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.1735626266.970c2c73a4a5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5d1cb0372280334de87b32765721c93ddbcbc4a3ee7b8175272e35a7391647
+size 864418

README.md

@@ -0,0 +1,56 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: doom_health_gathering_supreme
+      type: doom_health_gathering_supreme
+    metrics:
+    - type: mean_reward
+      value: 7.59 +/- 2.70
+      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 LunaMeme/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_000000978_4005888_reward_10.496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58ee3d1c2c68cc0626ee7e38d2b529ce81b565245886f247e347975429ee4c7
+size 34929051

checkpoint_p0/checkpoint_000000921_3772416.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df474029663b523eace78dffca857b014df7d6cee2df85039d7e23c8436039b8
+size 34929477

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c765b6d42724967f5ae1b13e9a0fe7a180c8d10c8d69da1dac29f11722fd1f9e
+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:e1a2c45838ad1860981f90b9974c5105fdcf9fae353ea36041766bad91074181
+size 13727530

sf_log.txt

@@ -0,0 +1,889 @@
+[2024-12-31 06:24:32,564][00788] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-12-31 06:24:32,566][00788] Rollout worker 0 uses device cpu
+[2024-12-31 06:24:32,568][00788] Rollout worker 1 uses device cpu
+[2024-12-31 06:24:32,570][00788] Rollout worker 2 uses device cpu
+[2024-12-31 06:24:32,571][00788] Rollout worker 3 uses device cpu
+[2024-12-31 06:24:32,572][00788] Rollout worker 4 uses device cpu
+[2024-12-31 06:24:32,573][00788] Rollout worker 5 uses device cpu
+[2024-12-31 06:24:32,574][00788] Rollout worker 6 uses device cpu
+[2024-12-31 06:24:32,575][00788] Rollout worker 7 uses device cpu
+[2024-12-31 06:24:32,732][00788] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-31 06:24:32,734][00788] InferenceWorker_p0-w0: min num requests: 2
+[2024-12-31 06:24:32,766][00788] Starting all processes...
+[2024-12-31 06:24:32,767][00788] Starting process learner_proc0
+[2024-12-31 06:24:32,814][00788] Starting all processes...
+[2024-12-31 06:24:32,821][00788] Starting process inference_proc0-0
+[2024-12-31 06:24:32,821][00788] Starting process rollout_proc0
+[2024-12-31 06:24:32,822][00788] Starting process rollout_proc1
+[2024-12-31 06:24:32,823][00788] Starting process rollout_proc2
+[2024-12-31 06:24:32,823][00788] Starting process rollout_proc3
+[2024-12-31 06:24:32,823][00788] Starting process rollout_proc4
+[2024-12-31 06:24:32,823][00788] Starting process rollout_proc5
+[2024-12-31 06:24:32,823][00788] Starting process rollout_proc6
+[2024-12-31 06:24:32,823][00788] Starting process rollout_proc7
+[2024-12-31 06:24:48,949][03021] Worker 7 uses CPU cores [1]
+[2024-12-31 06:24:48,955][03019] Worker 5 uses CPU cores [1]
+[2024-12-31 06:24:49,098][03017] Worker 2 uses CPU cores [0]
+[2024-12-31 06:24:49,156][03015] Worker 1 uses CPU cores [1]
+[2024-12-31 06:24:49,182][03020] Worker 6 uses CPU cores [0]
+[2024-12-31 06:24:49,187][03016] Worker 3 uses CPU cores [1]
+[2024-12-31 06:24:49,252][03014] Worker 0 uses CPU cores [0]
+[2024-12-31 06:24:49,257][03000] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-31 06:24:49,258][03000] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-12-31 06:24:49,275][03000] Num visible devices: 1
+[2024-12-31 06:24:49,297][03000] Starting seed is not provided
+[2024-12-31 06:24:49,298][03000] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-31 06:24:49,299][03000] Initializing actor-critic model on device cuda:0
+[2024-12-31 06:24:49,299][03000] RunningMeanStd input shape: (3, 72, 128)
+[2024-12-31 06:24:49,303][03000] RunningMeanStd input shape: (1,)
+[2024-12-31 06:24:49,335][03018] Worker 4 uses CPU cores [0]
+[2024-12-31 06:24:49,330][03000] ConvEncoder: input_channels=3
+[2024-12-31 06:24:49,351][03013] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-31 06:24:49,352][03013] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-12-31 06:24:49,368][03013] Num visible devices: 1
+[2024-12-31 06:24:49,596][03000] Conv encoder output size: 512
+[2024-12-31 06:24:49,596][03000] Policy head output size: 512
+[2024-12-31 06:24:49,644][03000] Created Actor Critic model with architecture:
+[2024-12-31 06:24:49,645][03000] 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)
+  )
+)
+[2024-12-31 06:24:50,009][03000] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-12-31 06:24:52,730][00788] Heartbeat connected on Batcher_0
+[2024-12-31 06:24:52,733][00788] Heartbeat connected on InferenceWorker_p0-w0
+[2024-12-31 06:24:52,742][00788] Heartbeat connected on RolloutWorker_w0
+[2024-12-31 06:24:52,745][00788] Heartbeat connected on RolloutWorker_w1
+[2024-12-31 06:24:52,749][00788] Heartbeat connected on RolloutWorker_w2
+[2024-12-31 06:24:52,752][00788] Heartbeat connected on RolloutWorker_w3
+[2024-12-31 06:24:52,755][00788] Heartbeat connected on RolloutWorker_w4
+[2024-12-31 06:24:52,759][00788] Heartbeat connected on RolloutWorker_w5
+[2024-12-31 06:24:52,764][00788] Heartbeat connected on RolloutWorker_w6
+[2024-12-31 06:24:52,767][00788] Heartbeat connected on RolloutWorker_w7
+[2024-12-31 06:24:53,290][03000] No checkpoints found
+[2024-12-31 06:24:53,290][03000] Did not load from checkpoint, starting from scratch!
+[2024-12-31 06:24:53,290][03000] Initialized policy 0 weights for model version 0
+[2024-12-31 06:24:53,294][03000] LearnerWorker_p0 finished initialization!
+[2024-12-31 06:24:53,295][03000] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-12-31 06:24:53,304][00788] Heartbeat connected on LearnerWorker_p0
+[2024-12-31 06:24:53,493][03013] RunningMeanStd input shape: (3, 72, 128)
+[2024-12-31 06:24:53,494][03013] RunningMeanStd input shape: (1,)
+[2024-12-31 06:24:53,507][03013] ConvEncoder: input_channels=3
+[2024-12-31 06:24:53,612][03013] Conv encoder output size: 512
+[2024-12-31 06:24:53,613][03013] Policy head output size: 512
+[2024-12-31 06:24:53,663][00788] Inference worker 0-0 is ready!
+[2024-12-31 06:24:53,664][00788] All inference workers are ready! Signal rollout workers to start!
+[2024-12-31 06:24:53,844][03021] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:24:53,846][03015] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:24:53,848][03016] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:24:53,849][03019] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:24:53,886][03020] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:24:53,889][03014] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:24:53,893][03017] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:24:53,891][03018] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:24:54,522][03014] Decorrelating experience for 0 frames...
+[2024-12-31 06:24:55,145][03016] Decorrelating experience for 0 frames...
+[2024-12-31 06:24:55,152][03021] Decorrelating experience for 0 frames...
+[2024-12-31 06:24:55,156][03015] Decorrelating experience for 0 frames...
+[2024-12-31 06:24:55,151][03019] Decorrelating experience for 0 frames...
+[2024-12-31 06:24:55,896][03020] Decorrelating experience for 0 frames...
+[2024-12-31 06:24:55,943][03014] Decorrelating experience for 32 frames...
+[2024-12-31 06:24:56,725][00788] 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)
+[2024-12-31 06:24:56,870][03021] Decorrelating experience for 32 frames...
+[2024-12-31 06:24:56,867][03015] Decorrelating experience for 32 frames...
+[2024-12-31 06:24:56,876][03016] Decorrelating experience for 32 frames...
+[2024-12-31 06:24:56,890][03019] Decorrelating experience for 32 frames...
+[2024-12-31 06:24:57,707][03018] Decorrelating experience for 0 frames...
+[2024-12-31 06:24:58,122][03014] Decorrelating experience for 64 frames...
+[2024-12-31 06:24:58,478][03017] Decorrelating experience for 0 frames...
+[2024-12-31 06:24:58,491][03020] Decorrelating experience for 32 frames...
+[2024-12-31 06:24:59,567][03021] Decorrelating experience for 64 frames...
+[2024-12-31 06:24:59,586][03019] Decorrelating experience for 64 frames...
+[2024-12-31 06:25:00,521][03016] Decorrelating experience for 64 frames...
+[2024-12-31 06:25:01,345][03017] Decorrelating experience for 32 frames...
+[2024-12-31 06:25:01,445][03014] Decorrelating experience for 96 frames...
+[2024-12-31 06:25:01,728][00788] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-12-31 06:25:02,151][03020] Decorrelating experience for 64 frames...
+[2024-12-31 06:25:02,297][03015] Decorrelating experience for 64 frames...
+[2024-12-31 06:25:02,336][03018] Decorrelating experience for 32 frames...
+[2024-12-31 06:25:02,434][03021] Decorrelating experience for 96 frames...
+[2024-12-31 06:25:03,273][03016] Decorrelating experience for 96 frames...
+[2024-12-31 06:25:03,802][03015] Decorrelating experience for 96 frames...
+[2024-12-31 06:25:04,022][03020] Decorrelating experience for 96 frames...
+[2024-12-31 06:25:04,151][03017] Decorrelating experience for 64 frames...
+[2024-12-31 06:25:04,627][03018] Decorrelating experience for 64 frames...
+[2024-12-31 06:25:06,491][03017] Decorrelating experience for 96 frames...
+[2024-12-31 06:25:06,725][00788] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 128.6. Samples: 1286. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-12-31 06:25:06,727][00788] Avg episode reward: [(0, '2.320')]
+[2024-12-31 06:25:07,242][03000] Signal inference workers to stop experience collection...
+[2024-12-31 06:25:07,256][03013] InferenceWorker_p0-w0: stopping experience collection
+[2024-12-31 06:25:07,300][03018] Decorrelating experience for 96 frames...
+[2024-12-31 06:25:07,371][03019] Decorrelating experience for 96 frames...
+[2024-12-31 06:25:10,320][03000] Signal inference workers to resume experience collection...
+[2024-12-31 06:25:10,321][03013] InferenceWorker_p0-w0: resuming experience collection
+[2024-12-31 06:25:11,725][00788] Fps is (10 sec: 1229.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 12288. Throughput: 0: 231.7. Samples: 3476. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2024-12-31 06:25:11,726][00788] Avg episode reward: [(0, '3.094')]
+[2024-12-31 06:25:16,725][00788] Fps is (10 sec: 2867.1, 60 sec: 1433.6, 300 sec: 1433.6). Total num frames: 28672. Throughput: 0: 328.8. Samples: 6576. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:25:16,732][00788] Avg episode reward: [(0, '3.800')]
+[2024-12-31 06:25:20,472][03013] Updated weights for policy 0, policy_version 10 (0.0158)
+[2024-12-31 06:25:21,726][00788] Fps is (10 sec: 3276.2, 60 sec: 1802.1, 300 sec: 1802.1). Total num frames: 45056. Throughput: 0: 448.7. Samples: 11218. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:25:21,728][00788] Avg episode reward: [(0, '4.292')]
+[2024-12-31 06:25:26,725][00788] Fps is (10 sec: 4096.1, 60 sec: 2321.1, 300 sec: 2321.1). Total num frames: 69632. Throughput: 0: 623.1. Samples: 18692. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:25:26,731][00788] Avg episode reward: [(0, '4.451')]
+[2024-12-31 06:25:28,563][03013] Updated weights for policy 0, policy_version 20 (0.0020)
+[2024-12-31 06:25:31,725][00788] Fps is (10 sec: 4915.7, 60 sec: 2691.6, 300 sec: 2691.6). Total num frames: 94208. Throughput: 0: 637.3. Samples: 22306. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-31 06:25:31,728][00788] Avg episode reward: [(0, '4.349')]
+[2024-12-31 06:25:36,728][00788] Fps is (10 sec: 3685.0, 60 sec: 2662.1, 300 sec: 2662.1). Total num frames: 106496. Throughput: 0: 675.5. Samples: 27024. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:25:36,736][00788] Avg episode reward: [(0, '4.230')]
+[2024-12-31 06:25:36,741][03000] Saving new best policy, reward=4.230!
+[2024-12-31 06:25:39,944][03013] Updated weights for policy 0, policy_version 30 (0.0025)
+[2024-12-31 06:25:41,725][00788] Fps is (10 sec: 3686.7, 60 sec: 2912.7, 300 sec: 2912.7). Total num frames: 131072. Throughput: 0: 742.7. Samples: 33422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:25:41,731][00788] Avg episode reward: [(0, '4.298')]
+[2024-12-31 06:25:41,734][03000] Saving new best policy, reward=4.298!
+[2024-12-31 06:25:46,725][00788] Fps is (10 sec: 4917.0, 60 sec: 3113.0, 300 sec: 3113.0). Total num frames: 155648. Throughput: 0: 823.7. Samples: 37062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:25:46,727][00788] Avg episode reward: [(0, '4.453')]
+[2024-12-31 06:25:46,733][03000] Saving new best policy, reward=4.453!
+[2024-12-31 06:25:48,836][03013] Updated weights for policy 0, policy_version 40 (0.0017)
+[2024-12-31 06:25:51,731][00788] Fps is (10 sec: 4096.0, 60 sec: 3127.9, 300 sec: 3127.9). Total num frames: 172032. Throughput: 0: 925.2. Samples: 42918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:25:51,734][00788] Avg episode reward: [(0, '4.539')]
+[2024-12-31 06:25:51,736][03000] Saving new best policy, reward=4.539!
+[2024-12-31 06:25:56,725][00788] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3140.3). Total num frames: 188416. Throughput: 0: 1002.2. Samples: 48574. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:25:56,730][00788] Avg episode reward: [(0, '4.472')]
+[2024-12-31 06:25:59,353][03013] Updated weights for policy 0, policy_version 50 (0.0023)
+[2024-12-31 06:26:01,725][00788] Fps is (10 sec: 4096.0, 60 sec: 3550.1, 300 sec: 3276.8). Total num frames: 212992. Throughput: 0: 1014.5. Samples: 52228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:01,730][00788] Avg episode reward: [(0, '4.312')]
+[2024-12-31 06:26:06,725][00788] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3335.3). Total num frames: 233472. Throughput: 0: 1056.0. Samples: 58736. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:06,727][00788] Avg episode reward: [(0, '4.342')]
+[2024-12-31 06:26:10,214][03013] Updated weights for policy 0, policy_version 60 (0.0019)
+[2024-12-31 06:26:11,725][00788] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3331.4). Total num frames: 249856. Throughput: 0: 997.1. Samples: 63560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:11,731][00788] Avg episode reward: [(0, '4.571')]
+[2024-12-31 06:26:11,734][03000] Saving new best policy, reward=4.571!
+[2024-12-31 06:26:16,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3430.4). Total num frames: 274432. Throughput: 0: 996.2. Samples: 67136. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:16,729][00788] Avg episode reward: [(0, '4.663')]
+[2024-12-31 06:26:16,736][03000] Saving new best policy, reward=4.663!
+[2024-12-31 06:26:18,818][03013] Updated weights for policy 0, policy_version 70 (0.0034)
+[2024-12-31 06:26:21,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4232.7, 300 sec: 3517.7). Total num frames: 299008. Throughput: 0: 1054.6. Samples: 74478. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:21,730][00788] Avg episode reward: [(0, '4.453')]
+[2024-12-31 06:26:26,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3458.8). Total num frames: 311296. Throughput: 0: 1013.3. Samples: 79022. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:26,732][00788] Avg episode reward: [(0, '4.416')]
+[2024-12-31 06:26:26,738][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000076_311296.pth...
+[2024-12-31 06:26:30,006][03013] Updated weights for policy 0, policy_version 80 (0.0036)
+[2024-12-31 06:26:31,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 3535.5). Total num frames: 335872. Throughput: 0: 1002.5. Samples: 82176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:31,729][00788] Avg episode reward: [(0, '4.533')]
+[2024-12-31 06:26:36,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.5, 300 sec: 3563.5). Total num frames: 356352. Throughput: 0: 1033.6. Samples: 89432. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:36,730][00788] Avg episode reward: [(0, '4.306')]
+[2024-12-31 06:26:38,680][03013] Updated weights for policy 0, policy_version 90 (0.0030)
+[2024-12-31 06:26:41,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3588.9). Total num frames: 376832. Throughput: 0: 1025.9. Samples: 94738. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-12-31 06:26:41,731][00788] Avg episode reward: [(0, '4.245')]
+[2024-12-31 06:26:46,725][00788] Fps is (10 sec: 3686.3, 60 sec: 3959.4, 300 sec: 3574.7). Total num frames: 393216. Throughput: 0: 999.0. Samples: 97184. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-31 06:26:46,732][00788] Avg episode reward: [(0, '4.601')]
+[2024-12-31 06:26:49,441][03013] Updated weights for policy 0, policy_version 100 (0.0019)
+[2024-12-31 06:26:51,725][00788] Fps is (10 sec: 4095.9, 60 sec: 4096.0, 300 sec: 3633.0). Total num frames: 417792. Throughput: 0: 1020.0. Samples: 104634. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:26:51,733][00788] Avg episode reward: [(0, '4.627')]
+[2024-12-31 06:26:56,725][00788] Fps is (10 sec: 4505.7, 60 sec: 4164.3, 300 sec: 3652.3). Total num frames: 438272. Throughput: 0: 1051.6. Samples: 110884. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-31 06:26:56,730][00788] Avg episode reward: [(0, '4.379')]
+[2024-12-31 06:26:59,894][03013] Updated weights for policy 0, policy_version 110 (0.0039)
+[2024-12-31 06:27:01,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3637.2). Total num frames: 454656. Throughput: 0: 1021.7. Samples: 113112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:27:01,730][00788] Avg episode reward: [(0, '4.297')]
+[2024-12-31 06:27:06,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3686.4). Total num frames: 479232. Throughput: 0: 1004.2. Samples: 119668. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-31 06:27:06,727][00788] Avg episode reward: [(0, '4.533')]
+[2024-12-31 06:27:08,626][03013] Updated weights for policy 0, policy_version 120 (0.0019)
+[2024-12-31 06:27:11,725][00788] Fps is (10 sec: 4915.4, 60 sec: 4232.5, 300 sec: 3731.9). Total num frames: 503808. Throughput: 0: 1062.2. Samples: 126822. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:27:11,731][00788] Avg episode reward: [(0, '4.599')]
+[2024-12-31 06:27:16,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3686.4). Total num frames: 516096. Throughput: 0: 1040.8. Samples: 129010. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:27:16,729][00788] Avg episode reward: [(0, '4.451')]
+[2024-12-31 06:27:19,701][03013] Updated weights for policy 0, policy_version 130 (0.0030)
+[2024-12-31 06:27:21,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3728.8). Total num frames: 540672. Throughput: 0: 1009.0. Samples: 134836. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:27:21,732][00788] Avg episode reward: [(0, '4.504')]
+[2024-12-31 06:27:26,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4232.5, 300 sec: 3768.3). Total num frames: 565248. Throughput: 0: 1056.6. Samples: 142284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:27:26,732][00788] Avg episode reward: [(0, '4.543')]
+[2024-12-31 06:27:28,009][03013] Updated weights for policy 0, policy_version 140 (0.0016)
+[2024-12-31 06:27:31,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3752.5). Total num frames: 581632. Throughput: 0: 1065.5. Samples: 145130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:27:31,727][00788] Avg episode reward: [(0, '4.376')]
+[2024-12-31 06:27:36,725][00788] Fps is (10 sec: 3686.3, 60 sec: 4096.0, 300 sec: 3763.2). Total num frames: 602112. Throughput: 0: 1006.5. Samples: 149928. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:27:36,732][00788] Avg episode reward: [(0, '4.459')]
+[2024-12-31 06:27:39,125][03013] Updated weights for policy 0, policy_version 150 (0.0022)
+[2024-12-31 06:27:41,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 3798.1). Total num frames: 626688. Throughput: 0: 1030.8. Samples: 157272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:27:41,726][00788] Avg episode reward: [(0, '4.424')]
+[2024-12-31 06:27:46,725][00788] Fps is (10 sec: 4505.4, 60 sec: 4232.5, 300 sec: 3806.9). Total num frames: 647168. Throughput: 0: 1065.1. Samples: 161042. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:27:46,728][00788] Avg episode reward: [(0, '4.360')]
+[2024-12-31 06:27:48,987][03013] Updated weights for policy 0, policy_version 160 (0.0026)
+[2024-12-31 06:27:51,725][00788] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3768.3). Total num frames: 659456. Throughput: 0: 1020.9. Samples: 165608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:27:51,730][00788] Avg episode reward: [(0, '4.394')]
+[2024-12-31 06:27:56,725][00788] Fps is (10 sec: 4096.3, 60 sec: 4164.3, 300 sec: 3822.9). Total num frames: 688128. Throughput: 0: 1014.6. Samples: 172478. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:27:56,727][00788] Avg episode reward: [(0, '4.341')]
+[2024-12-31 06:27:58,323][03013] Updated weights for policy 0, policy_version 170 (0.0018)
+[2024-12-31 06:28:01,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4232.6, 300 sec: 3830.3). Total num frames: 708608. Throughput: 0: 1047.5. Samples: 176146. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:28:01,727][00788] Avg episode reward: [(0, '4.455')]
+[2024-12-31 06:28:06,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3815.7). Total num frames: 724992. Throughput: 0: 1040.5. Samples: 181660. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:28:06,731][00788] Avg episode reward: [(0, '4.434')]
+[2024-12-31 06:28:09,546][03013] Updated weights for policy 0, policy_version 180 (0.0027)
+[2024-12-31 06:28:11,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3822.9). Total num frames: 745472. Throughput: 0: 1006.0. Samples: 187554. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:28:11,727][00788] Avg episode reward: [(0, '4.379')]
+[2024-12-31 06:28:16,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4232.5, 300 sec: 3850.2). Total num frames: 770048. Throughput: 0: 1024.0. Samples: 191208. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:28:16,727][00788] Avg episode reward: [(0, '4.661')]
+[2024-12-31 06:28:17,690][03013] Updated weights for policy 0, policy_version 190 (0.0026)
+[2024-12-31 06:28:21,727][00788] Fps is (10 sec: 4504.7, 60 sec: 4164.1, 300 sec: 3856.2). Total num frames: 790528. Throughput: 0: 1063.4. Samples: 197784. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:28:21,729][00788] Avg episode reward: [(0, '4.908')]
+[2024-12-31 06:28:21,733][03000] Saving new best policy, reward=4.908!
+[2024-12-31 06:28:26,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3842.4). Total num frames: 806912. Throughput: 0: 1009.5. Samples: 202700. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:28:26,728][00788] Avg episode reward: [(0, '4.734')]
+[2024-12-31 06:28:26,746][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000197_806912.pth...
+[2024-12-31 06:28:28,793][03013] Updated weights for policy 0, policy_version 200 (0.0036)
+[2024-12-31 06:28:31,725][00788] Fps is (10 sec: 4096.8, 60 sec: 4164.3, 300 sec: 3867.4). Total num frames: 831488. Throughput: 0: 1005.3. Samples: 206278. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:28:31,729][00788] Avg episode reward: [(0, '4.457')]
+[2024-12-31 06:28:36,729][00788] Fps is (10 sec: 4503.5, 60 sec: 4164.0, 300 sec: 3872.5). Total num frames: 851968. Throughput: 0: 1064.5. Samples: 213516. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:28:36,736][00788] Avg episode reward: [(0, '4.538')]
+[2024-12-31 06:28:38,277][03013] Updated weights for policy 0, policy_version 210 (0.0021)
+[2024-12-31 06:28:41,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3859.3). Total num frames: 868352. Throughput: 0: 1012.8. Samples: 218052. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:28:41,730][00788] Avg episode reward: [(0, '4.596')]
+[2024-12-31 06:28:46,725][00788] Fps is (10 sec: 4097.9, 60 sec: 4096.0, 300 sec: 3882.3). Total num frames: 892928. Throughput: 0: 1005.0. Samples: 221372. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:28:46,727][00788] Avg episode reward: [(0, '4.484')]
+[2024-12-31 06:28:48,283][03013] Updated weights for policy 0, policy_version 220 (0.0015)
+[2024-12-31 06:28:51,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4300.8, 300 sec: 3904.3). Total num frames: 917504. Throughput: 0: 1047.0. Samples: 228774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:28:51,727][00788] Avg episode reward: [(0, '4.475')]
+[2024-12-31 06:28:56,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3891.2). Total num frames: 933888. Throughput: 0: 1036.1. Samples: 234178. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:28:56,730][00788] Avg episode reward: [(0, '4.386')]
+[2024-12-31 06:28:59,381][03013] Updated weights for policy 0, policy_version 230 (0.0020)
+[2024-12-31 06:29:01,725][00788] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3878.7). Total num frames: 950272. Throughput: 0: 1008.6. Samples: 236594. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-31 06:29:01,734][00788] Avg episode reward: [(0, '4.448')]
+[2024-12-31 06:29:06,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3899.4). Total num frames: 974848. Throughput: 0: 1025.9. Samples: 243946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:29:06,726][00788] Avg episode reward: [(0, '4.642')]
+[2024-12-31 06:29:07,632][03013] Updated weights for policy 0, policy_version 240 (0.0025)
+[2024-12-31 06:29:11,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 3903.2). Total num frames: 995328. Throughput: 0: 1056.6. Samples: 250248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:29:11,727][00788] Avg episode reward: [(0, '4.508')]
+[2024-12-31 06:29:16,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3891.2). Total num frames: 1011712. Throughput: 0: 1025.8. Samples: 252440. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:29:16,727][00788] Avg episode reward: [(0, '4.402')]
+[2024-12-31 06:29:18,690][03013] Updated weights for policy 0, policy_version 250 (0.0028)
+[2024-12-31 06:29:21,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.1, 300 sec: 3910.5). Total num frames: 1036288. Throughput: 0: 1013.1. Samples: 259100. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:29:21,732][00788] Avg episode reward: [(0, '4.560')]
+[2024-12-31 06:29:26,726][00788] Fps is (10 sec: 4914.6, 60 sec: 4232.4, 300 sec: 3929.1). Total num frames: 1060864. Throughput: 0: 1072.0. Samples: 266294. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:29:26,733][00788] Avg episode reward: [(0, '4.428')]
+[2024-12-31 06:29:27,302][03013] Updated weights for policy 0, policy_version 260 (0.0024)
+[2024-12-31 06:29:31,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3917.3). Total num frames: 1077248. Throughput: 0: 1047.1. Samples: 268490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:29:31,732][00788] Avg episode reward: [(0, '4.437')]
+[2024-12-31 06:29:36,725][00788] Fps is (10 sec: 3686.6, 60 sec: 4096.3, 300 sec: 3920.4). Total num frames: 1097728. Throughput: 0: 1006.8. Samples: 274082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:29:36,728][00788] Avg episode reward: [(0, '4.462')]
+[2024-12-31 06:29:38,043][03013] Updated weights for policy 0, policy_version 270 (0.0033)
+[2024-12-31 06:29:41,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4232.5, 300 sec: 3937.9). Total num frames: 1122304. Throughput: 0: 1052.4. Samples: 281536. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:29:41,726][00788] Avg episode reward: [(0, '4.569')]
+[2024-12-31 06:29:46,725][00788] Fps is (10 sec: 4096.1, 60 sec: 4096.0, 300 sec: 3926.5). Total num frames: 1138688. Throughput: 0: 1062.9. Samples: 284424. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:29:46,731][00788] Avg episode reward: [(0, '4.546')]
+[2024-12-31 06:29:48,418][03013] Updated weights for policy 0, policy_version 280 (0.0016)
+[2024-12-31 06:29:51,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1159168. Throughput: 0: 1008.6. Samples: 289332. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:29:51,727][00788] Avg episode reward: [(0, '4.500')]
+[2024-12-31 06:29:56,725][00788] Fps is (10 sec: 4505.9, 60 sec: 4164.3, 300 sec: 4012.7). Total num frames: 1183744. Throughput: 0: 1031.2. Samples: 296654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:29:56,729][00788] Avg episode reward: [(0, '4.599')]
+[2024-12-31 06:29:57,512][03013] Updated weights for policy 0, policy_version 290 (0.0025)
+[2024-12-31 06:30:01,727][00788] Fps is (10 sec: 4504.4, 60 sec: 4232.3, 300 sec: 4082.1). Total num frames: 1204224. Throughput: 0: 1064.3. Samples: 300338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:30:01,729][00788] Avg episode reward: [(0, '4.781')]
+[2024-12-31 06:30:06,725][00788] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 1216512. Throughput: 0: 1018.0. Samples: 304912. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:30:06,727][00788] Avg episode reward: [(0, '4.650')]
+[2024-12-31 06:30:08,571][03013] Updated weights for policy 0, policy_version 300 (0.0035)
+[2024-12-31 06:30:11,725][00788] Fps is (10 sec: 3687.4, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 1241088. Throughput: 0: 1010.9. Samples: 311782. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-31 06:30:11,727][00788] Avg episode reward: [(0, '4.635')]
+[2024-12-31 06:30:16,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4232.5, 300 sec: 4137.7). Total num frames: 1265664. Throughput: 0: 1043.7. Samples: 315456. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:30:16,727][00788] Avg episode reward: [(0, '4.611')]
+[2024-12-31 06:30:16,811][03013] Updated weights for policy 0, policy_version 310 (0.0018)
+[2024-12-31 06:30:21,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 1282048. Throughput: 0: 1043.1. Samples: 321022. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-12-31 06:30:21,727][00788] Avg episode reward: [(0, '4.727')]
+[2024-12-31 06:30:26,726][00788] Fps is (10 sec: 3685.7, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 1302528. Throughput: 0: 1011.1. Samples: 327038. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:30:26,729][00788] Avg episode reward: [(0, '4.914')]
+[2024-12-31 06:30:26,819][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000319_1306624.pth...
+[2024-12-31 06:30:26,956][03000] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000076_311296.pth
+[2024-12-31 06:30:26,976][03000] Saving new best policy, reward=4.914!
+[2024-12-31 06:30:27,848][03013] Updated weights for policy 0, policy_version 320 (0.0035)
+[2024-12-31 06:30:31,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4137.7). Total num frames: 1327104. Throughput: 0: 1023.6. Samples: 330484. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:30:31,727][00788] Avg episode reward: [(0, '4.796')]
+[2024-12-31 06:30:36,725][00788] Fps is (10 sec: 4506.4, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 1347584. Throughput: 0: 1056.7. Samples: 336882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:30:36,726][00788] Avg episode reward: [(0, '4.590')]
+[2024-12-31 06:30:37,932][03013] Updated weights for policy 0, policy_version 330 (0.0023)
+[2024-12-31 06:30:41,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 1363968. Throughput: 0: 1003.5. Samples: 341810. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:30:41,729][00788] Avg episode reward: [(0, '4.565')]
+[2024-12-31 06:30:46,725][00788] Fps is (10 sec: 4095.9, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 1388544. Throughput: 0: 1004.1. Samples: 345520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:30:46,732][00788] Avg episode reward: [(0, '4.640')]
+[2024-12-31 06:30:47,276][03013] Updated weights for policy 0, policy_version 340 (0.0022)
+[2024-12-31 06:30:51,727][00788] Fps is (10 sec: 4913.8, 60 sec: 4232.3, 300 sec: 4151.5). Total num frames: 1413120. Throughput: 0: 1067.5. Samples: 352954. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:30:51,730][00788] Avg episode reward: [(0, '4.689')]
+[2024-12-31 06:30:56,725][00788] Fps is (10 sec: 3686.5, 60 sec: 4027.7, 300 sec: 4109.9). Total num frames: 1425408. Throughput: 0: 1015.6. Samples: 357482. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-12-31 06:30:56,728][00788] Avg episode reward: [(0, '4.706')]
+[2024-12-31 06:30:58,113][03013] Updated weights for policy 0, policy_version 350 (0.0026)
+[2024-12-31 06:31:01,725][00788] Fps is (10 sec: 3687.4, 60 sec: 4096.2, 300 sec: 4123.8). Total num frames: 1449984. Throughput: 0: 1007.4. Samples: 360790. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:31:01,731][00788] Avg episode reward: [(0, '4.591')]
+[2024-12-31 06:31:06,545][03013] Updated weights for policy 0, policy_version 360 (0.0017)
+[2024-12-31 06:31:06,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4300.8, 300 sec: 4151.5). Total num frames: 1474560. Throughput: 0: 1045.8. Samples: 368084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:31:06,731][00788] Avg episode reward: [(0, '4.505')]
+[2024-12-31 06:31:11,734][00788] Fps is (10 sec: 4092.2, 60 sec: 4163.6, 300 sec: 4123.6). Total num frames: 1490944. Throughput: 0: 1027.9. Samples: 373302. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:31:11,737][00788] Avg episode reward: [(0, '4.468')]
+[2024-12-31 06:31:16,725][00788] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 1507328. Throughput: 0: 1006.8. Samples: 375790. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:31:16,728][00788] Avg episode reward: [(0, '4.486')]
+[2024-12-31 06:31:17,604][03013] Updated weights for policy 0, policy_version 370 (0.0018)
+[2024-12-31 06:31:21,725][00788] Fps is (10 sec: 4099.8, 60 sec: 4164.3, 300 sec: 4137.7). Total num frames: 1531904. Throughput: 0: 1028.4. Samples: 383160. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:31:21,726][00788] Avg episode reward: [(0, '4.662')]
+[2024-12-31 06:31:26,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.4, 300 sec: 4123.8). Total num frames: 1552384. Throughput: 0: 1058.4. Samples: 389438. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-31 06:31:26,732][00788] Avg episode reward: [(0, '4.754')]
+[2024-12-31 06:31:27,152][03013] Updated weights for policy 0, policy_version 380 (0.0018)
+[2024-12-31 06:31:31,725][00788] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 4109.9). Total num frames: 1568768. Throughput: 0: 1024.4. Samples: 391620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:31:31,731][00788] Avg episode reward: [(0, '4.636')]
+[2024-12-31 06:31:36,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4123.8). Total num frames: 1593344. Throughput: 0: 1006.6. Samples: 398246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:31:36,729][00788] Avg episode reward: [(0, '4.646')]
+[2024-12-31 06:31:37,062][03013] Updated weights for policy 0, policy_version 390 (0.0016)
+[2024-12-31 06:31:41,725][00788] Fps is (10 sec: 4915.3, 60 sec: 4232.5, 300 sec: 4151.5). Total num frames: 1617920. Throughput: 0: 1061.6. Samples: 405254. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:31:41,729][00788] Avg episode reward: [(0, '4.846')]
+[2024-12-31 06:31:46,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 4109.9). Total num frames: 1630208. Throughput: 0: 1036.4. Samples: 407426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:31:46,727][00788] Avg episode reward: [(0, '4.713')]
+[2024-12-31 06:31:48,266][03013] Updated weights for policy 0, policy_version 400 (0.0020)
+[2024-12-31 06:31:51,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.9, 300 sec: 4123.8). Total num frames: 1654784. Throughput: 0: 1003.8. Samples: 413256. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:31:51,732][00788] Avg episode reward: [(0, '4.591')]
+[2024-12-31 06:31:56,513][03013] Updated weights for policy 0, policy_version 410 (0.0021)
+[2024-12-31 06:31:56,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4232.5, 300 sec: 4151.5). Total num frames: 1679360. Throughput: 0: 1050.1. Samples: 420548. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:31:56,731][00788] Avg episode reward: [(0, '4.621')]
+[2024-12-31 06:32:01,727][00788] Fps is (10 sec: 4094.9, 60 sec: 4095.8, 300 sec: 4123.7). Total num frames: 1695744. Throughput: 0: 1059.6. Samples: 423474. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:32:01,732][00788] Avg episode reward: [(0, '4.783')]
+[2024-12-31 06:32:06,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4109.9). Total num frames: 1716224. Throughput: 0: 1005.5. Samples: 428406. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:32:06,727][00788] Avg episode reward: [(0, '4.762')]
+[2024-12-31 06:32:07,661][03013] Updated weights for policy 0, policy_version 420 (0.0039)
+[2024-12-31 06:32:11,725][00788] Fps is (10 sec: 4097.1, 60 sec: 4096.6, 300 sec: 4137.7). Total num frames: 1736704. Throughput: 0: 1026.2. Samples: 435618. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:32:11,728][00788] Avg episode reward: [(0, '4.849')]
+[2024-12-31 06:32:16,581][03013] Updated weights for policy 0, policy_version 430 (0.0019)
+[2024-12-31 06:32:16,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4232.5, 300 sec: 4137.7). Total num frames: 1761280. Throughput: 0: 1058.8. Samples: 439266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:32:16,727][00788] Avg episode reward: [(0, '4.901')]
+[2024-12-31 06:32:21,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 1773568. Throughput: 0: 1013.4. Samples: 443848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:32:21,732][00788] Avg episode reward: [(0, '5.011')]
+[2024-12-31 06:32:21,734][03000] Saving new best policy, reward=5.011!
+[2024-12-31 06:32:26,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4123.8). Total num frames: 1798144. Throughput: 0: 1008.2. Samples: 450622. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:32:26,732][00788] Avg episode reward: [(0, '5.006')]
+[2024-12-31 06:32:26,740][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000439_1798144.pth...
+[2024-12-31 06:32:26,861][03000] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000197_806912.pth
+[2024-12-31 06:32:27,188][03013] Updated weights for policy 0, policy_version 440 (0.0025)
+[2024-12-31 06:32:31,725][00788] Fps is (10 sec: 4915.0, 60 sec: 4232.5, 300 sec: 4137.7). Total num frames: 1822720. Throughput: 0: 1037.9. Samples: 454132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:32:31,731][00788] Avg episode reward: [(0, '4.958')]
+[2024-12-31 06:32:36,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 1839104. Throughput: 0: 1028.7. Samples: 459548. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:32:36,731][00788] Avg episode reward: [(0, '5.068')]
+[2024-12-31 06:32:36,739][03000] Saving new best policy, reward=5.068!
+[2024-12-31 06:32:38,275][03013] Updated weights for policy 0, policy_version 450 (0.0029)
+[2024-12-31 06:32:41,725][00788] Fps is (10 sec: 3276.9, 60 sec: 3959.5, 300 sec: 4096.0). Total num frames: 1855488. Throughput: 0: 994.2. Samples: 465286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:32:41,731][00788] Avg episode reward: [(0, '4.949')]
+[2024-12-31 06:32:46,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4137.7). Total num frames: 1880064. Throughput: 0: 1009.8. Samples: 468914. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:32:46,731][00788] Avg episode reward: [(0, '4.886')]
+[2024-12-31 06:32:46,900][03013] Updated weights for policy 0, policy_version 460 (0.0026)
+[2024-12-31 06:32:51,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 1900544. Throughput: 0: 1042.8. Samples: 475330. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:32:51,730][00788] Avg episode reward: [(0, '4.834')]
+[2024-12-31 06:32:56,725][00788] Fps is (10 sec: 3686.3, 60 sec: 3959.5, 300 sec: 4096.0). Total num frames: 1916928. Throughput: 0: 991.8. Samples: 480248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:32:56,727][00788] Avg episode reward: [(0, '4.701')]
+[2024-12-31 06:32:58,054][03013] Updated weights for policy 0, policy_version 470 (0.0018)
+[2024-12-31 06:33:01,725][00788] Fps is (10 sec: 4095.9, 60 sec: 4096.2, 300 sec: 4123.8). Total num frames: 1941504. Throughput: 0: 991.6. Samples: 483890. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:33:01,727][00788] Avg episode reward: [(0, '4.660')]
+[2024-12-31 06:33:06,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4123.8). Total num frames: 1961984. Throughput: 0: 1049.0. Samples: 491052. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:33:06,727][00788] Avg episode reward: [(0, '4.563')]
+[2024-12-31 06:33:07,164][03013] Updated weights for policy 0, policy_version 480 (0.0018)
+[2024-12-31 06:33:11,725][00788] Fps is (10 sec: 3686.5, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 1978368. Throughput: 0: 995.3. Samples: 495412. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:33:11,727][00788] Avg episode reward: [(0, '4.830')]
+[2024-12-31 06:33:16,725][00788] Fps is (10 sec: 3686.5, 60 sec: 3959.5, 300 sec: 4096.0). Total num frames: 1998848. Throughput: 0: 987.2. Samples: 498554. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:33:16,730][00788] Avg episode reward: [(0, '4.740')]
+[2024-12-31 06:33:17,855][03013] Updated weights for policy 0, policy_version 490 (0.0022)
+[2024-12-31 06:33:21,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 2023424. Throughput: 0: 1029.3. Samples: 505868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:33:21,729][00788] Avg episode reward: [(0, '4.469')]
+[2024-12-31 06:33:26,725][00788] Fps is (10 sec: 4095.9, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 2039808. Throughput: 0: 1023.0. Samples: 511322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-31 06:33:26,727][00788] Avg episode reward: [(0, '4.724')]
+[2024-12-31 06:33:28,422][03013] Updated weights for policy 0, policy_version 500 (0.0025)
+[2024-12-31 06:33:31,725][00788] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4096.1). Total num frames: 2060288. Throughput: 0: 992.2. Samples: 513562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:33:31,727][00788] Avg episode reward: [(0, '4.799')]
+[2024-12-31 06:33:36,725][00788] Fps is (10 sec: 4505.8, 60 sec: 4096.0, 300 sec: 4123.8). Total num frames: 2084864. Throughput: 0: 1010.8. Samples: 520816. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-31 06:33:36,727][00788] Avg episode reward: [(0, '4.584')]
+[2024-12-31 06:33:37,451][03013] Updated weights for policy 0, policy_version 510 (0.0018)
+[2024-12-31 06:33:41,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 2105344. Throughput: 0: 1038.9. Samples: 526998. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:33:41,727][00788] Avg episode reward: [(0, '4.674')]
+[2024-12-31 06:33:46,725][00788] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4068.2). Total num frames: 2117632. Throughput: 0: 1006.5. Samples: 529182. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-31 06:33:46,727][00788] Avg episode reward: [(0, '4.645')]
+[2024-12-31 06:33:48,482][03013] Updated weights for policy 0, policy_version 520 (0.0027)
+[2024-12-31 06:33:51,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 2142208. Throughput: 0: 993.5. Samples: 535758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:33:51,731][00788] Avg episode reward: [(0, '4.654')]
+[2024-12-31 06:33:56,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 2166784. Throughput: 0: 1057.9. Samples: 543018. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:33:56,727][00788] Avg episode reward: [(0, '4.778')]
+[2024-12-31 06:33:57,217][03013] Updated weights for policy 0, policy_version 530 (0.0042)
+[2024-12-31 06:34:01,725][00788] Fps is (10 sec: 4095.9, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 2183168. Throughput: 0: 1037.1. Samples: 545222. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:34:01,730][00788] Avg episode reward: [(0, '4.677')]
+[2024-12-31 06:34:06,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 2203648. Throughput: 0: 1000.4. Samples: 550888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:34:06,730][00788] Avg episode reward: [(0, '4.556')]
+[2024-12-31 06:34:07,966][03013] Updated weights for policy 0, policy_version 540 (0.0016)
+[2024-12-31 06:34:11,725][00788] Fps is (10 sec: 4505.7, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 2228224. Throughput: 0: 1039.6. Samples: 558102. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:34:11,730][00788] Avg episode reward: [(0, '4.526')]
+[2024-12-31 06:34:16,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2244608. Throughput: 0: 1056.0. Samples: 561080. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:34:16,731][00788] Avg episode reward: [(0, '4.593')]
+[2024-12-31 06:34:18,617][03013] Updated weights for policy 0, policy_version 550 (0.0028)
+[2024-12-31 06:34:21,725][00788] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 2265088. Throughput: 0: 997.7. Samples: 565714. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:34:21,727][00788] Avg episode reward: [(0, '5.112')]
+[2024-12-31 06:34:21,731][03000] Saving new best policy, reward=5.112!
+[2024-12-31 06:34:26,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2285568. Throughput: 0: 1023.3. Samples: 573048. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-31 06:34:26,729][00788] Avg episode reward: [(0, '5.052')]
+[2024-12-31 06:34:26,750][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000559_2289664.pth...
+[2024-12-31 06:34:26,879][03000] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000319_1306624.pth
+[2024-12-31 06:34:27,638][03013] Updated weights for policy 0, policy_version 560 (0.0036)
+[2024-12-31 06:34:31,728][00788] Fps is (10 sec: 4503.9, 60 sec: 4164.0, 300 sec: 4109.8). Total num frames: 2310144. Throughput: 0: 1052.9. Samples: 576566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-31 06:34:31,736][00788] Avg episode reward: [(0, '4.617')]
+[2024-12-31 06:34:36,725][00788] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4068.2). Total num frames: 2322432. Throughput: 0: 1010.4. Samples: 581224. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:34:36,727][00788] Avg episode reward: [(0, '4.755')]
+[2024-12-31 06:34:38,725][03013] Updated weights for policy 0, policy_version 570 (0.0019)
+[2024-12-31 06:34:41,725][00788] Fps is (10 sec: 3687.8, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 2347008. Throughput: 0: 995.8. Samples: 587830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:34:41,732][00788] Avg episode reward: [(0, '4.932')]
+[2024-12-31 06:34:46,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4232.5, 300 sec: 4109.9). Total num frames: 2371584. Throughput: 0: 1027.3. Samples: 591452. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:34:46,730][00788] Avg episode reward: [(0, '4.857')]
+[2024-12-31 06:34:47,015][03013] Updated weights for policy 0, policy_version 580 (0.0029)
+[2024-12-31 06:34:51,729][00788] Fps is (10 sec: 4094.1, 60 sec: 4095.7, 300 sec: 4082.1). Total num frames: 2387968. Throughput: 0: 1025.1. Samples: 597024. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:34:51,732][00788] Avg episode reward: [(0, '4.577')]
+[2024-12-31 06:34:56,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4082.2). Total num frames: 2408448. Throughput: 0: 993.6. Samples: 602814. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:34:56,727][00788] Avg episode reward: [(0, '4.594')]
+[2024-12-31 06:34:58,252][03013] Updated weights for policy 0, policy_version 590 (0.0022)
+[2024-12-31 06:35:01,725][00788] Fps is (10 sec: 4507.7, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 2433024. Throughput: 0: 1008.6. Samples: 606468. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:35:01,731][00788] Avg episode reward: [(0, '4.565')]
+[2024-12-31 06:35:06,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2449408. Throughput: 0: 1046.7. Samples: 612814. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:35:06,731][00788] Avg episode reward: [(0, '4.532')]
+[2024-12-31 06:35:08,377][03013] Updated weights for policy 0, policy_version 600 (0.0026)
+[2024-12-31 06:35:11,725][00788] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4068.2). Total num frames: 2465792. Throughput: 0: 992.1. Samples: 617692. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:35:11,736][00788] Avg episode reward: [(0, '4.475')]
+[2024-12-31 06:35:16,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2490368. Throughput: 0: 994.4. Samples: 621308. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:35:16,731][00788] Avg episode reward: [(0, '4.573')]
+[2024-12-31 06:35:17,786][03013] Updated weights for policy 0, policy_version 610 (0.0035)
+[2024-12-31 06:35:21,725][00788] Fps is (10 sec: 4915.1, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 2514944. Throughput: 0: 1054.4. Samples: 628670. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:35:21,729][00788] Avg episode reward: [(0, '4.640')]
+[2024-12-31 06:35:26,730][00788] Fps is (10 sec: 3684.3, 60 sec: 4027.4, 300 sec: 4068.2). Total num frames: 2527232. Throughput: 0: 1006.7. Samples: 633136. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:35:26,732][00788] Avg episode reward: [(0, '4.693')]
+[2024-12-31 06:35:28,965][03013] Updated weights for policy 0, policy_version 620 (0.0033)
+[2024-12-31 06:35:31,725][00788] Fps is (10 sec: 3686.5, 60 sec: 4028.0, 300 sec: 4082.1). Total num frames: 2551808. Throughput: 0: 1000.1. Samples: 636458. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:35:31,730][00788] Avg episode reward: [(0, '5.191')]
+[2024-12-31 06:35:31,734][03000] Saving new best policy, reward=5.191!
+[2024-12-31 06:35:36,725][00788] Fps is (10 sec: 4918.0, 60 sec: 4232.5, 300 sec: 4109.9). Total num frames: 2576384. Throughput: 0: 1037.0. Samples: 643682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:35:36,731][00788] Avg episode reward: [(0, '5.190')]
+[2024-12-31 06:35:37,376][03013] Updated weights for policy 0, policy_version 630 (0.0031)
+[2024-12-31 06:35:41,726][00788] Fps is (10 sec: 4095.5, 60 sec: 4095.9, 300 sec: 4082.1). Total num frames: 2592768. Throughput: 0: 1023.0. Samples: 648850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:35:41,729][00788] Avg episode reward: [(0, '5.067')]
+[2024-12-31 06:35:46,725][00788] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4054.4). Total num frames: 2609152. Throughput: 0: 991.9. Samples: 651102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:35:46,730][00788] Avg episode reward: [(0, '4.876')]
+[2024-12-31 06:35:48,646][03013] Updated weights for policy 0, policy_version 640 (0.0030)
+[2024-12-31 06:35:51,725][00788] Fps is (10 sec: 4096.5, 60 sec: 4096.3, 300 sec: 4096.0). Total num frames: 2633728. Throughput: 0: 1015.4. Samples: 658506. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-12-31 06:35:51,729][00788] Avg episode reward: [(0, '4.652')]
+[2024-12-31 06:35:56,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 2654208. Throughput: 0: 1047.6. Samples: 664832. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:35:56,728][00788] Avg episode reward: [(0, '4.710')]
+[2024-12-31 06:35:58,400][03013] Updated weights for policy 0, policy_version 650 (0.0029)
+[2024-12-31 06:36:01,725][00788] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4054.3). Total num frames: 2670592. Throughput: 0: 1015.8. Samples: 667020. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:36:01,731][00788] Avg episode reward: [(0, '4.812')]
+[2024-12-31 06:36:06,725][00788] Fps is (10 sec: 4095.9, 60 sec: 4096.0, 300 sec: 4082.2). Total num frames: 2695168. Throughput: 0: 998.3. Samples: 673594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:36:06,732][00788] Avg episode reward: [(0, '4.758')]
+[2024-12-31 06:36:08,067][03013] Updated weights for policy 0, policy_version 660 (0.0019)
+[2024-12-31 06:36:11,725][00788] Fps is (10 sec: 4915.1, 60 sec: 4232.5, 300 sec: 4109.9). Total num frames: 2719744. Throughput: 0: 1056.5. Samples: 680672. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:36:11,728][00788] Avg episode reward: [(0, '4.755')]
+[2024-12-31 06:36:16,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4068.2). Total num frames: 2732032. Throughput: 0: 1030.7. Samples: 682842. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:36:16,733][00788] Avg episode reward: [(0, '4.900')]
+[2024-12-31 06:36:19,133][03013] Updated weights for policy 0, policy_version 670 (0.0024)
+[2024-12-31 06:36:21,725][00788] Fps is (10 sec: 3686.5, 60 sec: 4027.8, 300 sec: 4082.1). Total num frames: 2756608. Throughput: 0: 997.1. Samples: 688550. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:36:21,726][00788] Avg episode reward: [(0, '5.248')]
+[2024-12-31 06:36:21,735][03000] Saving new best policy, reward=5.248!
+[2024-12-31 06:36:26,725][00788] Fps is (10 sec: 4505.7, 60 sec: 4164.7, 300 sec: 4096.0). Total num frames: 2777088. Throughput: 0: 1044.4. Samples: 695846. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:36:26,731][00788] Avg episode reward: [(0, '5.210')]
+[2024-12-31 06:36:26,742][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000679_2781184.pth...
+[2024-12-31 06:36:26,876][03000] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000439_1798144.pth
+[2024-12-31 06:36:27,708][03013] Updated weights for policy 0, policy_version 680 (0.0034)
+[2024-12-31 06:36:31,727][00788] Fps is (10 sec: 4095.2, 60 sec: 4095.9, 300 sec: 4082.1). Total num frames: 2797568. Throughput: 0: 1056.2. Samples: 698634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:36:31,731][00788] Avg episode reward: [(0, '4.850')]
+[2024-12-31 06:36:36,725][00788] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4054.3). Total num frames: 2813952. Throughput: 0: 999.2. Samples: 703470. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-31 06:36:36,728][00788] Avg episode reward: [(0, '4.681')]
+[2024-12-31 06:36:38,681][03013] Updated weights for policy 0, policy_version 690 (0.0021)
+[2024-12-31 06:36:41,725][00788] Fps is (10 sec: 4096.8, 60 sec: 4096.1, 300 sec: 4096.0). Total num frames: 2838528. Throughput: 0: 1019.7. Samples: 710720. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:36:41,727][00788] Avg episode reward: [(0, '4.471')]
+[2024-12-31 06:36:46,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 2859008. Throughput: 0: 1053.9. Samples: 714446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:36:46,731][00788] Avg episode reward: [(0, '4.451')]
+[2024-12-31 06:36:48,454][03013] Updated weights for policy 0, policy_version 700 (0.0023)
+[2024-12-31 06:36:51,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 2875392. Throughput: 0: 1009.3. Samples: 719014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:36:51,731][00788] Avg episode reward: [(0, '4.515')]
+[2024-12-31 06:36:56,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4082.2). Total num frames: 2899968. Throughput: 0: 1009.7. Samples: 726110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:36:56,734][00788] Avg episode reward: [(0, '4.693')]
+[2024-12-31 06:36:57,849][03013] Updated weights for policy 0, policy_version 710 (0.0023)
+[2024-12-31 06:37:01,727][00788] Fps is (10 sec: 4914.1, 60 sec: 4232.4, 300 sec: 4096.0). Total num frames: 2924544. Throughput: 0: 1041.2. Samples: 729700. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:37:01,733][00788] Avg episode reward: [(0, '4.819')]
+[2024-12-31 06:37:06,729][00788] Fps is (10 sec: 4094.0, 60 sec: 4095.7, 300 sec: 4082.0). Total num frames: 2940928. Throughput: 0: 1034.4. Samples: 735104. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:37:06,732][00788] Avg episode reward: [(0, '4.836')]
+[2024-12-31 06:37:08,831][03013] Updated weights for policy 0, policy_version 720 (0.0015)
+[2024-12-31 06:37:11,725][00788] Fps is (10 sec: 3687.2, 60 sec: 4027.8, 300 sec: 4068.2). Total num frames: 2961408. Throughput: 0: 1008.4. Samples: 741222. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:37:11,727][00788] Avg episode reward: [(0, '4.679')]
+[2024-12-31 06:37:16,725][00788] Fps is (10 sec: 4507.7, 60 sec: 4232.6, 300 sec: 4109.9). Total num frames: 2985984. Throughput: 0: 1030.0. Samples: 744984. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:37:16,727][00788] Avg episode reward: [(0, '4.755')]
+[2024-12-31 06:37:17,140][03013] Updated weights for policy 0, policy_version 730 (0.0026)
+[2024-12-31 06:37:21,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 3002368. Throughput: 0: 1064.4. Samples: 751370. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:37:21,729][00788] Avg episode reward: [(0, '4.694')]
+[2024-12-31 06:37:26,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 3022848. Throughput: 0: 1024.0. Samples: 756798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:37:26,728][00788] Avg episode reward: [(0, '4.793')]
+[2024-12-31 06:37:27,977][03013] Updated weights for policy 0, policy_version 740 (0.0015)
+[2024-12-31 06:37:31,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.4, 300 sec: 4096.0). Total num frames: 3047424. Throughput: 0: 1024.1. Samples: 760532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:37:31,728][00788] Avg episode reward: [(0, '5.149')]
+[2024-12-31 06:37:36,726][00788] Fps is (10 sec: 4504.8, 60 sec: 4232.4, 300 sec: 4109.9). Total num frames: 3067904. Throughput: 0: 1082.3. Samples: 767720. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:37:36,731][00788] Avg episode reward: [(0, '5.430')]
+[2024-12-31 06:37:36,779][03000] Saving new best policy, reward=5.430!
+[2024-12-31 06:37:36,782][03013] Updated weights for policy 0, policy_version 750 (0.0036)
+[2024-12-31 06:37:41,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 3084288. Throughput: 0: 1024.7. Samples: 772222. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-31 06:37:41,727][00788] Avg episode reward: [(0, '5.348')]
+[2024-12-31 06:37:46,725][00788] Fps is (10 sec: 4096.7, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3108864. Throughput: 0: 1026.3. Samples: 775882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:37:46,729][00788] Avg episode reward: [(0, '5.058')]
+[2024-12-31 06:37:46,959][03013] Updated weights for policy 0, policy_version 760 (0.0021)
+[2024-12-31 06:37:51,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4300.8, 300 sec: 4123.8). Total num frames: 3133440. Throughput: 0: 1073.2. Samples: 783394. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:37:51,729][00788] Avg episode reward: [(0, '5.273')]
+[2024-12-31 06:37:56,726][00788] Fps is (10 sec: 4095.5, 60 sec: 4164.2, 300 sec: 4096.0). Total num frames: 3149824. Throughput: 0: 1051.3. Samples: 788530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:37:56,735][00788] Avg episode reward: [(0, '5.479')]
+[2024-12-31 06:37:56,751][03000] Saving new best policy, reward=5.479!
+[2024-12-31 06:37:57,379][03013] Updated weights for policy 0, policy_version 770 (0.0014)
+[2024-12-31 06:38:01,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.2, 300 sec: 4096.0). Total num frames: 3170304. Throughput: 0: 1029.3. Samples: 791304. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:38:01,731][00788] Avg episode reward: [(0, '5.492')]
+[2024-12-31 06:38:01,741][03000] Saving new best policy, reward=5.492!
+[2024-12-31 06:38:06,096][03013] Updated weights for policy 0, policy_version 780 (0.0027)
+[2024-12-31 06:38:06,725][00788] Fps is (10 sec: 4506.1, 60 sec: 4232.9, 300 sec: 4123.8). Total num frames: 3194880. Throughput: 0: 1053.8. Samples: 798792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:38:06,729][00788] Avg episode reward: [(0, '5.542')]
+[2024-12-31 06:38:06,738][03000] Saving new best policy, reward=5.542!
+[2024-12-31 06:38:11,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4232.5, 300 sec: 4123.8). Total num frames: 3215360. Throughput: 0: 1061.0. Samples: 804544. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:38:11,727][00788] Avg episode reward: [(0, '5.708')]
+[2024-12-31 06:38:11,734][03000] Saving new best policy, reward=5.708!
+[2024-12-31 06:38:16,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 3231744. Throughput: 0: 1027.4. Samples: 806764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:38:16,731][00788] Avg episode reward: [(0, '6.143')]
+[2024-12-31 06:38:16,739][03000] Saving new best policy, reward=6.143!
+[2024-12-31 06:38:17,290][03013] Updated weights for policy 0, policy_version 790 (0.0019)
+[2024-12-31 06:38:21,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 4123.8). Total num frames: 3256320. Throughput: 0: 1023.9. Samples: 813794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:38:21,731][00788] Avg episode reward: [(0, '6.453')]
+[2024-12-31 06:38:21,734][03000] Saving new best policy, reward=6.453!
+[2024-12-31 06:38:25,532][03013] Updated weights for policy 0, policy_version 800 (0.0019)
+[2024-12-31 06:38:26,729][00788] Fps is (10 sec: 4503.5, 60 sec: 4232.2, 300 sec: 4123.7). Total num frames: 3276800. Throughput: 0: 1076.6. Samples: 820676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:38:26,732][00788] Avg episode reward: [(0, '6.212')]
+[2024-12-31 06:38:26,821][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000801_3280896.pth...
+[2024-12-31 06:38:26,995][03000] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000559_2289664.pth
+[2024-12-31 06:38:31,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 3293184. Throughput: 0: 1041.7. Samples: 822760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:38:31,727][00788] Avg episode reward: [(0, '6.360')]
+[2024-12-31 06:38:36,471][03013] Updated weights for policy 0, policy_version 810 (0.0021)
+[2024-12-31 06:38:36,725][00788] Fps is (10 sec: 4097.9, 60 sec: 4164.4, 300 sec: 4109.9). Total num frames: 3317760. Throughput: 0: 1009.7. Samples: 828832. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:38:36,727][00788] Avg episode reward: [(0, '6.445')]
+[2024-12-31 06:38:41,725][00788] Fps is (10 sec: 4505.5, 60 sec: 4232.5, 300 sec: 4137.7). Total num frames: 3338240. Throughput: 0: 1057.9. Samples: 836136. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:38:41,727][00788] Avg episode reward: [(0, '6.525')]
+[2024-12-31 06:38:41,793][03000] Saving new best policy, reward=6.525!
+[2024-12-31 06:38:46,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 3354624. Throughput: 0: 1049.0. Samples: 838510. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:38:46,731][00788] Avg episode reward: [(0, '6.823')]
+[2024-12-31 06:38:46,750][03000] Saving new best policy, reward=6.823!
+[2024-12-31 06:38:47,297][03013] Updated weights for policy 0, policy_version 820 (0.0021)
+[2024-12-31 06:38:51,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3375104. Throughput: 0: 999.6. Samples: 843776. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:38:51,727][00788] Avg episode reward: [(0, '6.252')]
+[2024-12-31 06:38:56,006][03013] Updated weights for policy 0, policy_version 830 (0.0049)
+[2024-12-31 06:38:56,725][00788] Fps is (10 sec: 4915.3, 60 sec: 4232.6, 300 sec: 4137.7). Total num frames: 3403776. Throughput: 0: 1040.0. Samples: 851346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:38:56,731][00788] Avg episode reward: [(0, '5.721')]
+[2024-12-31 06:39:01,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.2, 300 sec: 4123.8). Total num frames: 3420160. Throughput: 0: 1064.0. Samples: 854644. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:39:01,729][00788] Avg episode reward: [(0, '6.046')]
+[2024-12-31 06:39:06,725][00788] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3436544. Throughput: 0: 1010.9. Samples: 859284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:39:06,727][00788] Avg episode reward: [(0, '6.603')]
+[2024-12-31 06:39:06,858][03013] Updated weights for policy 0, policy_version 840 (0.0016)
+[2024-12-31 06:39:11,725][00788] Fps is (10 sec: 4096.1, 60 sec: 4096.0, 300 sec: 4123.8). Total num frames: 3461120. Throughput: 0: 1022.2. Samples: 866668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:39:11,732][00788] Avg episode reward: [(0, '6.764')]
+[2024-12-31 06:39:15,197][03013] Updated weights for policy 0, policy_version 850 (0.0034)
+[2024-12-31 06:39:16,727][00788] Fps is (10 sec: 4913.8, 60 sec: 4232.3, 300 sec: 4137.6). Total num frames: 3485696. Throughput: 0: 1059.9. Samples: 870458. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:39:16,730][00788] Avg episode reward: [(0, '6.579')]
+[2024-12-31 06:39:21,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4123.8). Total num frames: 3502080. Throughput: 0: 1035.4. Samples: 875426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:39:21,727][00788] Avg episode reward: [(0, '6.595')]
+[2024-12-31 06:39:25,952][03013] Updated weights for policy 0, policy_version 860 (0.0035)
+[2024-12-31 06:39:26,725][00788] Fps is (10 sec: 4097.1, 60 sec: 4164.6, 300 sec: 4123.8). Total num frames: 3526656. Throughput: 0: 1022.2. Samples: 882136. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:39:26,728][00788] Avg episode reward: [(0, '7.343')]
+[2024-12-31 06:39:26,737][03000] Saving new best policy, reward=7.343!
+[2024-12-31 06:39:31,728][00788] Fps is (10 sec: 4503.9, 60 sec: 4232.3, 300 sec: 4151.5). Total num frames: 3547136. Throughput: 0: 1050.6. Samples: 885792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:39:31,734][00788] Avg episode reward: [(0, '8.127')]
+[2024-12-31 06:39:31,752][03000] Saving new best policy, reward=8.127!
+[2024-12-31 06:39:35,561][03013] Updated weights for policy 0, policy_version 870 (0.0021)
+[2024-12-31 06:39:36,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4123.8). Total num frames: 3563520. Throughput: 0: 1061.1. Samples: 891524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:39:36,730][00788] Avg episode reward: [(0, '8.015')]
+[2024-12-31 06:39:41,725][00788] Fps is (10 sec: 3687.7, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 3584000. Throughput: 0: 1017.8. Samples: 897148. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:39:41,727][00788] Avg episode reward: [(0, '7.574')]
+[2024-12-31 06:39:45,322][03013] Updated weights for policy 0, policy_version 880 (0.0013)
+[2024-12-31 06:39:46,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4232.5, 300 sec: 4137.7). Total num frames: 3608576. Throughput: 0: 1026.3. Samples: 900826. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:39:46,727][00788] Avg episode reward: [(0, '8.188')]
+[2024-12-31 06:39:46,738][03000] Saving new best policy, reward=8.188!
+[2024-12-31 06:39:51,725][00788] Fps is (10 sec: 4505.7, 60 sec: 4232.5, 300 sec: 4137.7). Total num frames: 3629056. Throughput: 0: 1072.8. Samples: 907562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:39:51,727][00788] Avg episode reward: [(0, '8.649')]
+[2024-12-31 06:39:51,732][03000] Saving new best policy, reward=8.649!
+[2024-12-31 06:39:56,539][03013] Updated weights for policy 0, policy_version 890 (0.0019)
+[2024-12-31 06:39:56,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4109.9). Total num frames: 3645440. Throughput: 0: 1010.6. Samples: 912144. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-12-31 06:39:56,728][00788] Avg episode reward: [(0, '8.509')]
+[2024-12-31 06:40:01,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4137.7). Total num frames: 3670016. Throughput: 0: 1010.1. Samples: 915908. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:40:01,729][00788] Avg episode reward: [(0, '7.351')]
+[2024-12-31 06:40:04,754][03013] Updated weights for policy 0, policy_version 900 (0.0026)
+[2024-12-31 06:40:06,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4300.8, 300 sec: 4165.4). Total num frames: 3694592. Throughput: 0: 1064.5. Samples: 923328. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:40:06,727][00788] Avg episode reward: [(0, '7.777')]
+[2024-12-31 06:40:11,726][00788] Fps is (10 sec: 3685.9, 60 sec: 4095.9, 300 sec: 4123.8). Total num frames: 3706880. Throughput: 0: 1021.3. Samples: 928096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:40:11,734][00788] Avg episode reward: [(0, '8.393')]
+[2024-12-31 06:40:15,761][03013] Updated weights for policy 0, policy_version 910 (0.0022)
+[2024-12-31 06:40:16,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.2, 300 sec: 4123.8). Total num frames: 3731456. Throughput: 0: 1004.7. Samples: 931000. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:40:16,726][00788] Avg episode reward: [(0, '8.184')]
+[2024-12-31 06:40:21,725][00788] Fps is (10 sec: 4915.9, 60 sec: 4232.5, 300 sec: 4165.5). Total num frames: 3756032. Throughput: 0: 1042.9. Samples: 938454. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:40:21,732][00788] Avg episode reward: [(0, '7.912')]
+[2024-12-31 06:40:24,531][03013] Updated weights for policy 0, policy_version 920 (0.0025)
+[2024-12-31 06:40:26,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4137.7). Total num frames: 3772416. Throughput: 0: 1044.9. Samples: 944168. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:40:26,729][00788] Avg episode reward: [(0, '8.519')]
+[2024-12-31 06:40:26,736][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000921_3772416.pth...
+[2024-12-31 06:40:26,922][03000] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000679_2781184.pth
+[2024-12-31 06:40:31,725][00788] Fps is (10 sec: 3276.7, 60 sec: 4028.0, 300 sec: 4109.9). Total num frames: 3788800. Throughput: 0: 1013.3. Samples: 946426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:40:31,727][00788] Avg episode reward: [(0, '9.684')]
+[2024-12-31 06:40:31,737][03000] Saving new best policy, reward=9.684!
+[2024-12-31 06:40:35,243][03013] Updated weights for policy 0, policy_version 930 (0.0029)
+[2024-12-31 06:40:36,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4137.7). Total num frames: 3813376. Throughput: 0: 1019.3. Samples: 953432. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:40:36,729][00788] Avg episode reward: [(0, '8.932')]
+[2024-12-31 06:40:41,725][00788] Fps is (10 sec: 4915.3, 60 sec: 4232.5, 300 sec: 4165.4). Total num frames: 3837952. Throughput: 0: 1067.9. Samples: 960198. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:40:41,730][00788] Avg episode reward: [(0, '9.035')]
+[2024-12-31 06:40:45,588][03013] Updated weights for policy 0, policy_version 940 (0.0019)
+[2024-12-31 06:40:46,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4123.8). Total num frames: 3850240. Throughput: 0: 1031.6. Samples: 962332. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-12-31 06:40:46,727][00788] Avg episode reward: [(0, '9.110')]
+[2024-12-31 06:40:51,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4137.7). Total num frames: 3874816. Throughput: 0: 1004.5. Samples: 968532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-12-31 06:40:51,727][00788] Avg episode reward: [(0, '10.204')]
+[2024-12-31 06:40:51,734][03000] Saving new best policy, reward=10.204!
+[2024-12-31 06:40:54,750][03013] Updated weights for policy 0, policy_version 950 (0.0025)
+[2024-12-31 06:40:56,725][00788] Fps is (10 sec: 4915.2, 60 sec: 4232.5, 300 sec: 4165.4). Total num frames: 3899392. Throughput: 0: 1060.3. Samples: 975810. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:40:56,731][00788] Avg episode reward: [(0, '9.868')]
+[2024-12-31 06:41:01,725][00788] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4137.7). Total num frames: 3915776. Throughput: 0: 1053.5. Samples: 978408. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-12-31 06:41:01,729][00788] Avg episode reward: [(0, '9.479')]
+[2024-12-31 06:41:05,710][03013] Updated weights for policy 0, policy_version 960 (0.0029)
+[2024-12-31 06:41:06,725][00788] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4123.8). Total num frames: 3936256. Throughput: 0: 1004.9. Samples: 983674. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-12-31 06:41:06,732][00788] Avg episode reward: [(0, '9.567')]
+[2024-12-31 06:41:11,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4232.6, 300 sec: 4165.4). Total num frames: 3960832. Throughput: 0: 1043.4. Samples: 991120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:41:11,727][00788] Avg episode reward: [(0, '9.947')]
+[2024-12-31 06:41:13,926][03013] Updated weights for policy 0, policy_version 970 (0.0021)
+[2024-12-31 06:41:16,725][00788] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4151.5). Total num frames: 3981312. Throughput: 0: 1069.1. Samples: 994536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:41:16,732][00788] Avg episode reward: [(0, '10.466')]
+[2024-12-31 06:41:16,743][03000] Saving new best policy, reward=10.466!
+[2024-12-31 06:41:21,725][00788] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4123.8). Total num frames: 3993600. Throughput: 0: 1011.9. Samples: 998966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-12-31 06:41:21,732][00788] Avg episode reward: [(0, '10.210')]
+[2024-12-31 06:41:23,462][03000] Stopping Batcher_0...
+[2024-12-31 06:41:23,463][03000] Loop batcher_evt_loop terminating...
+[2024-12-31 06:41:23,464][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-12-31 06:41:23,463][00788] Component Batcher_0 stopped!
+[2024-12-31 06:41:23,524][03013] Weights refcount: 2 0
+[2024-12-31 06:41:23,530][00788] Component InferenceWorker_p0-w0 stopped!
+[2024-12-31 06:41:23,537][03013] Stopping InferenceWorker_p0-w0...
+[2024-12-31 06:41:23,537][03013] Loop inference_proc0-0_evt_loop terminating...
+[2024-12-31 06:41:23,601][03000] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000801_3280896.pth
+[2024-12-31 06:41:23,620][03000] Saving new best policy, reward=10.496!
+[2024-12-31 06:41:23,765][03000] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-12-31 06:41:23,877][03020] Stopping RolloutWorker_w6...
+[2024-12-31 06:41:23,884][00788] Component RolloutWorker_w6 stopped!
+[2024-12-31 06:41:23,879][03020] Loop rollout_proc6_evt_loop terminating...
+[2024-12-31 06:41:23,934][00788] Component RolloutWorker_w4 stopped!
+[2024-12-31 06:41:23,939][03018] Stopping RolloutWorker_w4...
+[2024-12-31 06:41:23,950][00788] Component RolloutWorker_w0 stopped!
+[2024-12-31 06:41:23,967][00788] Component RolloutWorker_w2 stopped!
+[2024-12-31 06:41:23,972][03017] Stopping RolloutWorker_w2...
+[2024-12-31 06:41:23,943][03018] Loop rollout_proc4_evt_loop terminating...
+[2024-12-31 06:41:23,976][03015] Stopping RolloutWorker_w1...
+[2024-12-31 06:41:23,976][00788] Component RolloutWorker_w1 stopped!
+[2024-12-31 06:41:23,976][03015] Loop rollout_proc1_evt_loop terminating...
+[2024-12-31 06:41:23,955][03014] Stopping RolloutWorker_w0...
+[2024-12-31 06:41:23,973][03017] Loop rollout_proc2_evt_loop terminating...
+[2024-12-31 06:41:23,981][03014] Loop rollout_proc0_evt_loop terminating...
+[2024-12-31 06:41:24,001][03016] Stopping RolloutWorker_w3...
+[2024-12-31 06:41:24,003][03019] Stopping RolloutWorker_w5...
+[2024-12-31 06:41:24,004][03019] Loop rollout_proc5_evt_loop terminating...
+[2024-12-31 06:41:23,998][00788] Component RolloutWorker_w3 stopped!
+[2024-12-31 06:41:24,004][03016] Loop rollout_proc3_evt_loop terminating...
+[2024-12-31 06:41:24,007][00788] Component RolloutWorker_w5 stopped!
+[2024-12-31 06:41:24,023][03021] Stopping RolloutWorker_w7...
+[2024-12-31 06:41:24,023][00788] Component RolloutWorker_w7 stopped!
+[2024-12-31 06:41:24,028][03021] Loop rollout_proc7_evt_loop terminating...
+[2024-12-31 06:41:24,044][00788] Component LearnerWorker_p0 stopped!
+[2024-12-31 06:41:24,043][03000] Stopping LearnerWorker_p0...
+[2024-12-31 06:41:24,045][00788] Waiting for process learner_proc0 to stop...
+[2024-12-31 06:41:24,045][03000] Loop learner_proc0_evt_loop terminating...
+[2024-12-31 06:41:25,596][00788] Waiting for process inference_proc0-0 to join...
+[2024-12-31 06:41:25,599][00788] Waiting for process rollout_proc0 to join...
+[2024-12-31 06:41:27,455][00788] Waiting for process rollout_proc1 to join...
+[2024-12-31 06:41:27,457][00788] Waiting for process rollout_proc2 to join...
+[2024-12-31 06:41:27,458][00788] Waiting for process rollout_proc3 to join...
+[2024-12-31 06:41:27,460][00788] Waiting for process rollout_proc4 to join...
+[2024-12-31 06:41:27,462][00788] Waiting for process rollout_proc5 to join...
+[2024-12-31 06:41:27,464][00788] Waiting for process rollout_proc6 to join...
+[2024-12-31 06:41:27,466][00788] Waiting for process rollout_proc7 to join...
+[2024-12-31 06:41:27,468][00788] Batcher 0 profile tree view:
+batching: 26.1969, releasing_batches: 0.0258
+[2024-12-31 06:41:27,470][00788] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 381.0816
+update_model: 8.5363
+  weight_update: 0.0028
+one_step: 0.0024
+  handle_policy_step: 557.1223
+    deserialize: 14.3121, stack: 3.0853, obs_to_device_normalize: 119.5419, forward: 278.4132, send_messages: 26.9837
+    prepare_outputs: 86.8674
+      to_cpu: 52.9164
+[2024-12-31 06:41:27,471][00788] Learner 0 profile tree view:
+misc: 0.0051, prepare_batch: 13.2330
+train: 73.3492
+  epoch_init: 0.0128, minibatch_init: 0.0125, losses_postprocess: 0.7573, kl_divergence: 0.5518, after_optimizer: 33.6334
+  calculate_losses: 26.2378
+    losses_init: 0.0045, forward_head: 1.2232, bptt_initial: 17.7144, tail: 1.0115, advantages_returns: 0.2426, losses: 3.7787
+    bptt: 1.9598
+      bptt_forward_core: 1.8419
+  update: 11.4862
+    clip: 0.8621
+[2024-12-31 06:41:27,472][00788] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.3549, enqueue_policy_requests: 87.8263, env_step: 774.6256, overhead: 11.7799, complete_rollouts: 6.3283
+save_policy_outputs: 20.1779
+  split_output_tensors: 8.1182
+[2024-12-31 06:41:27,474][00788] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.3151, enqueue_policy_requests: 85.8950, env_step: 774.6481, overhead: 12.4036, complete_rollouts: 7.0383
+save_policy_outputs: 20.6207
+  split_output_tensors: 8.2105
+[2024-12-31 06:41:27,475][00788] Loop Runner_EvtLoop terminating...
+[2024-12-31 06:41:27,477][00788] Runner profile tree view:
+main_loop: 1014.7117
+[2024-12-31 06:41:27,478][00788] Collected {0: 4005888}, FPS: 3947.8
+[2024-12-31 06:44:38,578][00788] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-12-31 06:44:38,580][00788] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-12-31 06:44:38,581][00788] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-12-31 06:44:38,583][00788] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-12-31 06:44:38,585][00788] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-12-31 06:44:38,587][00788] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-12-31 06:44:38,588][00788] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-12-31 06:44:38,590][00788] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-12-31 06:44:38,592][00788] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-12-31 06:44:38,593][00788] Adding new argument 'hf_repository'='LunaMeme/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-12-31 06:44:38,594][00788] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-12-31 06:44:38,595][00788] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-12-31 06:44:38,596][00788] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-12-31 06:44:38,597][00788] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-12-31 06:44:38,598][00788] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-12-31 06:44:38,630][00788] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-12-31 06:44:38,634][00788] RunningMeanStd input shape: (3, 72, 128)
+[2024-12-31 06:44:38,635][00788] RunningMeanStd input shape: (1,)
+[2024-12-31 06:44:38,652][00788] ConvEncoder: input_channels=3
+[2024-12-31 06:44:38,752][00788] Conv encoder output size: 512
+[2024-12-31 06:44:38,754][00788] Policy head output size: 512
+[2024-12-31 06:44:39,013][00788] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-12-31 06:44:39,825][00788] Num frames 100...
+[2024-12-31 06:44:39,943][00788] Num frames 200...
+[2024-12-31 06:44:40,071][00788] Num frames 300...
+[2024-12-31 06:44:40,191][00788] Num frames 400...
+[2024-12-31 06:44:40,311][00788] Num frames 500...
+[2024-12-31 06:44:40,433][00788] Num frames 600...
+[2024-12-31 06:44:40,550][00788] Num frames 700...
+[2024-12-31 06:44:40,675][00788] Num frames 800...
+[2024-12-31 06:44:40,797][00788] Num frames 900...
+[2024-12-31 06:44:40,915][00788] Num frames 1000...
+[2024-12-31 06:44:41,038][00788] Avg episode rewards: #0: 20.560, true rewards: #0: 10.560
+[2024-12-31 06:44:41,039][00788] Avg episode reward: 20.560, avg true_objective: 10.560
+[2024-12-31 06:44:41,103][00788] Num frames 1100...
+[2024-12-31 06:44:41,222][00788] Num frames 1200...
+[2024-12-31 06:44:41,348][00788] Num frames 1300...
+[2024-12-31 06:44:41,474][00788] Num frames 1400...
+[2024-12-31 06:44:41,594][00788] Num frames 1500...
+[2024-12-31 06:44:41,663][00788] Avg episode rewards: #0: 13.550, true rewards: #0: 7.550
+[2024-12-31 06:44:41,665][00788] Avg episode reward: 13.550, avg true_objective: 7.550
+[2024-12-31 06:44:41,776][00788] Num frames 1600...
+[2024-12-31 06:44:41,897][00788] Num frames 1700...
+[2024-12-31 06:44:42,014][00788] Num frames 1800...
+[2024-12-31 06:44:42,142][00788] Num frames 1900...
+[2024-12-31 06:44:42,260][00788] Num frames 2000...
+[2024-12-31 06:44:42,379][00788] Avg episode rewards: #0: 11.513, true rewards: #0: 6.847
+[2024-12-31 06:44:42,381][00788] Avg episode reward: 11.513, avg true_objective: 6.847
+[2024-12-31 06:44:42,443][00788] Num frames 2100...
+[2024-12-31 06:44:42,565][00788] Num frames 2200...
+[2024-12-31 06:44:42,689][00788] Num frames 2300...
+[2024-12-31 06:44:42,810][00788] Num frames 2400...
+[2024-12-31 06:44:42,933][00788] Num frames 2500...
+[2024-12-31 06:44:43,069][00788] Num frames 2600...
+[2024-12-31 06:44:43,228][00788] Avg episode rewards: #0: 11.155, true rewards: #0: 6.655
+[2024-12-31 06:44:43,230][00788] Avg episode reward: 11.155, avg true_objective: 6.655
+[2024-12-31 06:44:43,278][00788] Num frames 2700...
+[2024-12-31 06:44:43,406][00788] Num frames 2800...
+[2024-12-31 06:44:43,524][00788] Num frames 2900...
+[2024-12-31 06:44:43,643][00788] Num frames 3000...
+[2024-12-31 06:44:43,761][00788] Num frames 3100...
+[2024-12-31 06:44:43,885][00788] Num frames 3200...
+[2024-12-31 06:44:44,007][00788] Num frames 3300...
+[2024-12-31 06:44:44,125][00788] Num frames 3400...
+[2024-12-31 06:44:44,256][00788] Num frames 3500...
+[2024-12-31 06:44:44,382][00788] Num frames 3600...
+[2024-12-31 06:44:44,505][00788] Num frames 3700...
+[2024-12-31 06:44:44,584][00788] Avg episode rewards: #0: 13.036, true rewards: #0: 7.436
+[2024-12-31 06:44:44,585][00788] Avg episode reward: 13.036, avg true_objective: 7.436
+[2024-12-31 06:44:44,686][00788] Num frames 3800...
+[2024-12-31 06:44:44,803][00788] Num frames 3900...
+[2024-12-31 06:44:44,926][00788] Num frames 4000...
+[2024-12-31 06:44:45,045][00788] Num frames 4100...
+[2024-12-31 06:44:45,162][00788] Num frames 4200...
+[2024-12-31 06:44:45,293][00788] Num frames 4300...
+[2024-12-31 06:44:45,417][00788] Num frames 4400...
+[2024-12-31 06:44:45,585][00788] Avg episode rewards: #0: 12.977, true rewards: #0: 7.477
+[2024-12-31 06:44:45,587][00788] Avg episode reward: 12.977, avg true_objective: 7.477
+[2024-12-31 06:44:45,613][00788] Num frames 4500...
+[2024-12-31 06:44:45,778][00788] Num frames 4600...
+[2024-12-31 06:44:45,945][00788] Num frames 4700...
+[2024-12-31 06:44:46,111][00788] Num frames 4800...
+[2024-12-31 06:44:46,278][00788] Num frames 4900...
+[2024-12-31 06:44:46,446][00788] Num frames 5000...
+[2024-12-31 06:44:46,616][00788] Num frames 5100...
+[2024-12-31 06:44:46,781][00788] Num frames 5200...
+[2024-12-31 06:44:46,944][00788] Num frames 5300...
+[2024-12-31 06:44:47,121][00788] Num frames 5400...
+[2024-12-31 06:44:47,285][00788] Num frames 5500...
+[2024-12-31 06:44:47,463][00788] Num frames 5600...
+[2024-12-31 06:44:47,633][00788] Num frames 5700...
+[2024-12-31 06:44:47,752][00788] Avg episode rewards: #0: 14.763, true rewards: #0: 8.191
+[2024-12-31 06:44:47,754][00788] Avg episode reward: 14.763, avg true_objective: 8.191
+[2024-12-31 06:44:47,866][00788] Num frames 5800...
+[2024-12-31 06:44:48,008][00788] Num frames 5900...
+[2024-12-31 06:44:48,131][00788] Num frames 6000...
+[2024-12-31 06:44:48,248][00788] Num frames 6100...
+[2024-12-31 06:44:48,385][00788] Num frames 6200...
+[2024-12-31 06:44:48,513][00788] Num frames 6300...
+[2024-12-31 06:44:48,682][00788] Avg episode rewards: #0: 14.370, true rewards: #0: 7.995
+[2024-12-31 06:44:48,683][00788] Avg episode reward: 14.370, avg true_objective: 7.995
+[2024-12-31 06:44:48,692][00788] Num frames 6400...
+[2024-12-31 06:44:48,811][00788] Num frames 6500...
+[2024-12-31 06:44:48,929][00788] Num frames 6600...
+[2024-12-31 06:44:49,048][00788] Num frames 6700...
+[2024-12-31 06:44:49,198][00788] Avg episode rewards: #0: 13.200, true rewards: #0: 7.533
+[2024-12-31 06:44:49,200][00788] Avg episode reward: 13.200, avg true_objective: 7.533
+[2024-12-31 06:44:49,226][00788] Num frames 6800...
+[2024-12-31 06:44:49,358][00788] Num frames 6900...
+[2024-12-31 06:44:49,486][00788] Num frames 7000...
+[2024-12-31 06:44:49,605][00788] Num frames 7100...
+[2024-12-31 06:44:49,728][00788] Num frames 7200...
+[2024-12-31 06:44:49,849][00788] Num frames 7300...
+[2024-12-31 06:44:49,968][00788] Num frames 7400...
+[2024-12-31 06:44:50,089][00788] Num frames 7500...
+[2024-12-31 06:44:50,251][00788] Avg episode rewards: #0: 13.489, true rewards: #0: 7.589
+[2024-12-31 06:44:50,252][00788] Avg episode reward: 13.489, avg true_objective: 7.589
+[2024-12-31 06:45:31,854][00788] Replay video saved to /content/train_dir/default_experiment/replay.mp4!