Upload . with huggingface_hub

.gitattributes

@@ -32,3 +32,4 @@ 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.1677085682.68eb46b59ddb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8eff35e635b310646cfef5b5a7b29b74160a6c546413763935cf9702aed125
+size 915451

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: 11.84 +/- 5.22
+      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 cmenasse/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_000000923_3780608_reward_25.125.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f6192df3b124aebad9a7be05fb04aedfcf66d16eb0175c59e4decf12c8cbc2
+size 34928614

checkpoint_p0/checkpoint_000000969_3969024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f1a50be6869b00ac9ff4d00f3ba7dc89bece6ee100e27e317568fa5fc5c153
+size 34929028

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd6a0e7fffc4abc2d5949ebbcc8a5df6fffd8285a67d704d8b0231e54baed26
+size 34929028

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:d3a2918256ea5683712d0614732adac31c83213b03bcfa37c71390c511ca2edc
+size 21868082

sf_log.txt

@@ -0,0 +1,992 @@
+[2023-02-22 17:08:06,788][00238] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2023-02-22 17:08:06,791][00238] Rollout worker 0 uses device cpu
+[2023-02-22 17:08:06,793][00238] Rollout worker 1 uses device cpu
+[2023-02-22 17:08:06,795][00238] Rollout worker 2 uses device cpu
+[2023-02-22 17:08:06,797][00238] Rollout worker 3 uses device cpu
+[2023-02-22 17:08:06,800][00238] Rollout worker 4 uses device cpu
+[2023-02-22 17:08:06,801][00238] Rollout worker 5 uses device cpu
+[2023-02-22 17:08:06,803][00238] Rollout worker 6 uses device cpu
+[2023-02-22 17:08:06,805][00238] Rollout worker 7 uses device cpu
+[2023-02-22 17:08:07,008][00238] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-22 17:08:07,011][00238] InferenceWorker_p0-w0: min num requests: 2
+[2023-02-22 17:08:07,046][00238] Starting all processes...
+[2023-02-22 17:08:07,047][00238] Starting process learner_proc0
+[2023-02-22 17:08:07,105][00238] Starting all processes...
+[2023-02-22 17:08:07,121][00238] Starting process inference_proc0-0
+[2023-02-22 17:08:07,122][00238] Starting process rollout_proc0
+[2023-02-22 17:08:07,123][00238] Starting process rollout_proc1
+[2023-02-22 17:08:07,129][00238] Starting process rollout_proc2
+[2023-02-22 17:08:07,165][00238] Starting process rollout_proc4
+[2023-02-22 17:08:07,161][00238] Starting process rollout_proc3
+[2023-02-22 17:08:07,166][00238] Starting process rollout_proc5
+[2023-02-22 17:08:07,167][00238] Starting process rollout_proc6
+[2023-02-22 17:08:07,172][00238] Starting process rollout_proc7
+[2023-02-22 17:08:17,921][17475] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-22 17:08:17,921][17475] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-02-22 17:08:18,129][17489] Worker 0 uses CPU cores [0]
+[2023-02-22 17:08:18,573][17493] Worker 4 uses CPU cores [0]
+[2023-02-22 17:08:18,614][17492] Worker 1 uses CPU cores [1]
+[2023-02-22 17:08:18,635][17491] Worker 2 uses CPU cores [0]
+[2023-02-22 17:08:18,979][17495] Worker 6 uses CPU cores [0]
+[2023-02-22 17:08:19,002][17496] Worker 3 uses CPU cores [1]
+[2023-02-22 17:08:19,024][17494] Worker 5 uses CPU cores [1]
+[2023-02-22 17:08:19,099][17490] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-22 17:08:19,104][17490] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-02-22 17:08:19,316][17497] Worker 7 uses CPU cores [1]
+[2023-02-22 17:08:19,428][17490] Num visible devices: 1
+[2023-02-22 17:08:19,428][17475] Num visible devices: 1
+[2023-02-22 17:08:19,433][17475] Starting seed is not provided
+[2023-02-22 17:08:19,433][17475] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-22 17:08:19,433][17475] Initializing actor-critic model on device cuda:0
+[2023-02-22 17:08:19,434][17475] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-22 17:08:19,438][17475] RunningMeanStd input shape: (1,)
+[2023-02-22 17:08:19,460][17475] ConvEncoder: input_channels=3
+[2023-02-22 17:08:19,798][17475] Conv encoder output size: 512
+[2023-02-22 17:08:19,798][17475] Policy head output size: 512
+[2023-02-22 17:08:19,845][17475] Created Actor Critic model with architecture:
+[2023-02-22 17:08:19,845][17475] 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)
+  )
+)
+[2023-02-22 17:08:26,564][17475] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-02-22 17:08:26,566][17475] No checkpoints found
+[2023-02-22 17:08:26,566][17475] Did not load from checkpoint, starting from scratch!
+[2023-02-22 17:08:26,567][17475] Initialized policy 0 weights for model version 0
+[2023-02-22 17:08:26,570][17475] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-22 17:08:26,577][17475] LearnerWorker_p0 finished initialization!
+[2023-02-22 17:08:26,785][17490] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-22 17:08:26,786][17490] RunningMeanStd input shape: (1,)
+[2023-02-22 17:08:26,800][17490] ConvEncoder: input_channels=3
+[2023-02-22 17:08:26,903][17490] Conv encoder output size: 512
+[2023-02-22 17:08:26,903][17490] Policy head output size: 512
+[2023-02-22 17:08:27,000][00238] Heartbeat connected on Batcher_0
+[2023-02-22 17:08:27,009][00238] Heartbeat connected on LearnerWorker_p0
+[2023-02-22 17:08:27,020][00238] Heartbeat connected on RolloutWorker_w0
+[2023-02-22 17:08:27,025][00238] Heartbeat connected on RolloutWorker_w1
+[2023-02-22 17:08:27,028][00238] Heartbeat connected on RolloutWorker_w2
+[2023-02-22 17:08:27,033][00238] Heartbeat connected on RolloutWorker_w3
+[2023-02-22 17:08:27,036][00238] Heartbeat connected on RolloutWorker_w4
+[2023-02-22 17:08:27,039][00238] Heartbeat connected on RolloutWorker_w5
+[2023-02-22 17:08:27,043][00238] Heartbeat connected on RolloutWorker_w6
+[2023-02-22 17:08:27,046][00238] Heartbeat connected on RolloutWorker_w7
+[2023-02-22 17:08:27,685][00238] 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)
+[2023-02-22 17:08:29,203][00238] Inference worker 0-0 is ready!
+[2023-02-22 17:08:29,205][00238] All inference workers are ready! Signal rollout workers to start!
+[2023-02-22 17:08:29,207][00238] Heartbeat connected on InferenceWorker_p0-w0
+[2023-02-22 17:08:29,298][17492] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:08:29,300][17496] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:08:29,313][17494] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:08:29,325][17497] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:08:29,344][17493] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:08:29,354][17491] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:08:29,375][17489] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:08:29,383][17495] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:08:30,590][17489] Decorrelating experience for 0 frames...
+[2023-02-22 17:08:30,595][17491] Decorrelating experience for 0 frames...
+[2023-02-22 17:08:31,379][17496] Decorrelating experience for 0 frames...
+[2023-02-22 17:08:31,376][17494] Decorrelating experience for 0 frames...
+[2023-02-22 17:08:31,382][17497] Decorrelating experience for 0 frames...
+[2023-02-22 17:08:31,384][17492] Decorrelating experience for 0 frames...
+[2023-02-22 17:08:31,783][17491] Decorrelating experience for 32 frames...
+[2023-02-22 17:08:31,786][17489] Decorrelating experience for 32 frames...
+[2023-02-22 17:08:32,686][00238] 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)
+[2023-02-22 17:08:32,842][17494] Decorrelating experience for 32 frames...
+[2023-02-22 17:08:32,872][17492] Decorrelating experience for 32 frames...
+[2023-02-22 17:08:33,021][17493] Decorrelating experience for 0 frames...
+[2023-02-22 17:08:33,053][17495] Decorrelating experience for 0 frames...
+[2023-02-22 17:08:33,492][17496] Decorrelating experience for 32 frames...
+[2023-02-22 17:08:33,665][17489] Decorrelating experience for 64 frames...
+[2023-02-22 17:08:34,352][17497] Decorrelating experience for 32 frames...
+[2023-02-22 17:08:34,624][17492] Decorrelating experience for 64 frames...
+[2023-02-22 17:08:34,743][17495] Decorrelating experience for 32 frames...
+[2023-02-22 17:08:34,744][17491] Decorrelating experience for 64 frames...
+[2023-02-22 17:08:35,158][17493] Decorrelating experience for 32 frames...
+[2023-02-22 17:08:35,937][17496] Decorrelating experience for 64 frames...
+[2023-02-22 17:08:36,146][17497] Decorrelating experience for 64 frames...
+[2023-02-22 17:08:36,292][17492] Decorrelating experience for 96 frames...
+[2023-02-22 17:08:36,320][17489] Decorrelating experience for 96 frames...
+[2023-02-22 17:08:36,749][17491] Decorrelating experience for 96 frames...
+[2023-02-22 17:08:36,928][17493] Decorrelating experience for 64 frames...
+[2023-02-22 17:08:37,290][17495] Decorrelating experience for 64 frames...
+[2023-02-22 17:08:37,685][00238] 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)
+[2023-02-22 17:08:37,710][17494] Decorrelating experience for 64 frames...
+[2023-02-22 17:08:38,101][17496] Decorrelating experience for 96 frames...
+[2023-02-22 17:08:38,244][17493] Decorrelating experience for 96 frames...
+[2023-02-22 17:08:38,304][17495] Decorrelating experience for 96 frames...
+[2023-02-22 17:08:38,685][17494] Decorrelating experience for 96 frames...
+[2023-02-22 17:08:38,862][17497] Decorrelating experience for 96 frames...
+[2023-02-22 17:08:42,685][00238] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 51.2. Samples: 768. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-22 17:08:42,690][00238] Avg episode reward: [(0, '1.163')]
+[2023-02-22 17:08:43,046][17475] Signal inference workers to stop experience collection...
+[2023-02-22 17:08:43,066][17490] InferenceWorker_p0-w0: stopping experience collection
+[2023-02-22 17:08:45,437][17475] Signal inference workers to resume experience collection...
+[2023-02-22 17:08:45,439][17490] InferenceWorker_p0-w0: resuming experience collection
+[2023-02-22 17:08:47,685][00238] Fps is (10 sec: 1228.8, 60 sec: 614.4, 300 sec: 614.4). Total num frames: 12288. Throughput: 0: 163.5. Samples: 3270. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2023-02-22 17:08:47,692][00238] Avg episode reward: [(0, '2.720')]
+[2023-02-22 17:08:52,685][00238] Fps is (10 sec: 2457.6, 60 sec: 983.0, 300 sec: 983.0). Total num frames: 24576. Throughput: 0: 225.1. Samples: 5628. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
+[2023-02-22 17:08:52,688][00238] Avg episode reward: [(0, '3.480')]
+[2023-02-22 17:08:57,019][17490] Updated weights for policy 0, policy_version 10 (0.0020)
+[2023-02-22 17:08:57,685][00238] Fps is (10 sec: 2867.2, 60 sec: 1365.3, 300 sec: 1365.3). Total num frames: 40960. Throughput: 0: 334.1. Samples: 10024. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:08:57,687][00238] Avg episode reward: [(0, '3.973')]
+[2023-02-22 17:09:02,685][00238] Fps is (10 sec: 4096.1, 60 sec: 1872.5, 300 sec: 1872.5). Total num frames: 65536. Throughput: 0: 466.5. Samples: 16326. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:09:02,692][00238] Avg episode reward: [(0, '4.268')]
+[2023-02-22 17:09:07,159][17490] Updated weights for policy 0, policy_version 20 (0.0021)
+[2023-02-22 17:09:07,685][00238] Fps is (10 sec: 4096.0, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 81920. Throughput: 0: 481.0. Samples: 19240. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:09:07,691][00238] Avg episode reward: [(0, '4.312')]
+[2023-02-22 17:09:12,685][00238] Fps is (10 sec: 2867.2, 60 sec: 2093.5, 300 sec: 2093.5). Total num frames: 94208. Throughput: 0: 529.5. Samples: 23828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:09:12,688][00238] Avg episode reward: [(0, '4.373')]
+[2023-02-22 17:09:17,685][00238] Fps is (10 sec: 2867.2, 60 sec: 2211.8, 300 sec: 2211.8). Total num frames: 110592. Throughput: 0: 627.5. Samples: 28238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:09:17,690][00238] Avg episode reward: [(0, '4.414')]
+[2023-02-22 17:09:17,693][17475] Saving new best policy, reward=4.414!
+[2023-02-22 17:09:19,962][17490] Updated weights for policy 0, policy_version 30 (0.0032)
+[2023-02-22 17:09:22,685][00238] Fps is (10 sec: 4096.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 135168. Throughput: 0: 701.6. Samples: 31572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:09:22,692][00238] Avg episode reward: [(0, '4.313')]
+[2023-02-22 17:09:27,685][00238] Fps is (10 sec: 4505.6, 60 sec: 2594.1, 300 sec: 2594.1). Total num frames: 155648. Throughput: 0: 838.0. Samples: 38480. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:09:27,687][00238] Avg episode reward: [(0, '4.275')]
+[2023-02-22 17:09:29,461][17490] Updated weights for policy 0, policy_version 40 (0.0023)
+[2023-02-22 17:09:32,685][00238] Fps is (10 sec: 3686.4, 60 sec: 2867.3, 300 sec: 2646.6). Total num frames: 172032. Throughput: 0: 892.0. Samples: 43412. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-02-22 17:09:32,687][00238] Avg episode reward: [(0, '4.384')]
+[2023-02-22 17:09:37,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 2633.1). Total num frames: 184320. Throughput: 0: 887.5. Samples: 45564. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:09:37,687][00238] Avg episode reward: [(0, '4.468')]
+[2023-02-22 17:09:37,689][17475] Saving new best policy, reward=4.468!
+[2023-02-22 17:09:41,453][17490] Updated weights for policy 0, policy_version 50 (0.0021)
+[2023-02-22 17:09:42,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 2785.3). Total num frames: 208896. Throughput: 0: 920.6. Samples: 51452. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-02-22 17:09:42,688][00238] Avg episode reward: [(0, '4.465')]
+[2023-02-22 17:09:47,685][00238] Fps is (10 sec: 4915.0, 60 sec: 3686.4, 300 sec: 2918.4). Total num frames: 233472. Throughput: 0: 934.2. Samples: 58366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:09:47,688][00238] Avg episode reward: [(0, '4.382')]
+[2023-02-22 17:09:51,948][17490] Updated weights for policy 0, policy_version 60 (0.0015)
+[2023-02-22 17:09:52,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 2891.3). Total num frames: 245760. Throughput: 0: 922.0. Samples: 60730. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:09:52,687][00238] Avg episode reward: [(0, '4.387')]
+[2023-02-22 17:09:57,687][00238] Fps is (10 sec: 2457.1, 60 sec: 3618.0, 300 sec: 2867.1). Total num frames: 258048. Throughput: 0: 911.5. Samples: 64846. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:09:57,690][00238] Avg episode reward: [(0, '4.550')]
+[2023-02-22 17:09:57,699][17475] Saving new best policy, reward=4.550!
+[2023-02-22 17:10:02,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 2975.0). Total num frames: 282624. Throughput: 0: 950.2. Samples: 70996. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:10:02,690][00238] Avg episode reward: [(0, '4.420')]
+[2023-02-22 17:10:02,704][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000069_282624.pth...
+[2023-02-22 17:10:03,564][17490] Updated weights for policy 0, policy_version 70 (0.0012)
+[2023-02-22 17:10:07,685][00238] Fps is (10 sec: 4096.9, 60 sec: 3618.1, 300 sec: 2990.1). Total num frames: 299008. Throughput: 0: 942.5. Samples: 73986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:10:07,691][00238] Avg episode reward: [(0, '4.453')]
+[2023-02-22 17:10:12,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3003.7). Total num frames: 315392. Throughput: 0: 895.2. Samples: 78762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:10:12,692][00238] Avg episode reward: [(0, '4.510')]
+[2023-02-22 17:10:16,453][17490] Updated weights for policy 0, policy_version 80 (0.0017)
+[2023-02-22 17:10:17,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 2978.9). Total num frames: 327680. Throughput: 0: 883.6. Samples: 83174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:10:17,687][00238] Avg episode reward: [(0, '4.668')]
+[2023-02-22 17:10:17,694][17475] Saving new best policy, reward=4.668!
+[2023-02-22 17:10:22,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3063.1). Total num frames: 352256. Throughput: 0: 903.2. Samples: 86210. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:10:22,694][00238] Avg episode reward: [(0, '4.499')]
+[2023-02-22 17:10:25,673][17490] Updated weights for policy 0, policy_version 90 (0.0020)
+[2023-02-22 17:10:27,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3686.4, 300 sec: 3140.3). Total num frames: 376832. Throughput: 0: 932.6. Samples: 93420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:10:27,693][00238] Avg episode reward: [(0, '4.375')]
+[2023-02-22 17:10:32,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3145.7). Total num frames: 393216. Throughput: 0: 899.7. Samples: 98852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:10:32,687][00238] Avg episode reward: [(0, '4.384')]
+[2023-02-22 17:10:37,686][00238] Fps is (10 sec: 2866.9, 60 sec: 3686.3, 300 sec: 3119.2). Total num frames: 405504. Throughput: 0: 896.1. Samples: 101056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:10:37,689][00238] Avg episode reward: [(0, '4.564')]
+[2023-02-22 17:10:37,836][17490] Updated weights for policy 0, policy_version 100 (0.0018)
+[2023-02-22 17:10:42,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3185.8). Total num frames: 430080. Throughput: 0: 941.0. Samples: 107190. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:10:42,692][00238] Avg episode reward: [(0, '4.528')]
+[2023-02-22 17:10:46,199][17490] Updated weights for policy 0, policy_version 110 (0.0016)
+[2023-02-22 17:10:47,685][00238] Fps is (10 sec: 4915.8, 60 sec: 3686.4, 300 sec: 3247.5). Total num frames: 454656. Throughput: 0: 960.9. Samples: 114238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:10:47,686][00238] Avg episode reward: [(0, '4.395')]
+[2023-02-22 17:10:52,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3248.6). Total num frames: 471040. Throughput: 0: 951.0. Samples: 116782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:10:52,693][00238] Avg episode reward: [(0, '4.314')]
+[2023-02-22 17:10:57,685][00238] Fps is (10 sec: 3276.7, 60 sec: 3823.1, 300 sec: 3249.5). Total num frames: 487424. Throughput: 0: 947.0. Samples: 121378. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:10:57,693][00238] Avg episode reward: [(0, '4.334')]
+[2023-02-22 17:10:58,584][17490] Updated weights for policy 0, policy_version 120 (0.0027)
+[2023-02-22 17:11:02,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3276.8). Total num frames: 507904. Throughput: 0: 987.8. Samples: 127624. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:11:02,690][00238] Avg episode reward: [(0, '4.466')]
+[2023-02-22 17:11:07,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3302.4). Total num frames: 528384. Throughput: 0: 987.3. Samples: 130640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:11:07,688][00238] Avg episode reward: [(0, '4.615')]
+[2023-02-22 17:11:08,919][17490] Updated weights for policy 0, policy_version 130 (0.0030)
+[2023-02-22 17:11:12,686][00238] Fps is (10 sec: 3276.5, 60 sec: 3754.6, 300 sec: 3276.8). Total num frames: 540672. Throughput: 0: 933.2. Samples: 135416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:11:12,688][00238] Avg episode reward: [(0, '4.703')]
+[2023-02-22 17:11:12,704][17475] Saving new best policy, reward=4.703!
+[2023-02-22 17:11:17,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 557056. Throughput: 0: 910.4. Samples: 139820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:11:17,687][00238] Avg episode reward: [(0, '4.722')]
+[2023-02-22 17:11:17,691][17475] Saving new best policy, reward=4.722!
+[2023-02-22 17:11:20,896][17490] Updated weights for policy 0, policy_version 140 (0.0021)
+[2023-02-22 17:11:22,685][00238] Fps is (10 sec: 4096.4, 60 sec: 3822.9, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 933.8. Samples: 143076. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:11:22,688][00238] Avg episode reward: [(0, '4.663')]
+[2023-02-22 17:11:27,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3345.1). Total num frames: 602112. Throughput: 0: 959.5. Samples: 150368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:11:27,691][00238] Avg episode reward: [(0, '4.393')]
+[2023-02-22 17:11:30,376][17490] Updated weights for policy 0, policy_version 150 (0.0015)
+[2023-02-22 17:11:32,690][00238] Fps is (10 sec: 3684.5, 60 sec: 3754.3, 300 sec: 3343.1). Total num frames: 618496. Throughput: 0: 919.0. Samples: 155598. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:11:32,692][00238] Avg episode reward: [(0, '4.385')]
+[2023-02-22 17:11:37,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3341.5). Total num frames: 634880. Throughput: 0: 912.1. Samples: 157828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:11:37,688][00238] Avg episode reward: [(0, '4.420')]
+[2023-02-22 17:11:41,547][17490] Updated weights for policy 0, policy_version 160 (0.0016)
+[2023-02-22 17:11:42,685][00238] Fps is (10 sec: 4098.1, 60 sec: 3822.9, 300 sec: 3381.8). Total num frames: 659456. Throughput: 0: 948.1. Samples: 164044. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:11:42,686][00238] Avg episode reward: [(0, '4.488')]
+[2023-02-22 17:11:47,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3822.9, 300 sec: 3420.2). Total num frames: 684032. Throughput: 0: 968.3. Samples: 171198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:11:47,694][00238] Avg episode reward: [(0, '4.588')]
+[2023-02-22 17:11:51,302][17490] Updated weights for policy 0, policy_version 170 (0.0027)
+[2023-02-22 17:11:52,685][00238] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3416.7). Total num frames: 700416. Throughput: 0: 956.1. Samples: 173664. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:11:52,692][00238] Avg episode reward: [(0, '4.587')]
+[2023-02-22 17:11:57,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 951.6. Samples: 178238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:11:57,689][00238] Avg episode reward: [(0, '4.697')]
+[2023-02-22 17:12:02,384][17490] Updated weights for policy 0, policy_version 180 (0.0021)
+[2023-02-22 17:12:02,685][00238] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3429.2). Total num frames: 737280. Throughput: 0: 997.4. Samples: 184704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:12:02,688][00238] Avg episode reward: [(0, '4.728')]
+[2023-02-22 17:12:02,697][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000180_737280.pth...
+[2023-02-22 17:12:02,846][17475] Saving new best policy, reward=4.728!
+[2023-02-22 17:12:07,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3444.4). Total num frames: 757760. Throughput: 0: 990.1. Samples: 187632. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:12:07,689][00238] Avg episode reward: [(0, '4.725')]
+[2023-02-22 17:12:12,691][00238] Fps is (10 sec: 3274.8, 60 sec: 3822.6, 300 sec: 3422.3). Total num frames: 770048. Throughput: 0: 936.9. Samples: 192536. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:12:12,694][00238] Avg episode reward: [(0, '4.757')]
+[2023-02-22 17:12:12,709][17475] Saving new best policy, reward=4.757!
+[2023-02-22 17:12:15,077][17490] Updated weights for policy 0, policy_version 190 (0.0012)
+[2023-02-22 17:12:17,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3754.7, 300 sec: 3401.5). Total num frames: 782336. Throughput: 0: 914.7. Samples: 196756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:12:17,687][00238] Avg episode reward: [(0, '4.796')]
+[2023-02-22 17:12:17,691][17475] Saving new best policy, reward=4.796!
+[2023-02-22 17:12:22,685][00238] Fps is (10 sec: 3688.7, 60 sec: 3754.7, 300 sec: 3433.7). Total num frames: 806912. Throughput: 0: 933.3. Samples: 199828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:12:22,693][00238] Avg episode reward: [(0, '4.838')]
+[2023-02-22 17:12:22,704][17475] Saving new best policy, reward=4.838!
+[2023-02-22 17:12:25,114][17490] Updated weights for policy 0, policy_version 200 (0.0026)
+[2023-02-22 17:12:27,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3447.5). Total num frames: 827392. Throughput: 0: 941.9. Samples: 206430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:12:27,690][00238] Avg episode reward: [(0, '4.640')]
+[2023-02-22 17:12:32,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3755.0, 300 sec: 3444.0). Total num frames: 843776. Throughput: 0: 898.2. Samples: 211618. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:12:32,691][00238] Avg episode reward: [(0, '4.864')]
+[2023-02-22 17:12:32,704][17475] Saving new best policy, reward=4.864!
+[2023-02-22 17:12:37,350][17490] Updated weights for policy 0, policy_version 210 (0.0034)
+[2023-02-22 17:12:37,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3440.6). Total num frames: 860160. Throughput: 0: 892.8. Samples: 213840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:12:37,688][00238] Avg episode reward: [(0, '4.874')]
+[2023-02-22 17:12:37,691][17475] Saving new best policy, reward=4.874!
+[2023-02-22 17:12:42,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3453.5). Total num frames: 880640. Throughput: 0: 921.4. Samples: 219702. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:12:42,689][00238] Avg episode reward: [(0, '4.745')]
+[2023-02-22 17:12:46,420][17490] Updated weights for policy 0, policy_version 220 (0.0015)
+[2023-02-22 17:12:47,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3481.6). Total num frames: 905216. Throughput: 0: 939.4. Samples: 226976. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:12:47,687][00238] Avg episode reward: [(0, '4.765')]
+[2023-02-22 17:12:52,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3462.3). Total num frames: 917504. Throughput: 0: 924.8. Samples: 229246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:12:52,693][00238] Avg episode reward: [(0, '4.799')]
+[2023-02-22 17:12:57,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3443.7). Total num frames: 929792. Throughput: 0: 897.4. Samples: 232914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:12:57,692][00238] Avg episode reward: [(0, '4.832')]
+[2023-02-22 17:13:01,236][17490] Updated weights for policy 0, policy_version 230 (0.0036)
+[2023-02-22 17:13:02,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3425.7). Total num frames: 942080. Throughput: 0: 885.2. Samples: 236592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:13:02,688][00238] Avg episode reward: [(0, '4.570')]
+[2023-02-22 17:13:07,685][00238] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3437.7). Total num frames: 962560. Throughput: 0: 873.7. Samples: 239144. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:13:07,688][00238] Avg episode reward: [(0, '4.859')]
+[2023-02-22 17:13:11,934][17490] Updated weights for policy 0, policy_version 240 (0.0027)
+[2023-02-22 17:13:12,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3550.2, 300 sec: 3449.3). Total num frames: 983040. Throughput: 0: 868.0. Samples: 245488. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:13:12,687][00238] Avg episode reward: [(0, '5.080')]
+[2023-02-22 17:13:12,756][17475] Saving new best policy, reward=5.080!
+[2023-02-22 17:13:17,685][00238] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3446.3). Total num frames: 999424. Throughput: 0: 874.8. Samples: 250984. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:13:17,692][00238] Avg episode reward: [(0, '5.072')]
+[2023-02-22 17:13:22,688][00238] Fps is (10 sec: 3275.7, 60 sec: 3481.4, 300 sec: 3443.4). Total num frames: 1015808. Throughput: 0: 876.0. Samples: 253262. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-02-22 17:13:22,696][00238] Avg episode reward: [(0, '5.059')]
+[2023-02-22 17:13:23,950][17490] Updated weights for policy 0, policy_version 250 (0.0028)
+[2023-02-22 17:13:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 1040384. Throughput: 0: 878.1. Samples: 259216. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:13:27,692][00238] Avg episode reward: [(0, '5.281')]
+[2023-02-22 17:13:27,695][17475] Saving new best policy, reward=5.281!
+[2023-02-22 17:13:32,443][17490] Updated weights for policy 0, policy_version 260 (0.0017)
+[2023-02-22 17:13:32,685][00238] Fps is (10 sec: 4916.9, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1064960. Throughput: 0: 876.6. Samples: 266422. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:13:32,692][00238] Avg episode reward: [(0, '5.117')]
+[2023-02-22 17:13:37,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1081344. Throughput: 0: 888.1. Samples: 269212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:13:37,690][00238] Avg episode reward: [(0, '5.299')]
+[2023-02-22 17:13:37,695][17475] Saving new best policy, reward=5.299!
+[2023-02-22 17:13:42,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 1093632. Throughput: 0: 907.1. Samples: 273734. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:13:42,691][00238] Avg episode reward: [(0, '5.426')]
+[2023-02-22 17:13:42,710][17475] Saving new best policy, reward=5.426!
+[2023-02-22 17:13:44,829][17490] Updated weights for policy 0, policy_version 270 (0.0026)
+[2023-02-22 17:13:47,685][00238] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3707.2). Total num frames: 1118208. Throughput: 0: 965.2. Samples: 280026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:13:47,691][00238] Avg episode reward: [(0, '5.682')]
+[2023-02-22 17:13:47,697][17475] Saving new best policy, reward=5.682!
+[2023-02-22 17:13:52,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1142784. Throughput: 0: 988.4. Samples: 283620. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:13:52,687][00238] Avg episode reward: [(0, '5.636')]
+[2023-02-22 17:13:53,286][17490] Updated weights for policy 0, policy_version 280 (0.0017)
+[2023-02-22 17:13:57,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 1159168. Throughput: 0: 978.0. Samples: 289498. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:13:57,691][00238] Avg episode reward: [(0, '5.455')]
+[2023-02-22 17:14:02,685][00238] Fps is (10 sec: 2867.1, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1171456. Throughput: 0: 956.4. Samples: 294022. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:14:02,691][00238] Avg episode reward: [(0, '5.144')]
+[2023-02-22 17:14:02,704][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000286_1171456.pth...
+[2023-02-22 17:14:02,879][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000069_282624.pth
+[2023-02-22 17:14:06,215][17490] Updated weights for policy 0, policy_version 290 (0.0017)
+[2023-02-22 17:14:07,685][00238] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1191936. Throughput: 0: 962.2. Samples: 296556. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:14:07,693][00238] Avg episode reward: [(0, '5.374')]
+[2023-02-22 17:14:12,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 1216512. Throughput: 0: 972.3. Samples: 302970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:14:12,691][00238] Avg episode reward: [(0, '5.580')]
+[2023-02-22 17:14:16,248][17490] Updated weights for policy 0, policy_version 300 (0.0018)
+[2023-02-22 17:14:17,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 1228800. Throughput: 0: 932.4. Samples: 308378. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:14:17,687][00238] Avg episode reward: [(0, '5.724')]
+[2023-02-22 17:14:17,715][17475] Saving new best policy, reward=5.724!
+[2023-02-22 17:14:22,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3823.2, 300 sec: 3693.3). Total num frames: 1245184. Throughput: 0: 919.8. Samples: 310604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:14:22,690][00238] Avg episode reward: [(0, '5.974')]
+[2023-02-22 17:14:22,704][17475] Saving new best policy, reward=5.974!
+[2023-02-22 17:14:27,589][17490] Updated weights for policy 0, policy_version 310 (0.0013)
+[2023-02-22 17:14:27,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1269760. Throughput: 0: 948.8. Samples: 316428. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-02-22 17:14:27,687][00238] Avg episode reward: [(0, '6.014')]
+[2023-02-22 17:14:27,691][17475] Saving new best policy, reward=6.014!
+[2023-02-22 17:14:32,689][00238] Fps is (10 sec: 4503.8, 60 sec: 3754.4, 300 sec: 3748.8). Total num frames: 1290240. Throughput: 0: 967.0. Samples: 323546. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:14:32,691][00238] Avg episode reward: [(0, '6.496')]
+[2023-02-22 17:14:32,753][17475] Saving new best policy, reward=6.496!
+[2023-02-22 17:14:37,692][00238] Fps is (10 sec: 3683.7, 60 sec: 3754.2, 300 sec: 3721.0). Total num frames: 1306624. Throughput: 0: 946.0. Samples: 326196. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:14:37,695][00238] Avg episode reward: [(0, '6.873')]
+[2023-02-22 17:14:37,702][17475] Saving new best policy, reward=6.873!
+[2023-02-22 17:14:38,097][17490] Updated weights for policy 0, policy_version 320 (0.0028)
+[2023-02-22 17:14:42,685][00238] Fps is (10 sec: 3278.1, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1323008. Throughput: 0: 913.9. Samples: 330626. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:14:42,688][00238] Avg episode reward: [(0, '6.610')]
+[2023-02-22 17:14:47,685][00238] Fps is (10 sec: 3689.1, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1343488. Throughput: 0: 949.0. Samples: 336726. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:14:47,687][00238] Avg episode reward: [(0, '6.584')]
+[2023-02-22 17:14:48,728][17490] Updated weights for policy 0, policy_version 330 (0.0018)
+[2023-02-22 17:14:52,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1368064. Throughput: 0: 971.1. Samples: 340254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:14:52,687][00238] Avg episode reward: [(0, '6.918')]
+[2023-02-22 17:14:52,696][17475] Saving new best policy, reward=6.918!
+[2023-02-22 17:14:57,691][00238] Fps is (10 sec: 4093.4, 60 sec: 3754.3, 300 sec: 3734.9). Total num frames: 1384448. Throughput: 0: 956.7. Samples: 346026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:14:57,694][00238] Avg episode reward: [(0, '6.930')]
+[2023-02-22 17:14:57,699][17475] Saving new best policy, reward=6.930!
+[2023-02-22 17:15:00,105][17490] Updated weights for policy 0, policy_version 340 (0.0018)
+[2023-02-22 17:15:02,688][00238] Fps is (10 sec: 2866.4, 60 sec: 3754.5, 300 sec: 3721.1). Total num frames: 1396736. Throughput: 0: 935.5. Samples: 350480. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:15:02,696][00238] Avg episode reward: [(0, '6.576')]
+[2023-02-22 17:15:07,685][00238] Fps is (10 sec: 3278.9, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1417216. Throughput: 0: 942.4. Samples: 353014. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:15:07,688][00238] Avg episode reward: [(0, '6.648')]
+[2023-02-22 17:15:11,005][17490] Updated weights for policy 0, policy_version 350 (0.0014)
+[2023-02-22 17:15:12,685][00238] Fps is (10 sec: 4506.9, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 1441792. Throughput: 0: 952.4. Samples: 359284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:15:12,692][00238] Avg episode reward: [(0, '6.703')]
+[2023-02-22 17:15:17,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1458176. Throughput: 0: 921.9. Samples: 365028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:15:17,687][00238] Avg episode reward: [(0, '6.894')]
+[2023-02-22 17:15:22,653][17490] Updated weights for policy 0, policy_version 360 (0.0019)
+[2023-02-22 17:15:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1474560. Throughput: 0: 912.2. Samples: 367238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:15:22,688][00238] Avg episode reward: [(0, '7.038')]
+[2023-02-22 17:15:22,702][17475] Saving new best policy, reward=7.038!
+[2023-02-22 17:15:27,687][00238] Fps is (10 sec: 3685.6, 60 sec: 3754.5, 300 sec: 3735.0). Total num frames: 1495040. Throughput: 0: 939.4. Samples: 372900. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:15:27,691][00238] Avg episode reward: [(0, '7.149')]
+[2023-02-22 17:15:27,694][17475] Saving new best policy, reward=7.149!
+[2023-02-22 17:15:31,758][17490] Updated weights for policy 0, policy_version 370 (0.0015)
+[2023-02-22 17:15:32,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3823.2, 300 sec: 3776.7). Total num frames: 1519616. Throughput: 0: 962.0. Samples: 380018. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:15:32,687][00238] Avg episode reward: [(0, '7.430')]
+[2023-02-22 17:15:32,700][17475] Saving new best policy, reward=7.430!
+[2023-02-22 17:15:37,685][00238] Fps is (10 sec: 4096.9, 60 sec: 3823.4, 300 sec: 3748.9). Total num frames: 1536000. Throughput: 0: 948.4. Samples: 382930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:15:37,696][00238] Avg episode reward: [(0, '7.617')]
+[2023-02-22 17:15:37,699][17475] Saving new best policy, reward=7.617!
+[2023-02-22 17:15:42,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1548288. Throughput: 0: 919.8. Samples: 387410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:15:42,693][00238] Avg episode reward: [(0, '7.885')]
+[2023-02-22 17:15:42,807][17475] Saving new best policy, reward=7.885!
+[2023-02-22 17:15:44,022][17490] Updated weights for policy 0, policy_version 380 (0.0023)
+[2023-02-22 17:15:47,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 1572864. Throughput: 0: 957.8. Samples: 393580. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:15:47,695][00238] Avg episode reward: [(0, '8.603')]
+[2023-02-22 17:15:47,696][17475] Saving new best policy, reward=8.603!
+[2023-02-22 17:15:52,490][17490] Updated weights for policy 0, policy_version 390 (0.0024)
+[2023-02-22 17:15:52,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1597440. Throughput: 0: 980.0. Samples: 397116. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:15:52,692][00238] Avg episode reward: [(0, '8.876')]
+[2023-02-22 17:15:52,707][17475] Saving new best policy, reward=8.876!
+[2023-02-22 17:15:57,692][00238] Fps is (10 sec: 4093.1, 60 sec: 3822.9, 300 sec: 3748.8). Total num frames: 1613824. Throughput: 0: 974.4. Samples: 403140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:15:57,694][00238] Avg episode reward: [(0, '8.958')]
+[2023-02-22 17:15:57,696][17475] Saving new best policy, reward=8.958!
+[2023-02-22 17:16:02,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3823.1, 300 sec: 3721.1). Total num frames: 1626112. Throughput: 0: 947.9. Samples: 407682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:16:02,692][00238] Avg episode reward: [(0, '8.921')]
+[2023-02-22 17:16:02,705][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000397_1626112.pth...
+[2023-02-22 17:16:02,874][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000180_737280.pth
+[2023-02-22 17:16:05,386][17490] Updated weights for policy 0, policy_version 400 (0.0037)
+[2023-02-22 17:16:07,685][00238] Fps is (10 sec: 3279.2, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1646592. Throughput: 0: 952.2. Samples: 410086. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:16:07,687][00238] Avg episode reward: [(0, '8.806')]
+[2023-02-22 17:16:12,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1667072. Throughput: 0: 966.2. Samples: 416378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:16:12,687][00238] Avg episode reward: [(0, '9.416')]
+[2023-02-22 17:16:12,789][17475] Saving new best policy, reward=9.416!
+[2023-02-22 17:16:15,054][17490] Updated weights for policy 0, policy_version 410 (0.0017)
+[2023-02-22 17:16:17,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1687552. Throughput: 0: 935.3. Samples: 422108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:16:17,690][00238] Avg episode reward: [(0, '9.607')]
+[2023-02-22 17:16:17,694][17475] Saving new best policy, reward=9.607!
+[2023-02-22 17:16:22,685][00238] Fps is (10 sec: 3276.6, 60 sec: 3754.6, 300 sec: 3721.1). Total num frames: 1699840. Throughput: 0: 919.8. Samples: 424322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:16:22,690][00238] Avg episode reward: [(0, '10.540')]
+[2023-02-22 17:16:22,700][17475] Saving new best policy, reward=10.540!
+[2023-02-22 17:16:26,549][17490] Updated weights for policy 0, policy_version 420 (0.0019)
+[2023-02-22 17:16:27,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3823.1, 300 sec: 3748.9). Total num frames: 1724416. Throughput: 0: 950.8. Samples: 430196. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:16:27,691][00238] Avg episode reward: [(0, '10.032')]
+[2023-02-22 17:16:32,686][00238] Fps is (10 sec: 4914.9, 60 sec: 3822.8, 300 sec: 3776.6). Total num frames: 1748992. Throughput: 0: 980.3. Samples: 437694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:16:32,688][00238] Avg episode reward: [(0, '9.555')]
+[2023-02-22 17:16:35,675][17490] Updated weights for policy 0, policy_version 430 (0.0030)
+[2023-02-22 17:16:37,685][00238] Fps is (10 sec: 4095.8, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1765376. Throughput: 0: 967.8. Samples: 440668. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-02-22 17:16:37,692][00238] Avg episode reward: [(0, '9.564')]
+[2023-02-22 17:16:42,685][00238] Fps is (10 sec: 3277.1, 60 sec: 3891.2, 300 sec: 3721.1). Total num frames: 1781760. Throughput: 0: 937.7. Samples: 445328. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:16:42,692][00238] Avg episode reward: [(0, '9.309')]
+[2023-02-22 17:16:46,832][17490] Updated weights for policy 0, policy_version 440 (0.0035)
+[2023-02-22 17:16:47,685][00238] Fps is (10 sec: 3686.6, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 1802240. Throughput: 0: 978.8. Samples: 451730. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:16:47,691][00238] Avg episode reward: [(0, '9.550')]
+[2023-02-22 17:16:52,685][00238] Fps is (10 sec: 4915.4, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 1830912. Throughput: 0: 1006.6. Samples: 455382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:16:52,691][00238] Avg episode reward: [(0, '10.577')]
+[2023-02-22 17:16:52,701][17475] Saving new best policy, reward=10.577!
+[2023-02-22 17:16:55,988][17490] Updated weights for policy 0, policy_version 450 (0.0017)
+[2023-02-22 17:16:57,685][00238] Fps is (10 sec: 4505.5, 60 sec: 3891.7, 300 sec: 3762.8). Total num frames: 1847296. Throughput: 0: 1005.2. Samples: 461612. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:16:57,692][00238] Avg episode reward: [(0, '11.426')]
+[2023-02-22 17:16:57,694][17475] Saving new best policy, reward=11.426!
+[2023-02-22 17:17:02,685][00238] Fps is (10 sec: 3276.6, 60 sec: 3959.4, 300 sec: 3748.9). Total num frames: 1863680. Throughput: 0: 979.5. Samples: 466188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:17:02,693][00238] Avg episode reward: [(0, '11.336')]
+[2023-02-22 17:17:07,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1880064. Throughput: 0: 989.8. Samples: 468864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:17:07,695][00238] Avg episode reward: [(0, '11.188')]
+[2023-02-22 17:17:08,031][17490] Updated weights for policy 0, policy_version 460 (0.0024)
+[2023-02-22 17:17:12,685][00238] Fps is (10 sec: 4096.2, 60 sec: 3959.5, 300 sec: 3804.4). Total num frames: 1904640. Throughput: 0: 1001.6. Samples: 475266. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:17:12,687][00238] Avg episode reward: [(0, '11.304')]
+[2023-02-22 17:17:17,685][00238] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3776.6). Total num frames: 1921024. Throughput: 0: 960.2. Samples: 480904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:17:17,699][00238] Avg episode reward: [(0, '11.488')]
+[2023-02-22 17:17:17,705][17475] Saving new best policy, reward=11.488!
+[2023-02-22 17:17:18,429][17490] Updated weights for policy 0, policy_version 470 (0.0019)
+[2023-02-22 17:17:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3762.8). Total num frames: 1937408. Throughput: 0: 942.9. Samples: 483096. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:17:22,687][00238] Avg episode reward: [(0, '13.259')]
+[2023-02-22 17:17:22,701][17475] Saving new best policy, reward=13.259!
+[2023-02-22 17:17:27,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3790.5). Total num frames: 1961984. Throughput: 0: 979.5. Samples: 489406. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:17:27,692][00238] Avg episode reward: [(0, '12.872')]
+[2023-02-22 17:17:28,381][17490] Updated weights for policy 0, policy_version 480 (0.0023)
+[2023-02-22 17:17:32,685][00238] Fps is (10 sec: 4915.1, 60 sec: 3959.5, 300 sec: 3818.3). Total num frames: 1986560. Throughput: 0: 1004.4. Samples: 496928. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:17:32,687][00238] Avg episode reward: [(0, '13.302')]
+[2023-02-22 17:17:32,696][17475] Saving new best policy, reward=13.302!
+[2023-02-22 17:17:37,687][00238] Fps is (10 sec: 4095.2, 60 sec: 3959.4, 300 sec: 3804.4). Total num frames: 2002944. Throughput: 0: 981.0. Samples: 499530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:17:37,690][00238] Avg episode reward: [(0, '12.795')]
+[2023-02-22 17:17:38,836][17490] Updated weights for policy 0, policy_version 490 (0.0017)
+[2023-02-22 17:17:42,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3776.7). Total num frames: 2019328. Throughput: 0: 948.3. Samples: 504286. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:17:42,693][00238] Avg episode reward: [(0, '13.052')]
+[2023-02-22 17:17:47,685][00238] Fps is (10 sec: 3687.1, 60 sec: 3959.5, 300 sec: 3804.4). Total num frames: 2039808. Throughput: 0: 997.3. Samples: 511068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:17:47,687][00238] Avg episode reward: [(0, '14.671')]
+[2023-02-22 17:17:47,714][17475] Saving new best policy, reward=14.671!
+[2023-02-22 17:17:48,676][17490] Updated weights for policy 0, policy_version 500 (0.0037)
+[2023-02-22 17:17:52,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2068480. Throughput: 0: 1018.7. Samples: 514706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:17:52,689][00238] Avg episode reward: [(0, '14.953')]
+[2023-02-22 17:17:52,699][17475] Saving new best policy, reward=14.953!
+[2023-02-22 17:17:57,687][00238] Fps is (10 sec: 4095.0, 60 sec: 3891.1, 300 sec: 3859.9). Total num frames: 2080768. Throughput: 0: 1007.5. Samples: 520608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:17:57,694][00238] Avg episode reward: [(0, '13.942')]
+[2023-02-22 17:17:59,237][17490] Updated weights for policy 0, policy_version 510 (0.0016)
+[2023-02-22 17:18:02,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2097152. Throughput: 0: 985.1. Samples: 525234. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-02-22 17:18:02,687][00238] Avg episode reward: [(0, '13.886')]
+[2023-02-22 17:18:02,701][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000512_2097152.pth...
+[2023-02-22 17:18:02,816][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000286_1171456.pth
+[2023-02-22 17:18:07,685][00238] Fps is (10 sec: 3687.3, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 2117632. Throughput: 0: 998.9. Samples: 528046. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:18:07,688][00238] Avg episode reward: [(0, '13.182')]
+[2023-02-22 17:18:10,095][17490] Updated weights for policy 0, policy_version 520 (0.0012)
+[2023-02-22 17:18:12,685][00238] Fps is (10 sec: 4505.4, 60 sec: 3959.4, 300 sec: 3873.8). Total num frames: 2142208. Throughput: 0: 1003.1. Samples: 534544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:18:12,688][00238] Avg episode reward: [(0, '13.255')]
+[2023-02-22 17:18:17,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3873.9). Total num frames: 2158592. Throughput: 0: 956.3. Samples: 539962. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:18:17,687][00238] Avg episode reward: [(0, '14.100')]
+[2023-02-22 17:18:21,328][17490] Updated weights for policy 0, policy_version 530 (0.0022)
+[2023-02-22 17:18:22,685][00238] Fps is (10 sec: 3277.0, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 2174976. Throughput: 0: 948.8. Samples: 542222. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:18:22,687][00238] Avg episode reward: [(0, '13.187')]
+[2023-02-22 17:18:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 2199552. Throughput: 0: 986.1. Samples: 548660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:18:27,687][00238] Avg episode reward: [(0, '13.973')]
+[2023-02-22 17:18:30,100][17490] Updated weights for policy 0, policy_version 540 (0.0017)
+[2023-02-22 17:18:32,685][00238] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2220032. Throughput: 0: 1003.0. Samples: 556204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:18:32,688][00238] Avg episode reward: [(0, '13.946')]
+[2023-02-22 17:18:37,688][00238] Fps is (10 sec: 3685.2, 60 sec: 3891.1, 300 sec: 3873.8). Total num frames: 2236416. Throughput: 0: 978.2. Samples: 558730. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:18:37,699][00238] Avg episode reward: [(0, '14.762')]
+[2023-02-22 17:18:41,735][17490] Updated weights for policy 0, policy_version 550 (0.0022)
+[2023-02-22 17:18:42,689][00238] Fps is (10 sec: 3275.5, 60 sec: 3890.9, 300 sec: 3846.0). Total num frames: 2252800. Throughput: 0: 951.5. Samples: 563426. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:18:42,691][00238] Avg episode reward: [(0, '15.970')]
+[2023-02-22 17:18:42,710][17475] Saving new best policy, reward=15.970!
+[2023-02-22 17:18:47,687][00238] Fps is (10 sec: 4505.9, 60 sec: 4027.6, 300 sec: 3859.9). Total num frames: 2281472. Throughput: 0: 1003.6. Samples: 570400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:18:47,693][00238] Avg episode reward: [(0, '16.793')]
+[2023-02-22 17:18:47,701][17475] Saving new best policy, reward=16.793!
+[2023-02-22 17:18:50,227][17490] Updated weights for policy 0, policy_version 560 (0.0025)
+[2023-02-22 17:18:52,685][00238] Fps is (10 sec: 4917.3, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2301952. Throughput: 0: 1021.9. Samples: 574032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:18:52,693][00238] Avg episode reward: [(0, '17.725')]
+[2023-02-22 17:18:52,710][17475] Saving new best policy, reward=17.725!
+[2023-02-22 17:18:57,685][00238] Fps is (10 sec: 3687.3, 60 sec: 3959.6, 300 sec: 3887.7). Total num frames: 2318336. Throughput: 0: 1002.9. Samples: 579674. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:18:57,692][00238] Avg episode reward: [(0, '17.752')]
+[2023-02-22 17:18:57,698][17475] Saving new best policy, reward=17.752!
+[2023-02-22 17:19:02,086][17490] Updated weights for policy 0, policy_version 570 (0.0017)
+[2023-02-22 17:19:02,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2334720. Throughput: 0: 988.0. Samples: 584420. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:19:02,694][00238] Avg episode reward: [(0, '18.938')]
+[2023-02-22 17:19:02,702][17475] Saving new best policy, reward=18.938!
+[2023-02-22 17:19:07,685][00238] Fps is (10 sec: 3276.9, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2351104. Throughput: 0: 997.9. Samples: 587128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:19:07,689][00238] Avg episode reward: [(0, '19.535')]
+[2023-02-22 17:19:07,695][17475] Saving new best policy, reward=19.535!
+[2023-02-22 17:19:12,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3846.1). Total num frames: 2363392. Throughput: 0: 945.6. Samples: 591212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:19:12,687][00238] Avg episode reward: [(0, '20.093')]
+[2023-02-22 17:19:12,699][17475] Saving new best policy, reward=20.093!
+[2023-02-22 17:19:16,163][17490] Updated weights for policy 0, policy_version 580 (0.0035)
+[2023-02-22 17:19:17,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3846.1). Total num frames: 2379776. Throughput: 0: 870.6. Samples: 595382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:19:17,693][00238] Avg episode reward: [(0, '18.368')]
+[2023-02-22 17:19:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 2396160. Throughput: 0: 865.7. Samples: 597682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:19:22,692][00238] Avg episode reward: [(0, '19.091')]
+[2023-02-22 17:19:26,654][17490] Updated weights for policy 0, policy_version 590 (0.0026)
+[2023-02-22 17:19:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 2420736. Throughput: 0: 905.8. Samples: 604184. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:19:27,687][00238] Avg episode reward: [(0, '18.661')]
+[2023-02-22 17:19:32,687][00238] Fps is (10 sec: 4914.1, 60 sec: 3754.5, 300 sec: 3860.0). Total num frames: 2445312. Throughput: 0: 918.9. Samples: 611748. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:19:32,689][00238] Avg episode reward: [(0, '17.727')]
+[2023-02-22 17:19:36,272][17490] Updated weights for policy 0, policy_version 600 (0.0020)
+[2023-02-22 17:19:37,686][00238] Fps is (10 sec: 3686.0, 60 sec: 3686.5, 300 sec: 3846.1). Total num frames: 2457600. Throughput: 0: 892.0. Samples: 614172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:19:37,688][00238] Avg episode reward: [(0, '18.220')]
+[2023-02-22 17:19:42,685][00238] Fps is (10 sec: 2867.8, 60 sec: 3686.7, 300 sec: 3832.2). Total num frames: 2473984. Throughput: 0: 870.8. Samples: 618858. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:19:42,687][00238] Avg episode reward: [(0, '17.422')]
+[2023-02-22 17:19:46,772][17490] Updated weights for policy 0, policy_version 610 (0.0013)
+[2023-02-22 17:19:47,685][00238] Fps is (10 sec: 4506.0, 60 sec: 3686.6, 300 sec: 3846.1). Total num frames: 2502656. Throughput: 0: 919.2. Samples: 625786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:19:47,692][00238] Avg episode reward: [(0, '17.940')]
+[2023-02-22 17:19:52,687][00238] Fps is (10 sec: 5323.6, 60 sec: 3754.5, 300 sec: 3873.9). Total num frames: 2527232. Throughput: 0: 941.0. Samples: 629474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:19:52,689][00238] Avg episode reward: [(0, '19.356')]
+[2023-02-22 17:19:56,417][17490] Updated weights for policy 0, policy_version 620 (0.0027)
+[2023-02-22 17:19:57,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3873.9). Total num frames: 2539520. Throughput: 0: 978.6. Samples: 635250. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:19:57,689][00238] Avg episode reward: [(0, '20.813')]
+[2023-02-22 17:19:57,698][17475] Saving new best policy, reward=20.813!
+[2023-02-22 17:20:02,685][00238] Fps is (10 sec: 2867.8, 60 sec: 3686.4, 300 sec: 3860.0). Total num frames: 2555904. Throughput: 0: 989.2. Samples: 639894. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:20:02,687][00238] Avg episode reward: [(0, '20.903')]
+[2023-02-22 17:20:02,700][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000624_2555904.pth...
+[2023-02-22 17:20:02,814][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000397_1626112.pth
+[2023-02-22 17:20:02,824][17475] Saving new best policy, reward=20.903!
+[2023-02-22 17:20:07,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 2576384. Throughput: 0: 1004.8. Samples: 642898. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:20:07,690][00238] Avg episode reward: [(0, '22.217')]
+[2023-02-22 17:20:07,694][17475] Saving new best policy, reward=22.217!
+[2023-02-22 17:20:08,080][17490] Updated weights for policy 0, policy_version 630 (0.0012)
+[2023-02-22 17:20:12,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2596864. Throughput: 0: 998.6. Samples: 649120. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:20:12,688][00238] Avg episode reward: [(0, '22.377')]
+[2023-02-22 17:20:12,705][17475] Saving new best policy, reward=22.377!
+[2023-02-22 17:20:17,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2613248. Throughput: 0: 939.7. Samples: 654034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:20:17,692][00238] Avg episode reward: [(0, '21.309')]
+[2023-02-22 17:20:19,556][17490] Updated weights for policy 0, policy_version 640 (0.0027)
+[2023-02-22 17:20:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2629632. Throughput: 0: 936.3. Samples: 656306. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:20:22,687][00238] Avg episode reward: [(0, '20.285')]
+[2023-02-22 17:20:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2654208. Throughput: 0: 985.0. Samples: 663182. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:20:27,687][00238] Avg episode reward: [(0, '19.473')]
+[2023-02-22 17:20:28,676][17490] Updated weights for policy 0, policy_version 650 (0.0015)
+[2023-02-22 17:20:32,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3891.3, 300 sec: 3873.8). Total num frames: 2678784. Throughput: 0: 993.5. Samples: 670494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:20:32,695][00238] Avg episode reward: [(0, '18.216')]
+[2023-02-22 17:20:37,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2695168. Throughput: 0: 962.4. Samples: 672782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:20:37,690][00238] Avg episode reward: [(0, '17.894')]
+[2023-02-22 17:20:39,775][17490] Updated weights for policy 0, policy_version 660 (0.0011)
+[2023-02-22 17:20:42,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2711552. Throughput: 0: 938.5. Samples: 677482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:20:42,689][00238] Avg episode reward: [(0, '17.989')]
+[2023-02-22 17:20:47,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2736128. Throughput: 0: 999.6. Samples: 684874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:20:47,692][00238] Avg episode reward: [(0, '18.739')]
+[2023-02-22 17:20:48,648][17490] Updated weights for policy 0, policy_version 670 (0.0015)
+[2023-02-22 17:20:52,685][00238] Fps is (10 sec: 4915.1, 60 sec: 3891.3, 300 sec: 3887.8). Total num frames: 2760704. Throughput: 0: 1015.7. Samples: 688606. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:20:52,687][00238] Avg episode reward: [(0, '18.376')]
+[2023-02-22 17:20:57,688][00238] Fps is (10 sec: 4094.6, 60 sec: 3959.2, 300 sec: 3901.6). Total num frames: 2777088. Throughput: 0: 995.3. Samples: 693910. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:20:57,692][00238] Avg episode reward: [(0, '18.546')]
+[2023-02-22 17:21:00,125][17490] Updated weights for policy 0, policy_version 680 (0.0036)
+[2023-02-22 17:21:02,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2793472. Throughput: 0: 1000.7. Samples: 699066. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-02-22 17:21:02,688][00238] Avg episode reward: [(0, '18.798')]
+[2023-02-22 17:21:07,685][00238] Fps is (10 sec: 3687.6, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2813952. Throughput: 0: 1019.6. Samples: 702188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:21:07,688][00238] Avg episode reward: [(0, '17.964')]
+[2023-02-22 17:21:09,977][17490] Updated weights for policy 0, policy_version 690 (0.0019)
+[2023-02-22 17:21:12,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2834432. Throughput: 0: 1007.9. Samples: 708536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:21:12,690][00238] Avg episode reward: [(0, '18.064')]
+[2023-02-22 17:21:17,687][00238] Fps is (10 sec: 3685.6, 60 sec: 3959.3, 300 sec: 3901.6). Total num frames: 2850816. Throughput: 0: 949.2. Samples: 713212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:21:17,695][00238] Avg episode reward: [(0, '18.554')]
+[2023-02-22 17:21:21,892][17490] Updated weights for policy 0, policy_version 700 (0.0014)
+[2023-02-22 17:21:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2867200. Throughput: 0: 951.0. Samples: 715578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:21:22,687][00238] Avg episode reward: [(0, '19.220')]
+[2023-02-22 17:21:27,685][00238] Fps is (10 sec: 4506.6, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 2895872. Throughput: 0: 1004.7. Samples: 722694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:21:27,687][00238] Avg episode reward: [(0, '20.236')]
+[2023-02-22 17:21:30,076][17490] Updated weights for policy 0, policy_version 710 (0.0012)
+[2023-02-22 17:21:32,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2916352. Throughput: 0: 996.5. Samples: 729716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:21:32,687][00238] Avg episode reward: [(0, '20.865')]
+[2023-02-22 17:21:37,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2932736. Throughput: 0: 966.2. Samples: 732084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:21:37,691][00238] Avg episode reward: [(0, '21.422')]
+[2023-02-22 17:21:41,933][17490] Updated weights for policy 0, policy_version 720 (0.0021)
+[2023-02-22 17:21:42,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2949120. Throughput: 0: 955.6. Samples: 736908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:21:42,692][00238] Avg episode reward: [(0, '21.739')]
+[2023-02-22 17:21:47,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2973696. Throughput: 0: 1008.6. Samples: 744452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:21:47,687][00238] Avg episode reward: [(0, '21.641')]
+[2023-02-22 17:21:50,185][17490] Updated weights for policy 0, policy_version 730 (0.0023)
+[2023-02-22 17:21:52,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2998272. Throughput: 0: 1020.4. Samples: 748108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:21:52,691][00238] Avg episode reward: [(0, '21.539')]
+[2023-02-22 17:21:57,685][00238] Fps is (10 sec: 4095.9, 60 sec: 3959.7, 300 sec: 3901.6). Total num frames: 3014656. Throughput: 0: 993.0. Samples: 753220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:21:57,689][00238] Avg episode reward: [(0, '21.156')]
+[2023-02-22 17:22:02,009][17490] Updated weights for policy 0, policy_version 740 (0.0024)
+[2023-02-22 17:22:02,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3031040. Throughput: 0: 1007.7. Samples: 758558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:22:02,690][00238] Avg episode reward: [(0, '20.613')]
+[2023-02-22 17:22:02,700][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000740_3031040.pth...
+[2023-02-22 17:22:02,823][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000512_2097152.pth
+[2023-02-22 17:22:07,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3051520. Throughput: 0: 1023.8. Samples: 761648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:22:07,691][00238] Avg episode reward: [(0, '19.956')]
+[2023-02-22 17:22:12,253][17490] Updated weights for policy 0, policy_version 750 (0.0015)
+[2023-02-22 17:22:12,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3072000. Throughput: 0: 1002.7. Samples: 767814. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:22:12,690][00238] Avg episode reward: [(0, '20.563')]
+[2023-02-22 17:22:17,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.6, 300 sec: 3901.6). Total num frames: 3088384. Throughput: 0: 949.5. Samples: 772442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:22:17,687][00238] Avg episode reward: [(0, '20.306')]
+[2023-02-22 17:22:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 3104768. Throughput: 0: 948.4. Samples: 774764. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:22:22,687][00238] Avg episode reward: [(0, '21.763')]
+[2023-02-22 17:22:23,619][17490] Updated weights for policy 0, policy_version 760 (0.0011)
+[2023-02-22 17:22:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 3129344. Throughput: 0: 1003.8. Samples: 782080. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:22:27,686][00238] Avg episode reward: [(0, '21.634')]
+[2023-02-22 17:22:32,690][00238] Fps is (10 sec: 4503.2, 60 sec: 3890.9, 300 sec: 3887.7). Total num frames: 3149824. Throughput: 0: 984.0. Samples: 788738. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:22:32,705][00238] Avg episode reward: [(0, '22.197')]
+[2023-02-22 17:22:32,727][17490] Updated weights for policy 0, policy_version 770 (0.0031)
+[2023-02-22 17:22:37,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3166208. Throughput: 0: 955.8. Samples: 791118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:22:37,686][00238] Avg episode reward: [(0, '21.919')]
+[2023-02-22 17:22:42,688][00238] Fps is (10 sec: 3687.1, 60 sec: 3959.3, 300 sec: 3887.7). Total num frames: 3186688. Throughput: 0: 955.4. Samples: 796214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:22:42,694][00238] Avg episode reward: [(0, '21.380')]
+[2023-02-22 17:22:43,695][17490] Updated weights for policy 0, policy_version 780 (0.0016)
+[2023-02-22 17:22:47,685][00238] Fps is (10 sec: 4915.1, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 3215360. Throughput: 0: 1006.5. Samples: 803852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:22:47,687][00238] Avg episode reward: [(0, '21.215')]
+[2023-02-22 17:22:52,375][17490] Updated weights for policy 0, policy_version 790 (0.0015)
+[2023-02-22 17:22:52,686][00238] Fps is (10 sec: 4916.7, 60 sec: 3959.4, 300 sec: 3915.5). Total num frames: 3235840. Throughput: 0: 1020.3. Samples: 807560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:22:52,689][00238] Avg episode reward: [(0, '21.510')]
+[2023-02-22 17:22:57,686][00238] Fps is (10 sec: 3276.4, 60 sec: 3891.1, 300 sec: 3901.6). Total num frames: 3248128. Throughput: 0: 991.7. Samples: 812442. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:22:57,689][00238] Avg episode reward: [(0, '21.099')]
+[2023-02-22 17:23:02,685][00238] Fps is (10 sec: 3276.9, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3268608. Throughput: 0: 1010.5. Samples: 817916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:23:02,691][00238] Avg episode reward: [(0, '21.396')]
+[2023-02-22 17:23:03,896][17490] Updated weights for policy 0, policy_version 800 (0.0018)
+[2023-02-22 17:23:07,685][00238] Fps is (10 sec: 4096.5, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3289088. Throughput: 0: 1027.7. Samples: 821010. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:23:07,687][00238] Avg episode reward: [(0, '21.600')]
+[2023-02-22 17:23:12,689][00238] Fps is (10 sec: 4094.2, 60 sec: 3959.2, 300 sec: 3901.6). Total num frames: 3309568. Throughput: 0: 1001.8. Samples: 827164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:23:12,696][00238] Avg episode reward: [(0, '22.072')]
+[2023-02-22 17:23:14,914][17490] Updated weights for policy 0, policy_version 810 (0.0025)
+[2023-02-22 17:23:17,689][00238] Fps is (10 sec: 3684.8, 60 sec: 3959.2, 300 sec: 3901.6). Total num frames: 3325952. Throughput: 0: 958.0. Samples: 831848. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:23:17,691][00238] Avg episode reward: [(0, '22.259')]
+[2023-02-22 17:23:22,685][00238] Fps is (10 sec: 3688.0, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 3346432. Throughput: 0: 958.8. Samples: 834262. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:23:22,687][00238] Avg episode reward: [(0, '22.668')]
+[2023-02-22 17:23:22,700][17475] Saving new best policy, reward=22.668!
+[2023-02-22 17:23:25,132][17490] Updated weights for policy 0, policy_version 820 (0.0020)
+[2023-02-22 17:23:27,685][00238] Fps is (10 sec: 4507.5, 60 sec: 4027.7, 300 sec: 3901.6). Total num frames: 3371008. Throughput: 0: 1009.0. Samples: 841614. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:23:27,687][00238] Avg episode reward: [(0, '22.371')]
+[2023-02-22 17:23:32,687][00238] Fps is (10 sec: 4504.7, 60 sec: 4027.9, 300 sec: 3915.5). Total num frames: 3391488. Throughput: 0: 987.7. Samples: 848302. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:23:32,694][00238] Avg episode reward: [(0, '19.841')]
+[2023-02-22 17:23:34,744][17490] Updated weights for policy 0, policy_version 830 (0.0012)
+[2023-02-22 17:23:37,685][00238] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3915.6). Total num frames: 3407872. Throughput: 0: 958.5. Samples: 850692. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:23:37,689][00238] Avg episode reward: [(0, '18.614')]
+[2023-02-22 17:23:42,685][00238] Fps is (10 sec: 3687.2, 60 sec: 4028.0, 300 sec: 3887.8). Total num frames: 3428352. Throughput: 0: 967.9. Samples: 855996. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:23:42,687][00238] Avg episode reward: [(0, '18.305')]
+[2023-02-22 17:23:44,999][17490] Updated weights for policy 0, policy_version 840 (0.0012)
+[2023-02-22 17:23:47,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3452928. Throughput: 0: 1012.7. Samples: 863486. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:23:47,693][00238] Avg episode reward: [(0, '18.609')]
+[2023-02-22 17:23:52,685][00238] Fps is (10 sec: 4505.3, 60 sec: 3959.4, 300 sec: 3915.5). Total num frames: 3473408. Throughput: 0: 1024.1. Samples: 867094. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:23:52,689][00238] Avg episode reward: [(0, '19.289')]
+[2023-02-22 17:23:54,868][17490] Updated weights for policy 0, policy_version 850 (0.0029)
+[2023-02-22 17:23:57,685][00238] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 3915.5). Total num frames: 3489792. Throughput: 0: 994.2. Samples: 871900. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:23:57,691][00238] Avg episode reward: [(0, '20.332')]
+[2023-02-22 17:24:02,685][00238] Fps is (10 sec: 3686.7, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 3510272. Throughput: 0: 1020.4. Samples: 877762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:24:02,692][00238] Avg episode reward: [(0, '20.552')]
+[2023-02-22 17:24:02,708][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000857_3510272.pth...
+[2023-02-22 17:24:02,851][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000624_2555904.pth
+[2023-02-22 17:24:05,616][17490] Updated weights for policy 0, policy_version 860 (0.0015)
+[2023-02-22 17:24:07,685][00238] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 3530752. Throughput: 0: 1034.8. Samples: 880830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:24:07,687][00238] Avg episode reward: [(0, '21.995')]
+[2023-02-22 17:24:12,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.7, 300 sec: 3957.2). Total num frames: 3547136. Throughput: 0: 1000.8. Samples: 886648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:24:12,687][00238] Avg episode reward: [(0, '22.720')]
+[2023-02-22 17:24:12,706][17475] Saving new best policy, reward=22.720!
+[2023-02-22 17:24:17,527][17490] Updated weights for policy 0, policy_version 870 (0.0012)
+[2023-02-22 17:24:17,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.7, 300 sec: 3957.2). Total num frames: 3563520. Throughput: 0: 956.3. Samples: 891332. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:24:17,691][00238] Avg episode reward: [(0, '20.908')]
+[2023-02-22 17:24:22,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3584000. Throughput: 0: 957.5. Samples: 893780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:24:22,687][00238] Avg episode reward: [(0, '21.421')]
+[2023-02-22 17:24:26,591][17490] Updated weights for policy 0, policy_version 880 (0.0015)
+[2023-02-22 17:24:27,685][00238] Fps is (10 sec: 4505.5, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3608576. Throughput: 0: 1007.8. Samples: 901346. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:24:27,687][00238] Avg episode reward: [(0, '20.722')]
+[2023-02-22 17:24:32,692][00238] Fps is (10 sec: 4502.4, 60 sec: 3959.1, 300 sec: 3971.0). Total num frames: 3629056. Throughput: 0: 985.0. Samples: 907820. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:24:32,695][00238] Avg episode reward: [(0, '19.621')]
+[2023-02-22 17:24:37,586][17490] Updated weights for policy 0, policy_version 890 (0.0023)
+[2023-02-22 17:24:37,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3645440. Throughput: 0: 957.7. Samples: 910190. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:24:37,687][00238] Avg episode reward: [(0, '19.681')]
+[2023-02-22 17:24:42,685][00238] Fps is (10 sec: 3689.1, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3665920. Throughput: 0: 970.4. Samples: 915570. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-22 17:24:42,689][00238] Avg episode reward: [(0, '20.281')]
+[2023-02-22 17:24:46,605][17490] Updated weights for policy 0, policy_version 900 (0.0012)
+[2023-02-22 17:24:47,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3690496. Throughput: 0: 1006.7. Samples: 923064. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-22 17:24:47,686][00238] Avg episode reward: [(0, '22.170')]
+[2023-02-22 17:24:52,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3710976. Throughput: 0: 1014.6. Samples: 926486. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:24:52,687][00238] Avg episode reward: [(0, '22.098')]
+[2023-02-22 17:24:57,516][17490] Updated weights for policy 0, policy_version 910 (0.0032)
+[2023-02-22 17:24:57,685][00238] Fps is (10 sec: 3686.3, 60 sec: 3959.4, 300 sec: 3971.0). Total num frames: 3727360. Throughput: 0: 990.7. Samples: 931230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:24:57,692][00238] Avg episode reward: [(0, '22.821')]
+[2023-02-22 17:24:57,694][17475] Saving new best policy, reward=22.821!
+[2023-02-22 17:25:02,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3747840. Throughput: 0: 1018.0. Samples: 937140. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:25:02,692][00238] Avg episode reward: [(0, '23.553')]
+[2023-02-22 17:25:02,700][17475] Saving new best policy, reward=23.553!
+[2023-02-22 17:25:07,596][17490] Updated weights for policy 0, policy_version 920 (0.0018)
+[2023-02-22 17:25:07,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3768320. Throughput: 0: 1030.3. Samples: 940144. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:25:07,692][00238] Avg episode reward: [(0, '24.198')]
+[2023-02-22 17:25:07,698][17475] Saving new best policy, reward=24.198!
+[2023-02-22 17:25:12,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 3780608. Throughput: 0: 976.3. Samples: 945280. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:25:12,691][00238] Avg episode reward: [(0, '25.125')]
+[2023-02-22 17:25:12,704][17475] Saving new best policy, reward=25.125!
+[2023-02-22 17:25:17,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3822.9, 300 sec: 3943.3). Total num frames: 3792896. Throughput: 0: 914.1. Samples: 948950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-22 17:25:17,689][00238] Avg episode reward: [(0, '24.629')]
+[2023-02-22 17:25:22,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3686.4, 300 sec: 3901.6). Total num frames: 3805184. Throughput: 0: 901.6. Samples: 950760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:25:22,688][00238] Avg episode reward: [(0, '24.062')]
+[2023-02-22 17:25:23,253][17490] Updated weights for policy 0, policy_version 930 (0.0055)
+[2023-02-22 17:25:27,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3887.7). Total num frames: 3825664. Throughput: 0: 893.0. Samples: 955756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:25:27,687][00238] Avg episode reward: [(0, '24.958')]
+[2023-02-22 17:25:32,110][17490] Updated weights for policy 0, policy_version 940 (0.0015)
+[2023-02-22 17:25:32,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3686.8, 300 sec: 3915.5). Total num frames: 3850240. Throughput: 0: 892.8. Samples: 963238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:25:32,689][00238] Avg episode reward: [(0, '23.170')]
+[2023-02-22 17:25:37,685][00238] Fps is (10 sec: 4505.4, 60 sec: 3754.6, 300 sec: 3929.4). Total num frames: 3870720. Throughput: 0: 896.1. Samples: 966810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:25:37,688][00238] Avg episode reward: [(0, '21.971')]
+[2023-02-22 17:25:42,685][00238] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3901.6). Total num frames: 3887104. Throughput: 0: 894.3. Samples: 971474. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:25:42,695][00238] Avg episode reward: [(0, '22.026')]
+[2023-02-22 17:25:43,425][17490] Updated weights for policy 0, policy_version 950 (0.0020)
+[2023-02-22 17:25:47,685][00238] Fps is (10 sec: 3686.6, 60 sec: 3618.1, 300 sec: 3887.7). Total num frames: 3907584. Throughput: 0: 895.6. Samples: 977444. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-22 17:25:47,690][00238] Avg episode reward: [(0, '20.046')]
+[2023-02-22 17:25:52,176][17490] Updated weights for policy 0, policy_version 960 (0.0021)
+[2023-02-22 17:25:52,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3686.4, 300 sec: 3915.5). Total num frames: 3932160. Throughput: 0: 911.3. Samples: 981152. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:25:52,687][00238] Avg episode reward: [(0, '20.134')]
+[2023-02-22 17:25:57,688][00238] Fps is (10 sec: 4504.8, 60 sec: 3754.6, 300 sec: 3929.4). Total num frames: 3952640. Throughput: 0: 945.6. Samples: 987834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-22 17:25:57,690][00238] Avg episode reward: [(0, '20.555')]
+[2023-02-22 17:26:02,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3901.6). Total num frames: 3964928. Throughput: 0: 966.9. Samples: 992462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-22 17:26:02,688][00238] Avg episode reward: [(0, '20.993')]
+[2023-02-22 17:26:02,790][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000969_3969024.pth...
+[2023-02-22 17:26:02,937][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000740_3031040.pth
+[2023-02-22 17:26:04,599][17490] Updated weights for policy 0, policy_version 970 (0.0015)
+[2023-02-22 17:26:07,685][00238] Fps is (10 sec: 3277.4, 60 sec: 3618.1, 300 sec: 3901.6). Total num frames: 3985408. Throughput: 0: 974.4. Samples: 994608. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-22 17:26:07,686][00238] Avg episode reward: [(0, '21.267')]
+[2023-02-22 17:26:12,031][17475] Stopping Batcher_0...
+[2023-02-22 17:26:12,032][17475] Loop batcher_evt_loop terminating...
+[2023-02-22 17:26:12,033][00238] Component Batcher_0 stopped!
+[2023-02-22 17:26:12,035][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-22 17:26:12,093][00238] Component RolloutWorker_w5 stopped!
+[2023-02-22 17:26:12,093][17496] Stopping RolloutWorker_w3...
+[2023-02-22 17:26:12,102][17491] Stopping RolloutWorker_w2...
+[2023-02-22 17:26:12,095][00238] Component RolloutWorker_w3 stopped!
+[2023-02-22 17:26:12,102][17491] Loop rollout_proc2_evt_loop terminating...
+[2023-02-22 17:26:12,102][00238] Component RolloutWorker_w2 stopped!
+[2023-02-22 17:26:12,095][17494] Stopping RolloutWorker_w5...
+[2023-02-22 17:26:12,106][17493] Stopping RolloutWorker_w4...
+[2023-02-22 17:26:12,108][17493] Loop rollout_proc4_evt_loop terminating...
+[2023-02-22 17:26:12,112][00238] Component RolloutWorker_w4 stopped!
+[2023-02-22 17:26:12,125][00238] Component RolloutWorker_w1 stopped!
+[2023-02-22 17:26:12,097][17496] Loop rollout_proc3_evt_loop terminating...
+[2023-02-22 17:26:12,129][00238] Component RolloutWorker_w0 stopped!
+[2023-02-22 17:26:12,131][17489] Stopping RolloutWorker_w0...
+[2023-02-22 17:26:12,136][17490] Weights refcount: 2 0
+[2023-02-22 17:26:12,141][17490] Stopping InferenceWorker_p0-w0...
+[2023-02-22 17:26:12,125][17492] Stopping RolloutWorker_w1...
+[2023-02-22 17:26:12,126][17494] Loop rollout_proc5_evt_loop terminating...
+[2023-02-22 17:26:12,141][00238] Component RolloutWorker_w6 stopped!
+[2023-02-22 17:26:12,144][00238] Component InferenceWorker_p0-w0 stopped!
+[2023-02-22 17:26:12,146][17495] Stopping RolloutWorker_w6...
+[2023-02-22 17:26:12,131][17489] Loop rollout_proc0_evt_loop terminating...
+[2023-02-22 17:26:12,150][17490] Loop inference_proc0-0_evt_loop terminating...
+[2023-02-22 17:26:12,154][17492] Loop rollout_proc1_evt_loop terminating...
+[2023-02-22 17:26:12,155][17497] Stopping RolloutWorker_w7...
+[2023-02-22 17:26:12,155][00238] Component RolloutWorker_w7 stopped!
+[2023-02-22 17:26:12,152][17495] Loop rollout_proc6_evt_loop terminating...
+[2023-02-22 17:26:12,164][17497] Loop rollout_proc7_evt_loop terminating...
+[2023-02-22 17:26:12,226][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000857_3510272.pth
+[2023-02-22 17:26:12,242][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-22 17:26:12,409][00238] Component LearnerWorker_p0 stopped!
+[2023-02-22 17:26:12,410][00238] Waiting for process learner_proc0 to stop...
+[2023-02-22 17:26:12,408][17475] Stopping LearnerWorker_p0...
+[2023-02-22 17:26:12,423][17475] Loop learner_proc0_evt_loop terminating...
+[2023-02-22 17:26:14,126][00238] Waiting for process inference_proc0-0 to join...
+[2023-02-22 17:26:14,562][00238] Waiting for process rollout_proc0 to join...
+[2023-02-22 17:26:14,799][00238] Waiting for process rollout_proc1 to join...
+[2023-02-22 17:26:15,137][00238] Waiting for process rollout_proc2 to join...
+[2023-02-22 17:26:15,141][00238] Waiting for process rollout_proc3 to join...
+[2023-02-22 17:26:15,142][00238] Waiting for process rollout_proc4 to join...
+[2023-02-22 17:26:15,143][00238] Waiting for process rollout_proc5 to join...
+[2023-02-22 17:26:15,145][00238] Waiting for process rollout_proc6 to join...
+[2023-02-22 17:26:15,148][00238] Waiting for process rollout_proc7 to join...
+[2023-02-22 17:26:15,149][00238] Batcher 0 profile tree view:
+batching: 25.6537, releasing_batches: 0.0283
+[2023-02-22 17:26:15,150][00238] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 505.7360
+update_model: 7.5130
+  weight_update: 0.0016
+one_step: 0.0090
+  handle_policy_step: 507.4398
+    deserialize: 14.8855, stack: 2.9028, obs_to_device_normalize: 113.7429, forward: 242.3296, send_messages: 26.2909
+    prepare_outputs: 82.1078
+      to_cpu: 50.6604
+[2023-02-22 17:26:15,153][00238] Learner 0 profile tree view:
+misc: 0.0057, prepare_batch: 15.5572
+train: 76.2907
+  epoch_init: 0.0059, minibatch_init: 0.0075, losses_postprocess: 0.6440, kl_divergence: 0.5798, after_optimizer: 33.1588
+  calculate_losses: 26.9921
+    losses_init: 0.0036, forward_head: 1.6895, bptt_initial: 17.8884, tail: 1.0892, advantages_returns: 0.2423, losses: 3.5040
+    bptt: 2.2078
+      bptt_forward_core: 2.1317
+  update: 14.3101
+    clip: 1.3961
+[2023-02-22 17:26:15,154][00238] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.3761, enqueue_policy_requests: 130.4311, env_step: 804.8662, overhead: 19.5726, complete_rollouts: 6.9588
+save_policy_outputs: 20.0405
+  split_output_tensors: 9.6544
+[2023-02-22 17:26:15,156][00238] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.3353, enqueue_policy_requests: 133.7615, env_step: 801.4917, overhead: 19.6378, complete_rollouts: 6.9079
+save_policy_outputs: 19.9991
+  split_output_tensors: 9.7333
+[2023-02-22 17:26:15,158][00238] Loop Runner_EvtLoop terminating...
+[2023-02-22 17:26:15,160][00238] Runner profile tree view:
+main_loop: 1088.1145
+[2023-02-22 17:26:15,163][00238] Collected {0: 4005888}, FPS: 3681.5
+[2023-02-22 17:32:44,396][00238] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-22 17:32:44,398][00238] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-22 17:32:44,400][00238] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-22 17:32:44,402][00238] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-22 17:32:44,404][00238] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-22 17:32:44,406][00238] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-22 17:32:44,407][00238] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-02-22 17:32:44,410][00238] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-22 17:32:44,411][00238] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-02-22 17:32:44,413][00238] Adding new argument 'hf_repository'='cmenasse/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-02-22 17:32:44,414][00238] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-22 17:32:44,415][00238] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-22 17:32:44,416][00238] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-22 17:32:44,418][00238] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-22 17:32:44,420][00238] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-22 17:32:44,451][00238] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-22 17:32:44,454][00238] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-22 17:32:44,457][00238] RunningMeanStd input shape: (1,)
+[2023-02-22 17:32:44,473][00238] ConvEncoder: input_channels=3
+[2023-02-22 17:32:45,150][00238] Conv encoder output size: 512
+[2023-02-22 17:32:45,151][00238] Policy head output size: 512
+[2023-02-22 17:32:47,521][00238] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-22 17:32:48,778][00238] Num frames 100...
+[2023-02-22 17:32:48,893][00238] Num frames 200...
+[2023-02-22 17:32:49,005][00238] Num frames 300...
+[2023-02-22 17:32:49,123][00238] Num frames 400...
+[2023-02-22 17:32:49,248][00238] Num frames 500...
+[2023-02-22 17:32:49,374][00238] Num frames 600...
+[2023-02-22 17:32:49,475][00238] Avg episode rewards: #0: 14.290, true rewards: #0: 6.290
+[2023-02-22 17:32:49,477][00238] Avg episode reward: 14.290, avg true_objective: 6.290
+[2023-02-22 17:32:49,571][00238] Num frames 700...
+[2023-02-22 17:32:49,680][00238] Num frames 800...
+[2023-02-22 17:32:49,796][00238] Num frames 900...
+[2023-02-22 17:32:49,916][00238] Num frames 1000...
+[2023-02-22 17:32:50,026][00238] Num frames 1100...
+[2023-02-22 17:32:50,138][00238] Num frames 1200...
+[2023-02-22 17:32:50,251][00238] Num frames 1300...
+[2023-02-22 17:32:50,343][00238] Avg episode rewards: #0: 13.665, true rewards: #0: 6.665
+[2023-02-22 17:32:50,345][00238] Avg episode reward: 13.665, avg true_objective: 6.665
+[2023-02-22 17:32:50,419][00238] Num frames 1400...
+[2023-02-22 17:32:50,530][00238] Num frames 1500...
+[2023-02-22 17:32:50,642][00238] Num frames 1600...
+[2023-02-22 17:32:50,753][00238] Num frames 1700...
+[2023-02-22 17:32:50,862][00238] Num frames 1800...
+[2023-02-22 17:32:50,972][00238] Num frames 1900...
+[2023-02-22 17:32:51,079][00238] Num frames 2000...
+[2023-02-22 17:32:51,196][00238] Num frames 2100...
+[2023-02-22 17:32:51,334][00238] Num frames 2200...
+[2023-02-22 17:32:51,491][00238] Num frames 2300...
+[2023-02-22 17:32:51,652][00238] Num frames 2400...
+[2023-02-22 17:32:51,808][00238] Num frames 2500...
+[2023-02-22 17:32:51,958][00238] Num frames 2600...
+[2023-02-22 17:32:52,120][00238] Num frames 2700...
+[2023-02-22 17:32:52,273][00238] Num frames 2800...
+[2023-02-22 17:32:52,433][00238] Num frames 2900...
+[2023-02-22 17:32:52,588][00238] Num frames 3000...
+[2023-02-22 17:32:52,752][00238] Num frames 3100...
+[2023-02-22 17:32:52,946][00238] Avg episode rewards: #0: 22.630, true rewards: #0: 10.630
+[2023-02-22 17:32:52,948][00238] Avg episode reward: 22.630, avg true_objective: 10.630
+[2023-02-22 17:32:52,966][00238] Num frames 3200...
+[2023-02-22 17:32:53,115][00238] Num frames 3300...
+[2023-02-22 17:32:53,267][00238] Num frames 3400...
+[2023-02-22 17:32:53,415][00238] Num frames 3500...
+[2023-02-22 17:32:53,571][00238] Num frames 3600...
+[2023-02-22 17:32:53,732][00238] Num frames 3700...
+[2023-02-22 17:32:53,894][00238] Num frames 3800...
+[2023-02-22 17:32:54,052][00238] Num frames 3900...
+[2023-02-22 17:32:54,246][00238] Avg episode rewards: #0: 20.972, true rewards: #0: 9.972
+[2023-02-22 17:32:54,249][00238] Avg episode reward: 20.972, avg true_objective: 9.972
+[2023-02-22 17:32:54,267][00238] Num frames 4000...
+[2023-02-22 17:32:54,423][00238] Num frames 4100...
+[2023-02-22 17:32:54,580][00238] Num frames 4200...
+[2023-02-22 17:32:54,739][00238] Num frames 4300...
+[2023-02-22 17:32:54,872][00238] Num frames 4400...
+[2023-02-22 17:32:54,982][00238] Num frames 4500...
+[2023-02-22 17:32:55,097][00238] Num frames 4600...
+[2023-02-22 17:32:55,208][00238] Num frames 4700...
+[2023-02-22 17:32:55,323][00238] Num frames 4800...
+[2023-02-22 17:32:55,433][00238] Num frames 4900...
+[2023-02-22 17:32:55,541][00238] Num frames 5000...
+[2023-02-22 17:32:55,651][00238] Num frames 5100...
+[2023-02-22 17:32:55,767][00238] Num frames 5200...
+[2023-02-22 17:32:55,880][00238] Num frames 5300...
+[2023-02-22 17:32:55,991][00238] Num frames 5400...
+[2023-02-22 17:32:56,101][00238] Num frames 5500...
+[2023-02-22 17:32:56,214][00238] Num frames 5600...
+[2023-02-22 17:32:56,322][00238] Num frames 5700...
+[2023-02-22 17:32:56,439][00238] Num frames 5800...
+[2023-02-22 17:32:56,548][00238] Num frames 5900...
+[2023-02-22 17:32:56,672][00238] Num frames 6000...
+[2023-02-22 17:32:56,848][00238] Avg episode rewards: #0: 27.778, true rewards: #0: 12.178
+[2023-02-22 17:32:56,850][00238] Avg episode reward: 27.778, avg true_objective: 12.178
+[2023-02-22 17:32:56,865][00238] Num frames 6100...
+[2023-02-22 17:32:56,977][00238] Num frames 6200...
+[2023-02-22 17:32:57,094][00238] Num frames 6300...
+[2023-02-22 17:32:57,219][00238] Num frames 6400...
+[2023-02-22 17:32:57,329][00238] Num frames 6500...
+[2023-02-22 17:32:57,451][00238] Num frames 6600...
+[2023-02-22 17:32:57,580][00238] Num frames 6700...
+[2023-02-22 17:32:57,700][00238] Num frames 6800...
+[2023-02-22 17:32:57,817][00238] Num frames 6900...
+[2023-02-22 17:32:57,928][00238] Avg episode rewards: #0: 25.921, true rewards: #0: 11.588
+[2023-02-22 17:32:57,930][00238] Avg episode reward: 25.921, avg true_objective: 11.588
+[2023-02-22 17:32:57,984][00238] Num frames 7000...
+[2023-02-22 17:32:58,091][00238] Num frames 7100...
+[2023-02-22 17:32:58,201][00238] Num frames 7200...
+[2023-02-22 17:32:58,307][00238] Num frames 7300...
+[2023-02-22 17:32:58,414][00238] Num frames 7400...
+[2023-02-22 17:32:58,572][00238] Avg episode rewards: #0: 23.281, true rewards: #0: 10.710
+[2023-02-22 17:32:58,574][00238] Avg episode reward: 23.281, avg true_objective: 10.710
+[2023-02-22 17:32:58,581][00238] Num frames 7500...
+[2023-02-22 17:32:58,690][00238] Num frames 7600...
+[2023-02-22 17:32:58,815][00238] Num frames 7700...
+[2023-02-22 17:32:58,935][00238] Num frames 7800...
+[2023-02-22 17:32:59,051][00238] Num frames 7900...
+[2023-02-22 17:32:59,162][00238] Num frames 8000...
+[2023-02-22 17:32:59,276][00238] Num frames 8100...
+[2023-02-22 17:32:59,385][00238] Num frames 8200...
+[2023-02-22 17:32:59,497][00238] Num frames 8300...
+[2023-02-22 17:32:59,610][00238] Num frames 8400...
+[2023-02-22 17:32:59,718][00238] Num frames 8500...
+[2023-02-22 17:32:59,839][00238] Num frames 8600...
+[2023-02-22 17:32:59,950][00238] Num frames 8700...
+[2023-02-22 17:33:00,063][00238] Num frames 8800...
+[2023-02-22 17:33:00,200][00238] Avg episode rewards: #0: 24.091, true rewards: #0: 11.091
+[2023-02-22 17:33:00,201][00238] Avg episode reward: 24.091, avg true_objective: 11.091
+[2023-02-22 17:33:00,234][00238] Num frames 8900...
+[2023-02-22 17:33:00,347][00238] Num frames 9000...
+[2023-02-22 17:33:00,454][00238] Num frames 9100...
+[2023-02-22 17:33:00,564][00238] Num frames 9200...
+[2023-02-22 17:33:00,673][00238] Num frames 9300...
+[2023-02-22 17:33:00,788][00238] Num frames 9400...
+[2023-02-22 17:33:00,898][00238] Num frames 9500...
+[2023-02-22 17:33:01,008][00238] Num frames 9600...
+[2023-02-22 17:33:01,128][00238] Num frames 9700...
+[2023-02-22 17:33:01,241][00238] Num frames 9800...
+[2023-02-22 17:33:01,350][00238] Num frames 9900...
+[2023-02-22 17:33:01,477][00238] Num frames 10000...
+[2023-02-22 17:33:01,605][00238] Num frames 10100...
+[2023-02-22 17:33:01,736][00238] Num frames 10200...
+[2023-02-22 17:33:01,864][00238] Num frames 10300...
+[2023-02-22 17:33:01,980][00238] Num frames 10400...
+[2023-02-22 17:33:02,106][00238] Avg episode rewards: #0: 25.728, true rewards: #0: 11.617
+[2023-02-22 17:33:02,109][00238] Avg episode reward: 25.728, avg true_objective: 11.617
+[2023-02-22 17:33:02,166][00238] Num frames 10500...
+[2023-02-22 17:33:02,284][00238] Num frames 10600...
+[2023-02-22 17:33:02,403][00238] Num frames 10700...
+[2023-02-22 17:33:02,517][00238] Num frames 10800...
+[2023-02-22 17:33:02,636][00238] Num frames 10900...
+[2023-02-22 17:33:02,752][00238] Num frames 11000...
+[2023-02-22 17:33:02,872][00238] Num frames 11100...
+[2023-02-22 17:33:02,987][00238] Num frames 11200...
+[2023-02-22 17:33:03,102][00238] Num frames 11300...
+[2023-02-22 17:33:03,220][00238] Num frames 11400...
+[2023-02-22 17:33:03,339][00238] Num frames 11500...
+[2023-02-22 17:33:03,458][00238] Num frames 11600...
+[2023-02-22 17:33:03,585][00238] Num frames 11700...
+[2023-02-22 17:33:03,707][00238] Num frames 11800...
+[2023-02-22 17:33:03,813][00238] Avg episode rewards: #0: 26.541, true rewards: #0: 11.841
+[2023-02-22 17:33:03,815][00238] Avg episode reward: 26.541, avg true_objective: 11.841
+[2023-02-22 17:34:13,172][00238] Replay video saved to /content/train_dir/default_experiment/replay.mp4!