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.1735554602.f4e7411e8516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ac201f6eee0c4aec383f2027f8ae0426163f7e0ec4b3978142e4481beef2e4
+size 400383

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: 4.00 +/- 0.26
+      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 AneeshSinha/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_000000637_2609152_reward_5.352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cdd5cd1539de61ac5395ea232451853afd0e0e983a99b16dbdc7b2bce876337
+size 34929051

checkpoint_p0/checkpoint_000001536_6291456.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d868820aa898f35f568dcd4614754ea09f9e2f719ea6d8fe165d156a61878a
+size 34929541

checkpoint_p0/checkpoint_000001955_8007680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31cc0c4097e6747363805ece0eb5d99e19edc8b4c6c5ae205c2b0820a84e2f66
+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": 8000000,
+  "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=8000000",
+  "cli_args": {
+    "env": "doom_health_gathering_supreme",
+    "num_workers": 8,
+    "num_envs_per_worker": 4,
+    "train_for_env_steps": 8000000
+  },
+  "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:b594f47cd9d3acf60360c4eb38dd9fcf40d72e0de2bbf7e66becf535247f991d
+size 5286806

sf_log.txt

@@ -0,0 +1,776 @@
+[2024-12-30 10:30:07,792][01465] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-12-30 10:30:07,794][01465] Rollout worker 0 uses device cpu
+[2024-12-30 10:30:07,796][01465] Rollout worker 1 uses device cpu
+[2024-12-30 10:30:07,797][01465] Rollout worker 2 uses device cpu
+[2024-12-30 10:30:07,798][01465] Rollout worker 3 uses device cpu
+[2024-12-30 10:30:07,800][01465] Rollout worker 4 uses device cpu
+[2024-12-30 10:30:07,801][01465] Rollout worker 5 uses device cpu
+[2024-12-30 10:30:07,802][01465] Rollout worker 6 uses device cpu
+[2024-12-30 10:30:07,804][01465] Rollout worker 7 uses device cpu
+[2024-12-30 10:30:07,893][01465] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-30 10:30:07,895][01465] InferenceWorker_p0-w0: min num requests: 2
+[2024-12-30 10:30:07,927][01465] Starting all processes...
+[2024-12-30 10:30:07,928][01465] Starting process learner_proc0
+[2024-12-30 10:30:07,974][01465] Starting all processes...
+[2024-12-30 10:30:07,980][01465] Starting process inference_proc0-0
+[2024-12-30 10:30:07,981][01465] Starting process rollout_proc0
+[2024-12-30 10:30:07,981][01465] Starting process rollout_proc1
+[2024-12-30 10:30:07,982][01465] Starting process rollout_proc2
+[2024-12-30 10:30:07,982][01465] Starting process rollout_proc3
+[2024-12-30 10:30:07,983][01465] Starting process rollout_proc4
+[2024-12-30 10:30:07,985][01465] Starting process rollout_proc5
+[2024-12-30 10:30:07,989][01465] Starting process rollout_proc6
+[2024-12-30 10:30:07,990][01465] Starting process rollout_proc7
+[2024-12-30 10:30:10,784][03485] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-12-30 10:30:10,951][03468] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-30 10:30:10,951][03468] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-12-30 10:30:10,970][03468] Num visible devices: 1
+[2024-12-30 10:30:10,998][03468] Starting seed is not provided
+[2024-12-30 10:30:10,998][03468] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-30 10:30:10,999][03468] Initializing actor-critic model on device cuda:0
+[2024-12-30 10:30:10,999][03468] RunningMeanStd input shape: (3, 72, 128)
+[2024-12-30 10:30:11,002][03468] RunningMeanStd input shape: (1,)
+[2024-12-30 10:30:11,020][03468] ConvEncoder: input_channels=3
+[2024-12-30 10:30:11,061][03483] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-12-30 10:30:11,064][03486] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-12-30 10:30:11,072][03484] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-12-30 10:30:11,251][03482] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-12-30 10:30:11,265][03487] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-12-30 10:30:11,270][03468] Conv encoder output size: 512
+[2024-12-30 10:30:11,271][03468] Policy head output size: 512
+[2024-12-30 10:30:11,287][03481] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-30 10:30:11,288][03481] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-12-30 10:30:11,290][03488] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-12-30 10:30:11,305][03481] Num visible devices: 1
+[2024-12-30 10:30:11,309][03489] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+[2024-12-30 10:30:11,329][03468] Created Actor Critic model with architecture:
+[2024-12-30 10:30:11,329][03468] 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)
+  )
+)
+[2024-12-30 10:30:11,574][03468] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-12-30 10:30:14,944][03468] No checkpoints found
+[2024-12-30 10:30:14,944][03468] Did not load from checkpoint, starting from scratch!
+[2024-12-30 10:30:14,945][03468] Initialized policy 0 weights for model version 0
+[2024-12-30 10:30:14,947][03468] LearnerWorker_p0 finished initialization!
+[2024-12-30 10:30:14,948][03468] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-30 10:30:15,024][03481] RunningMeanStd input shape: (3, 72, 128)
+[2024-12-30 10:30:15,025][03481] RunningMeanStd input shape: (1,)
+[2024-12-30 10:30:15,038][03481] ConvEncoder: input_channels=3
+[2024-12-30 10:30:15,146][03481] Conv encoder output size: 512
+[2024-12-30 10:30:15,146][03481] Policy head output size: 512
+[2024-12-30 10:30:15,198][01465] Inference worker 0-0 is ready!
+[2024-12-30 10:30:15,200][01465] All inference workers are ready! Signal rollout workers to start!
+[2024-12-30 10:30:15,233][03484] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:30:15,233][03482] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:30:15,252][03487] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:30:15,252][03488] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:30:15,253][03483] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:30:15,253][03486] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:30:15,253][03485] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:30:15,253][03489] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:30:15,603][03485] Decorrelating experience for 0 frames...
+[2024-12-30 10:30:15,603][03483] Decorrelating experience for 0 frames...
+[2024-12-30 10:30:15,604][03487] Decorrelating experience for 0 frames...
+[2024-12-30 10:30:15,604][03489] Decorrelating experience for 0 frames...
+[2024-12-30 10:30:15,604][03488] Decorrelating experience for 0 frames...
+[2024-12-30 10:30:15,634][03482] Decorrelating experience for 0 frames...
+[2024-12-30 10:30:15,661][03486] Decorrelating experience for 0 frames...
+[2024-12-30 10:30:15,847][03489] Decorrelating experience for 32 frames...
+[2024-12-30 10:30:15,848][03483] Decorrelating experience for 32 frames...
+[2024-12-30 10:30:15,848][03487] Decorrelating experience for 32 frames...
+[2024-12-30 10:30:15,919][03486] Decorrelating experience for 32 frames...
+[2024-12-30 10:30:16,169][03482] Decorrelating experience for 32 frames...
+[2024-12-30 10:30:16,194][03488] Decorrelating experience for 32 frames...
+[2024-12-30 10:30:16,209][03483] Decorrelating experience for 64 frames...
+[2024-12-30 10:30:16,227][03489] Decorrelating experience for 64 frames...
+[2024-12-30 10:30:16,237][03487] Decorrelating experience for 64 frames...
+[2024-12-30 10:30:16,250][03485] Decorrelating experience for 32 frames...
+[2024-12-30 10:30:16,368][03486] Decorrelating experience for 64 frames...
+[2024-12-30 10:30:16,499][03483] Decorrelating experience for 96 frames...
+[2024-12-30 10:30:16,522][03489] Decorrelating experience for 96 frames...
+[2024-12-30 10:30:16,536][03482] Decorrelating experience for 64 frames...
+[2024-12-30 10:30:16,542][03488] Decorrelating experience for 64 frames...
+[2024-12-30 10:30:16,591][03485] Decorrelating experience for 64 frames...
+[2024-12-30 10:30:16,739][03487] Decorrelating experience for 96 frames...
+[2024-12-30 10:30:16,761][03486] Decorrelating experience for 96 frames...
+[2024-12-30 10:30:16,860][03488] Decorrelating experience for 96 frames...
+[2024-12-30 10:30:16,872][03482] Decorrelating experience for 96 frames...
+[2024-12-30 10:30:17,111][03485] Decorrelating experience for 96 frames...
+[2024-12-30 10:30:17,837][01465] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-12-30 10:30:18,756][03468] Signal inference workers to stop experience collection...
+[2024-12-30 10:30:18,760][03481] InferenceWorker_p0-w0: stopping experience collection
+[2024-12-30 10:30:21,337][03468] Signal inference workers to resume experience collection...
+[2024-12-30 10:30:21,338][03481] InferenceWorker_p0-w0: resuming experience collection
+[2024-12-30 10:30:22,837][01465] Fps is (10 sec: 5734.2, 60 sec: 5734.2, 300 sec: 5734.2). Total num frames: 28672. Throughput: 0: 586.8. Samples: 2934. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2024-12-30 10:30:22,839][01465] Avg episode reward: [(0, '3.879')]
+[2024-12-30 10:30:23,305][03481] Updated weights for policy 0, policy_version 10 (0.0147)
+[2024-12-30 10:30:25,610][03481] Updated weights for policy 0, policy_version 20 (0.0013)
+[2024-12-30 10:30:27,837][01465] Fps is (10 sec: 11878.3, 60 sec: 11878.3, 300 sec: 11878.3). Total num frames: 118784. Throughput: 0: 2822.0. Samples: 28220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:30:27,839][01465] Avg episode reward: [(0, '4.386')]
+[2024-12-30 10:30:27,841][03468] Saving new best policy, reward=4.386!
+[2024-12-30 10:30:27,844][03481] Updated weights for policy 0, policy_version 30 (0.0013)
+[2024-12-30 10:30:27,885][01465] Heartbeat connected on Batcher_0
+[2024-12-30 10:30:27,898][01465] Heartbeat connected on InferenceWorker_p0-w0
+[2024-12-30 10:30:27,900][01465] Heartbeat connected on RolloutWorker_w0
+[2024-12-30 10:30:27,906][01465] Heartbeat connected on RolloutWorker_w1
+[2024-12-30 10:30:27,912][01465] Heartbeat connected on LearnerWorker_p0
+[2024-12-30 10:30:27,915][01465] Heartbeat connected on RolloutWorker_w3
+[2024-12-30 10:30:27,918][01465] Heartbeat connected on RolloutWorker_w4
+[2024-12-30 10:30:27,920][01465] Heartbeat connected on RolloutWorker_w5
+[2024-12-30 10:30:27,924][01465] Heartbeat connected on RolloutWorker_w6
+[2024-12-30 10:30:27,926][01465] Heartbeat connected on RolloutWorker_w7
+[2024-12-30 10:30:30,074][03481] Updated weights for policy 0, policy_version 40 (0.0013)
+[2024-12-30 10:30:32,275][03481] Updated weights for policy 0, policy_version 50 (0.0013)
+[2024-12-30 10:30:32,837][01465] Fps is (10 sec: 18431.9, 60 sec: 14199.3, 300 sec: 14199.3). Total num frames: 212992. Throughput: 0: 2813.7. Samples: 42206. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-12-30 10:30:32,840][01465] Avg episode reward: [(0, '4.401')]
+[2024-12-30 10:30:32,846][03468] Saving new best policy, reward=4.401!
+[2024-12-30 10:30:34,499][03481] Updated weights for policy 0, policy_version 60 (0.0012)
+[2024-12-30 10:30:36,663][03481] Updated weights for policy 0, policy_version 70 (0.0012)
+[2024-12-30 10:30:37,837][01465] Fps is (10 sec: 18841.7, 60 sec: 15360.0, 300 sec: 15360.0). Total num frames: 307200. Throughput: 0: 3507.0. Samples: 70140. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-30 10:30:37,840][01465] Avg episode reward: [(0, '4.241')]
+[2024-12-30 10:30:38,852][03481] Updated weights for policy 0, policy_version 80 (0.0012)
+[2024-12-30 10:30:41,185][03481] Updated weights for policy 0, policy_version 90 (0.0013)
+[2024-12-30 10:30:42,837][01465] Fps is (10 sec: 18432.1, 60 sec: 15892.4, 300 sec: 15892.4). Total num frames: 397312. Throughput: 0: 3903.7. Samples: 97594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:30:42,840][01465] Avg episode reward: [(0, '4.367')]
+[2024-12-30 10:30:43,332][03481] Updated weights for policy 0, policy_version 100 (0.0012)
+[2024-12-30 10:30:45,549][03481] Updated weights for policy 0, policy_version 110 (0.0013)
+[2024-12-30 10:30:47,709][03481] Updated weights for policy 0, policy_version 120 (0.0013)
+[2024-12-30 10:30:47,837][01465] Fps is (10 sec: 18431.9, 60 sec: 16384.0, 300 sec: 16384.0). Total num frames: 491520. Throughput: 0: 3720.1. Samples: 111604. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:30:47,839][01465] Avg episode reward: [(0, '4.609')]
+[2024-12-30 10:30:47,841][03468] Saving new best policy, reward=4.609!
+[2024-12-30 10:30:49,941][03481] Updated weights for policy 0, policy_version 130 (0.0012)
+[2024-12-30 10:30:52,142][03481] Updated weights for policy 0, policy_version 140 (0.0012)
+[2024-12-30 10:30:52,837][01465] Fps is (10 sec: 18841.7, 60 sec: 16735.0, 300 sec: 16735.0). Total num frames: 585728. Throughput: 0: 3990.4. Samples: 139664. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-30 10:30:52,839][01465] Avg episode reward: [(0, '4.921')]
+[2024-12-30 10:30:52,846][03468] Saving new best policy, reward=4.921!
+[2024-12-30 10:30:54,385][03481] Updated weights for policy 0, policy_version 150 (0.0012)
+[2024-12-30 10:30:56,642][03481] Updated weights for policy 0, policy_version 160 (0.0012)
+[2024-12-30 10:30:57,837][01465] Fps is (10 sec: 18432.0, 60 sec: 16896.0, 300 sec: 16896.0). Total num frames: 675840. Throughput: 0: 4177.0. Samples: 167080. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-30 10:30:57,839][01465] Avg episode reward: [(0, '4.752')]
+[2024-12-30 10:30:58,816][03481] Updated weights for policy 0, policy_version 170 (0.0012)
+[2024-12-30 10:31:01,086][03481] Updated weights for policy 0, policy_version 180 (0.0012)
+[2024-12-30 10:31:02,837][01465] Fps is (10 sec: 18022.5, 60 sec: 17021.1, 300 sec: 17021.1). Total num frames: 765952. Throughput: 0: 4019.6. Samples: 180882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:31:02,839][01465] Avg episode reward: [(0, '4.489')]
+[2024-12-30 10:31:03,303][03481] Updated weights for policy 0, policy_version 190 (0.0013)
+[2024-12-30 10:31:05,569][03481] Updated weights for policy 0, policy_version 200 (0.0012)
+[2024-12-30 10:31:07,837][01465] Fps is (10 sec: 18022.4, 60 sec: 17121.2, 300 sec: 17121.2). Total num frames: 856064. Throughput: 0: 4562.5. Samples: 208248. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-30 10:31:07,840][01465] Avg episode reward: [(0, '4.748')]
+[2024-12-30 10:31:07,887][03481] Updated weights for policy 0, policy_version 210 (0.0013)
+[2024-12-30 10:31:10,121][03481] Updated weights for policy 0, policy_version 220 (0.0012)
+[2024-12-30 10:31:12,325][03481] Updated weights for policy 0, policy_version 230 (0.0012)
+[2024-12-30 10:31:12,837][01465] Fps is (10 sec: 18431.9, 60 sec: 17277.6, 300 sec: 17277.6). Total num frames: 950272. Throughput: 0: 4606.6. Samples: 235516. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:31:12,840][01465] Avg episode reward: [(0, '4.747')]
+[2024-12-30 10:31:14,524][03481] Updated weights for policy 0, policy_version 240 (0.0012)
+[2024-12-30 10:31:16,748][03481] Updated weights for policy 0, policy_version 250 (0.0012)
+[2024-12-30 10:31:17,837][01465] Fps is (10 sec: 18841.7, 60 sec: 17408.0, 300 sec: 17408.0). Total num frames: 1044480. Throughput: 0: 4605.7. Samples: 249464. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:31:17,839][01465] Avg episode reward: [(0, '4.732')]
+[2024-12-30 10:31:18,935][03481] Updated weights for policy 0, policy_version 260 (0.0012)
+[2024-12-30 10:31:21,241][03481] Updated weights for policy 0, policy_version 270 (0.0012)
+[2024-12-30 10:31:22,837][01465] Fps is (10 sec: 18022.5, 60 sec: 18363.7, 300 sec: 17392.2). Total num frames: 1130496. Throughput: 0: 4596.2. Samples: 276968. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:31:22,840][01465] Avg episode reward: [(0, '4.599')]
+[2024-12-30 10:31:23,529][03481] Updated weights for policy 0, policy_version 280 (0.0012)
+[2024-12-30 10:31:25,689][03481] Updated weights for policy 0, policy_version 290 (0.0012)
+[2024-12-30 10:31:27,837][01465] Fps is (10 sec: 18022.5, 60 sec: 18432.0, 300 sec: 17495.8). Total num frames: 1224704. Throughput: 0: 4599.3. Samples: 304560. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:31:27,839][01465] Avg episode reward: [(0, '4.502')]
+[2024-12-30 10:31:27,875][03481] Updated weights for policy 0, policy_version 300 (0.0013)
+[2024-12-30 10:31:30,089][03481] Updated weights for policy 0, policy_version 310 (0.0012)
+[2024-12-30 10:31:32,296][03481] Updated weights for policy 0, policy_version 320 (0.0012)
+[2024-12-30 10:31:32,837][01465] Fps is (10 sec: 18841.6, 60 sec: 18432.0, 300 sec: 17585.5). Total num frames: 1318912. Throughput: 0: 4598.3. Samples: 318526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:31:32,840][01465] Avg episode reward: [(0, '4.486')]
+[2024-12-30 10:31:34,603][03481] Updated weights for policy 0, policy_version 330 (0.0012)
+[2024-12-30 10:31:36,853][03481] Updated weights for policy 0, policy_version 340 (0.0012)
+[2024-12-30 10:31:37,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18363.7, 300 sec: 17612.8). Total num frames: 1409024. Throughput: 0: 4580.1. Samples: 345768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:31:37,839][01465] Avg episode reward: [(0, '4.402')]
+[2024-12-30 10:31:39,047][03481] Updated weights for policy 0, policy_version 350 (0.0013)
+[2024-12-30 10:31:41,232][03481] Updated weights for policy 0, policy_version 360 (0.0012)
+[2024-12-30 10:31:42,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 17685.1). Total num frames: 1503232. Throughput: 0: 4590.1. Samples: 373636. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:31:42,840][01465] Avg episode reward: [(0, '4.739')]
+[2024-12-30 10:31:43,439][03481] Updated weights for policy 0, policy_version 370 (0.0012)
+[2024-12-30 10:31:45,656][03481] Updated weights for policy 0, policy_version 380 (0.0012)
+[2024-12-30 10:31:47,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18363.7, 300 sec: 17703.8). Total num frames: 1593344. Throughput: 0: 4593.6. Samples: 387596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:31:47,840][01465] Avg episode reward: [(0, '4.706')]
+[2024-12-30 10:31:47,903][03481] Updated weights for policy 0, policy_version 390 (0.0013)
+[2024-12-30 10:31:50,226][03481] Updated weights for policy 0, policy_version 400 (0.0012)
+[2024-12-30 10:31:52,397][03481] Updated weights for policy 0, policy_version 410 (0.0012)
+[2024-12-30 10:31:52,837][01465] Fps is (10 sec: 18432.2, 60 sec: 18363.8, 300 sec: 17763.7). Total num frames: 1687552. Throughput: 0: 4591.3. Samples: 414854. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:31:52,839][01465] Avg episode reward: [(0, '4.779')]
+[2024-12-30 10:31:54,594][03481] Updated weights for policy 0, policy_version 420 (0.0012)
+[2024-12-30 10:31:56,816][03481] Updated weights for policy 0, policy_version 430 (0.0013)
+[2024-12-30 10:31:57,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18363.7, 300 sec: 17776.6). Total num frames: 1777664. Throughput: 0: 4605.9. Samples: 442782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:31:57,840][01465] Avg episode reward: [(0, '4.781')]
+[2024-12-30 10:31:58,976][03481] Updated weights for policy 0, policy_version 440 (0.0013)
+[2024-12-30 10:32:01,226][03481] Updated weights for policy 0, policy_version 450 (0.0012)
+[2024-12-30 10:32:02,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 17827.3). Total num frames: 1871872. Throughput: 0: 4608.1. Samples: 456830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:32:02,839][01465] Avg episode reward: [(0, '4.366')]
+[2024-12-30 10:32:02,847][03468] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000457_1871872.pth...
+[2024-12-30 10:32:03,512][03481] Updated weights for policy 0, policy_version 460 (0.0013)
+[2024-12-30 10:32:05,753][03481] Updated weights for policy 0, policy_version 470 (0.0013)
+[2024-12-30 10:32:07,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 17836.2). Total num frames: 1961984. Throughput: 0: 4600.4. Samples: 483986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:32:07,839][01465] Avg episode reward: [(0, '4.349')]
+[2024-12-30 10:32:07,953][03481] Updated weights for policy 0, policy_version 480 (0.0013)
+[2024-12-30 10:32:10,143][03481] Updated weights for policy 0, policy_version 490 (0.0012)
+[2024-12-30 10:32:12,308][03481] Updated weights for policy 0, policy_version 500 (0.0012)
+[2024-12-30 10:32:12,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18432.0, 300 sec: 17879.9). Total num frames: 2056192. Throughput: 0: 4610.8. Samples: 512048. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:32:12,839][01465] Avg episode reward: [(0, '4.975')]
+[2024-12-30 10:32:12,846][03468] Saving new best policy, reward=4.975!
+[2024-12-30 10:32:14,534][03481] Updated weights for policy 0, policy_version 510 (0.0012)
+[2024-12-30 10:32:16,846][03481] Updated weights for policy 0, policy_version 520 (0.0013)
+[2024-12-30 10:32:17,837][01465] Fps is (10 sec: 18432.2, 60 sec: 18363.8, 300 sec: 17885.9). Total num frames: 2146304. Throughput: 0: 4606.5. Samples: 525820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:32:17,839][01465] Avg episode reward: [(0, '4.614')]
+[2024-12-30 10:32:19,095][03481] Updated weights for policy 0, policy_version 530 (0.0012)
+[2024-12-30 10:32:21,315][03481] Updated weights for policy 0, policy_version 540 (0.0013)
+[2024-12-30 10:32:22,837][01465] Fps is (10 sec: 18022.3, 60 sec: 18432.0, 300 sec: 17891.3). Total num frames: 2236416. Throughput: 0: 4608.5. Samples: 553150. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:32:22,839][01465] Avg episode reward: [(0, '4.727')]
+[2024-12-30 10:32:23,522][03481] Updated weights for policy 0, policy_version 550 (0.0012)
+[2024-12-30 10:32:25,731][03481] Updated weights for policy 0, policy_version 560 (0.0013)
+[2024-12-30 10:32:27,837][01465] Fps is (10 sec: 18431.8, 60 sec: 18432.0, 300 sec: 17927.9). Total num frames: 2330624. Throughput: 0: 4605.8. Samples: 580896. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:32:27,840][01465] Avg episode reward: [(0, '4.535')]
+[2024-12-30 10:32:27,927][03481] Updated weights for policy 0, policy_version 570 (0.0012)
+[2024-12-30 10:32:30,212][03481] Updated weights for policy 0, policy_version 580 (0.0012)
+[2024-12-30 10:32:32,473][03481] Updated weights for policy 0, policy_version 590 (0.0012)
+[2024-12-30 10:32:32,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18363.7, 300 sec: 17931.4). Total num frames: 2420736. Throughput: 0: 4597.1. Samples: 594464. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-12-30 10:32:32,839][01465] Avg episode reward: [(0, '5.173')]
+[2024-12-30 10:32:32,846][03468] Saving new best policy, reward=5.173!
+[2024-12-30 10:32:34,637][03481] Updated weights for policy 0, policy_version 600 (0.0012)
+[2024-12-30 10:32:36,839][03481] Updated weights for policy 0, policy_version 610 (0.0012)
+[2024-12-30 10:32:37,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 17963.9). Total num frames: 2514944. Throughput: 0: 4610.0. Samples: 622302. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:32:37,839][01465] Avg episode reward: [(0, '4.956')]
+[2024-12-30 10:32:39,011][03481] Updated weights for policy 0, policy_version 620 (0.0012)
+[2024-12-30 10:32:41,203][03481] Updated weights for policy 0, policy_version 630 (0.0012)
+[2024-12-30 10:32:42,837][01465] Fps is (10 sec: 18841.6, 60 sec: 18432.0, 300 sec: 17994.1). Total num frames: 2609152. Throughput: 0: 4609.5. Samples: 650210. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:32:42,839][01465] Avg episode reward: [(0, '5.352')]
+[2024-12-30 10:32:42,847][03468] Saving new best policy, reward=5.352!
+[2024-12-30 10:32:43,489][03481] Updated weights for policy 0, policy_version 640 (0.0013)
+[2024-12-30 10:32:45,769][03481] Updated weights for policy 0, policy_version 650 (0.0013)
+[2024-12-30 10:32:47,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 17995.1). Total num frames: 2699264. Throughput: 0: 4595.8. Samples: 663640. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-30 10:32:47,839][01465] Avg episode reward: [(0, '5.205')]
+[2024-12-30 10:32:47,950][03481] Updated weights for policy 0, policy_version 660 (0.0012)
+[2024-12-30 10:32:50,096][03481] Updated weights for policy 0, policy_version 670 (0.0012)
+[2024-12-30 10:32:52,380][03481] Updated weights for policy 0, policy_version 680 (0.0013)
+[2024-12-30 10:32:52,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 18022.4). Total num frames: 2793472. Throughput: 0: 4614.5. Samples: 691640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:32:52,840][01465] Avg episode reward: [(0, '4.539')]
+[2024-12-30 10:32:54,509][03481] Updated weights for policy 0, policy_version 690 (0.0013)
+[2024-12-30 10:32:56,766][03481] Updated weights for policy 0, policy_version 700 (0.0012)
+[2024-12-30 10:32:57,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 18022.4). Total num frames: 2883584. Throughput: 0: 4605.3. Samples: 719284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:32:57,839][01465] Avg episode reward: [(0, '4.633')]
+[2024-12-30 10:32:59,069][03481] Updated weights for policy 0, policy_version 710 (0.0013)
+[2024-12-30 10:33:01,274][03481] Updated weights for policy 0, policy_version 720 (0.0013)
+[2024-12-30 10:33:02,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 18047.2). Total num frames: 2977792. Throughput: 0: 4600.3. Samples: 732836. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-30 10:33:02,839][01465] Avg episode reward: [(0, '4.739')]
+[2024-12-30 10:33:03,492][03481] Updated weights for policy 0, policy_version 730 (0.0012)
+[2024-12-30 10:33:05,657][03481] Updated weights for policy 0, policy_version 740 (0.0012)
+[2024-12-30 10:33:07,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 18046.5). Total num frames: 3067904. Throughput: 0: 4614.7. Samples: 760810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:33:07,840][01465] Avg episode reward: [(0, '4.622')]
+[2024-12-30 10:33:07,899][03481] Updated weights for policy 0, policy_version 750 (0.0012)
+[2024-12-30 10:33:10,052][03481] Updated weights for policy 0, policy_version 760 (0.0012)
+[2024-12-30 10:33:12,362][03481] Updated weights for policy 0, policy_version 770 (0.0012)
+[2024-12-30 10:33:12,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 18069.2). Total num frames: 3162112. Throughput: 0: 4611.0. Samples: 788390. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:33:12,839][01465] Avg episode reward: [(0, '4.580')]
+[2024-12-30 10:33:14,564][03481] Updated weights for policy 0, policy_version 780 (0.0013)
+[2024-12-30 10:33:16,742][03481] Updated weights for policy 0, policy_version 790 (0.0012)
+[2024-12-30 10:33:17,837][01465] Fps is (10 sec: 18431.8, 60 sec: 18432.0, 300 sec: 18067.9). Total num frames: 3252224. Throughput: 0: 4618.4. Samples: 802290. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:33:17,840][01465] Avg episode reward: [(0, '4.420')]
+[2024-12-30 10:33:18,958][03481] Updated weights for policy 0, policy_version 800 (0.0012)
+[2024-12-30 10:33:21,156][03481] Updated weights for policy 0, policy_version 810 (0.0013)
+[2024-12-30 10:33:22,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18500.3, 300 sec: 18088.8). Total num frames: 3346432. Throughput: 0: 4619.7. Samples: 830190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:33:22,839][01465] Avg episode reward: [(0, '4.652')]
+[2024-12-30 10:33:23,373][03481] Updated weights for policy 0, policy_version 820 (0.0013)
+[2024-12-30 10:33:25,684][03481] Updated weights for policy 0, policy_version 830 (0.0013)
+[2024-12-30 10:33:27,837][01465] Fps is (10 sec: 18432.2, 60 sec: 18432.0, 300 sec: 18087.1). Total num frames: 3436544. Throughput: 0: 4603.9. Samples: 857386. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:33:27,840][01465] Avg episode reward: [(0, '4.672')]
+[2024-12-30 10:33:27,921][03481] Updated weights for policy 0, policy_version 840 (0.0013)
+[2024-12-30 10:33:30,126][03481] Updated weights for policy 0, policy_version 850 (0.0013)
+[2024-12-30 10:33:32,293][03481] Updated weights for policy 0, policy_version 860 (0.0011)
+[2024-12-30 10:33:32,837][01465] Fps is (10 sec: 18431.8, 60 sec: 18500.3, 300 sec: 18106.4). Total num frames: 3530752. Throughput: 0: 4615.3. Samples: 871330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:33:32,839][01465] Avg episode reward: [(0, '4.675')]
+[2024-12-30 10:33:34,517][03481] Updated weights for policy 0, policy_version 870 (0.0013)
+[2024-12-30 10:33:36,658][03481] Updated weights for policy 0, policy_version 880 (0.0012)
+[2024-12-30 10:33:37,837][01465] Fps is (10 sec: 18841.5, 60 sec: 18500.3, 300 sec: 18124.8). Total num frames: 3624960. Throughput: 0: 4619.2. Samples: 899504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:33:37,840][01465] Avg episode reward: [(0, '4.331')]
+[2024-12-30 10:33:38,979][03481] Updated weights for policy 0, policy_version 890 (0.0012)
+[2024-12-30 10:33:41,215][03481] Updated weights for policy 0, policy_version 900 (0.0013)
+[2024-12-30 10:33:42,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 18122.3). Total num frames: 3715072. Throughput: 0: 4612.9. Samples: 926866. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-30 10:33:42,839][01465] Avg episode reward: [(0, '4.514')]
+[2024-12-30 10:33:43,384][03481] Updated weights for policy 0, policy_version 910 (0.0012)
+[2024-12-30 10:33:45,579][03481] Updated weights for policy 0, policy_version 920 (0.0012)
+[2024-12-30 10:33:47,752][03481] Updated weights for policy 0, policy_version 930 (0.0013)
+[2024-12-30 10:33:47,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18500.2, 300 sec: 18139.4). Total num frames: 3809280. Throughput: 0: 4623.3. Samples: 940884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:33:47,839][01465] Avg episode reward: [(0, '4.490')]
+[2024-12-30 10:33:49,988][03481] Updated weights for policy 0, policy_version 940 (0.0012)
+[2024-12-30 10:33:52,221][03481] Updated weights for policy 0, policy_version 950 (0.0013)
+[2024-12-30 10:33:52,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18432.0, 300 sec: 18136.7). Total num frames: 3899392. Throughput: 0: 4620.8. Samples: 968748. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:33:52,839][01465] Avg episode reward: [(0, '4.556')]
+[2024-12-30 10:33:54,508][03481] Updated weights for policy 0, policy_version 960 (0.0013)
+[2024-12-30 10:33:56,668][03481] Updated weights for policy 0, policy_version 970 (0.0012)
+[2024-12-30 10:33:57,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18500.2, 300 sec: 18152.7). Total num frames: 3993600. Throughput: 0: 4621.3. Samples: 996350. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:33:57,839][01465] Avg episode reward: [(0, '4.768')]
+[2024-12-30 10:33:58,882][03481] Updated weights for policy 0, policy_version 980 (0.0012)
+[2024-12-30 10:34:01,062][03481] Updated weights for policy 0, policy_version 990 (0.0012)
+[2024-12-30 10:34:02,837][01465] Fps is (10 sec: 18841.7, 60 sec: 18500.3, 300 sec: 18168.0). Total num frames: 4087808. Throughput: 0: 4622.4. Samples: 1010296. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:34:02,839][01465] Avg episode reward: [(0, '4.821')]
+[2024-12-30 10:34:02,848][03468] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000998_4087808.pth...
+[2024-12-30 10:34:03,262][03481] Updated weights for policy 0, policy_version 1000 (0.0012)
+[2024-12-30 10:34:05,516][03481] Updated weights for policy 0, policy_version 1010 (0.0013)
+[2024-12-30 10:34:07,794][03481] Updated weights for policy 0, policy_version 1020 (0.0013)
+[2024-12-30 10:34:07,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18500.2, 300 sec: 18164.9). Total num frames: 4177920. Throughput: 0: 4614.7. Samples: 1037854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:34:07,840][01465] Avg episode reward: [(0, '4.733')]
+[2024-12-30 10:34:10,027][03481] Updated weights for policy 0, policy_version 1030 (0.0012)
+[2024-12-30 10:34:12,226][03481] Updated weights for policy 0, policy_version 1040 (0.0012)
+[2024-12-30 10:34:12,837][01465] Fps is (10 sec: 18022.6, 60 sec: 18432.0, 300 sec: 18161.8). Total num frames: 4268032. Throughput: 0: 4624.7. Samples: 1065498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:34:12,839][01465] Avg episode reward: [(0, '4.737')]
+[2024-12-30 10:34:14,445][03481] Updated weights for policy 0, policy_version 1050 (0.0012)
+[2024-12-30 10:34:16,611][03481] Updated weights for policy 0, policy_version 1060 (0.0013)
+[2024-12-30 10:34:17,837][01465] Fps is (10 sec: 18432.2, 60 sec: 18500.3, 300 sec: 18176.0). Total num frames: 4362240. Throughput: 0: 4625.0. Samples: 1079456. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-30 10:34:17,839][01465] Avg episode reward: [(0, '4.850')]
+[2024-12-30 10:34:18,841][03481] Updated weights for policy 0, policy_version 1070 (0.0012)
+[2024-12-30 10:34:21,167][03481] Updated weights for policy 0, policy_version 1080 (0.0012)
+[2024-12-30 10:34:22,837][01465] Fps is (10 sec: 18431.8, 60 sec: 18432.0, 300 sec: 18172.9). Total num frames: 4452352. Throughput: 0: 4603.6. Samples: 1106666. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:34:22,839][01465] Avg episode reward: [(0, '4.792')]
+[2024-12-30 10:34:23,430][03481] Updated weights for policy 0, policy_version 1090 (0.0012)
+[2024-12-30 10:34:25,667][03481] Updated weights for policy 0, policy_version 1100 (0.0012)
+[2024-12-30 10:34:27,837][01465] Fps is (10 sec: 18022.3, 60 sec: 18432.0, 300 sec: 18169.9). Total num frames: 4542464. Throughput: 0: 4604.3. Samples: 1134060. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-12-30 10:34:27,839][01465] Avg episode reward: [(0, '4.692')]
+[2024-12-30 10:34:27,882][03481] Updated weights for policy 0, policy_version 1110 (0.0012)
+[2024-12-30 10:34:30,090][03481] Updated weights for policy 0, policy_version 1120 (0.0012)
+[2024-12-30 10:34:32,278][03481] Updated weights for policy 0, policy_version 1130 (0.0012)
+[2024-12-30 10:34:32,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 18183.0). Total num frames: 4636672. Throughput: 0: 4605.2. Samples: 1148120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:34:32,839][01465] Avg episode reward: [(0, '4.820')]
+[2024-12-30 10:34:34,576][03481] Updated weights for policy 0, policy_version 1140 (0.0013)
+[2024-12-30 10:34:36,839][03481] Updated weights for policy 0, policy_version 1150 (0.0013)
+[2024-12-30 10:34:37,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18363.8, 300 sec: 18179.9). Total num frames: 4726784. Throughput: 0: 4589.0. Samples: 1175254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:34:37,839][01465] Avg episode reward: [(0, '4.628')]
+[2024-12-30 10:34:39,046][03481] Updated weights for policy 0, policy_version 1160 (0.0013)
+[2024-12-30 10:34:41,252][03481] Updated weights for policy 0, policy_version 1170 (0.0012)
+[2024-12-30 10:34:42,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 18192.4). Total num frames: 4820992. Throughput: 0: 4596.0. Samples: 1203168. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:34:42,840][01465] Avg episode reward: [(0, '4.768')]
+[2024-12-30 10:34:43,444][03481] Updated weights for policy 0, policy_version 1180 (0.0012)
+[2024-12-30 10:34:45,672][03481] Updated weights for policy 0, policy_version 1190 (0.0012)
+[2024-12-30 10:34:47,837][01465] Fps is (10 sec: 18431.7, 60 sec: 18363.7, 300 sec: 18189.3). Total num frames: 4911104. Throughput: 0: 4595.6. Samples: 1217098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:34:47,839][01465] Avg episode reward: [(0, '4.601')]
+[2024-12-30 10:34:47,946][03481] Updated weights for policy 0, policy_version 1200 (0.0013)
+[2024-12-30 10:34:50,205][03481] Updated weights for policy 0, policy_version 1210 (0.0013)
+[2024-12-30 10:34:52,386][03481] Updated weights for policy 0, policy_version 1220 (0.0012)
+[2024-12-30 10:34:52,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 18201.1). Total num frames: 5005312. Throughput: 0: 4588.5. Samples: 1244338. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:34:52,839][01465] Avg episode reward: [(0, '4.512')]
+[2024-12-30 10:34:54,581][03481] Updated weights for policy 0, policy_version 1230 (0.0013)
+[2024-12-30 10:34:56,795][03481] Updated weights for policy 0, policy_version 1240 (0.0013)
+[2024-12-30 10:34:57,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18363.7, 300 sec: 18197.9). Total num frames: 5095424. Throughput: 0: 4594.5. Samples: 1272252. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:34:57,839][01465] Avg episode reward: [(0, '4.458')]
+[2024-12-30 10:34:59,000][03481] Updated weights for policy 0, policy_version 1250 (0.0013)
+[2024-12-30 10:35:01,279][03481] Updated weights for policy 0, policy_version 1260 (0.0012)
+[2024-12-30 10:35:02,837][01465] Fps is (10 sec: 18022.2, 60 sec: 18295.5, 300 sec: 18194.9). Total num frames: 5185536. Throughput: 0: 4590.5. Samples: 1286030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:35:02,839][01465] Avg episode reward: [(0, '4.709')]
+[2024-12-30 10:35:03,577][03481] Updated weights for policy 0, policy_version 1270 (0.0012)
+[2024-12-30 10:35:05,802][03481] Updated weights for policy 0, policy_version 1280 (0.0013)
+[2024-12-30 10:35:07,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18363.7, 300 sec: 18206.0). Total num frames: 5279744. Throughput: 0: 4590.8. Samples: 1313252. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-12-30 10:35:07,839][01465] Avg episode reward: [(0, '4.521')]
+[2024-12-30 10:35:07,992][03481] Updated weights for policy 0, policy_version 1290 (0.0012)
+[2024-12-30 10:35:10,158][03481] Updated weights for policy 0, policy_version 1300 (0.0012)
+[2024-12-30 10:35:12,395][03481] Updated weights for policy 0, policy_version 1310 (0.0012)
+[2024-12-30 10:35:12,837][01465] Fps is (10 sec: 18841.6, 60 sec: 18432.0, 300 sec: 18216.8). Total num frames: 5373952. Throughput: 0: 4602.0. Samples: 1341152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:35:12,839][01465] Avg episode reward: [(0, '4.527')]
+[2024-12-30 10:35:14,572][03481] Updated weights for policy 0, policy_version 1320 (0.0013)
+[2024-12-30 10:35:16,895][03481] Updated weights for policy 0, policy_version 1330 (0.0012)
+[2024-12-30 10:35:17,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18363.7, 300 sec: 18425.1). Total num frames: 5464064. Throughput: 0: 4597.9. Samples: 1355026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:35:17,840][01465] Avg episode reward: [(0, '4.708')]
+[2024-12-30 10:35:19,081][03481] Updated weights for policy 0, policy_version 1340 (0.0012)
+[2024-12-30 10:35:21,276][03481] Updated weights for policy 0, policy_version 1350 (0.0012)
+[2024-12-30 10:35:22,837][01465] Fps is (10 sec: 18432.2, 60 sec: 18432.0, 300 sec: 18438.9). Total num frames: 5558272. Throughput: 0: 4609.2. Samples: 1382670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:35:22,839][01465] Avg episode reward: [(0, '4.684')]
+[2024-12-30 10:35:23,490][03481] Updated weights for policy 0, policy_version 1360 (0.0012)
+[2024-12-30 10:35:25,683][03481] Updated weights for policy 0, policy_version 1370 (0.0012)
+[2024-12-30 10:35:27,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 18425.1). Total num frames: 5648384. Throughput: 0: 4606.9. Samples: 1410480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:35:27,839][01465] Avg episode reward: [(0, '4.692')]
+[2024-12-30 10:35:27,985][03481] Updated weights for policy 0, policy_version 1380 (0.0013)
+[2024-12-30 10:35:30,277][03481] Updated weights for policy 0, policy_version 1390 (0.0013)
+[2024-12-30 10:35:32,514][03481] Updated weights for policy 0, policy_version 1400 (0.0011)
+[2024-12-30 10:35:32,837][01465] Fps is (10 sec: 18022.4, 60 sec: 18363.7, 300 sec: 18411.2). Total num frames: 5738496. Throughput: 0: 4589.7. Samples: 1423634. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:35:32,839][01465] Avg episode reward: [(0, '4.731')]
+[2024-12-30 10:35:34,708][03481] Updated weights for policy 0, policy_version 1410 (0.0012)
+[2024-12-30 10:35:36,908][03481] Updated weights for policy 0, policy_version 1420 (0.0012)
+[2024-12-30 10:35:37,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18432.0, 300 sec: 18425.1). Total num frames: 5832704. Throughput: 0: 4601.9. Samples: 1451424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:35:37,839][01465] Avg episode reward: [(0, '4.544')]
+[2024-12-30 10:35:39,129][03481] Updated weights for policy 0, policy_version 1430 (0.0013)
+[2024-12-30 10:35:41,338][03481] Updated weights for policy 0, policy_version 1440 (0.0012)
+[2024-12-30 10:35:42,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18363.7, 300 sec: 18411.2). Total num frames: 5922816. Throughput: 0: 4597.6. Samples: 1479146. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:35:42,840][01465] Avg episode reward: [(0, '4.629')]
+[2024-12-30 10:35:43,627][03481] Updated weights for policy 0, policy_version 1450 (0.0013)
+[2024-12-30 10:35:45,878][03481] Updated weights for policy 0, policy_version 1460 (0.0012)
+[2024-12-30 10:35:47,837][01465] Fps is (10 sec: 18022.5, 60 sec: 18363.8, 300 sec: 18397.3). Total num frames: 6012928. Throughput: 0: 4588.6. Samples: 1492516. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-30 10:35:47,840][01465] Avg episode reward: [(0, '4.814')]
+[2024-12-30 10:35:48,078][03481] Updated weights for policy 0, policy_version 1470 (0.0013)
+[2024-12-30 10:35:50,276][03481] Updated weights for policy 0, policy_version 1480 (0.0012)
+[2024-12-30 10:35:52,471][03481] Updated weights for policy 0, policy_version 1490 (0.0012)
+[2024-12-30 10:35:52,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18363.7, 300 sec: 18411.2). Total num frames: 6107136. Throughput: 0: 4604.4. Samples: 1520452. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:35:52,840][01465] Avg episode reward: [(0, '4.757')]
+[2024-12-30 10:35:54,713][03481] Updated weights for policy 0, policy_version 1500 (0.0012)
+[2024-12-30 10:35:56,982][03481] Updated weights for policy 0, policy_version 1510 (0.0013)
+[2024-12-30 10:35:57,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18363.8, 300 sec: 18411.2). Total num frames: 6197248. Throughput: 0: 4592.5. Samples: 1547812. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:35:57,839][01465] Avg episode reward: [(0, '4.777')]
+[2024-12-30 10:35:59,257][03481] Updated weights for policy 0, policy_version 1520 (0.0012)
+[2024-12-30 10:36:01,445][03481] Updated weights for policy 0, policy_version 1530 (0.0012)
+[2024-12-30 10:36:02,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 18425.1). Total num frames: 6291456. Throughput: 0: 4589.8. Samples: 1561566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:36:02,839][01465] Avg episode reward: [(0, '4.565')]
+[2024-12-30 10:36:02,846][03468] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001536_6291456.pth...
+[2024-12-30 10:36:02,913][03468] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000457_1871872.pth
+[2024-12-30 10:36:03,656][03481] Updated weights for policy 0, policy_version 1540 (0.0012)
+[2024-12-30 10:36:05,898][03481] Updated weights for policy 0, policy_version 1550 (0.0012)
+[2024-12-30 10:36:07,837][01465] Fps is (10 sec: 18841.6, 60 sec: 18432.0, 300 sec: 18425.1). Total num frames: 6385664. Throughput: 0: 4591.9. Samples: 1589306. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:36:07,839][01465] Avg episode reward: [(0, '4.667')]
+[2024-12-30 10:36:08,073][03481] Updated weights for policy 0, policy_version 1560 (0.0012)
+[2024-12-30 10:36:10,359][03481] Updated weights for policy 0, policy_version 1570 (0.0013)
+[2024-12-30 10:36:12,655][03481] Updated weights for policy 0, policy_version 1580 (0.0013)
+[2024-12-30 10:36:12,837][01465] Fps is (10 sec: 18022.2, 60 sec: 18295.5, 300 sec: 18397.3). Total num frames: 6471680. Throughput: 0: 4577.9. Samples: 1616484. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-30 10:36:12,839][01465] Avg episode reward: [(0, '4.465')]
+[2024-12-30 10:36:14,902][03481] Updated weights for policy 0, policy_version 1590 (0.0013)
+[2024-12-30 10:36:17,112][03481] Updated weights for policy 0, policy_version 1600 (0.0012)
+[2024-12-30 10:36:17,837][01465] Fps is (10 sec: 18022.4, 60 sec: 18363.7, 300 sec: 18425.1). Total num frames: 6565888. Throughput: 0: 4590.7. Samples: 1630216. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:36:17,840][01465] Avg episode reward: [(0, '4.685')]
+[2024-12-30 10:36:19,335][03481] Updated weights for policy 0, policy_version 1610 (0.0012)
+[2024-12-30 10:36:21,571][03481] Updated weights for policy 0, policy_version 1620 (0.0012)
+[2024-12-30 10:36:22,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18295.4, 300 sec: 18411.2). Total num frames: 6656000. Throughput: 0: 4588.1. Samples: 1657888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:36:22,839][01465] Avg episode reward: [(0, '4.692')]
+[2024-12-30 10:36:23,813][03481] Updated weights for policy 0, policy_version 1630 (0.0012)
+[2024-12-30 10:36:26,118][03481] Updated weights for policy 0, policy_version 1640 (0.0012)
+[2024-12-30 10:36:27,837][01465] Fps is (10 sec: 18022.3, 60 sec: 18295.5, 300 sec: 18397.3). Total num frames: 6746112. Throughput: 0: 4574.4. Samples: 1684994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:36:27,839][01465] Avg episode reward: [(0, '4.640')]
+[2024-12-30 10:36:28,315][03481] Updated weights for policy 0, policy_version 1650 (0.0012)
+[2024-12-30 10:36:30,613][03481] Updated weights for policy 0, policy_version 1660 (0.0012)
+[2024-12-30 10:36:32,808][03481] Updated weights for policy 0, policy_version 1670 (0.0012)
+[2024-12-30 10:36:32,837][01465] Fps is (10 sec: 18432.2, 60 sec: 18363.7, 300 sec: 18411.2). Total num frames: 6840320. Throughput: 0: 4580.3. Samples: 1698628. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:36:32,839][01465] Avg episode reward: [(0, '4.775')]
+[2024-12-30 10:36:34,991][03481] Updated weights for policy 0, policy_version 1680 (0.0012)
+[2024-12-30 10:36:37,253][03481] Updated weights for policy 0, policy_version 1690 (0.0012)
+[2024-12-30 10:36:37,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18295.5, 300 sec: 18397.3). Total num frames: 6930432. Throughput: 0: 4578.8. Samples: 1726496. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:36:37,839][01465] Avg episode reward: [(0, '4.610')]
+[2024-12-30 10:36:39,552][03481] Updated weights for policy 0, policy_version 1700 (0.0013)
+[2024-12-30 10:36:41,756][03481] Updated weights for policy 0, policy_version 1710 (0.0012)
+[2024-12-30 10:36:42,837][01465] Fps is (10 sec: 18022.3, 60 sec: 18295.5, 300 sec: 18397.3). Total num frames: 7020544. Throughput: 0: 4575.5. Samples: 1753710. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:36:42,840][01465] Avg episode reward: [(0, '4.874')]
+[2024-12-30 10:36:43,954][03481] Updated weights for policy 0, policy_version 1720 (0.0012)
+[2024-12-30 10:36:46,163][03481] Updated weights for policy 0, policy_version 1730 (0.0012)
+[2024-12-30 10:36:47,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18363.7, 300 sec: 18397.3). Total num frames: 7114752. Throughput: 0: 4581.5. Samples: 1767732. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:36:47,839][01465] Avg episode reward: [(0, '4.603')]
+[2024-12-30 10:36:48,355][03481] Updated weights for policy 0, policy_version 1740 (0.0012)
+[2024-12-30 10:36:50,593][03481] Updated weights for policy 0, policy_version 1750 (0.0013)
+[2024-12-30 10:36:52,816][03481] Updated weights for policy 0, policy_version 1760 (0.0013)
+[2024-12-30 10:36:52,837][01465] Fps is (10 sec: 18841.8, 60 sec: 18363.8, 300 sec: 18411.2). Total num frames: 7208960. Throughput: 0: 4583.2. Samples: 1795548. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:36:52,839][01465] Avg episode reward: [(0, '4.803')]
+[2024-12-30 10:36:55,065][03481] Updated weights for policy 0, policy_version 1770 (0.0012)
+[2024-12-30 10:36:57,274][03481] Updated weights for policy 0, policy_version 1780 (0.0012)
+[2024-12-30 10:36:57,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18363.7, 300 sec: 18397.3). Total num frames: 7299072. Throughput: 0: 4588.7. Samples: 1822976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:36:57,839][01465] Avg episode reward: [(0, '4.428')]
+[2024-12-30 10:36:59,450][03481] Updated weights for policy 0, policy_version 1790 (0.0013)
+[2024-12-30 10:37:01,695][03481] Updated weights for policy 0, policy_version 1800 (0.0012)
+[2024-12-30 10:37:02,837][01465] Fps is (10 sec: 18432.0, 60 sec: 18363.7, 300 sec: 18411.2). Total num frames: 7393280. Throughput: 0: 4593.8. Samples: 1836936. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:37:02,839][01465] Avg episode reward: [(0, '4.588')]
+[2024-12-30 10:37:03,840][03481] Updated weights for policy 0, policy_version 1810 (0.0013)
+[2024-12-30 10:37:06,195][03481] Updated weights for policy 0, policy_version 1820 (0.0013)
+[2024-12-30 10:37:07,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18295.5, 300 sec: 18397.3). Total num frames: 7483392. Throughput: 0: 4590.4. Samples: 1864454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:37:07,839][01465] Avg episode reward: [(0, '4.568')]
+[2024-12-30 10:37:08,427][03481] Updated weights for policy 0, policy_version 1830 (0.0012)
+[2024-12-30 10:37:10,650][03481] Updated weights for policy 0, policy_version 1840 (0.0013)
+[2024-12-30 10:37:12,837][01465] Fps is (10 sec: 18022.4, 60 sec: 18363.8, 300 sec: 18397.3). Total num frames: 7573504. Throughput: 0: 4599.6. Samples: 1891974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:37:12,839][01465] Avg episode reward: [(0, '4.662')]
+[2024-12-30 10:37:12,855][03481] Updated weights for policy 0, policy_version 1850 (0.0012)
+[2024-12-30 10:37:15,044][03481] Updated weights for policy 0, policy_version 1860 (0.0012)
+[2024-12-30 10:37:17,255][03481] Updated weights for policy 0, policy_version 1870 (0.0012)
+[2024-12-30 10:37:17,837][01465] Fps is (10 sec: 18431.8, 60 sec: 18363.7, 300 sec: 18411.2). Total num frames: 7667712. Throughput: 0: 4607.8. Samples: 1905980. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-30 10:37:17,840][01465] Avg episode reward: [(0, '4.525')]
+[2024-12-30 10:37:19,474][03481] Updated weights for policy 0, policy_version 1880 (0.0012)
+[2024-12-30 10:37:21,790][03481] Updated weights for policy 0, policy_version 1890 (0.0013)
+[2024-12-30 10:37:22,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18363.8, 300 sec: 18397.3). Total num frames: 7757824. Throughput: 0: 4596.8. Samples: 1933350. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-30 10:37:22,840][01465] Avg episode reward: [(0, '4.804')]
+[2024-12-30 10:37:23,951][03481] Updated weights for policy 0, policy_version 1900 (0.0012)
+[2024-12-30 10:37:26,188][03481] Updated weights for policy 0, policy_version 1910 (0.0012)
+[2024-12-30 10:37:27,837][01465] Fps is (10 sec: 18432.1, 60 sec: 18432.0, 300 sec: 18411.2). Total num frames: 7852032. Throughput: 0: 4610.0. Samples: 1961158. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-30 10:37:27,839][01465] Avg episode reward: [(0, '4.649')]
+[2024-12-30 10:37:28,420][03481] Updated weights for policy 0, policy_version 1920 (0.0012)
+[2024-12-30 10:37:30,689][03481] Updated weights for policy 0, policy_version 1930 (0.0012)
+[2024-12-30 10:37:32,837][01465] Fps is (10 sec: 18431.9, 60 sec: 18363.7, 300 sec: 18397.3). Total num frames: 7942144. Throughput: 0: 4604.5. Samples: 1974936. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-30 10:37:32,840][01465] Avg episode reward: [(0, '4.867')]
+[2024-12-30 10:37:32,914][03481] Updated weights for policy 0, policy_version 1940 (0.0012)
+[2024-12-30 10:37:35,216][03481] Updated weights for policy 0, policy_version 1950 (0.0013)
+[2024-12-30 10:37:36,332][03468] Stopping Batcher_0...
+[2024-12-30 10:37:36,332][03468] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-12-30 10:37:36,332][01465] Component Batcher_0 stopped!
+[2024-12-30 10:37:36,336][01465] Component RolloutWorker_w2 process died already! Don't wait for it.
+[2024-12-30 10:37:36,333][03468] Loop batcher_evt_loop terminating...
+[2024-12-30 10:37:36,352][03481] Weights refcount: 2 0
+[2024-12-30 10:37:36,354][03481] Stopping InferenceWorker_p0-w0...
+[2024-12-30 10:37:36,354][03481] Loop inference_proc0-0_evt_loop terminating...
+[2024-12-30 10:37:36,354][01465] Component InferenceWorker_p0-w0 stopped!
+[2024-12-30 10:37:36,374][03482] Stopping RolloutWorker_w0...
+[2024-12-30 10:37:36,374][03482] Loop rollout_proc0_evt_loop terminating...
+[2024-12-30 10:37:36,375][03488] Stopping RolloutWorker_w6...
+[2024-12-30 10:37:36,376][03488] Loop rollout_proc6_evt_loop terminating...
+[2024-12-30 10:37:36,376][03489] Stopping RolloutWorker_w7...
+[2024-12-30 10:37:36,377][03489] Loop rollout_proc7_evt_loop terminating...
+[2024-12-30 10:37:36,374][01465] Component RolloutWorker_w0 stopped!
+[2024-12-30 10:37:36,378][03487] Stopping RolloutWorker_w5...
+[2024-12-30 10:37:36,378][03487] Loop rollout_proc5_evt_loop terminating...
+[2024-12-30 10:37:36,379][03486] Stopping RolloutWorker_w4...
+[2024-12-30 10:37:36,378][01465] Component RolloutWorker_w6 stopped!
+[2024-12-30 10:37:36,379][03486] Loop rollout_proc4_evt_loop terminating...
+[2024-12-30 10:37:36,381][03485] Stopping RolloutWorker_w3...
+[2024-12-30 10:37:36,381][03483] Stopping RolloutWorker_w1...
+[2024-12-30 10:37:36,380][01465] Component RolloutWorker_w7 stopped!
+[2024-12-30 10:37:36,382][03483] Loop rollout_proc1_evt_loop terminating...
+[2024-12-30 10:37:36,382][03485] Loop rollout_proc3_evt_loop terminating...
+[2024-12-30 10:37:36,381][01465] Component RolloutWorker_w5 stopped!
+[2024-12-30 10:37:36,384][01465] Component RolloutWorker_w4 stopped!
+[2024-12-30 10:37:36,386][01465] Component RolloutWorker_w1 stopped!
+[2024-12-30 10:37:36,387][01465] Component RolloutWorker_w3 stopped!
+[2024-12-30 10:37:36,403][03468] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000998_4087808.pth
+[2024-12-30 10:37:36,410][03468] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-12-30 10:37:36,501][03468] Stopping LearnerWorker_p0...
+[2024-12-30 10:37:36,502][03468] Loop learner_proc0_evt_loop terminating...
+[2024-12-30 10:37:36,501][01465] Component LearnerWorker_p0 stopped!
+[2024-12-30 10:37:36,503][01465] Waiting for process learner_proc0 to stop...
+[2024-12-30 10:37:37,294][01465] Waiting for process inference_proc0-0 to join...
+[2024-12-30 10:37:37,297][01465] Waiting for process rollout_proc0 to join...
+[2024-12-30 10:37:37,300][01465] Waiting for process rollout_proc1 to join...
+[2024-12-30 10:37:37,302][01465] Waiting for process rollout_proc2 to join...
+[2024-12-30 10:37:37,303][01465] Waiting for process rollout_proc3 to join...
+[2024-12-30 10:37:37,306][01465] Waiting for process rollout_proc4 to join...
+[2024-12-30 10:37:37,308][01465] Waiting for process rollout_proc5 to join...
+[2024-12-30 10:37:37,310][01465] Waiting for process rollout_proc6 to join...
+[2024-12-30 10:37:37,312][01465] Waiting for process rollout_proc7 to join...
+[2024-12-30 10:37:37,314][01465] Batcher 0 profile tree view:
+batching: 33.3854, releasing_batches: 0.0470
+[2024-12-30 10:37:37,315][01465] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 6.2712
+update_model: 7.1247
+  weight_update: 0.0013
+one_step: 0.0026
+  handle_policy_step: 405.1775
+    deserialize: 15.8144, stack: 2.8331, obs_to_device_normalize: 99.4388, forward: 190.8124, send_messages: 26.6499
+    prepare_outputs: 50.8271
+      to_cpu: 32.1937
+[2024-12-30 10:37:37,317][01465] Learner 0 profile tree view:
+misc: 0.0104, prepare_batch: 12.0264
+train: 37.1198
+  epoch_init: 0.0111, minibatch_init: 0.0121, losses_postprocess: 0.5828, kl_divergence: 0.6577, after_optimizer: 3.8842
+  calculate_losses: 17.6783
+    losses_init: 0.0067, forward_head: 1.2012, bptt_initial: 10.3624, tail: 1.1699, advantages_returns: 0.2829, losses: 2.2039
+    bptt: 2.1274
+      bptt_forward_core: 2.0285
+  update: 13.6242
+    clip: 1.3669
+[2024-12-30 10:37:37,319][01465] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.3386, enqueue_policy_requests: 16.8010, env_step: 277.7332, overhead: 13.5700, complete_rollouts: 0.5059
+save_policy_outputs: 20.1764
+  split_output_tensors: 8.1735
+[2024-12-30 10:37:37,321][01465] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.3207, enqueue_policy_requests: 16.6135, env_step: 278.3224, overhead: 13.7889, complete_rollouts: 0.5063
+save_policy_outputs: 19.5848
+  split_output_tensors: 7.9144
+[2024-12-30 10:37:37,322][01465] Loop Runner_EvtLoop terminating...
+[2024-12-30 10:37:37,324][01465] Runner profile tree view:
+main_loop: 449.3978
+[2024-12-30 10:37:37,325][01465] Collected {0: 8007680}, FPS: 17818.7
+[2024-12-30 10:38:48,430][01465] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-12-30 10:38:48,431][01465] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-12-30 10:38:48,433][01465] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-12-30 10:38:48,435][01465] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-12-30 10:38:48,436][01465] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-12-30 10:38:48,437][01465] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-12-30 10:38:48,439][01465] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-12-30 10:38:48,441][01465] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-12-30 10:38:48,442][01465] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-12-30 10:38:48,444][01465] Adding new argument 'hf_repository'='AneeshSinha/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-12-30 10:38:48,445][01465] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-12-30 10:38:48,446][01465] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-12-30 10:38:48,447][01465] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-12-30 10:38:48,449][01465] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-12-30 10:38:48,451][01465] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-12-30 10:38:48,479][01465] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-30 10:38:48,483][01465] RunningMeanStd input shape: (3, 72, 128)
+[2024-12-30 10:38:48,485][01465] RunningMeanStd input shape: (1,)
+[2024-12-30 10:38:48,500][01465] ConvEncoder: input_channels=3
+[2024-12-30 10:38:48,611][01465] Conv encoder output size: 512
+[2024-12-30 10:38:48,612][01465] Policy head output size: 512
+[2024-12-30 10:38:48,770][01465] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-12-30 10:38:49,553][01465] Num frames 100...
+[2024-12-30 10:38:49,675][01465] Num frames 200...
+[2024-12-30 10:38:49,796][01465] Num frames 300...
+[2024-12-30 10:38:49,916][01465] Num frames 400...
+[2024-12-30 10:38:50,028][01465] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2024-12-30 10:38:50,029][01465] Avg episode reward: 5.480, avg true_objective: 4.480
+[2024-12-30 10:38:50,093][01465] Num frames 500...
+[2024-12-30 10:38:50,215][01465] Num frames 600...
+[2024-12-30 10:38:50,336][01465] Num frames 700...
+[2024-12-30 10:38:50,457][01465] Num frames 800...
+[2024-12-30 10:38:50,551][01465] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160
+[2024-12-30 10:38:50,553][01465] Avg episode reward: 4.660, avg true_objective: 4.160
+[2024-12-30 10:38:50,635][01465] Num frames 900...
+[2024-12-30 10:38:50,755][01465] Num frames 1000...
+[2024-12-30 10:38:50,874][01465] Num frames 1100...
+[2024-12-30 10:38:50,989][01465] Num frames 1200...
+[2024-12-30 10:38:51,063][01465] Avg episode rewards: #0: 4.387, true rewards: #0: 4.053
+[2024-12-30 10:38:51,064][01465] Avg episode reward: 4.387, avg true_objective: 4.053
+[2024-12-30 10:38:51,165][01465] Num frames 1300...
+[2024-12-30 10:38:51,284][01465] Num frames 1400...
+[2024-12-30 10:38:51,409][01465] Num frames 1500...
+[2024-12-30 10:38:51,529][01465] Num frames 1600...
+[2024-12-30 10:38:51,668][01465] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160
+[2024-12-30 10:38:51,669][01465] Avg episode reward: 4.660, avg true_objective: 4.160
+[2024-12-30 10:38:51,715][01465] Num frames 1700...
+[2024-12-30 10:38:51,835][01465] Num frames 1800...
+[2024-12-30 10:38:51,965][01465] Num frames 1900...
+[2024-12-30 10:38:52,098][01465] Num frames 2000...
+[2024-12-30 10:38:52,256][01465] Avg episode rewards: #0: 4.970, true rewards: #0: 4.170
+[2024-12-30 10:38:52,257][01465] Avg episode reward: 4.970, avg true_objective: 4.170
+[2024-12-30 10:38:52,276][01465] Num frames 2100...
+[2024-12-30 10:38:52,396][01465] Num frames 2200...
+[2024-12-30 10:38:52,516][01465] Num frames 2300...
+[2024-12-30 10:38:52,639][01465] Num frames 2400...
+[2024-12-30 10:38:52,780][01465] Avg episode rewards: #0: 4.782, true rewards: #0: 4.115
+[2024-12-30 10:38:52,781][01465] Avg episode reward: 4.782, avg true_objective: 4.115
+[2024-12-30 10:38:52,819][01465] Num frames 2500...
+[2024-12-30 10:38:52,939][01465] Num frames 2600...
+[2024-12-30 10:38:53,059][01465] Num frames 2700...
+[2024-12-30 10:38:53,179][01465] Num frames 2800...
+[2024-12-30 10:38:53,299][01465] Avg episode rewards: #0: 4.647, true rewards: #0: 4.076
+[2024-12-30 10:38:53,301][01465] Avg episode reward: 4.647, avg true_objective: 4.076
+[2024-12-30 10:38:53,357][01465] Num frames 2900...
+[2024-12-30 10:38:53,474][01465] Num frames 3000...
+[2024-12-30 10:38:53,595][01465] Num frames 3100...
+[2024-12-30 10:38:53,716][01465] Num frames 3200...
+[2024-12-30 10:38:53,855][01465] Avg episode rewards: #0: 4.586, true rewards: #0: 4.086
+[2024-12-30 10:38:53,857][01465] Avg episode reward: 4.586, avg true_objective: 4.086
+[2024-12-30 10:38:53,894][01465] Num frames 3300...
+[2024-12-30 10:38:54,014][01465] Num frames 3400...
+[2024-12-30 10:38:54,136][01465] Num frames 3500...
+[2024-12-30 10:38:54,257][01465] Num frames 3600...
+[2024-12-30 10:38:54,377][01465] Avg episode rewards: #0: 4.503, true rewards: #0: 4.059
+[2024-12-30 10:38:54,378][01465] Avg episode reward: 4.503, avg true_objective: 4.059
+[2024-12-30 10:38:54,440][01465] Num frames 3700...
+[2024-12-30 10:38:54,561][01465] Num frames 3800...
+[2024-12-30 10:38:54,684][01465] Num frames 3900...
+[2024-12-30 10:38:54,805][01465] Num frames 4000...
+[2024-12-30 10:38:54,905][01465] Avg episode rewards: #0: 4.437, true rewards: #0: 4.037
+[2024-12-30 10:38:54,906][01465] Avg episode reward: 4.437, avg true_objective: 4.037
+[2024-12-30 10:39:03,403][01465] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-12-30 10:39:10,074][01465] The model has been pushed to https://huggingface.co/AneeshSinha/rl_course_vizdoom_health_gathering_supreme
+[2024-12-30 10:44:34,778][01465] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-12-30 10:44:34,779][01465] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-12-30 10:44:34,781][01465] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-12-30 10:44:34,782][01465] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-12-30 10:44:34,784][01465] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-12-30 10:44:34,785][01465] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-12-30 10:44:34,786][01465] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-12-30 10:44:34,787][01465] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-12-30 10:44:34,789][01465] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-12-30 10:44:34,790][01465] Adding new argument 'hf_repository'='AneeshSinha/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-12-30 10:44:34,791][01465] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-12-30 10:44:34,792][01465] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-12-30 10:44:34,794][01465] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-12-30 10:44:34,795][01465] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-12-30 10:44:34,797][01465] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-12-30 10:44:34,820][01465] RunningMeanStd input shape: (3, 72, 128)
+[2024-12-30 10:44:34,822][01465] RunningMeanStd input shape: (1,)
+[2024-12-30 10:44:34,833][01465] ConvEncoder: input_channels=3
+[2024-12-30 10:44:34,873][01465] Conv encoder output size: 512
+[2024-12-30 10:44:34,875][01465] Policy head output size: 512
+[2024-12-30 10:44:34,896][01465] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-12-30 10:44:35,305][01465] Num frames 100...
+[2024-12-30 10:44:35,427][01465] Num frames 200...
+[2024-12-30 10:44:35,548][01465] Num frames 300...
+[2024-12-30 10:44:35,668][01465] Num frames 400...
+[2024-12-30 10:44:35,743][01465] Avg episode rewards: #0: 5.160, true rewards: #0: 4.160
+[2024-12-30 10:44:35,745][01465] Avg episode reward: 5.160, avg true_objective: 4.160
+[2024-12-30 10:44:35,845][01465] Num frames 500...
+[2024-12-30 10:44:35,964][01465] Num frames 600...
+[2024-12-30 10:44:36,082][01465] Num frames 700...
+[2024-12-30 10:44:36,204][01465] Num frames 800...
+[2024-12-30 10:44:36,257][01465] Avg episode rewards: #0: 4.500, true rewards: #0: 4.000
+[2024-12-30 10:44:36,258][01465] Avg episode reward: 4.500, avg true_objective: 4.000
+[2024-12-30 10:44:36,376][01465] Num frames 900...
+[2024-12-30 10:44:36,491][01465] Num frames 1000...
+[2024-12-30 10:44:36,610][01465] Num frames 1100...
+[2024-12-30 10:44:36,764][01465] Avg episode rewards: #0: 4.280, true rewards: #0: 3.947
+[2024-12-30 10:44:36,765][01465] Avg episode reward: 4.280, avg true_objective: 3.947
+[2024-12-30 10:44:36,788][01465] Num frames 1200...
+[2024-12-30 10:44:36,910][01465] Num frames 1300...
+[2024-12-30 10:44:37,037][01465] Num frames 1400...
+[2024-12-30 10:44:37,159][01465] Num frames 1500...
+[2024-12-30 10:44:37,296][01465] Avg episode rewards: #0: 4.170, true rewards: #0: 3.920
+[2024-12-30 10:44:37,297][01465] Avg episode reward: 4.170, avg true_objective: 3.920
+[2024-12-30 10:44:37,338][01465] Num frames 1600...
+[2024-12-30 10:44:37,460][01465] Num frames 1700...
+[2024-12-30 10:44:37,585][01465] Num frames 1800...
+[2024-12-30 10:44:37,706][01465] Num frames 1900...
+[2024-12-30 10:44:37,823][01465] Avg episode rewards: #0: 4.104, true rewards: #0: 3.904
+[2024-12-30 10:44:37,824][01465] Avg episode reward: 4.104, avg true_objective: 3.904
+[2024-12-30 10:44:37,884][01465] Num frames 2000...
+[2024-12-30 10:44:38,004][01465] Num frames 2100...
+[2024-12-30 10:44:38,125][01465] Num frames 2200...
+[2024-12-30 10:44:38,243][01465] Num frames 2300...
+[2024-12-30 10:44:38,339][01465] Avg episode rewards: #0: 4.060, true rewards: #0: 3.893
+[2024-12-30 10:44:38,341][01465] Avg episode reward: 4.060, avg true_objective: 3.893
+[2024-12-30 10:44:38,430][01465] Num frames 2400...
+[2024-12-30 10:44:38,553][01465] Num frames 2500...
+[2024-12-30 10:44:38,669][01465] Num frames 2600...
+[2024-12-30 10:44:38,790][01465] Num frames 2700...
+[2024-12-30 10:44:38,947][01465] Avg episode rewards: #0: 4.263, true rewards: #0: 3.977
+[2024-12-30 10:44:38,948][01465] Avg episode reward: 4.263, avg true_objective: 3.977
+[2024-12-30 10:44:38,970][01465] Num frames 2800...
+[2024-12-30 10:44:39,105][01465] Num frames 2900...
+[2024-12-30 10:44:39,223][01465] Num frames 3000...
+[2024-12-30 10:44:39,342][01465] Num frames 3100...
+[2024-12-30 10:44:39,476][01465] Avg episode rewards: #0: 4.210, true rewards: #0: 3.960
+[2024-12-30 10:44:39,478][01465] Avg episode reward: 4.210, avg true_objective: 3.960
+[2024-12-30 10:44:39,520][01465] Num frames 3200...
+[2024-12-30 10:44:39,639][01465] Num frames 3300...
+[2024-12-30 10:44:39,765][01465] Num frames 3400...
+[2024-12-30 10:44:39,896][01465] Num frames 3500...
+[2024-12-30 10:44:40,020][01465] Avg episode rewards: #0: 4.169, true rewards: #0: 3.947
+[2024-12-30 10:44:40,022][01465] Avg episode reward: 4.169, avg true_objective: 3.947
+[2024-12-30 10:44:40,085][01465] Num frames 3600...
+[2024-12-30 10:44:40,213][01465] Num frames 3700...
+[2024-12-30 10:44:40,402][01465] Num frames 3800...
+[2024-12-30 10:44:40,524][01465] Num frames 3900...
+[2024-12-30 10:44:40,650][01465] Num frames 4000...
+[2024-12-30 10:44:40,703][01465] Avg episode rewards: #0: 4.300, true rewards: #0: 4.000
+[2024-12-30 10:44:40,704][01465] Avg episode reward: 4.300, avg true_objective: 4.000
+[2024-12-30 10:44:48,944][01465] Replay video saved to /content/train_dir/default_experiment/replay.mp4!