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.1729444491.90806ce10b21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e316ff30c6e83fb553913b8413230fd63efbf326f96376452bc6c7ff55487a2
+size 915741

README.md

@@ -0,0 +1,56 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: doom_health_gathering_supreme
+      type: doom_health_gathering_supreme
+    metrics:
+    - type: mean_reward
+      value: 4.48 +/- 0.66
+      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 jerryvc/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_000000885_3624960_reward_5.461.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dbaba111d7271188901b91ca8061ed95d22cd78133bdb6b15f8d58aa0e2e20c
+size 34929051

checkpoint_p0/checkpoint_000000955_3911680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fcdeac66b49f75be99ed85b5c669b82557c4df5cf56e247cbfae93b8847d8ad
+size 34929541

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed53f888ced599dd929a852a22f480d0ae3bc3b27211de662a5f8675dc7a21d
+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 sha256:24c9b0c85b1482d69ed5a7e956d27b7d01b7dd7d68cde3d10baa413ed582ddb1
+size 5707871

sf_log.txt

@@ -0,0 +1,959 @@
+[2024-10-20 17:15:03,060][00556] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-10-20 17:15:03,062][00556] Rollout worker 0 uses device cpu
+[2024-10-20 17:15:03,064][00556] Rollout worker 1 uses device cpu
+[2024-10-20 17:15:03,065][00556] Rollout worker 2 uses device cpu
+[2024-10-20 17:15:03,066][00556] Rollout worker 3 uses device cpu
+[2024-10-20 17:15:03,068][00556] Rollout worker 4 uses device cpu
+[2024-10-20 17:15:03,069][00556] Rollout worker 5 uses device cpu
+[2024-10-20 17:15:03,070][00556] Rollout worker 6 uses device cpu
+[2024-10-20 17:15:03,071][00556] Rollout worker 7 uses device cpu
+[2024-10-20 17:15:03,247][00556] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-10-20 17:15:03,249][00556] InferenceWorker_p0-w0: min num requests: 2
+[2024-10-20 17:15:03,282][00556] Starting all processes...
+[2024-10-20 17:15:03,283][00556] Starting process learner_proc0
+[2024-10-20 17:15:05,374][00556] Starting all processes...
+[2024-10-20 17:15:05,383][00556] Starting process inference_proc0-0
+[2024-10-20 17:15:05,384][00556] Starting process rollout_proc0
+[2024-10-20 17:15:05,385][00556] Starting process rollout_proc1
+[2024-10-20 17:15:05,385][00556] Starting process rollout_proc2
+[2024-10-20 17:15:05,385][00556] Starting process rollout_proc3
+[2024-10-20 17:15:05,386][00556] Starting process rollout_proc4
+[2024-10-20 17:15:05,386][00556] Starting process rollout_proc5
+[2024-10-20 17:15:05,389][00556] Starting process rollout_proc6
+[2024-10-20 17:15:05,389][00556] Starting process rollout_proc7
+[2024-10-20 17:15:20,894][02541] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-10-20 17:15:20,894][02541] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-10-20 17:15:20,919][02558] Worker 2 uses CPU cores [0]
+[2024-10-20 17:15:20,964][02541] Num visible devices: 1
+[2024-10-20 17:15:21,000][02541] Starting seed is not provided
+[2024-10-20 17:15:21,001][02541] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-10-20 17:15:21,002][02541] Initializing actor-critic model on device cuda:0
+[2024-10-20 17:15:21,003][02541] RunningMeanStd input shape: (3, 72, 128)
+[2024-10-20 17:15:21,005][02541] RunningMeanStd input shape: (1,)
+[2024-10-20 17:15:21,074][02541] ConvEncoder: input_channels=3
+[2024-10-20 17:15:21,102][02556] Worker 1 uses CPU cores [1]
+[2024-10-20 17:15:21,193][02557] Worker 3 uses CPU cores [1]
+[2024-10-20 17:15:21,201][02555] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-10-20 17:15:21,202][02555] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-10-20 17:15:21,235][02559] Worker 6 uses CPU cores [0]
+[2024-10-20 17:15:21,266][02555] Num visible devices: 1
+[2024-10-20 17:15:21,274][02561] Worker 5 uses CPU cores [1]
+[2024-10-20 17:15:21,300][02562] Worker 7 uses CPU cores [1]
+[2024-10-20 17:15:21,325][02554] Worker 0 uses CPU cores [0]
+[2024-10-20 17:15:21,397][02560] Worker 4 uses CPU cores [0]
+[2024-10-20 17:15:21,467][02541] Conv encoder output size: 512
+[2024-10-20 17:15:21,467][02541] Policy head output size: 512
+[2024-10-20 17:15:21,526][02541] Created Actor Critic model with architecture:
+[2024-10-20 17:15:21,527][02541] 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)
+  )
+)
+[2024-10-20 17:15:21,822][02541] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-10-20 17:15:22,888][02541] No checkpoints found
+[2024-10-20 17:15:22,889][02541] Did not load from checkpoint, starting from scratch!
+[2024-10-20 17:15:22,889][02541] Initialized policy 0 weights for model version 0
+[2024-10-20 17:15:22,893][02541] LearnerWorker_p0 finished initialization!
+[2024-10-20 17:15:22,894][02541] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-10-20 17:15:22,986][02555] RunningMeanStd input shape: (3, 72, 128)
+[2024-10-20 17:15:22,987][02555] RunningMeanStd input shape: (1,)
+[2024-10-20 17:15:22,999][02555] ConvEncoder: input_channels=3
+[2024-10-20 17:15:23,101][02555] Conv encoder output size: 512
+[2024-10-20 17:15:23,101][02555] Policy head output size: 512
+[2024-10-20 17:15:23,153][00556] Inference worker 0-0 is ready!
+[2024-10-20 17:15:23,155][00556] All inference workers are ready! Signal rollout workers to start!
+[2024-10-20 17:15:23,239][00556] Heartbeat connected on Batcher_0
+[2024-10-20 17:15:23,242][00556] Heartbeat connected on LearnerWorker_p0
+[2024-10-20 17:15:23,284][00556] Heartbeat connected on InferenceWorker_p0-w0
+[2024-10-20 17:15:23,361][02557] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:15:23,360][02556] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:15:23,359][02562] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:15:23,357][02561] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:15:23,392][02554] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:15:23,396][02560] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:15:23,394][02559] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:15:23,404][02558] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:15:24,535][02557] Decorrelating experience for 0 frames...
+[2024-10-20 17:15:24,536][02562] Decorrelating experience for 0 frames...
+[2024-10-20 17:15:25,211][02554] Decorrelating experience for 0 frames...
+[2024-10-20 17:15:25,213][02560] Decorrelating experience for 0 frames...
+[2024-10-20 17:15:25,214][02558] Decorrelating experience for 0 frames...
+[2024-10-20 17:15:25,210][02559] Decorrelating experience for 0 frames...
+[2024-10-20 17:15:25,600][02562] Decorrelating experience for 32 frames...
+[2024-10-20 17:15:26,500][02554] Decorrelating experience for 32 frames...
+[2024-10-20 17:15:26,503][02559] Decorrelating experience for 32 frames...
+[2024-10-20 17:15:26,505][02558] Decorrelating experience for 32 frames...
+[2024-10-20 17:15:26,994][00556] 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)
+[2024-10-20 17:15:27,432][02556] Decorrelating experience for 0 frames...
+[2024-10-20 17:15:27,788][02562] Decorrelating experience for 64 frames...
+[2024-10-20 17:15:28,057][02561] Decorrelating experience for 0 frames...
+[2024-10-20 17:15:28,204][02560] Decorrelating experience for 32 frames...
+[2024-10-20 17:15:28,653][02559] Decorrelating experience for 64 frames...
+[2024-10-20 17:15:28,729][02556] Decorrelating experience for 32 frames...
+[2024-10-20 17:15:29,221][02562] Decorrelating experience for 96 frames...
+[2024-10-20 17:15:29,436][00556] Heartbeat connected on RolloutWorker_w7
+[2024-10-20 17:15:29,779][02558] Decorrelating experience for 64 frames...
+[2024-10-20 17:15:30,096][02561] Decorrelating experience for 32 frames...
+[2024-10-20 17:15:30,265][02560] Decorrelating experience for 64 frames...
+[2024-10-20 17:15:30,607][02556] Decorrelating experience for 64 frames...
+[2024-10-20 17:15:31,101][02554] Decorrelating experience for 64 frames...
+[2024-10-20 17:15:31,208][02558] Decorrelating experience for 96 frames...
+[2024-10-20 17:15:31,312][02557] Decorrelating experience for 32 frames...
+[2024-10-20 17:15:31,466][00556] Heartbeat connected on RolloutWorker_w2
+[2024-10-20 17:15:31,618][02561] Decorrelating experience for 64 frames...
+[2024-10-20 17:15:31,994][00556] 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)
+[2024-10-20 17:15:33,360][02560] Decorrelating experience for 96 frames...
+[2024-10-20 17:15:33,798][02554] Decorrelating experience for 96 frames...
+[2024-10-20 17:15:33,801][00556] Heartbeat connected on RolloutWorker_w4
+[2024-10-20 17:15:34,196][02556] Decorrelating experience for 96 frames...
+[2024-10-20 17:15:34,206][00556] Heartbeat connected on RolloutWorker_w0
+[2024-10-20 17:15:34,243][02557] Decorrelating experience for 64 frames...
+[2024-10-20 17:15:34,418][02561] Decorrelating experience for 96 frames...
+[2024-10-20 17:15:34,548][00556] Heartbeat connected on RolloutWorker_w1
+[2024-10-20 17:15:34,787][00556] Heartbeat connected on RolloutWorker_w5
+[2024-10-20 17:15:36,541][02541] Signal inference workers to stop experience collection...
+[2024-10-20 17:15:36,555][02555] InferenceWorker_p0-w0: stopping experience collection
+[2024-10-20 17:15:36,596][02559] Decorrelating experience for 96 frames...
+[2024-10-20 17:15:36,717][02557] Decorrelating experience for 96 frames...
+[2024-10-20 17:15:36,772][00556] Heartbeat connected on RolloutWorker_w6
+[2024-10-20 17:15:36,803][00556] Heartbeat connected on RolloutWorker_w3
+[2024-10-20 17:15:36,994][00556] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 151.6. Samples: 1516. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-10-20 17:15:36,996][00556] Avg episode reward: [(0, '2.669')]
+[2024-10-20 17:15:39,764][02541] Signal inference workers to resume experience collection...
+[2024-10-20 17:15:39,765][02555] InferenceWorker_p0-w0: resuming experience collection
+[2024-10-20 17:15:41,994][00556] Fps is (10 sec: 1228.8, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 12288. Throughput: 0: 207.7. Samples: 3116. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2024-10-20 17:15:42,000][00556] Avg episode reward: [(0, '2.906')]
+[2024-10-20 17:15:46,994][00556] Fps is (10 sec: 2457.6, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 24576. Throughput: 0: 262.0. Samples: 5240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:15:46,997][00556] Avg episode reward: [(0, '3.593')]
+[2024-10-20 17:15:49,960][02555] Updated weights for policy 0, policy_version 10 (0.0029)
+[2024-10-20 17:15:51,994][00556] Fps is (10 sec: 3686.4, 60 sec: 1966.1, 300 sec: 1966.1). Total num frames: 49152. Throughput: 0: 441.9. Samples: 11048. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:15:51,999][00556] Avg episode reward: [(0, '4.364')]
+[2024-10-20 17:15:56,998][00556] Fps is (10 sec: 4504.1, 60 sec: 2320.8, 300 sec: 2320.8). Total num frames: 69632. Throughput: 0: 584.8. Samples: 17546. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:15:57,000][00556] Avg episode reward: [(0, '4.628')]
+[2024-10-20 17:16:01,994][00556] Fps is (10 sec: 2867.2, 60 sec: 2223.5, 300 sec: 2223.5). Total num frames: 77824. Throughput: 0: 532.2. Samples: 18626. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:16:01,997][00556] Avg episode reward: [(0, '4.649')]
+[2024-10-20 17:16:02,757][02555] Updated weights for policy 0, policy_version 20 (0.0040)
+[2024-10-20 17:16:06,994][00556] Fps is (10 sec: 2868.2, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 98304. Throughput: 0: 577.2. Samples: 23088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:16:06,997][00556] Avg episode reward: [(0, '4.491')]
+[2024-10-20 17:16:11,996][00556] Fps is (10 sec: 3685.7, 60 sec: 2548.5, 300 sec: 2548.5). Total num frames: 114688. Throughput: 0: 648.3. Samples: 29176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:16:12,001][00556] Avg episode reward: [(0, '4.403')]
+[2024-10-20 17:16:12,062][02541] Saving new best policy, reward=4.403!
+[2024-10-20 17:16:13,033][02555] Updated weights for policy 0, policy_version 30 (0.0020)
+[2024-10-20 17:16:16,994][00556] Fps is (10 sec: 3276.8, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 131072. Throughput: 0: 716.0. Samples: 32220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:16:16,998][00556] Avg episode reward: [(0, '4.388')]
+[2024-10-20 17:16:21,994][00556] Fps is (10 sec: 3277.4, 60 sec: 2681.0, 300 sec: 2681.0). Total num frames: 147456. Throughput: 0: 774.0. Samples: 36344. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:16:21,997][00556] Avg episode reward: [(0, '4.313')]
+[2024-10-20 17:16:24,824][02555] Updated weights for policy 0, policy_version 40 (0.0020)
+[2024-10-20 17:16:26,994][00556] Fps is (10 sec: 4096.0, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 172032. Throughput: 0: 883.7. Samples: 42882. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:16:26,996][00556] Avg episode reward: [(0, '4.438')]
+[2024-10-20 17:16:27,005][02541] Saving new best policy, reward=4.438!
+[2024-10-20 17:16:31,996][00556] Fps is (10 sec: 4504.9, 60 sec: 3208.4, 300 sec: 2961.6). Total num frames: 192512. Throughput: 0: 907.9. Samples: 46098. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:16:31,998][00556] Avg episode reward: [(0, '4.485')]
+[2024-10-20 17:16:32,008][02541] Saving new best policy, reward=4.485!
+[2024-10-20 17:16:36,603][02555] Updated weights for policy 0, policy_version 50 (0.0025)
+[2024-10-20 17:16:36,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 2925.7). Total num frames: 204800. Throughput: 0: 879.0. Samples: 50602. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-10-20 17:16:37,001][00556] Avg episode reward: [(0, '4.468')]
+[2024-10-20 17:16:41,994][00556] Fps is (10 sec: 3277.3, 60 sec: 3549.9, 300 sec: 3003.7). Total num frames: 225280. Throughput: 0: 867.1. Samples: 56562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:16:41,996][00556] Avg episode reward: [(0, '4.318')]
+[2024-10-20 17:16:45,872][02555] Updated weights for policy 0, policy_version 60 (0.0035)
+[2024-10-20 17:16:46,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3123.2). Total num frames: 249856. Throughput: 0: 920.7. Samples: 60056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:16:47,000][00556] Avg episode reward: [(0, '4.379')]
+[2024-10-20 17:16:51,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3084.0). Total num frames: 262144. Throughput: 0: 948.0. Samples: 65748. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:16:52,002][00556] Avg episode reward: [(0, '4.477')]
+[2024-10-20 17:16:52,014][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth...
+[2024-10-20 17:16:56,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3140.3). Total num frames: 282624. Throughput: 0: 923.1. Samples: 70712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:16:57,004][00556] Avg episode reward: [(0, '4.471')]
+[2024-10-20 17:16:57,509][02555] Updated weights for policy 0, policy_version 70 (0.0026)
+[2024-10-20 17:17:01,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3233.7). Total num frames: 307200. Throughput: 0: 930.7. Samples: 74102. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:17:01,997][00556] Avg episode reward: [(0, '4.424')]
+[2024-10-20 17:17:06,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3235.8). Total num frames: 323584. Throughput: 0: 984.7. Samples: 80654. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:17:07,000][00556] Avg episode reward: [(0, '4.367')]
+[2024-10-20 17:17:07,842][02555] Updated weights for policy 0, policy_version 80 (0.0030)
+[2024-10-20 17:17:11,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3237.8). Total num frames: 339968. Throughput: 0: 931.3. Samples: 84792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:17:12,000][00556] Avg episode reward: [(0, '4.414')]
+[2024-10-20 17:17:16,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 360448. Throughput: 0: 936.8. Samples: 88252. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:17:16,998][00556] Avg episode reward: [(0, '4.510')]
+[2024-10-20 17:17:17,001][02541] Saving new best policy, reward=4.510!
+[2024-10-20 17:17:18,037][02555] Updated weights for policy 0, policy_version 90 (0.0034)
+[2024-10-20 17:17:22,000][00556] Fps is (10 sec: 4503.1, 60 sec: 3959.1, 300 sec: 3347.9). Total num frames: 385024. Throughput: 0: 992.4. Samples: 95266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:17:22,008][00556] Avg episode reward: [(0, '4.607')]
+[2024-10-20 17:17:22,017][02541] Saving new best policy, reward=4.607!
+[2024-10-20 17:17:26,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3310.9). Total num frames: 397312. Throughput: 0: 966.3. Samples: 100044. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:17:26,996][00556] Avg episode reward: [(0, '4.601')]
+[2024-10-20 17:17:29,405][02555] Updated weights for policy 0, policy_version 100 (0.0035)
+[2024-10-20 17:17:31,994][00556] Fps is (10 sec: 3278.6, 60 sec: 3754.8, 300 sec: 3342.3). Total num frames: 417792. Throughput: 0: 945.3. Samples: 102596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:17:32,001][00556] Avg episode reward: [(0, '4.566')]
+[2024-10-20 17:17:36,996][00556] Fps is (10 sec: 4504.9, 60 sec: 3959.4, 300 sec: 3402.8). Total num frames: 442368. Throughput: 0: 973.0. Samples: 109534. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:17:37,002][00556] Avg episode reward: [(0, '4.592')]
+[2024-10-20 17:17:38,479][02555] Updated weights for policy 0, policy_version 110 (0.0022)
+[2024-10-20 17:17:41,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3398.2). Total num frames: 458752. Throughput: 0: 985.1. Samples: 115042. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:17:41,998][00556] Avg episode reward: [(0, '4.664')]
+[2024-10-20 17:17:42,006][02541] Saving new best policy, reward=4.664!
+[2024-10-20 17:17:46,994][00556] Fps is (10 sec: 3277.3, 60 sec: 3754.7, 300 sec: 3393.8). Total num frames: 475136. Throughput: 0: 954.7. Samples: 117062. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:17:47,000][00556] Avg episode reward: [(0, '4.536')]
+[2024-10-20 17:17:49,896][02555] Updated weights for policy 0, policy_version 120 (0.0031)
+[2024-10-20 17:17:51,995][00556] Fps is (10 sec: 4095.8, 60 sec: 3959.4, 300 sec: 3446.3). Total num frames: 499712. Throughput: 0: 956.2. Samples: 123684. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:17:51,997][00556] Avg episode reward: [(0, '4.404')]
+[2024-10-20 17:17:56,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3467.9). Total num frames: 520192. Throughput: 0: 1007.4. Samples: 130126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:17:57,000][00556] Avg episode reward: [(0, '4.698')]
+[2024-10-20 17:17:57,005][02541] Saving new best policy, reward=4.698!
+[2024-10-20 17:18:01,623][02555] Updated weights for policy 0, policy_version 130 (0.0025)
+[2024-10-20 17:18:01,994][00556] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 3435.4). Total num frames: 532480. Throughput: 0: 973.4. Samples: 132056. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:18:02,001][00556] Avg episode reward: [(0, '4.713')]
+[2024-10-20 17:18:02,013][02541] Saving new best policy, reward=4.713!
+[2024-10-20 17:18:06,994][00556] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3456.0). Total num frames: 552960. Throughput: 0: 941.6. Samples: 137634. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:18:07,000][00556] Avg episode reward: [(0, '4.475')]
+[2024-10-20 17:18:10,782][02555] Updated weights for policy 0, policy_version 140 (0.0029)
+[2024-10-20 17:18:11,994][00556] Fps is (10 sec: 4505.5, 60 sec: 3959.4, 300 sec: 3500.2). Total num frames: 577536. Throughput: 0: 985.5. Samples: 144394. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:18:12,000][00556] Avg episode reward: [(0, '4.464')]
+[2024-10-20 17:18:16,994][00556] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3469.6). Total num frames: 589824. Throughput: 0: 982.7. Samples: 146816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:18:17,000][00556] Avg episode reward: [(0, '4.402')]
+[2024-10-20 17:18:21,994][00556] Fps is (10 sec: 3276.9, 60 sec: 3755.0, 300 sec: 3487.4). Total num frames: 610304. Throughput: 0: 935.7. Samples: 151638. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:18:21,997][00556] Avg episode reward: [(0, '4.324')]
+[2024-10-20 17:18:22,334][02555] Updated weights for policy 0, policy_version 150 (0.0037)
+[2024-10-20 17:18:26,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3527.1). Total num frames: 634880. Throughput: 0: 969.6. Samples: 158672. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:18:27,002][00556] Avg episode reward: [(0, '4.426')]
+[2024-10-20 17:18:31,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3520.3). Total num frames: 651264. Throughput: 0: 995.8. Samples: 161874. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:18:31,998][00556] Avg episode reward: [(0, '4.579')]
+[2024-10-20 17:18:33,044][02555] Updated weights for policy 0, policy_version 160 (0.0025)
+[2024-10-20 17:18:36,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3513.9). Total num frames: 667648. Throughput: 0: 940.7. Samples: 166016. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:18:36,997][00556] Avg episode reward: [(0, '4.686')]
+[2024-10-20 17:18:41,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3528.9). Total num frames: 688128. Throughput: 0: 942.2. Samples: 172524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:18:42,000][00556] Avg episode reward: [(0, '4.555')]
+[2024-10-20 17:18:43,120][02555] Updated weights for policy 0, policy_version 170 (0.0032)
+[2024-10-20 17:18:46,997][00556] Fps is (10 sec: 4094.9, 60 sec: 3891.0, 300 sec: 3543.0). Total num frames: 708608. Throughput: 0: 975.8. Samples: 175968. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:18:47,003][00556] Avg episode reward: [(0, '4.542')]
+[2024-10-20 17:18:51,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3536.5). Total num frames: 724992. Throughput: 0: 962.0. Samples: 180926. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:18:51,997][00556] Avg episode reward: [(0, '4.566')]
+[2024-10-20 17:18:52,020][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000177_724992.pth...
+[2024-10-20 17:18:54,722][02555] Updated weights for policy 0, policy_version 180 (0.0048)
+[2024-10-20 17:18:56,994][00556] Fps is (10 sec: 3687.4, 60 sec: 3754.7, 300 sec: 3549.9). Total num frames: 745472. Throughput: 0: 938.0. Samples: 186602. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:18:57,001][00556] Avg episode reward: [(0, '4.457')]
+[2024-10-20 17:19:01,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3581.6). Total num frames: 770048. Throughput: 0: 961.3. Samples: 190076. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:19:01,998][00556] Avg episode reward: [(0, '4.644')]
+[2024-10-20 17:19:04,069][02555] Updated weights for policy 0, policy_version 190 (0.0013)
+[2024-10-20 17:19:07,000][00556] Fps is (10 sec: 3684.4, 60 sec: 3822.6, 300 sec: 3556.0). Total num frames: 782336. Throughput: 0: 984.8. Samples: 195960. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:19:07,002][00556] Avg episode reward: [(0, '4.712')]
+[2024-10-20 17:19:11,994][00556] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3568.1). Total num frames: 802816. Throughput: 0: 934.2. Samples: 200712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:19:11,999][00556] Avg episode reward: [(0, '4.756')]
+[2024-10-20 17:19:12,008][02541] Saving new best policy, reward=4.756!
+[2024-10-20 17:19:15,359][02555] Updated weights for policy 0, policy_version 200 (0.0037)
+[2024-10-20 17:19:16,994][00556] Fps is (10 sec: 4098.2, 60 sec: 3891.2, 300 sec: 3579.5). Total num frames: 823296. Throughput: 0: 938.7. Samples: 204116. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:19:17,000][00556] Avg episode reward: [(0, '4.541')]
+[2024-10-20 17:19:21,997][00556] Fps is (10 sec: 4095.1, 60 sec: 3891.1, 300 sec: 3590.5). Total num frames: 843776. Throughput: 0: 994.2. Samples: 210756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:19:21,999][00556] Avg episode reward: [(0, '4.340')]
+[2024-10-20 17:19:26,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3566.9). Total num frames: 856064. Throughput: 0: 936.6. Samples: 214670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:19:26,997][00556] Avg episode reward: [(0, '4.488')]
+[2024-10-20 17:19:27,238][02555] Updated weights for policy 0, policy_version 210 (0.0017)
+[2024-10-20 17:19:31,994][00556] Fps is (10 sec: 3687.3, 60 sec: 3822.9, 300 sec: 3594.4). Total num frames: 880640. Throughput: 0: 928.8. Samples: 217760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:19:31,998][00556] Avg episode reward: [(0, '4.370')]
+[2024-10-20 17:19:36,708][02555] Updated weights for policy 0, policy_version 220 (0.0030)
+[2024-10-20 17:19:36,998][00556] Fps is (10 sec: 4504.1, 60 sec: 3891.0, 300 sec: 3604.4). Total num frames: 901120. Throughput: 0: 964.2. Samples: 224320. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:19:37,000][00556] Avg episode reward: [(0, '4.397')]
+[2024-10-20 17:19:41,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3582.0). Total num frames: 913408. Throughput: 0: 939.1. Samples: 228862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:19:41,997][00556] Avg episode reward: [(0, '4.374')]
+[2024-10-20 17:19:46,994][00556] Fps is (10 sec: 3277.9, 60 sec: 3754.8, 300 sec: 3591.9). Total num frames: 933888. Throughput: 0: 910.8. Samples: 231062. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:19:47,001][00556] Avg episode reward: [(0, '4.654')]
+[2024-10-20 17:19:48,771][02555] Updated weights for policy 0, policy_version 230 (0.0024)
+[2024-10-20 17:19:51,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3601.4). Total num frames: 954368. Throughput: 0: 928.9. Samples: 237754. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:19:52,002][00556] Avg episode reward: [(0, '4.973')]
+[2024-10-20 17:19:52,010][02541] Saving new best policy, reward=4.973!
+[2024-10-20 17:19:56,995][00556] Fps is (10 sec: 3685.9, 60 sec: 3754.6, 300 sec: 3595.4). Total num frames: 970752. Throughput: 0: 947.9. Samples: 243368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:19:57,000][00556] Avg episode reward: [(0, '4.925')]
+[2024-10-20 17:20:00,486][02555] Updated weights for policy 0, policy_version 240 (0.0020)
+[2024-10-20 17:20:01,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3589.6). Total num frames: 987136. Throughput: 0: 918.1. Samples: 245432. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:20:02,001][00556] Avg episode reward: [(0, '4.858')]
+[2024-10-20 17:20:06,996][00556] Fps is (10 sec: 4095.9, 60 sec: 3823.2, 300 sec: 3613.2). Total num frames: 1011712. Throughput: 0: 906.3. Samples: 251538. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-10-20 17:20:06,998][00556] Avg episode reward: [(0, '4.596')]
+[2024-10-20 17:20:09,878][02555] Updated weights for policy 0, policy_version 250 (0.0033)
+[2024-10-20 17:20:11,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3607.4). Total num frames: 1028096. Throughput: 0: 962.8. Samples: 257998. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-10-20 17:20:12,001][00556] Avg episode reward: [(0, '4.561')]
+[2024-10-20 17:20:16,994][00556] Fps is (10 sec: 3277.3, 60 sec: 3686.4, 300 sec: 3601.7). Total num frames: 1044480. Throughput: 0: 937.6. Samples: 259954. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:20:17,000][00556] Avg episode reward: [(0, '4.634')]
+[2024-10-20 17:20:21,595][02555] Updated weights for policy 0, policy_version 260 (0.0020)
+[2024-10-20 17:20:21,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3610.0). Total num frames: 1064960. Throughput: 0: 908.8. Samples: 265214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:20:22,000][00556] Avg episode reward: [(0, '4.502')]
+[2024-10-20 17:20:26,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 1085440. Throughput: 0: 957.8. Samples: 271964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:20:26,996][00556] Avg episode reward: [(0, '4.740')]
+[2024-10-20 17:20:31,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1101824. Throughput: 0: 968.5. Samples: 274646. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:20:32,003][00556] Avg episode reward: [(0, '5.000')]
+[2024-10-20 17:20:32,017][02541] Saving new best policy, reward=5.000!
+[2024-10-20 17:20:32,964][02555] Updated weights for policy 0, policy_version 270 (0.0026)
+[2024-10-20 17:20:36,999][00556] Fps is (10 sec: 3275.3, 60 sec: 3618.1, 300 sec: 3748.8). Total num frames: 1118208. Throughput: 0: 918.0. Samples: 279070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:20:37,001][00556] Avg episode reward: [(0, '4.945')]
+[2024-10-20 17:20:41,994][00556] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1142784. Throughput: 0: 941.9. Samples: 285752. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:20:41,998][00556] Avg episode reward: [(0, '4.762')]
+[2024-10-20 17:20:42,566][02555] Updated weights for policy 0, policy_version 280 (0.0024)
+[2024-10-20 17:20:46,998][00556] Fps is (10 sec: 4505.7, 60 sec: 3822.7, 300 sec: 3776.6). Total num frames: 1163264. Throughput: 0: 970.7. Samples: 289116. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:20:47,002][00556] Avg episode reward: [(0, '4.688')]
+[2024-10-20 17:20:51,994][00556] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 1175552. Throughput: 0: 932.0. Samples: 293478. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:20:52,000][00556] Avg episode reward: [(0, '4.577')]
+[2024-10-20 17:20:52,010][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000287_1175552.pth...
+[2024-10-20 17:20:52,131][02541] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth
+[2024-10-20 17:20:54,261][02555] Updated weights for policy 0, policy_version 290 (0.0038)
+[2024-10-20 17:20:56,994][00556] Fps is (10 sec: 3687.9, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 1200128. Throughput: 0: 923.6. Samples: 299562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:20:57,006][00556] Avg episode reward: [(0, '4.978')]
+[2024-10-20 17:21:01,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 1220608. Throughput: 0: 955.8. Samples: 302966. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:21:02,002][00556] Avg episode reward: [(0, '4.826')]
+[2024-10-20 17:21:04,910][02555] Updated weights for policy 0, policy_version 300 (0.0017)
+[2024-10-20 17:21:06,994][00556] Fps is (10 sec: 3276.9, 60 sec: 3686.5, 300 sec: 3790.6). Total num frames: 1232896. Throughput: 0: 950.8. Samples: 308002. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:21:06,997][00556] Avg episode reward: [(0, '4.719')]
+[2024-10-20 17:21:11,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 1253376. Throughput: 0: 917.7. Samples: 313262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:21:11,999][00556] Avg episode reward: [(0, '4.776')]
+[2024-10-20 17:21:15,433][02555] Updated weights for policy 0, policy_version 310 (0.0019)
+[2024-10-20 17:21:16,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1273856. Throughput: 0: 932.1. Samples: 316592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:21:16,997][00556] Avg episode reward: [(0, '4.856')]
+[2024-10-20 17:21:21,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 1290240. Throughput: 0: 966.6. Samples: 322564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:21:22,006][00556] Avg episode reward: [(0, '4.800')]
+[2024-10-20 17:21:26,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 1306624. Throughput: 0: 918.4. Samples: 327080. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:21:26,999][00556] Avg episode reward: [(0, '4.793')]
+[2024-10-20 17:21:27,150][02555] Updated weights for policy 0, policy_version 320 (0.0027)
+[2024-10-20 17:21:31,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1331200. Throughput: 0: 917.7. Samples: 330410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:21:31,999][00556] Avg episode reward: [(0, '4.815')]
+[2024-10-20 17:21:36,637][02555] Updated weights for policy 0, policy_version 330 (0.0023)
+[2024-10-20 17:21:36,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.5, 300 sec: 3818.3). Total num frames: 1351680. Throughput: 0: 972.2. Samples: 337226. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:21:36,999][00556] Avg episode reward: [(0, '4.618')]
+[2024-10-20 17:21:41,997][00556] Fps is (10 sec: 3276.0, 60 sec: 3686.3, 300 sec: 3776.6). Total num frames: 1363968. Throughput: 0: 929.2. Samples: 341376. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:21:42,002][00556] Avg episode reward: [(0, '4.724')]
+[2024-10-20 17:21:46,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.7, 300 sec: 3804.4). Total num frames: 1384448. Throughput: 0: 914.3. Samples: 344108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:21:46,996][00556] Avg episode reward: [(0, '4.833')]
+[2024-10-20 17:21:48,289][02555] Updated weights for policy 0, policy_version 340 (0.0028)
+[2024-10-20 17:21:51,994][00556] Fps is (10 sec: 4506.7, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1409024. Throughput: 0: 955.1. Samples: 350982. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:21:51,997][00556] Avg episode reward: [(0, '4.703')]
+[2024-10-20 17:21:56,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 1421312. Throughput: 0: 952.0. Samples: 356100. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:21:56,999][00556] Avg episode reward: [(0, '4.475')]
+[2024-10-20 17:22:00,114][02555] Updated weights for policy 0, policy_version 350 (0.0034)
+[2024-10-20 17:22:01,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3790.5). Total num frames: 1441792. Throughput: 0: 924.8. Samples: 358206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:22:02,002][00556] Avg episode reward: [(0, '4.488')]
+[2024-10-20 17:22:06,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 1462272. Throughput: 0: 940.1. Samples: 364868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:22:06,997][00556] Avg episode reward: [(0, '4.633')]
+[2024-10-20 17:22:09,196][02555] Updated weights for policy 0, policy_version 360 (0.0024)
+[2024-10-20 17:22:11,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 1478656. Throughput: 0: 970.1. Samples: 370734. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:22:11,998][00556] Avg episode reward: [(0, '4.765')]
+[2024-10-20 17:22:16,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 1495040. Throughput: 0: 939.6. Samples: 372692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:22:17,001][00556] Avg episode reward: [(0, '4.802')]
+[2024-10-20 17:22:21,005][02555] Updated weights for policy 0, policy_version 370 (0.0037)
+[2024-10-20 17:22:21,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 1519616. Throughput: 0: 916.8. Samples: 378482. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:22:22,001][00556] Avg episode reward: [(0, '4.777')]
+[2024-10-20 17:22:26,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 1540096. Throughput: 0: 979.2. Samples: 385436. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:22:27,000][00556] Avg episode reward: [(0, '4.433')]
+[2024-10-20 17:22:31,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 1552384. Throughput: 0: 968.2. Samples: 387676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:22:31,997][00556] Avg episode reward: [(0, '4.478')]
+[2024-10-20 17:22:32,167][02555] Updated weights for policy 0, policy_version 380 (0.0025)
+[2024-10-20 17:22:36,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 1572864. Throughput: 0: 923.3. Samples: 392530. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:22:37,000][00556] Avg episode reward: [(0, '4.417')]
+[2024-10-20 17:22:41,833][02555] Updated weights for policy 0, policy_version 390 (0.0051)
+[2024-10-20 17:22:41,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.4, 300 sec: 3804.4). Total num frames: 1597440. Throughput: 0: 959.0. Samples: 399254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:22:42,002][00556] Avg episode reward: [(0, '4.413')]
+[2024-10-20 17:22:46,999][00556] Fps is (10 sec: 4094.2, 60 sec: 3822.7, 300 sec: 3776.6). Total num frames: 1613824. Throughput: 0: 981.0. Samples: 402356. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:22:47,001][00556] Avg episode reward: [(0, '4.597')]
+[2024-10-20 17:22:51,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 1630208. Throughput: 0: 925.0. Samples: 406494. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:22:51,999][00556] Avg episode reward: [(0, '4.710')]
+[2024-10-20 17:22:52,008][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000398_1630208.pth...
+[2024-10-20 17:22:52,126][02541] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000177_724992.pth
+[2024-10-20 17:22:53,659][02555] Updated weights for policy 0, policy_version 400 (0.0014)
+[2024-10-20 17:22:56,994][00556] Fps is (10 sec: 3688.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1650688. Throughput: 0: 939.7. Samples: 413022. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:22:56,999][00556] Avg episode reward: [(0, '4.779')]
+[2024-10-20 17:23:01,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1671168. Throughput: 0: 970.4. Samples: 416362. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:23:02,000][00556] Avg episode reward: [(0, '4.848')]
+[2024-10-20 17:23:04,254][02555] Updated weights for policy 0, policy_version 410 (0.0031)
+[2024-10-20 17:23:06,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 1683456. Throughput: 0: 944.8. Samples: 421000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:23:07,001][00556] Avg episode reward: [(0, '4.805')]
+[2024-10-20 17:23:11,994][00556] Fps is (10 sec: 3276.7, 60 sec: 3754.6, 300 sec: 3776.6). Total num frames: 1703936. Throughput: 0: 914.4. Samples: 426584. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:23:11,997][00556] Avg episode reward: [(0, '4.771')]
+[2024-10-20 17:23:14,595][02555] Updated weights for policy 0, policy_version 420 (0.0021)
+[2024-10-20 17:23:16,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 1728512. Throughput: 0: 940.2. Samples: 429984. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-10-20 17:23:17,001][00556] Avg episode reward: [(0, '4.734')]
+[2024-10-20 17:23:21,996][00556] Fps is (10 sec: 3686.0, 60 sec: 3686.3, 300 sec: 3748.9). Total num frames: 1740800. Throughput: 0: 957.6. Samples: 435624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:23:22,003][00556] Avg episode reward: [(0, '4.944')]
+[2024-10-20 17:23:26,691][02555] Updated weights for policy 0, policy_version 430 (0.0034)
+[2024-10-20 17:23:26,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 1761280. Throughput: 0: 915.1. Samples: 440432. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:23:26,997][00556] Avg episode reward: [(0, '5.364')]
+[2024-10-20 17:23:26,999][02541] Saving new best policy, reward=5.364!
+[2024-10-20 17:23:31,994][00556] Fps is (10 sec: 4506.2, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 1785856. Throughput: 0: 921.1. Samples: 443802. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:23:32,001][00556] Avg episode reward: [(0, '5.019')]
+[2024-10-20 17:23:36,201][02555] Updated weights for policy 0, policy_version 440 (0.0028)
+[2024-10-20 17:23:36,996][00556] Fps is (10 sec: 4095.4, 60 sec: 3822.8, 300 sec: 3776.6). Total num frames: 1802240. Throughput: 0: 973.7. Samples: 450314. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:23:37,000][00556] Avg episode reward: [(0, '4.710')]
+[2024-10-20 17:23:41,994][00556] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3748.9). Total num frames: 1814528. Throughput: 0: 919.2. Samples: 454386. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:23:42,001][00556] Avg episode reward: [(0, '4.684')]
+[2024-10-20 17:23:46,996][00556] Fps is (10 sec: 3686.3, 60 sec: 3754.8, 300 sec: 3776.6). Total num frames: 1839104. Throughput: 0: 913.8. Samples: 457484. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:23:47,007][00556] Avg episode reward: [(0, '4.459')]
+[2024-10-20 17:23:47,651][02555] Updated weights for policy 0, policy_version 450 (0.0026)
+[2024-10-20 17:23:51,998][00556] Fps is (10 sec: 4504.0, 60 sec: 3822.7, 300 sec: 3776.6). Total num frames: 1859584. Throughput: 0: 962.5. Samples: 464316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:23:52,003][00556] Avg episode reward: [(0, '4.597')]
+[2024-10-20 17:23:56,998][00556] Fps is (10 sec: 3685.4, 60 sec: 3754.4, 300 sec: 3748.8). Total num frames: 1875968. Throughput: 0: 944.4. Samples: 469084. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:23:57,001][00556] Avg episode reward: [(0, '4.627')]
+[2024-10-20 17:23:59,352][02555] Updated weights for policy 0, policy_version 460 (0.0029)
+[2024-10-20 17:24:01,994][00556] Fps is (10 sec: 3277.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 1892352. Throughput: 0: 919.8. Samples: 471376. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:24:01,997][00556] Avg episode reward: [(0, '4.696')]
+[2024-10-20 17:24:06,994][00556] Fps is (10 sec: 4097.7, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 1916928. Throughput: 0: 945.6. Samples: 478174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:24:07,000][00556] Avg episode reward: [(0, '4.839')]
+[2024-10-20 17:24:08,367][02555] Updated weights for policy 0, policy_version 470 (0.0027)
+[2024-10-20 17:24:11,994][00556] Fps is (10 sec: 4096.1, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 1933312. Throughput: 0: 966.9. Samples: 483942. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:24:11,996][00556] Avg episode reward: [(0, '4.737')]
+[2024-10-20 17:24:16,994][00556] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 1949696. Throughput: 0: 938.0. Samples: 486012. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:24:16,996][00556] Avg episode reward: [(0, '4.771')]
+[2024-10-20 17:24:20,063][02555] Updated weights for policy 0, policy_version 480 (0.0033)
+[2024-10-20 17:24:21,995][00556] Fps is (10 sec: 4095.8, 60 sec: 3891.3, 300 sec: 3790.5). Total num frames: 1974272. Throughput: 0: 932.6. Samples: 492278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:24:21,999][00556] Avg episode reward: [(0, '4.778')]
+[2024-10-20 17:24:26,998][00556] Fps is (10 sec: 4503.7, 60 sec: 3890.9, 300 sec: 3776.6). Total num frames: 1994752. Throughput: 0: 989.4. Samples: 498914. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:24:27,004][00556] Avg episode reward: [(0, '4.685')]
+[2024-10-20 17:24:31,202][02555] Updated weights for policy 0, policy_version 490 (0.0027)
+[2024-10-20 17:24:31,994][00556] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 2007040. Throughput: 0: 965.1. Samples: 500910. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:24:31,998][00556] Avg episode reward: [(0, '4.489')]
+[2024-10-20 17:24:36,994][00556] Fps is (10 sec: 3278.2, 60 sec: 3754.8, 300 sec: 3776.7). Total num frames: 2027520. Throughput: 0: 929.3. Samples: 506130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:24:36,996][00556] Avg episode reward: [(0, '4.545')]
+[2024-10-20 17:24:40,936][02555] Updated weights for policy 0, policy_version 500 (0.0035)
+[2024-10-20 17:24:41,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3790.5). Total num frames: 2052096. Throughput: 0: 970.8. Samples: 512764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:24:41,997][00556] Avg episode reward: [(0, '4.800')]
+[2024-10-20 17:24:46,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3776.7). Total num frames: 2068480. Throughput: 0: 983.1. Samples: 515614. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:24:46,998][00556] Avg episode reward: [(0, '4.732')]
+[2024-10-20 17:24:51,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.9, 300 sec: 3776.7). Total num frames: 2084864. Throughput: 0: 928.0. Samples: 519936. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:24:52,002][00556] Avg episode reward: [(0, '4.685')]
+[2024-10-20 17:24:52,013][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000509_2084864.pth...
+[2024-10-20 17:24:52,144][02541] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000287_1175552.pth
+[2024-10-20 17:24:52,823][02555] Updated weights for policy 0, policy_version 510 (0.0023)
+[2024-10-20 17:24:56,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3823.2, 300 sec: 3790.5). Total num frames: 2105344. Throughput: 0: 949.9. Samples: 526688. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:24:57,003][00556] Avg episode reward: [(0, '4.702')]
+[2024-10-20 17:25:01,995][00556] Fps is (10 sec: 4095.6, 60 sec: 3891.1, 300 sec: 3776.7). Total num frames: 2125824. Throughput: 0: 978.2. Samples: 530034. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:25:01,999][00556] Avg episode reward: [(0, '4.588')]
+[2024-10-20 17:25:02,938][02555] Updated weights for policy 0, policy_version 520 (0.0040)
+[2024-10-20 17:25:06,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 2138112. Throughput: 0: 937.6. Samples: 534468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:25:06,996][00556] Avg episode reward: [(0, '4.495')]
+[2024-10-20 17:25:11,998][00556] Fps is (10 sec: 3685.3, 60 sec: 3822.7, 300 sec: 3790.5). Total num frames: 2162688. Throughput: 0: 923.6. Samples: 540474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:25:12,001][00556] Avg episode reward: [(0, '4.351')]
+[2024-10-20 17:25:13,734][02555] Updated weights for policy 0, policy_version 530 (0.0019)
+[2024-10-20 17:25:16,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 2183168. Throughput: 0: 955.0. Samples: 543884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:25:16,997][00556] Avg episode reward: [(0, '4.457')]
+[2024-10-20 17:25:21,994][00556] Fps is (10 sec: 3278.1, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 2195456. Throughput: 0: 956.7. Samples: 549180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:25:21,997][00556] Avg episode reward: [(0, '4.714')]
+[2024-10-20 17:25:25,374][02555] Updated weights for policy 0, policy_version 540 (0.0053)
+[2024-10-20 17:25:26,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.7, 300 sec: 3776.7). Total num frames: 2215936. Throughput: 0: 925.3. Samples: 554404. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:25:27,002][00556] Avg episode reward: [(0, '4.837')]
+[2024-10-20 17:25:31,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3804.5). Total num frames: 2240512. Throughput: 0: 934.6. Samples: 557670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:25:32,000][00556] Avg episode reward: [(0, '4.752')]
+[2024-10-20 17:25:35,054][02555] Updated weights for policy 0, policy_version 550 (0.0034)
+[2024-10-20 17:25:36,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2256896. Throughput: 0: 972.8. Samples: 563714. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:25:36,998][00556] Avg episode reward: [(0, '4.594')]
+[2024-10-20 17:25:41,994][00556] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3748.9). Total num frames: 2269184. Throughput: 0: 915.7. Samples: 567896. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:25:41,997][00556] Avg episode reward: [(0, '4.525')]
+[2024-10-20 17:25:46,605][02555] Updated weights for policy 0, policy_version 560 (0.0025)
+[2024-10-20 17:25:46,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 2293760. Throughput: 0: 916.6. Samples: 571280. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:25:46,998][00556] Avg episode reward: [(0, '4.673')]
+[2024-10-20 17:25:51,996][00556] Fps is (10 sec: 4504.7, 60 sec: 3822.8, 300 sec: 3776.6). Total num frames: 2314240. Throughput: 0: 972.2. Samples: 578220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:25:52,001][00556] Avg episode reward: [(0, '4.823')]
+[2024-10-20 17:25:56,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2330624. Throughput: 0: 940.2. Samples: 582780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:25:56,997][00556] Avg episode reward: [(0, '4.919')]
+[2024-10-20 17:25:58,127][02555] Updated weights for policy 0, policy_version 570 (0.0019)
+[2024-10-20 17:26:01,994][00556] Fps is (10 sec: 3687.1, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 2351104. Throughput: 0: 923.7. Samples: 585452. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:26:01,997][00556] Avg episode reward: [(0, '4.706')]
+[2024-10-20 17:26:06,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 2371584. Throughput: 0: 956.9. Samples: 592240. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:26:07,001][00556] Avg episode reward: [(0, '4.485')]
+[2024-10-20 17:26:07,351][02555] Updated weights for policy 0, policy_version 580 (0.0049)
+[2024-10-20 17:26:11,994][00556] Fps is (10 sec: 3686.3, 60 sec: 3754.9, 300 sec: 3776.6). Total num frames: 2387968. Throughput: 0: 956.1. Samples: 597430. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:26:11,997][00556] Avg episode reward: [(0, '4.536')]
+[2024-10-20 17:26:16,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 2404352. Throughput: 0: 929.2. Samples: 599484. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:26:17,001][00556] Avg episode reward: [(0, '4.665')]
+[2024-10-20 17:26:19,046][02555] Updated weights for policy 0, policy_version 590 (0.0028)
+[2024-10-20 17:26:21,994][00556] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 2428928. Throughput: 0: 940.4. Samples: 606030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:26:22,003][00556] Avg episode reward: [(0, '4.743')]
+[2024-10-20 17:26:26,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2445312. Throughput: 0: 985.4. Samples: 612240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:26:27,000][00556] Avg episode reward: [(0, '4.689')]
+[2024-10-20 17:26:30,201][02555] Updated weights for policy 0, policy_version 600 (0.0029)
+[2024-10-20 17:26:31,994][00556] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 2461696. Throughput: 0: 954.0. Samples: 614212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:26:31,997][00556] Avg episode reward: [(0, '4.709')]
+[2024-10-20 17:26:36,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3790.6). Total num frames: 2482176. Throughput: 0: 928.2. Samples: 619986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:26:36,999][00556] Avg episode reward: [(0, '4.537')]
+[2024-10-20 17:26:39,918][02555] Updated weights for policy 0, policy_version 610 (0.0037)
+[2024-10-20 17:26:41,994][00556] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3804.4). Total num frames: 2506752. Throughput: 0: 974.3. Samples: 626622. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:26:42,001][00556] Avg episode reward: [(0, '4.535')]
+[2024-10-20 17:26:47,000][00556] Fps is (10 sec: 3684.4, 60 sec: 3754.3, 300 sec: 3762.7). Total num frames: 2519040. Throughput: 0: 963.4. Samples: 628808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:26:47,002][00556] Avg episode reward: [(0, '4.781')]
+[2024-10-20 17:26:51,785][02555] Updated weights for policy 0, policy_version 620 (0.0034)
+[2024-10-20 17:26:51,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3790.5). Total num frames: 2539520. Throughput: 0: 917.6. Samples: 633530. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:26:51,998][00556] Avg episode reward: [(0, '4.873')]
+[2024-10-20 17:26:52,012][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000620_2539520.pth...
+[2024-10-20 17:26:52,183][02541] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000398_1630208.pth
+[2024-10-20 17:26:56,994][00556] Fps is (10 sec: 4098.2, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2560000. Throughput: 0: 951.9. Samples: 640266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:26:57,003][00556] Avg episode reward: [(0, '4.658')]
+[2024-10-20 17:27:01,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3776.6). Total num frames: 2576384. Throughput: 0: 976.4. Samples: 643420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:27:01,997][00556] Avg episode reward: [(0, '4.596')]
+[2024-10-20 17:27:02,378][02555] Updated weights for policy 0, policy_version 630 (0.0023)
+[2024-10-20 17:27:06,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 2592768. Throughput: 0: 922.7. Samples: 647550. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:27:07,003][00556] Avg episode reward: [(0, '4.627')]
+[2024-10-20 17:27:11,994][00556] Fps is (10 sec: 4096.1, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 2617344. Throughput: 0: 931.9. Samples: 654174. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:27:12,002][00556] Avg episode reward: [(0, '4.807')]
+[2024-10-20 17:27:12,912][02555] Updated weights for policy 0, policy_version 640 (0.0036)
+[2024-10-20 17:27:16,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2633728. Throughput: 0: 957.7. Samples: 657310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:27:17,001][00556] Avg episode reward: [(0, '4.921')]
+[2024-10-20 17:27:21,998][00556] Fps is (10 sec: 3275.7, 60 sec: 3686.2, 300 sec: 3762.7). Total num frames: 2650112. Throughput: 0: 934.8. Samples: 662054. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:27:22,000][00556] Avg episode reward: [(0, '4.677')]
+[2024-10-20 17:27:24,618][02555] Updated weights for policy 0, policy_version 650 (0.0041)
+[2024-10-20 17:27:26,994][00556] Fps is (10 sec: 3686.3, 60 sec: 3754.6, 300 sec: 3790.5). Total num frames: 2670592. Throughput: 0: 916.4. Samples: 667862. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:27:26,996][00556] Avg episode reward: [(0, '4.529')]
+[2024-10-20 17:27:31,994][00556] Fps is (10 sec: 4507.1, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 2695168. Throughput: 0: 942.7. Samples: 671224. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:27:31,996][00556] Avg episode reward: [(0, '4.440')]
+[2024-10-20 17:27:34,301][02555] Updated weights for policy 0, policy_version 660 (0.0025)
+[2024-10-20 17:27:36,994][00556] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2707456. Throughput: 0: 967.6. Samples: 677072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:27:37,000][00556] Avg episode reward: [(0, '4.531')]
+[2024-10-20 17:27:41,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 2727936. Throughput: 0: 927.2. Samples: 681990. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:27:41,997][00556] Avg episode reward: [(0, '4.663')]
+[2024-10-20 17:27:45,328][02555] Updated weights for policy 0, policy_version 670 (0.0018)
+[2024-10-20 17:27:46,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3823.3, 300 sec: 3790.5). Total num frames: 2748416. Throughput: 0: 931.8. Samples: 685350. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:27:47,000][00556] Avg episode reward: [(0, '4.670')]
+[2024-10-20 17:27:51,996][00556] Fps is (10 sec: 4095.4, 60 sec: 3822.8, 300 sec: 3790.5). Total num frames: 2768896. Throughput: 0: 984.9. Samples: 691870. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:27:51,999][00556] Avg episode reward: [(0, '4.565')]
+[2024-10-20 17:27:56,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 2781184. Throughput: 0: 929.6. Samples: 696004. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:27:56,996][00556] Avg episode reward: [(0, '4.838')]
+[2024-10-20 17:27:57,025][02555] Updated weights for policy 0, policy_version 680 (0.0030)
+[2024-10-20 17:28:01,994][00556] Fps is (10 sec: 3686.9, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 2805760. Throughput: 0: 932.3. Samples: 699264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:28:02,001][00556] Avg episode reward: [(0, '4.913')]
+[2024-10-20 17:28:06,054][02555] Updated weights for policy 0, policy_version 690 (0.0033)
+[2024-10-20 17:28:06,996][00556] Fps is (10 sec: 4504.9, 60 sec: 3891.1, 300 sec: 3804.4). Total num frames: 2826240. Throughput: 0: 979.4. Samples: 706126. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:28:07,003][00556] Avg episode reward: [(0, '4.540')]
+[2024-10-20 17:28:11,996][00556] Fps is (10 sec: 3685.9, 60 sec: 3754.6, 300 sec: 3776.6). Total num frames: 2842624. Throughput: 0: 953.3. Samples: 710762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:28:12,002][00556] Avg episode reward: [(0, '4.684')]
+[2024-10-20 17:28:16,994][00556] Fps is (10 sec: 3277.3, 60 sec: 3754.7, 300 sec: 3790.6). Total num frames: 2859008. Throughput: 0: 929.2. Samples: 713036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:28:16,997][00556] Avg episode reward: [(0, '4.639')]
+[2024-10-20 17:28:17,962][02555] Updated weights for policy 0, policy_version 700 (0.0028)
+[2024-10-20 17:28:21,994][00556] Fps is (10 sec: 4096.6, 60 sec: 3891.4, 300 sec: 3804.4). Total num frames: 2883584. Throughput: 0: 949.9. Samples: 719818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:28:21,997][00556] Avg episode reward: [(0, '4.914')]
+[2024-10-20 17:28:26,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2899968. Throughput: 0: 965.8. Samples: 725452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:28:26,996][00556] Avg episode reward: [(0, '4.976')]
+[2024-10-20 17:28:29,403][02555] Updated weights for policy 0, policy_version 710 (0.0020)
+[2024-10-20 17:28:31,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 2916352. Throughput: 0: 935.8. Samples: 727460. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:28:32,001][00556] Avg episode reward: [(0, '4.898')]
+[2024-10-20 17:28:36,994][00556] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 2936832. Throughput: 0: 931.5. Samples: 733786. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:28:37,002][00556] Avg episode reward: [(0, '4.801')]
+[2024-10-20 17:28:38,815][02555] Updated weights for policy 0, policy_version 720 (0.0028)
+[2024-10-20 17:28:41,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 2961408. Throughput: 0: 983.6. Samples: 740264. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:28:42,002][00556] Avg episode reward: [(0, '4.805')]
+[2024-10-20 17:28:46,994][00556] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2973696. Throughput: 0: 955.8. Samples: 742276. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:28:46,998][00556] Avg episode reward: [(0, '4.785')]
+[2024-10-20 17:28:50,856][02555] Updated weights for policy 0, policy_version 730 (0.0033)
+[2024-10-20 17:28:51,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3790.6). Total num frames: 2994176. Throughput: 0: 918.5. Samples: 747456. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:28:52,002][00556] Avg episode reward: [(0, '4.639')]
+[2024-10-20 17:28:52,011][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000731_2994176.pth...
+[2024-10-20 17:28:52,146][02541] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000509_2084864.pth
+[2024-10-20 17:28:56,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3014656. Throughput: 0: 966.4. Samples: 754250. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:28:56,997][00556] Avg episode reward: [(0, '4.543')]
+[2024-10-20 17:29:00,864][02555] Updated weights for policy 0, policy_version 740 (0.0024)
+[2024-10-20 17:29:01,996][00556] Fps is (10 sec: 3685.9, 60 sec: 3754.6, 300 sec: 3776.6). Total num frames: 3031040. Throughput: 0: 978.7. Samples: 757078. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:29:02,001][00556] Avg episode reward: [(0, '4.622')]
+[2024-10-20 17:29:06,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 3790.5). Total num frames: 3051520. Throughput: 0: 921.9. Samples: 761304. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:29:06,996][00556] Avg episode reward: [(0, '4.663')]
+[2024-10-20 17:29:11,500][02555] Updated weights for policy 0, policy_version 750 (0.0015)
+[2024-10-20 17:29:11,994][00556] Fps is (10 sec: 4096.6, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 3072000. Throughput: 0: 951.8. Samples: 768284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:29:11,997][00556] Avg episode reward: [(0, '4.905')]
+[2024-10-20 17:29:16,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 3092480. Throughput: 0: 981.0. Samples: 771606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:29:16,996][00556] Avg episode reward: [(0, '4.757')]
+[2024-10-20 17:29:21,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 3104768. Throughput: 0: 941.6. Samples: 776158. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:29:22,000][00556] Avg episode reward: [(0, '4.859')]
+[2024-10-20 17:29:23,066][02555] Updated weights for policy 0, policy_version 760 (0.0018)
+[2024-10-20 17:29:26,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3129344. Throughput: 0: 938.8. Samples: 782512. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:29:26,997][00556] Avg episode reward: [(0, '4.867')]
+[2024-10-20 17:29:31,733][02555] Updated weights for policy 0, policy_version 770 (0.0027)
+[2024-10-20 17:29:31,997][00556] Fps is (10 sec: 4913.8, 60 sec: 3959.3, 300 sec: 3818.3). Total num frames: 3153920. Throughput: 0: 971.5. Samples: 785998. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:29:32,000][00556] Avg episode reward: [(0, '4.691')]
+[2024-10-20 17:29:36,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3776.7). Total num frames: 3166208. Throughput: 0: 973.7. Samples: 791272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:29:36,997][00556] Avg episode reward: [(0, '4.795')]
+[2024-10-20 17:29:41,994][00556] Fps is (10 sec: 3277.8, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3186688. Throughput: 0: 937.6. Samples: 796444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:29:41,997][00556] Avg episode reward: [(0, '4.931')]
+[2024-10-20 17:29:43,761][02555] Updated weights for policy 0, policy_version 780 (0.0024)
+[2024-10-20 17:29:46,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3207168. Throughput: 0: 946.5. Samples: 799670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:29:46,997][00556] Avg episode reward: [(0, '4.690')]
+[2024-10-20 17:29:52,002][00556] Fps is (10 sec: 3683.5, 60 sec: 3822.4, 300 sec: 3790.4). Total num frames: 3223552. Throughput: 0: 992.4. Samples: 805970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:29:52,008][00556] Avg episode reward: [(0, '4.689')]
+[2024-10-20 17:29:55,285][02555] Updated weights for policy 0, policy_version 790 (0.0018)
+[2024-10-20 17:29:56,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3239936. Throughput: 0: 933.4. Samples: 810288. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:29:56,997][00556] Avg episode reward: [(0, '4.649')]
+[2024-10-20 17:30:01,994][00556] Fps is (10 sec: 4099.2, 60 sec: 3891.3, 300 sec: 3818.3). Total num frames: 3264512. Throughput: 0: 934.1. Samples: 813640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:30:01,997][00556] Avg episode reward: [(0, '4.710')]
+[2024-10-20 17:30:04,508][02555] Updated weights for policy 0, policy_version 800 (0.0024)
+[2024-10-20 17:30:06,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3804.5). Total num frames: 3284992. Throughput: 0: 986.2. Samples: 820538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:30:06,998][00556] Avg episode reward: [(0, '4.660')]
+[2024-10-20 17:30:11,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3776.6). Total num frames: 3297280. Throughput: 0: 941.7. Samples: 824890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:30:11,997][00556] Avg episode reward: [(0, '4.815')]
+[2024-10-20 17:30:16,341][02555] Updated weights for policy 0, policy_version 810 (0.0059)
+[2024-10-20 17:30:16,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3317760. Throughput: 0: 921.1. Samples: 827446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:30:17,002][00556] Avg episode reward: [(0, '4.636')]
+[2024-10-20 17:30:21,994][00556] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3818.3). Total num frames: 3342336. Throughput: 0: 957.6. Samples: 834366. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:30:21,998][00556] Avg episode reward: [(0, '4.725')]
+[2024-10-20 17:30:26,937][02555] Updated weights for policy 0, policy_version 820 (0.0026)
+[2024-10-20 17:30:26,994][00556] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3358720. Throughput: 0: 961.3. Samples: 839702. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:30:26,997][00556] Avg episode reward: [(0, '4.849')]
+[2024-10-20 17:30:31,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.6, 300 sec: 3790.5). Total num frames: 3375104. Throughput: 0: 937.1. Samples: 841838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:30:31,998][00556] Avg episode reward: [(0, '4.802')]
+[2024-10-20 17:30:36,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3395584. Throughput: 0: 940.9. Samples: 848304. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:30:37,002][00556] Avg episode reward: [(0, '4.803')]
+[2024-10-20 17:30:37,042][02555] Updated weights for policy 0, policy_version 830 (0.0036)
+[2024-10-20 17:30:41,997][00556] Fps is (10 sec: 4095.0, 60 sec: 3822.8, 300 sec: 3804.4). Total num frames: 3416064. Throughput: 0: 985.5. Samples: 854636. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-10-20 17:30:41,999][00556] Avg episode reward: [(0, '5.010')]
+[2024-10-20 17:30:46,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3790.6). Total num frames: 3432448. Throughput: 0: 954.5. Samples: 856594. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:30:46,999][00556] Avg episode reward: [(0, '5.008')]
+[2024-10-20 17:30:48,848][02555] Updated weights for policy 0, policy_version 840 (0.0036)
+[2024-10-20 17:30:52,000][00556] Fps is (10 sec: 3685.1, 60 sec: 3823.1, 300 sec: 3804.3). Total num frames: 3452928. Throughput: 0: 924.4. Samples: 862142. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:30:52,004][00556] Avg episode reward: [(0, '4.853')]
+[2024-10-20 17:30:52,014][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000843_3452928.pth...
+[2024-10-20 17:30:52,170][02541] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000620_2539520.pth
+[2024-10-20 17:30:56,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3473408. Throughput: 0: 977.6. Samples: 868884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:30:56,999][00556] Avg episode reward: [(0, '4.693')]
+[2024-10-20 17:30:58,249][02555] Updated weights for policy 0, policy_version 850 (0.0028)
+[2024-10-20 17:31:01,994][00556] Fps is (10 sec: 3688.6, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3489792. Throughput: 0: 979.2. Samples: 871508. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:31:01,997][00556] Avg episode reward: [(0, '4.726')]
+[2024-10-20 17:31:06,994][00556] Fps is (10 sec: 3686.3, 60 sec: 3754.6, 300 sec: 3804.4). Total num frames: 3510272. Throughput: 0: 929.9. Samples: 876212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:31:06,997][00556] Avg episode reward: [(0, '4.915')]
+[2024-10-20 17:31:09,487][02555] Updated weights for policy 0, policy_version 860 (0.0019)
+[2024-10-20 17:31:11,994][00556] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 3530752. Throughput: 0: 969.4. Samples: 883326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:31:11,997][00556] Avg episode reward: [(0, '4.967')]
+[2024-10-20 17:31:16,994][00556] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3551232. Throughput: 0: 999.7. Samples: 886824. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:31:17,001][00556] Avg episode reward: [(0, '5.088')]
+[2024-10-20 17:31:20,733][02555] Updated weights for policy 0, policy_version 870 (0.0034)
+[2024-10-20 17:31:21,994][00556] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3567616. Throughput: 0: 947.2. Samples: 890930. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:31:21,998][00556] Avg episode reward: [(0, '5.315')]
+[2024-10-20 17:31:26,997][00556] Fps is (10 sec: 3685.5, 60 sec: 3822.8, 300 sec: 3818.3). Total num frames: 3588096. Throughput: 0: 944.8. Samples: 897150. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:31:27,004][00556] Avg episode reward: [(0, '5.374')]
+[2024-10-20 17:31:27,007][02541] Saving new best policy, reward=5.374!
+[2024-10-20 17:31:30,119][02555] Updated weights for policy 0, policy_version 880 (0.0024)
+[2024-10-20 17:31:32,014][00556] Fps is (10 sec: 4496.8, 60 sec: 3958.2, 300 sec: 3831.9). Total num frames: 3612672. Throughput: 0: 976.5. Samples: 900556. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:31:32,024][00556] Avg episode reward: [(0, '5.407')]
+[2024-10-20 17:31:32,050][02541] Saving new best policy, reward=5.407!
+[2024-10-20 17:31:36,998][00556] Fps is (10 sec: 3685.7, 60 sec: 3822.7, 300 sec: 3790.5). Total num frames: 3624960. Throughput: 0: 968.2. Samples: 905708. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:31:37,001][00556] Avg episode reward: [(0, '5.461')]
+[2024-10-20 17:31:37,003][02541] Saving new best policy, reward=5.461!
+[2024-10-20 17:31:41,994][00556] Fps is (10 sec: 2872.8, 60 sec: 3754.8, 300 sec: 3804.5). Total num frames: 3641344. Throughput: 0: 937.2. Samples: 911056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:31:41,996][00556] Avg episode reward: [(0, '5.237')]
+[2024-10-20 17:31:42,066][02555] Updated weights for policy 0, policy_version 890 (0.0045)
+[2024-10-20 17:31:46,994][00556] Fps is (10 sec: 4097.8, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 3665920. Throughput: 0: 952.3. Samples: 914362. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-10-20 17:31:46,997][00556] Avg episode reward: [(0, '4.998')]
+[2024-10-20 17:31:51,996][00556] Fps is (10 sec: 4095.5, 60 sec: 3823.2, 300 sec: 3804.4). Total num frames: 3682304. Throughput: 0: 978.7. Samples: 920256. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:31:52,000][00556] Avg episode reward: [(0, '4.980')]
+[2024-10-20 17:31:52,868][02555] Updated weights for policy 0, policy_version 900 (0.0030)
+[2024-10-20 17:31:56,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3698688. Throughput: 0: 919.6. Samples: 924708. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:31:56,997][00556] Avg episode reward: [(0, '4.915')]
+[2024-10-20 17:32:01,994][00556] Fps is (10 sec: 3686.9, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3719168. Throughput: 0: 916.8. Samples: 928082. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:32:01,997][00556] Avg episode reward: [(0, '4.540')]
+[2024-10-20 17:32:03,085][02555] Updated weights for policy 0, policy_version 910 (0.0024)
+[2024-10-20 17:32:06,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 3739648. Throughput: 0: 976.3. Samples: 934864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:32:06,998][00556] Avg episode reward: [(0, '4.468')]
+[2024-10-20 17:32:11,998][00556] Fps is (10 sec: 3685.0, 60 sec: 3754.4, 300 sec: 3804.4). Total num frames: 3756032. Throughput: 0: 930.0. Samples: 939000. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-10-20 17:32:12,004][00556] Avg episode reward: [(0, '4.704')]
+[2024-10-20 17:32:14,915][02555] Updated weights for policy 0, policy_version 920 (0.0024)
+[2024-10-20 17:32:16,995][00556] Fps is (10 sec: 3686.2, 60 sec: 3754.6, 300 sec: 3818.3). Total num frames: 3776512. Throughput: 0: 918.6. Samples: 941874. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:32:17,001][00556] Avg episode reward: [(0, '4.778')]
+[2024-10-20 17:32:21,994][00556] Fps is (10 sec: 4097.5, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3796992. Throughput: 0: 952.9. Samples: 948586. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:32:21,997][00556] Avg episode reward: [(0, '4.707')]
+[2024-10-20 17:32:25,209][02555] Updated weights for policy 0, policy_version 930 (0.0024)
+[2024-10-20 17:32:26,994][00556] Fps is (10 sec: 3686.6, 60 sec: 3754.8, 300 sec: 3790.5). Total num frames: 3813376. Throughput: 0: 946.4. Samples: 953646. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:32:27,001][00556] Avg episode reward: [(0, '4.644')]
+[2024-10-20 17:32:31,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3619.3, 300 sec: 3804.4). Total num frames: 3829760. Throughput: 0: 920.1. Samples: 955766. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:32:31,997][00556] Avg episode reward: [(0, '4.634')]
+[2024-10-20 17:32:35,894][02555] Updated weights for policy 0, policy_version 940 (0.0047)
+[2024-10-20 17:32:36,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3823.2, 300 sec: 3818.3). Total num frames: 3854336. Throughput: 0: 934.0. Samples: 962284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-10-20 17:32:37,003][00556] Avg episode reward: [(0, '4.554')]
+[2024-10-20 17:32:41,994][00556] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3870720. Throughput: 0: 971.2. Samples: 968414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-10-20 17:32:42,001][00556] Avg episode reward: [(0, '4.386')]
+[2024-10-20 17:32:46,994][00556] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3790.6). Total num frames: 3887104. Throughput: 0: 941.4. Samples: 970446. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:32:46,997][00556] Avg episode reward: [(0, '4.390')]
+[2024-10-20 17:32:47,676][02555] Updated weights for policy 0, policy_version 950 (0.0015)
+[2024-10-20 17:32:51,994][00556] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 3818.3). Total num frames: 3907584. Throughput: 0: 921.0. Samples: 976308. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-10-20 17:32:52,001][00556] Avg episode reward: [(0, '4.427')]
+[2024-10-20 17:32:52,052][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000955_3911680.pth...
+[2024-10-20 17:32:52,209][02541] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000731_2994176.pth
+[2024-10-20 17:32:56,572][02555] Updated weights for policy 0, policy_version 960 (0.0034)
+[2024-10-20 17:32:56,998][00556] Fps is (10 sec: 4503.7, 60 sec: 3890.9, 300 sec: 3818.3). Total num frames: 3932160. Throughput: 0: 979.6. Samples: 983082. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-10-20 17:32:57,003][00556] Avg episode reward: [(0, '4.519')]
+[2024-10-20 17:33:02,001][00556] Fps is (10 sec: 3683.9, 60 sec: 3754.2, 300 sec: 3790.5). Total num frames: 3944448. Throughput: 0: 966.5. Samples: 985372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:33:02,011][00556] Avg episode reward: [(0, '4.563')]
+[2024-10-20 17:33:06,994][00556] Fps is (10 sec: 3278.1, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3964928. Throughput: 0: 920.9. Samples: 990028. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-10-20 17:33:06,996][00556] Avg episode reward: [(0, '4.668')]
+[2024-10-20 17:33:08,575][02555] Updated weights for policy 0, policy_version 970 (0.0027)
+[2024-10-20 17:33:11,994][00556] Fps is (10 sec: 4098.7, 60 sec: 3823.2, 300 sec: 3818.3). Total num frames: 3985408. Throughput: 0: 959.4. Samples: 996818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-10-20 17:33:11,996][00556] Avg episode reward: [(0, '4.825')]
+[2024-10-20 17:33:16,991][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-10-20 17:33:17,016][02541] Stopping Batcher_0...
+[2024-10-20 17:33:17,016][02541] Loop batcher_evt_loop terminating...
+[2024-10-20 17:33:17,016][00556] Component Batcher_0 stopped!
+[2024-10-20 17:33:17,094][02555] Weights refcount: 2 0
+[2024-10-20 17:33:17,096][02555] Stopping InferenceWorker_p0-w0...
+[2024-10-20 17:33:17,096][02555] Loop inference_proc0-0_evt_loop terminating...
+[2024-10-20 17:33:17,098][00556] Component InferenceWorker_p0-w0 stopped!
+[2024-10-20 17:33:17,180][02541] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000843_3452928.pth
+[2024-10-20 17:33:17,217][02541] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-10-20 17:33:17,478][00556] Component LearnerWorker_p0 stopped!
+[2024-10-20 17:33:17,480][02541] Stopping LearnerWorker_p0...
+[2024-10-20 17:33:17,484][02541] Loop learner_proc0_evt_loop terminating...
+[2024-10-20 17:33:17,593][00556] Component RolloutWorker_w2 stopped!
+[2024-10-20 17:33:17,596][02558] Stopping RolloutWorker_w2...
+[2024-10-20 17:33:17,598][02558] Loop rollout_proc2_evt_loop terminating...
+[2024-10-20 17:33:17,630][00556] Component RolloutWorker_w0 stopped!
+[2024-10-20 17:33:17,633][02554] Stopping RolloutWorker_w0...
+[2024-10-20 17:33:17,642][02554] Loop rollout_proc0_evt_loop terminating...
+[2024-10-20 17:33:17,670][00556] Component RolloutWorker_w6 stopped!
+[2024-10-20 17:33:17,673][02559] Stopping RolloutWorker_w6...
+[2024-10-20 17:33:17,684][00556] Component RolloutWorker_w4 stopped!
+[2024-10-20 17:33:17,688][02560] Stopping RolloutWorker_w4...
+[2024-10-20 17:33:17,689][02560] Loop rollout_proc4_evt_loop terminating...
+[2024-10-20 17:33:17,674][02559] Loop rollout_proc6_evt_loop terminating...
+[2024-10-20 17:33:17,729][02562] Stopping RolloutWorker_w7...
+[2024-10-20 17:33:17,730][00556] Component RolloutWorker_w7 stopped!
+[2024-10-20 17:33:17,730][02562] Loop rollout_proc7_evt_loop terminating...
+[2024-10-20 17:33:17,761][00556] Component RolloutWorker_w5 stopped!
+[2024-10-20 17:33:17,765][02561] Stopping RolloutWorker_w5...
+[2024-10-20 17:33:17,767][02561] Loop rollout_proc5_evt_loop terminating...
+[2024-10-20 17:33:17,780][00556] Component RolloutWorker_w3 stopped!
+[2024-10-20 17:33:17,788][02557] Stopping RolloutWorker_w3...
+[2024-10-20 17:33:17,789][02557] Loop rollout_proc3_evt_loop terminating...
+[2024-10-20 17:33:17,796][00556] Component RolloutWorker_w1 stopped!
+[2024-10-20 17:33:17,798][00556] Waiting for process learner_proc0 to stop...
+[2024-10-20 17:33:17,802][02556] Stopping RolloutWorker_w1...
+[2024-10-20 17:33:17,803][02556] Loop rollout_proc1_evt_loop terminating...
+[2024-10-20 17:33:19,784][00556] Waiting for process inference_proc0-0 to join...
+[2024-10-20 17:33:19,789][00556] Waiting for process rollout_proc0 to join...
+[2024-10-20 17:33:21,985][00556] Waiting for process rollout_proc1 to join...
+[2024-10-20 17:33:21,989][00556] Waiting for process rollout_proc2 to join...
+[2024-10-20 17:33:21,994][00556] Waiting for process rollout_proc3 to join...
+[2024-10-20 17:33:21,997][00556] Waiting for process rollout_proc4 to join...
+[2024-10-20 17:33:22,002][00556] Waiting for process rollout_proc5 to join...
+[2024-10-20 17:33:22,004][00556] Waiting for process rollout_proc6 to join...
+[2024-10-20 17:33:22,011][00556] Waiting for process rollout_proc7 to join...
+[2024-10-20 17:33:22,017][00556] Batcher 0 profile tree view:
+batching: 26.2966, releasing_batches: 0.0304
+[2024-10-20 17:33:22,019][00556] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 427.7291
+update_model: 9.1894
+  weight_update: 0.0024
+one_step: 0.0246
+  handle_policy_step: 591.8972
+    deserialize: 15.4524, stack: 3.1635, obs_to_device_normalize: 120.7706, forward: 315.7641, send_messages: 28.2282
+    prepare_outputs: 79.9414
+      to_cpu: 45.7012
+[2024-10-20 17:33:22,021][00556] Learner 0 profile tree view:
+misc: 0.0056, prepare_batch: 14.0403
+train: 75.1067
+  epoch_init: 0.0132, minibatch_init: 0.0119, losses_postprocess: 0.6113, kl_divergence: 0.7346, after_optimizer: 34.5945
+  calculate_losses: 26.7507
+    losses_init: 0.0060, forward_head: 1.2384, bptt_initial: 18.0547, tail: 1.0522, advantages_returns: 0.2671, losses: 3.7825
+    bptt: 2.0385
+      bptt_forward_core: 1.9446
+  update: 11.7477
+    clip: 0.8929
+[2024-10-20 17:33:22,024][00556] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.3558, enqueue_policy_requests: 103.7466, env_step: 832.9414, overhead: 13.4578, complete_rollouts: 6.5863
+save_policy_outputs: 20.6964
+  split_output_tensors: 8.2401
+[2024-10-20 17:33:22,026][00556] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.3766, enqueue_policy_requests: 105.3575, env_step: 832.6607, overhead: 13.3658, complete_rollouts: 6.9517
+save_policy_outputs: 20.5847
+  split_output_tensors: 8.1255
+[2024-10-20 17:33:22,028][00556] Loop Runner_EvtLoop terminating...
+[2024-10-20 17:33:22,030][00556] Runner profile tree view:
+main_loop: 1098.7486
+[2024-10-20 17:33:22,031][00556] Collected {0: 4005888}, FPS: 3645.9
+[2024-10-20 17:33:22,617][00556] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-10-20 17:33:22,619][00556] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-10-20 17:33:22,621][00556] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-10-20 17:33:22,623][00556] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-10-20 17:33:22,625][00556] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-10-20 17:33:22,627][00556] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-10-20 17:33:22,628][00556] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-10-20 17:33:22,629][00556] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-10-20 17:33:22,630][00556] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-10-20 17:33:22,631][00556] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-10-20 17:33:22,633][00556] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-10-20 17:33:22,634][00556] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-10-20 17:33:22,635][00556] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-10-20 17:33:22,636][00556] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-10-20 17:33:22,637][00556] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-10-20 17:33:22,671][00556] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-10-20 17:33:22,674][00556] RunningMeanStd input shape: (3, 72, 128)
+[2024-10-20 17:33:22,676][00556] RunningMeanStd input shape: (1,)
+[2024-10-20 17:33:22,694][00556] ConvEncoder: input_channels=3
+[2024-10-20 17:33:22,796][00556] Conv encoder output size: 512
+[2024-10-20 17:33:22,797][00556] Policy head output size: 512
+[2024-10-20 17:33:22,969][00556] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-10-20 17:33:23,797][00556] Num frames 100...
+[2024-10-20 17:33:23,922][00556] Num frames 200...
+[2024-10-20 17:33:24,049][00556] Num frames 300...
+[2024-10-20 17:33:24,206][00556] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-10-20 17:33:24,208][00556] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-10-20 17:33:24,232][00556] Num frames 400...
+[2024-10-20 17:33:24,359][00556] Num frames 500...
+[2024-10-20 17:33:24,485][00556] Num frames 600...
+[2024-10-20 17:33:24,618][00556] Num frames 700...
+[2024-10-20 17:33:24,757][00556] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-10-20 17:33:24,759][00556] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-10-20 17:33:24,801][00556] Num frames 800...
+[2024-10-20 17:33:24,924][00556] Num frames 900...
+[2024-10-20 17:33:25,058][00556] Num frames 1000...
+[2024-10-20 17:33:25,180][00556] Num frames 1100...
+[2024-10-20 17:33:25,303][00556] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-10-20 17:33:25,306][00556] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-10-20 17:33:25,364][00556] Num frames 1200...
+[2024-10-20 17:33:25,501][00556] Num frames 1300...
+[2024-10-20 17:33:25,633][00556] Num frames 1400...
+[2024-10-20 17:33:25,752][00556] Num frames 1500...
+[2024-10-20 17:33:25,876][00556] Num frames 1600...
+[2024-10-20 17:33:25,970][00556] Avg episode rewards: #0: 4.330, true rewards: #0: 4.080
+[2024-10-20 17:33:25,973][00556] Avg episode reward: 4.330, avg true_objective: 4.080
+[2024-10-20 17:33:26,058][00556] Num frames 1700...
+[2024-10-20 17:33:26,183][00556] Num frames 1800...
+[2024-10-20 17:33:26,309][00556] Num frames 1900...
+[2024-10-20 17:33:26,444][00556] Num frames 2000...
+[2024-10-20 17:33:26,600][00556] Avg episode rewards: #0: 4.560, true rewards: #0: 4.160
+[2024-10-20 17:33:26,602][00556] Avg episode reward: 4.560, avg true_objective: 4.160
+[2024-10-20 17:33:26,630][00556] Num frames 2100...
+[2024-10-20 17:33:26,753][00556] Num frames 2200...
+[2024-10-20 17:33:26,876][00556] Num frames 2300...
+[2024-10-20 17:33:26,979][00556] Avg episode rewards: #0: 4.227, true rewards: #0: 3.893
+[2024-10-20 17:33:26,980][00556] Avg episode reward: 4.227, avg true_objective: 3.893
+[2024-10-20 17:33:27,065][00556] Num frames 2400...
+[2024-10-20 17:33:27,187][00556] Num frames 2500...
+[2024-10-20 17:33:27,314][00556] Num frames 2600...
+[2024-10-20 17:33:27,450][00556] Num frames 2700...
+[2024-10-20 17:33:27,573][00556] Num frames 2800...
+[2024-10-20 17:33:27,744][00556] Avg episode rewards: #0: 4.829, true rewards: #0: 4.114
+[2024-10-20 17:33:27,746][00556] Avg episode reward: 4.829, avg true_objective: 4.114
+[2024-10-20 17:33:27,774][00556] Num frames 2900...
+[2024-10-20 17:33:27,898][00556] Num frames 3000...
+[2024-10-20 17:33:28,021][00556] Num frames 3100...
+[2024-10-20 17:33:28,143][00556] Num frames 3200...
+[2024-10-20 17:33:28,280][00556] Avg episode rewards: #0: 4.705, true rewards: #0: 4.080
+[2024-10-20 17:33:28,281][00556] Avg episode reward: 4.705, avg true_objective: 4.080
+[2024-10-20 17:33:28,330][00556] Num frames 3300...
+[2024-10-20 17:33:28,462][00556] Num frames 3400...
+[2024-10-20 17:33:28,589][00556] Num frames 3500...
+[2024-10-20 17:33:28,725][00556] Num frames 3600...
+[2024-10-20 17:33:28,850][00556] Num frames 3700...
+[2024-10-20 17:33:28,921][00556] Avg episode rewards: #0: 4.791, true rewards: #0: 4.124
+[2024-10-20 17:33:28,923][00556] Avg episode reward: 4.791, avg true_objective: 4.124
+[2024-10-20 17:33:29,034][00556] Num frames 3800...
+[2024-10-20 17:33:29,164][00556] Num frames 3900...
+[2024-10-20 17:33:29,292][00556] Num frames 4000...
+[2024-10-20 17:33:29,478][00556] Avg episode rewards: #0: 4.696, true rewards: #0: 4.096
+[2024-10-20 17:33:29,480][00556] Avg episode reward: 4.696, avg true_objective: 4.096
+[2024-10-20 17:33:49,967][00556] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-10-20 17:41:26,483][00556] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-10-20 17:41:26,485][00556] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-10-20 17:41:26,486][00556] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-10-20 17:41:26,488][00556] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-10-20 17:41:26,489][00556] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-10-20 17:41:26,490][00556] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-10-20 17:41:26,491][00556] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-10-20 17:41:26,492][00556] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-10-20 17:41:26,494][00556] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-10-20 17:41:26,500][00556] Adding new argument 'hf_repository'='jerryvc/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-10-20 17:41:26,501][00556] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-10-20 17:41:26,502][00556] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-10-20 17:41:26,503][00556] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-10-20 17:41:26,504][00556] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-10-20 17:41:26,505][00556] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-10-20 17:41:26,541][00556] RunningMeanStd input shape: (3, 72, 128)
+[2024-10-20 17:41:26,543][00556] RunningMeanStd input shape: (1,)
+[2024-10-20 17:41:26,557][00556] ConvEncoder: input_channels=3
+[2024-10-20 17:41:26,594][00556] Conv encoder output size: 512
+[2024-10-20 17:41:26,595][00556] Policy head output size: 512
+[2024-10-20 17:41:26,617][00556] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-10-20 17:41:27,021][00556] Num frames 100...
+[2024-10-20 17:41:27,149][00556] Num frames 200...
+[2024-10-20 17:41:27,272][00556] Num frames 300...
+[2024-10-20 17:41:27,399][00556] Num frames 400...
+[2024-10-20 17:41:27,550][00556] Num frames 500...
+[2024-10-20 17:41:27,621][00556] Avg episode rewards: #0: 7.120, true rewards: #0: 5.120
+[2024-10-20 17:41:27,622][00556] Avg episode reward: 7.120, avg true_objective: 5.120
+[2024-10-20 17:41:27,740][00556] Num frames 600...
+[2024-10-20 17:41:27,871][00556] Num frames 700...
+[2024-10-20 17:41:27,999][00556] Num frames 800...
+[2024-10-20 17:41:28,124][00556] Num frames 900...
+[2024-10-20 17:41:28,260][00556] Avg episode rewards: #0: 6.300, true rewards: #0: 4.800
+[2024-10-20 17:41:28,263][00556] Avg episode reward: 6.300, avg true_objective: 4.800
+[2024-10-20 17:41:28,320][00556] Num frames 1000...
+[2024-10-20 17:41:28,454][00556] Num frames 1100...
+[2024-10-20 17:41:28,578][00556] Num frames 1200...
+[2024-10-20 17:41:28,703][00556] Num frames 1300...
+[2024-10-20 17:41:28,813][00556] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2024-10-20 17:41:28,815][00556] Avg episode reward: 5.480, avg true_objective: 4.480
+[2024-10-20 17:41:28,888][00556] Num frames 1400...
+[2024-10-20 17:41:29,017][00556] Num frames 1500...
+[2024-10-20 17:41:29,139][00556] Num frames 1600...
+[2024-10-20 17:41:29,270][00556] Num frames 1700...
+[2024-10-20 17:41:29,435][00556] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2024-10-20 17:41:29,437][00556] Avg episode reward: 5.480, avg true_objective: 4.480
+[2024-10-20 17:41:29,451][00556] Num frames 1800...
+[2024-10-20 17:41:29,576][00556] Num frames 1900...
+[2024-10-20 17:41:29,697][00556] Num frames 2000...
+[2024-10-20 17:41:29,820][00556] Num frames 2100...
+[2024-10-20 17:41:29,944][00556] Num frames 2200...
+[2024-10-20 17:41:30,048][00556] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2024-10-20 17:41:30,050][00556] Avg episode reward: 5.480, avg true_objective: 4.480
+[2024-10-20 17:41:30,128][00556] Num frames 2300...
+[2024-10-20 17:41:30,261][00556] Num frames 2400...
+[2024-10-20 17:41:30,385][00556] Num frames 2500...
+[2024-10-20 17:41:30,518][00556] Num frames 2600...
+[2024-10-20 17:41:30,607][00556] Avg episode rewards: #0: 5.207, true rewards: #0: 4.373
+[2024-10-20 17:41:30,611][00556] Avg episode reward: 5.207, avg true_objective: 4.373
+[2024-10-20 17:41:30,706][00556] Num frames 2700...
+[2024-10-20 17:41:30,825][00556] Num frames 2800...
+[2024-10-20 17:41:30,948][00556] Num frames 2900...
+[2024-10-20 17:41:31,070][00556] Num frames 3000...
+[2024-10-20 17:41:31,214][00556] Avg episode rewards: #0: 5.246, true rewards: #0: 4.389
+[2024-10-20 17:41:31,218][00556] Avg episode reward: 5.246, avg true_objective: 4.389
+[2024-10-20 17:41:31,257][00556] Num frames 3100...
+[2024-10-20 17:41:31,384][00556] Num frames 3200...
+[2024-10-20 17:41:31,521][00556] Num frames 3300...
+[2024-10-20 17:41:31,645][00556] Num frames 3400...
+[2024-10-20 17:41:31,784][00556] Num frames 3500...
+[2024-10-20 17:41:31,962][00556] Num frames 3600...
+[2024-10-20 17:41:32,156][00556] Avg episode rewards: #0: 5.725, true rewards: #0: 4.600
+[2024-10-20 17:41:32,158][00556] Avg episode reward: 5.725, avg true_objective: 4.600
+[2024-10-20 17:41:32,196][00556] Num frames 3700...
+[2024-10-20 17:41:32,376][00556] Num frames 3800...
+[2024-10-20 17:41:32,558][00556] Num frames 3900...
+[2024-10-20 17:41:32,728][00556] Num frames 4000...
+[2024-10-20 17:41:32,950][00556] Avg episode rewards: #0: 5.662, true rewards: #0: 4.551
+[2024-10-20 17:41:32,952][00556] Avg episode reward: 5.662, avg true_objective: 4.551
+[2024-10-20 17:41:32,966][00556] Num frames 4100...
+[2024-10-20 17:41:33,144][00556] Num frames 4200...
+[2024-10-20 17:41:33,329][00556] Num frames 4300...
+[2024-10-20 17:41:33,513][00556] Num frames 4400...
+[2024-10-20 17:41:33,710][00556] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2024-10-20 17:41:33,712][00556] Avg episode reward: 5.480, avg true_objective: 4.480
+[2024-10-20 17:41:53,429][00556] Replay video saved to /content/train_dir/default_experiment/replay.mp4!