (10 sec: 18022.4, 60 sec: 18022.4, 300 sec: 17320.2). Total num frames: 1212416. Throughput: 0: 4496.8. Samples: 293320. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-15 15:35:17,578][00283] Avg episode reward: [(0, '4.511')]
+[2024-09-15 15:35:18,423][00920] Updated weights for policy 0, policy_version 300 (0.0012)
+[2024-09-15 15:35:20,740][00920] Updated weights for policy 0, policy_version 310 (0.0012)
+[2024-09-15 15:35:22,575][00283] Fps is (10 sec: 18022.3, 60 sec: 18022.4, 300 sec: 17367.0). Total num frames: 1302528. Throughput: 0: 4497.1. Samples: 320010. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:35:22,578][00283] Avg episode reward: [(0, '4.327')]
+[2024-09-15 15:35:22,966][00920] Updated weights for policy 0, policy_version 320 (0.0012)
+[2024-09-15 15:35:25,248][00920] Updated weights for policy 0, policy_version 330 (0.0012)
+[2024-09-15 15:35:27,497][00920] Updated weights for policy 0, policy_version 340 (0.0012)
+[2024-09-15 15:35:27,575][00283] Fps is (10 sec: 18022.4, 60 sec: 18022.4, 300 sec: 17408.0). Total num frames: 1392640. Throughput: 0: 4505.7. Samples: 347218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:35:27,577][00283] Avg episode reward: [(0, '4.523')]
+[2024-09-15 15:35:29,759][00920] Updated weights for policy 0, policy_version 350 (0.0012)
+[2024-09-15 15:35:32,112][00920] Updated weights for policy 0, policy_version 360 (0.0013)
+[2024-09-15 15:35:32,575][00283] Fps is (10 sec: 18022.4, 60 sec: 18022.4, 300 sec: 17444.1). Total num frames: 1482752. Throughput: 0: 4504.8. Samples: 360804. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-15 15:35:32,577][00283] Avg episode reward: [(0, '4.304')]
+[2024-09-15 15:35:34,357][00920] Updated weights for policy 0, policy_version 370 (0.0013)
+[2024-09-15 15:35:36,702][00920] Updated weights for policy 0, policy_version 380 (0.0013)
+[2024-09-15 15:35:37,575][00283] Fps is (10 sec: 17613.0, 60 sec: 17954.1, 300 sec: 17430.8). Total num frames: 1568768. Throughput: 0: 4493.7. Samples: 387284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:35:37,577][00283] Avg episode reward: [(0, '4.624')]
+[2024-09-15 15:35:38,950][00920] Updated weights for policy 0, policy_version 390 (0.0013)
+[2024-09-15 15:35:41,209][00920] Updated weights for policy 0, policy_version 400 (0.0012)
+[2024-09-15 15:35:42,575][00283] Fps is (10 sec: 18022.6, 60 sec: 18022.4, 300 sec: 17505.0). Total num frames: 1662976. Throughput: 0: 4493.3. Samples: 414436. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:35:42,578][00283] Avg episode reward: [(0, '4.489')]
+[2024-09-15 15:35:43,487][00920] Updated weights for policy 0, policy_version 410 (0.0012)
+[2024-09-15 15:35:45,822][00920] Updated weights for policy 0, policy_version 420 (0.0013)
+[2024-09-15 15:35:47,575][00283] Fps is (10 sec: 18022.2, 60 sec: 17954.1, 300 sec: 17489.9). Total num frames: 1748992. Throughput: 0: 4487.1. Samples: 427714. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-15 15:35:47,577][00283] Avg episode reward: [(0, '5.006')]
+[2024-09-15 15:35:47,580][00905] Saving new best policy, reward=5.006!
+[2024-09-15 15:35:48,125][00920] Updated weights for policy 0, policy_version 430 (0.0012)
+[2024-09-15 15:35:50,325][00920] Updated weights for policy 0, policy_version 440 (0.0012)
+[2024-09-15 15:35:52,575][00283] Fps is (10 sec: 17612.7, 60 sec: 17954.1, 300 sec: 17515.3). Total num frames: 1839104. Throughput: 0: 4491.3. Samples: 454810. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:35:52,577][00283] Avg episode reward: [(0, '4.720')]
+[2024-09-15 15:35:52,585][00905] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000449_1839104.pth...
+[2024-09-15 15:35:52,689][00920] Updated weights for policy 0, policy_version 450 (0.0012)
+[2024-09-15 15:35:54,893][00920] Updated weights for policy 0, policy_version 460 (0.0013)
+[2024-09-15 15:35:57,162][00920] Updated weights for policy 0, policy_version 470 (0.0012)
+[2024-09-15 15:35:57,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.1, 300 sec: 17538.3). Total num frames: 1929216. Throughput: 0: 4487.6. Samples: 481760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:35:57,577][00283] Avg episode reward: [(0, '4.500')]
+[2024-09-15 15:35:59,523][00920] Updated weights for policy 0, policy_version 480 (0.0012)
+[2024-09-15 15:36:01,794][00920] Updated weights for policy 0, policy_version 490 (0.0012)
+[2024-09-15 15:36:02,575][00283] Fps is (10 sec: 18022.3, 60 sec: 17954.2, 300 sec: 17559.4). Total num frames: 2019328. Throughput: 0: 4479.7. Samples: 494908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:36:02,578][00283] Avg episode reward: [(0, '4.667')]
+[2024-09-15 15:36:04,050][00920] Updated weights for policy 0, policy_version 500 (0.0013)
+[2024-09-15 15:36:06,281][00920] Updated weights for policy 0, policy_version 510 (0.0012)
+[2024-09-15 15:36:07,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.1, 300 sec: 17578.7). Total num frames: 2109440. Throughput: 0: 4493.8. Samples: 522230. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:36:07,578][00283] Avg episode reward: [(0, '4.579')]
+[2024-09-15 15:36:08,561][00920] Updated weights for policy 0, policy_version 520 (0.0012)
+[2024-09-15 15:36:10,832][00920] Updated weights for policy 0, policy_version 530 (0.0012)
+[2024-09-15 15:36:12,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.1, 300 sec: 17596.4). Total num frames: 2199552. Throughput: 0: 4486.7. Samples: 549120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-15 15:36:12,577][00283] Avg episode reward: [(0, '4.761')]
+[2024-09-15 15:36:13,176][00920] Updated weights for policy 0, policy_version 540 (0.0013)
+[2024-09-15 15:36:15,427][00920] Updated weights for policy 0, policy_version 550 (0.0013)
+[2024-09-15 15:36:17,575][00283] Fps is (10 sec: 18022.6, 60 sec: 17954.2, 300 sec: 17612.8). Total num frames: 2289664. Throughput: 0: 4483.1. Samples: 562544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:36:17,578][00283] Avg episode reward: [(0, '4.830')]
+[2024-09-15 15:36:17,672][00920] Updated weights for policy 0, policy_version 560 (0.0012)
+[2024-09-15 15:36:19,912][00920] Updated weights for policy 0, policy_version 570 (0.0012)
+[2024-09-15 15:36:22,200][00920] Updated weights for policy 0, policy_version 580 (0.0012)
+[2024-09-15 15:36:22,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.1, 300 sec: 17628.0). Total num frames: 2379776. Throughput: 0: 4501.6. Samples: 589858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-15 15:36:22,577][00283] Avg episode reward: [(0, '5.021')]
+[2024-09-15 15:36:22,585][00905] Saving new best policy, reward=5.021!
+[2024-09-15 15:36:24,500][00920] Updated weights for policy 0, policy_version 590 (0.0012)
+[2024-09-15 15:36:26,819][00920] Updated weights for policy 0, policy_version 600 (0.0012)
+[2024-09-15 15:36:27,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.2, 300 sec: 17642.1). Total num frames: 2469888. Throughput: 0: 4489.4. Samples: 616458. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:36:27,577][00283] Avg episode reward: [(0, '4.679')]
+[2024-09-15 15:36:29,114][00920] Updated weights for policy 0, policy_version 610 (0.0012)
+[2024-09-15 15:36:31,340][00920] Updated weights for policy 0, policy_version 620 (0.0012)
+[2024-09-15 15:36:32,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.1, 300 sec: 17655.2). Total num frames: 2560000. Throughput: 0: 4495.9. Samples: 630028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:36:32,577][00283] Avg episode reward: [(0, '4.972')]
+[2024-09-15 15:36:33,590][00920] Updated weights for policy 0, policy_version 630 (0.0013)
+[2024-09-15 15:36:35,849][00920] Updated weights for policy 0, policy_version 640 (0.0012)
+[2024-09-15 15:36:37,575][00283] Fps is (10 sec: 18022.3, 60 sec: 18022.4, 300 sec: 17667.4). Total num frames: 2650112. Throughput: 0: 4501.5. Samples: 657376. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:36:37,578][00283] Avg episode reward: [(0, '4.711')]
+[2024-09-15 15:36:38,199][00920] Updated weights for policy 0, policy_version 650 (0.0013)
+[2024-09-15 15:36:40,549][00920] Updated weights for policy 0, policy_version 660 (0.0013)
+[2024-09-15 15:36:42,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.1, 300 sec: 17678.9). Total num frames: 2740224. Throughput: 0: 4489.2. Samples: 683774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:36:42,578][00283] Avg episode reward: [(0, '5.622')]
+[2024-09-15 15:36:42,586][00905] Saving new best policy, reward=5.622!
+[2024-09-15 15:36:42,762][00920] Updated weights for policy 0, policy_version 670 (0.0013)
+[2024-09-15 15:36:45,053][00920] Updated weights for policy 0, policy_version 680 (0.0012)
+[2024-09-15 15:36:47,268][00920] Updated weights for policy 0, policy_version 690 (0.0012)
+[2024-09-15 15:36:47,575][00283] Fps is (10 sec: 18022.4, 60 sec: 18022.4, 300 sec: 17689.6). Total num frames: 2830336. Throughput: 0: 4501.4. Samples: 697472. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:36:47,577][00283] Avg episode reward: [(0, '5.687')]
+[2024-09-15 15:36:47,579][00905] Saving new best policy, reward=5.687!
+[2024-09-15 15:36:49,519][00920] Updated weights for policy 0, policy_version 700 (0.0013)
+[2024-09-15 15:36:51,813][00920] Updated weights for policy 0, policy_version 710 (0.0012)
+[2024-09-15 15:36:52,575][00283] Fps is (10 sec: 18022.4, 60 sec: 18022.4, 300 sec: 17699.7). Total num frames: 2920448. Throughput: 0: 4498.7. Samples: 724672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-15 15:36:52,578][00283] Avg episode reward: [(0, '5.521')]
+[2024-09-15 15:36:54,144][00920] Updated weights for policy 0, policy_version 720 (0.0013)
+[2024-09-15 15:36:56,428][00920] Updated weights for policy 0, policy_version 730 (0.0013)
+[2024-09-15 15:36:57,575][00283] Fps is (10 sec: 18022.3, 60 sec: 18022.4, 300 sec: 17709.2). Total num frames: 3010560. Throughput: 0: 4497.1. Samples: 751490. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-15 15:36:57,577][00283] Avg episode reward: [(0, '5.582')]
+[2024-09-15 15:36:58,639][00920] Updated weights for policy 0, policy_version 740 (0.0012)
+[2024-09-15 15:37:00,911][00920] Updated weights for policy 0, policy_version 750 (0.0012)
+[2024-09-15 15:37:02,575][00283] Fps is (10 sec: 18022.5, 60 sec: 18022.4, 300 sec: 17718.1). Total num frames: 3100672. Throughput: 0: 4504.9. Samples: 765266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-15 15:37:02,577][00283] Avg episode reward: [(0, '4.894')]
+[2024-09-15 15:37:03,194][00920] Updated weights for policy 0, policy_version 760 (0.0012)
+[2024-09-15 15:37:05,466][00920] Updated weights for policy 0, policy_version 770 (0.0013)
+[2024-09-15 15:37:07,575][00283] Fps is (10 sec: 17612.9, 60 sec: 17954.1, 300 sec: 17703.8). Total num frames: 3186688. Throughput: 0: 4488.7. Samples: 791850. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:37:07,578][00283] Avg episode reward: [(0, '5.259')]
+[2024-09-15 15:37:07,889][00920] Updated weights for policy 0, policy_version 780 (0.0013)
+[2024-09-15 15:37:10,133][00920] Updated weights for policy 0, policy_version 790 (0.0012)
+[2024-09-15 15:37:12,451][00920] Updated weights for policy 0, policy_version 800 (0.0012)
+[2024-09-15 15:37:12,575][00283] Fps is (10 sec: 17612.7, 60 sec: 17954.1, 300 sec: 17712.4). Total num frames: 3276800. Throughput: 0: 4490.4. Samples: 818526. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:37:12,578][00283] Avg episode reward: [(0, '5.193')]
+[2024-09-15 15:37:14,683][00920] Updated weights for policy 0, policy_version 810 (0.0012)
+[2024-09-15 15:37:16,951][00920] Updated weights for policy 0, policy_version 820 (0.0012)
+[2024-09-15 15:37:17,575][00283] Fps is (10 sec: 18022.6, 60 sec: 17954.1, 300 sec: 17720.6). Total num frames: 3366912. Throughput: 0: 4489.6. Samples: 832060. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-15 15:37:17,577][00283] Avg episode reward: [(0, '5.314')]
+[2024-09-15 15:37:19,229][00920] Updated weights for policy 0, policy_version 830 (0.0012)
+[2024-09-15 15:37:21,559][00920] Updated weights for policy 0, policy_version 840 (0.0012)
+[2024-09-15 15:37:22,575][00283] Fps is (10 sec: 18022.5, 60 sec: 17954.2, 300 sec: 17728.3). Total num frames: 3457024. Throughput: 0: 4479.1. Samples: 858934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:37:22,578][00283] Avg episode reward: [(0, '5.790')]
+[2024-09-15 15:37:22,586][00905] Saving new best policy, reward=5.790!
+[2024-09-15 15:37:23,840][00920] Updated weights for policy 0, policy_version 850 (0.0012)
+[2024-09-15 15:37:26,039][00920] Updated weights for policy 0, policy_version 860 (0.0012)
+[2024-09-15 15:37:27,575][00283] Fps is (10 sec: 18022.3, 60 sec: 17954.1, 300 sec: 17735.7). Total num frames: 3547136. Throughput: 0: 4498.9. Samples: 886226. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-15 15:37:27,577][00283] Avg episode reward: [(0, '6.104')]
+[2024-09-15 15:37:27,579][00905] Saving new best policy, reward=6.104!
+[2024-09-15 15:37:28,319][00920] Updated weights for policy 0, policy_version 870 (0.0012)
+[2024-09-15 15:37:30,542][00920] Updated weights for policy 0, policy_version 880 (0.0012)
+[2024-09-15 15:37:32,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.2, 300 sec: 17742.7). Total num frames: 3637248. Throughput: 0: 4497.3. Samples: 899848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:37:32,577][00283] Avg episode reward: [(0, '6.669')]
+[2024-09-15 15:37:32,586][00905] Saving new best policy, reward=6.669!
+[2024-09-15 15:37:32,864][00920] Updated weights for policy 0, policy_version 890 (0.0012)
+[2024-09-15 15:37:35,199][00920] Updated weights for policy 0, policy_version 900 (0.0013)
+[2024-09-15 15:37:37,455][00920] Updated weights for policy 0, policy_version 910 (0.0012)
+[2024-09-15 15:37:37,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.2, 300 sec: 17749.3). Total num frames: 3727360. Throughput: 0: 4485.0. Samples: 926496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:37:37,577][00283] Avg episode reward: [(0, '6.612')]
+[2024-09-15 15:37:39,757][00920] Updated weights for policy 0, policy_version 920 (0.0012)
+[2024-09-15 15:37:42,007][00920] Updated weights for policy 0, policy_version 930 (0.0012)
+[2024-09-15 15:37:42,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.2, 300 sec: 17755.7). Total num frames: 3817472. Throughput: 0: 4491.7. Samples: 953616. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-15 15:37:42,577][00283] Avg episode reward: [(0, '7.084')]
+[2024-09-15 15:37:42,585][00905] Saving new best policy, reward=7.084!
+[2024-09-15 15:37:44,276][00920] Updated weights for policy 0, policy_version 940 (0.0012)
+[2024-09-15 15:37:46,586][00920] Updated weights for policy 0, policy_version 950 (0.0013)
+[2024-09-15 15:37:47,575][00283] Fps is (10 sec: 18022.4, 60 sec: 17954.2, 300 sec: 17761.7). Total num frames: 3907584. Throughput: 0: 4487.0. Samples: 967180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-15 15:37:47,577][00283] Avg episode reward: [(0, '6.702')]
+[2024-09-15 15:37:48,893][00920] Updated weights for policy 0, policy_version 960 (0.0013)
+[2024-09-15 15:37:51,120][00920] Updated weights for policy 0, policy_version 970 (0.0012)
+[2024-09-15 15:37:52,575][00283] Fps is (10 sec: 18022.1, 60 sec: 17954.1, 300 sec: 17767.5). Total num frames: 3997696. Throughput: 0: 4490.3. Samples: 993912. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-09-15 15:37:52,578][00283] Avg episode reward: [(0, '6.957')]
+[2024-09-15 15:37:52,586][00905] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000976_3997696.pth...
+[2024-09-15 15:37:52,959][00905] Stopping Batcher_0...
+[2024-09-15 15:37:52,960][00905] Loop batcher_evt_loop terminating...
+[2024-09-15 15:37:52,960][00905] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-15 15:37:52,959][00283] Component Batcher_0 stopped!
+[2024-09-15 15:37:52,961][00283] Component RolloutWorker_w0 process died already! Don't wait for it.
+[2024-09-15 15:37:52,978][00920] Weights refcount: 2 0
+[2024-09-15 15:37:52,979][00920] Stopping InferenceWorker_p0-w0...
+[2024-09-15 15:37:52,980][00920] Loop inference_proc0-0_evt_loop terminating...
+[2024-09-15 15:37:52,980][00283] Component InferenceWorker_p0-w0 stopped!
+[2024-09-15 15:37:53,010][00927] Stopping RolloutWorker_w6...
+[2024-09-15 15:37:53,010][00927] Loop rollout_proc6_evt_loop terminating...
+[2024-09-15 15:37:53,011][00923] Stopping RolloutWorker_w4...
+[2024-09-15 15:37:53,012][00923] Loop rollout_proc4_evt_loop terminating...
+[2024-09-15 15:37:53,010][00283] Component RolloutWorker_w6 stopped!
+[2024-09-15 15:37:53,013][00926] Stopping RolloutWorker_w7...
+[2024-09-15 15:37:53,013][00922] Stopping RolloutWorker_w2...
+[2024-09-15 15:37:53,013][00922] Loop rollout_proc2_evt_loop terminating...
+[2024-09-15 15:37:53,013][00926] Loop rollout_proc7_evt_loop terminating...
+[2024-09-15 15:37:53,012][00283] Component RolloutWorker_w4 stopped!
+[2024-09-15 15:37:53,015][00921] Stopping RolloutWorker_w1...
+[2024-09-15 15:37:53,016][00921] Loop rollout_proc1_evt_loop terminating...
+[2024-09-15 15:37:53,016][00925] Stopping RolloutWorker_w5...
+[2024-09-15 15:37:53,015][00283] Component RolloutWorker_w7 stopped!
+[2024-09-15 15:37:53,017][00925] Loop rollout_proc5_evt_loop terminating...
+[2024-09-15 15:37:53,017][00924] Stopping RolloutWorker_w3...
+[2024-09-15 15:37:53,017][00283] Component RolloutWorker_w2 stopped!
+[2024-09-15 15:37:53,018][00924] Loop rollout_proc3_evt_loop terminating...
+[2024-09-15 15:37:53,018][00283] Component RolloutWorker_w1 stopped!
+[2024-09-15 15:37:53,019][00283] Component RolloutWorker_w5 stopped!
+[2024-09-15 15:37:53,020][00283] Component RolloutWorker_w3 stopped!
+[2024-09-15 15:37:53,029][00905] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000449_1839104.pth
+[2024-09-15 15:37:53,035][00905] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-15 15:37:53,123][00905] Stopping LearnerWorker_p0...
+[2024-09-15 15:37:53,123][00905] Loop learner_proc0_evt_loop terminating...
+[2024-09-15 15:37:53,123][00283] Component LearnerWorker_p0 stopped!
+[2024-09-15 15:37:53,126][00283] Waiting for process learner_proc0 to stop...
+[2024-09-15 15:37:53,958][00283] Waiting for process inference_proc0-0 to join...
+[2024-09-15 15:37:53,961][00283] Waiting for process rollout_proc0 to join...
+[2024-09-15 15:37:53,962][00283] Waiting for process rollout_proc1 to join...
+[2024-09-15 15:37:53,964][00283] Waiting for process rollout_proc2 to join...
+[2024-09-15 15:37:53,966][00283] Waiting for process rollout_proc3 to join...
+[2024-09-15 15:37:53,968][00283] Waiting for process rollout_proc4 to join...
+[2024-09-15 15:37:53,970][00283] Waiting for process rollout_proc5 to join...
+[2024-09-15 15:37:53,972][00283] Waiting for process rollout_proc6 to join...
+[2024-09-15 15:37:53,973][00283] Waiting for process rollout_proc7 to join...
+[2024-09-15 15:37:53,975][00283] Batcher 0 profile tree view:
+batching: 13.5559, releasing_batches: 0.0228
+[2024-09-15 15:37:53,976][00283] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0001
+  wait_policy_total: 3.9341
+update_model: 3.6129
+  weight_update: 0.0012
+one_step: 0.0026
+  handle_policy_step: 209.1558
+    deserialize: 7.8546, stack: 1.3917, obs_to_device_normalize: 49.2185, forward: 105.4844, send_messages: 13.5968
+    prepare_outputs: 22.3562
+      to_cpu: 13.1604
+[2024-09-15 15:37:53,977][00283] Learner 0 profile tree view:
+misc: 0.0052, prepare_batch: 10.4311
+train: 24.0978
+  epoch_init: 0.0055, minibatch_init: 0.0061, losses_postprocess: 0.3000, kl_divergence: 0.4024, after_optimizer: 5.3092
+  calculate_losses: 10.1043
+    losses_init: 0.0033, forward_head: 0.6827, bptt_initial: 6.5923, tail: 0.5541, advantages_returns: 0.1398, losses: 1.0380
+    bptt: 0.9309
+      bptt_forward_core: 0.8807
+  update: 7.6408
+    clip: 0.7823
+[2024-09-15 15:37:53,980][00283] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.1627, enqueue_policy_requests: 8.2873, env_step: 137.4009, overhead: 6.8411, complete_rollouts: 0.2546
+save_policy_outputs: 9.7021
+  split_output_tensors: 3.8621
+[2024-09-15 15:37:53,981][00283] Loop Runner_EvtLoop terminating...
+[2024-09-15 15:37:53,984][00283] Runner profile tree view:
+main_loop: 236.1357
+[2024-09-15 15:37:53,985][00283] Collected {0: 4005888}, FPS: 16964.3
+[2024-09-15 15:37:54,248][00283] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-15 15:37:54,250][00283] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-15 15:37:54,251][00283] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-15 15:37:54,253][00283] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-15 15:37:54,254][00283] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-15 15:37:54,255][00283] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-15 15:37:54,256][00283] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-15 15:37:54,257][00283] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-15 15:37:54,259][00283] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-09-15 15:37:54,259][00283] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-09-15 15:37:54,261][00283] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-15 15:37:54,262][00283] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-15 15:37:54,264][00283] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-15 15:37:54,265][00283] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-15 15:37:54,266][00283] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-15 15:37:54,295][00283] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-15 15:37:54,298][00283] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-15 15:37:54,300][00283] RunningMeanStd input shape: (1,)
+[2024-09-15 15:37:54,314][00283] ConvEncoder: input_channels=3
+[2024-09-15 15:37:54,426][00283] Conv encoder output size: 512
+[2024-09-15 15:37:54,427][00283] Policy head output size: 512
+[2024-09-15 15:37:54,570][00283] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-15 15:37:55,418][00283] Num frames 100...
+[2024-09-15 15:37:55,538][00283] Num frames 200...
+[2024-09-15 15:37:55,659][00283] Num frames 300...
+[2024-09-15 15:37:55,780][00283] Num frames 400...
+[2024-09-15 15:37:55,892][00283] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2024-09-15 15:37:55,894][00283] Avg episode reward: 5.480, avg true_objective: 4.480
+[2024-09-15 15:37:55,956][00283] Num frames 500...
+[2024-09-15 15:37:56,071][00283] Num frames 600...
+[2024-09-15 15:37:56,188][00283] Num frames 700...
+[2024-09-15 15:37:56,313][00283] Num frames 800...
+[2024-09-15 15:37:56,406][00283] Avg episode rewards: #0: 6.160, true rewards: #0: 4.160
+[2024-09-15 15:37:56,407][00283] Avg episode reward: 6.160, avg true_objective: 4.160
+[2024-09-15 15:37:56,491][00283] Num frames 900...
+[2024-09-15 15:37:56,611][00283] Num frames 1000...
+[2024-09-15 15:37:56,729][00283] Num frames 1100...
+[2024-09-15 15:37:56,846][00283] Num frames 1200...
+[2024-09-15 15:37:56,964][00283] Num frames 1300...
+[2024-09-15 15:37:57,084][00283] Num frames 1400...
+[2024-09-15 15:37:57,186][00283] Avg episode rewards: #0: 7.133, true rewards: #0: 4.800
+[2024-09-15 15:37:57,187][00283] Avg episode reward: 7.133, avg true_objective: 4.800
+[2024-09-15 15:37:57,260][00283] Num frames 1500...
+[2024-09-15 15:37:57,377][00283] Num frames 1600...
+[2024-09-15 15:37:57,498][00283] Num frames 1700...
+[2024-09-15 15:37:57,615][00283] Num frames 1800...
+[2024-09-15 15:37:57,736][00283] Num frames 1900...
+[2024-09-15 15:37:57,901][00283] Avg episode rewards: #0: 7.483, true rewards: #0: 4.982
+[2024-09-15 15:37:57,903][00283] Avg episode reward: 7.483, avg true_objective: 4.982
+[2024-09-15 15:37:57,911][00283] Num frames 2000...
+[2024-09-15 15:37:58,027][00283] Num frames 2100...
+[2024-09-15 15:37:58,144][00283] Avg episode rewards: #0: 6.306, true rewards: #0: 4.306
+[2024-09-15 15:37:58,145][00283] Avg episode reward: 6.306, avg true_objective: 4.306
+[2024-09-15 15:37:58,201][00283] Num frames 2200...
+[2024-09-15 15:37:58,314][00283] Num frames 2300...
+[2024-09-15 15:37:58,431][00283] Num frames 2400...
+[2024-09-15 15:37:58,546][00283] Num frames 2500...
+[2024-09-15 15:37:58,668][00283] Num frames 2600...
+[2024-09-15 15:37:58,843][00283] Avg episode rewards: #0: 6.662, true rewards: #0: 4.495
+[2024-09-15 15:37:58,845][00283] Avg episode reward: 6.662, avg true_objective: 4.495
+[2024-09-15 15:37:58,849][00283] Num frames 2700...
+[2024-09-15 15:37:58,966][00283] Num frames 2800...
+[2024-09-15 15:37:59,085][00283] Num frames 2900...
+[2024-09-15 15:37:59,205][00283] Num frames 3000...
+[2024-09-15 15:37:59,328][00283] Num frames 3100...
+[2024-09-15 15:37:59,448][00283] Num frames 3200...
+[2024-09-15 15:37:59,515][00283] Avg episode rewards: #0: 6.727, true rewards: #0: 4.584
+[2024-09-15 15:37:59,516][00283] Avg episode reward: 6.727, avg true_objective: 4.584
+[2024-09-15 15:37:59,628][00283] Num frames 3300...
+[2024-09-15 15:37:59,754][00283] Num frames 3400...
+[2024-09-15 15:37:59,883][00283] Num frames 3500...
+[2024-09-15 15:38:00,012][00283] Num frames 3600...
+[2024-09-15 15:38:00,154][00283] Avg episode rewards: #0: 6.571, true rewards: #0: 4.571
+[2024-09-15 15:38:00,155][00283] Avg episode reward: 6.571, avg true_objective: 4.571
+[2024-09-15 15:38:00,208][00283] Num frames 3700...
+[2024-09-15 15:38:00,329][00283] Num frames 3800...
+[2024-09-15 15:38:00,450][00283] Num frames 3900...
+[2024-09-15 15:38:00,570][00283] Num frames 4000...
+[2024-09-15 15:38:00,690][00283] Num frames 4100...
+[2024-09-15 15:38:00,820][00283] Num frames 4200...
+[2024-09-15 15:38:00,953][00283] Avg episode rewards: #0: 6.850, true rewards: #0: 4.739
+[2024-09-15 15:38:00,954][00283] Avg episode reward: 6.850, avg true_objective: 4.739
+[2024-09-15 15:38:00,996][00283] Num frames 4300...
+[2024-09-15 15:38:01,115][00283] Num frames 4400...
+[2024-09-15 15:38:01,233][00283] Num frames 4500...
+[2024-09-15 15:38:01,352][00283] Num frames 4600...
+[2024-09-15 15:38:01,504][00283] Avg episode rewards: #0: 6.781, true rewards: #0: 4.681
+[2024-09-15 15:38:01,505][00283] Avg episode reward: 6.781, avg true_objective: 4.681
+[2024-09-15 15:38:12,554][00283] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-09-15 15:39:48,505][00283] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-15 15:39:48,506][00283] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-15 15:39:48,507][00283] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-15 15:39:48,508][00283] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-15 15:39:48,510][00283] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-15 15:39:48,512][00283] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-15 15:39:48,513][00283] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-09-15 15:39:48,515][00283] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-15 15:39:48,516][00283] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-09-15 15:39:48,518][00283] Adding new argument 'hf_repository'='Vivek-huggingface/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-09-15 15:39:48,519][00283] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-15 15:39:48,520][00283] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-15 15:39:48,522][00283] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-15 15:39:48,524][00283] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-15 15:39:48,525][00283] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-15 15:39:48,548][00283] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-15 15:39:48,550][00283] RunningMeanStd input shape: (1,)
+[2024-09-15 15:39:48,562][00283] ConvEncoder: input_channels=3
+[2024-09-15 15:39:48,600][00283] Conv encoder output size: 512
+[2024-09-15 15:39:48,601][00283] Policy head output size: 512
+[2024-09-15 15:39:48,620][00283] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-15 15:39:49,031][00283] Num frames 100...
+[2024-09-15 15:39:49,151][00283] Num frames 200...
+[2024-09-15 15:39:49,270][00283] Num frames 300...
+[2024-09-15 15:39:49,390][00283] Num frames 400...
+[2024-09-15 15:39:49,508][00283] Num frames 500...
+[2024-09-15 15:39:49,628][00283] Num frames 600...
+[2024-09-15 15:39:49,746][00283] Num frames 700...
+[2024-09-15 15:39:49,880][00283] Avg episode rewards: #0: 12.680, true rewards: #0: 7.680
+[2024-09-15 15:39:49,882][00283] Avg episode reward: 12.680, avg true_objective: 7.680
+[2024-09-15 15:39:49,921][00283] Num frames 800...
+[2024-09-15 15:39:50,037][00283] Num frames 900...
+[2024-09-15 15:39:50,154][00283] Num frames 1000...
+[2024-09-15 15:39:50,272][00283] Num frames 1100...
+[2024-09-15 15:39:50,390][00283] Num frames 1200...
+[2024-09-15 15:39:50,464][00283] Avg episode rewards: #0: 10.080, true rewards: #0: 6.080
+[2024-09-15 15:39:50,466][00283] Avg episode reward: 10.080, avg true_objective: 6.080
+[2024-09-15 15:39:50,564][00283] Num frames 1300...
+[2024-09-15 15:39:50,680][00283] Num frames 1400...
+[2024-09-15 15:39:50,796][00283] Num frames 1500...
+[2024-09-15 15:39:50,913][00283] Num frames 1600...
+[2024-09-15 15:39:51,030][00283] Num frames 1700...
+[2024-09-15 15:39:51,147][00283] Num frames 1800...
+[2024-09-15 15:39:51,265][00283] Num frames 1900...
+[2024-09-15 15:39:51,384][00283] Num frames 2000...
+[2024-09-15 15:39:51,503][00283] Num frames 2100...
+[2024-09-15 15:39:51,623][00283] Num frames 2200...
+[2024-09-15 15:39:51,767][00283] Avg episode rewards: #0: 13.243, true rewards: #0: 7.577
+[2024-09-15 15:39:51,768][00283] Avg episode reward: 13.243, avg true_objective: 7.577
+[2024-09-15 15:39:51,800][00283] Num frames 2300...
+[2024-09-15 15:39:51,917][00283] Num frames 2400...
+[2024-09-15 15:39:52,034][00283] Num frames 2500...
+[2024-09-15 15:39:52,152][00283] Num frames 2600...
+[2024-09-15 15:39:52,268][00283] Num frames 2700...
+[2024-09-15 15:39:52,383][00283] Num frames 2800...
+[2024-09-15 15:39:52,502][00283] Num frames 2900...
+[2024-09-15 15:39:52,620][00283] Num frames 3000...
+[2024-09-15 15:39:52,738][00283] Num frames 3100...
+[2024-09-15 15:39:52,862][00283] Num frames 3200...
+[2024-09-15 15:39:53,033][00283] Avg episode rewards: #0: 14.493, true rewards: #0: 8.242
+[2024-09-15 15:39:53,035][00283] Avg episode reward: 14.493, avg true_objective: 8.242
+[2024-09-15 15:39:53,039][00283] Num frames 3300...
+[2024-09-15 15:39:53,156][00283] Num frames 3400...
+[2024-09-15 15:39:53,271][00283] Num frames 3500...
+[2024-09-15 15:39:53,388][00283] Num frames 3600...
+[2024-09-15 15:39:53,544][00283] Avg episode rewards: #0: 12.362, true rewards: #0: 7.362
+[2024-09-15 15:39:53,546][00283] Avg episode reward: 12.362, avg true_objective: 7.362
+[2024-09-15 15:39:53,569][00283] Num frames 3700...
+[2024-09-15 15:39:53,687][00283] Num frames 3800...
+[2024-09-15 15:39:53,812][00283] Num frames 3900...
+[2024-09-15 15:39:53,937][00283] Num frames 4000...
+[2024-09-15 15:39:54,075][00283] Avg episode rewards: #0: 10.942, true rewards: #0: 6.775
+[2024-09-15 15:39:54,076][00283] Avg episode reward: 10.942, avg true_objective: 6.775
+[2024-09-15 15:39:54,118][00283] Num frames 4100...
+[2024-09-15 15:39:54,236][00283] Num frames 4200...
+[2024-09-15 15:39:54,353][00283] Num frames 4300...
+[2024-09-15 15:39:54,470][00283] Num frames 4400...
+[2024-09-15 15:39:54,594][00283] Num frames 4500...
+[2024-09-15 15:39:54,722][00283] Num frames 4600...
+[2024-09-15 15:39:54,850][00283] Num frames 4700...
+[2024-09-15 15:39:54,977][00283] Num frames 4800...
+[2024-09-15 15:39:55,074][00283] Avg episode rewards: #0: 11.333, true rewards: #0: 6.904
+[2024-09-15 15:39:55,076][00283] Avg episode reward: 11.333, avg true_objective: 6.904
+[2024-09-15 15:39:55,160][00283] Num frames 4900...
+[2024-09-15 15:39:55,286][00283] Num frames 5000...
+[2024-09-15 15:39:55,411][00283] Num frames 5100...
+[2024-09-15 15:39:55,537][00283] Num frames 5200...
+[2024-09-15 15:39:55,614][00283] Avg episode rewards: #0: 10.396, true rewards: #0: 6.521
+[2024-09-15 15:39:55,616][00283] Avg episode reward: 10.396, avg true_objective: 6.521
+[2024-09-15 15:39:55,718][00283] Num frames 5300...
+[2024-09-15 15:39:55,845][00283] Num frames 5400...
+[2024-09-15 15:39:55,965][00283] Num frames 5500...
+[2024-09-15 15:39:56,084][00283] Num frames 5600...
+[2024-09-15 15:39:56,216][00283] Avg episode rewards: #0: 9.850, true rewards: #0: 6.294
+[2024-09-15 15:39:56,217][00283] Avg episode reward: 9.850, avg true_objective: 6.294
+[2024-09-15 15:39:56,260][00283] Num frames 5700...
+[2024-09-15 15:39:56,376][00283] Num frames 5800...
+[2024-09-15 15:39:56,494][00283] Num frames 5900...
+[2024-09-15 15:39:56,610][00283] Num frames 6000...
+[2024-09-15 15:39:56,722][00283] Avg episode rewards: #0: 9.249, true rewards: #0: 6.049
+[2024-09-15 15:39:56,723][00283] Avg episode reward: 9.249, avg true_objective: 6.049
+[2024-09-15 15:40:09,911][00283] Replay video saved to /content/train_dir/default_experiment/replay.mp4!