Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1688485318.e07d25fd0378

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb791f51c742df8a1c9e16b6364c072572916cf73423a3f96a4b5dff483d3a28
+size 477121

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 8.86 +/- 5.05
+      value: 9.20 +/- 6.90
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000000923_3780608_reward_25.008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99eb7ed85310bb1ed9425b70f9c9391aab4a651382a677d483ab8c9dffabc3d
+size 34928806

checkpoint_p0/checkpoint_000000874_3579904.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32aa48de04dd532a12a43951fb5df18da0842821b98ec8cb3e5e1d6751d43e68
+size 34929220

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf53e5293626e176b0f248d7190abf8e64d8436f2862353319facf0fad5041e
+size 34929220

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 2000000,
+  "train_for_env_steps": 4000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c885fce2f959d628d1e5c5095cd9b5c61f11f9892ceb77046b737d7a7d6fe1e9
-size 16726721
+oid sha256:3cd28f20ee6e27ecd0b5908b6cc0b7023ae49b0c216d117bc4d9ea50b2dc22ac
+size 17560860

sf_log.txt

@@ -2951,3 +2951,829 @@ main_loop: 287.1521
 [2023-07-04 15:40:08,709][18333] Avg episode rewards: #0: 19.761, true rewards: #0: 8.861
 [2023-07-04 15:40:08,711][18333] Avg episode reward: 19.761, avg true_objective: 8.861
 [2023-07-04 15:41:03,224][18333] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2023-07-04 15:41:06,055][18333] The model has been pushed to https://huggingface.co/HilbertS/rl_course_vizdoom_health_gathering_supreme
+[2023-07-04 15:41:58,356][18333] Environment doom_basic already registered, overwriting...
+[2023-07-04 15:41:58,358][18333] Environment doom_two_colors_easy already registered, overwriting...
+[2023-07-04 15:41:58,360][18333] Environment doom_two_colors_hard already registered, overwriting...
+[2023-07-04 15:41:58,364][18333] Environment doom_dm already registered, overwriting...
+[2023-07-04 15:41:58,365][18333] Environment doom_dwango5 already registered, overwriting...
+[2023-07-04 15:41:58,367][18333] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2023-07-04 15:41:58,369][18333] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2023-07-04 15:41:58,370][18333] Environment doom_my_way_home already registered, overwriting...
+[2023-07-04 15:41:58,371][18333] Environment doom_deadly_corridor already registered, overwriting...
+[2023-07-04 15:41:58,373][18333] Environment doom_defend_the_center already registered, overwriting...
+[2023-07-04 15:41:58,375][18333] Environment doom_defend_the_line already registered, overwriting...
+[2023-07-04 15:41:58,376][18333] Environment doom_health_gathering already registered, overwriting...
+[2023-07-04 15:41:58,377][18333] Environment doom_health_gathering_supreme already registered, overwriting...
+[2023-07-04 15:41:58,379][18333] Environment doom_battle already registered, overwriting...
+[2023-07-04 15:41:58,380][18333] Environment doom_battle2 already registered, overwriting...
+[2023-07-04 15:41:58,381][18333] Environment doom_duel_bots already registered, overwriting...
+[2023-07-04 15:41:58,382][18333] Environment doom_deathmatch_bots already registered, overwriting...
+[2023-07-04 15:41:58,384][18333] Environment doom_duel already registered, overwriting...
+[2023-07-04 15:41:58,385][18333] Environment doom_deathmatch_full already registered, overwriting...
+[2023-07-04 15:41:58,386][18333] Environment doom_benchmark already registered, overwriting...
+[2023-07-04 15:41:58,387][18333] register_encoder_factory: <function make_vizdoom_encoder at 0x7f3d79124820>
+[2023-07-04 15:41:58,425][18333] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-07-04 15:41:58,426][18333] Overriding arg 'train_for_env_steps' with value 4000000 passed from command line
+[2023-07-04 15:41:58,433][18333] Experiment dir /content/train_dir/default_experiment already exists!
+[2023-07-04 15:41:58,435][18333] Resuming existing experiment from /content/train_dir/default_experiment...
+[2023-07-04 15:41:58,437][18333] Weights and Biases integration disabled
+[2023-07-04 15:41:58,443][18333] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2023-07-04 15:41:59,883][18333] Starting experiment with the following configuration:
+help=False
+algo=APPO
+env=doom_health_gathering_supreme
+experiment=default_experiment
+train_dir=/content/train_dir
+restart_behavior=resume
+device=gpu
+seed=None
+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=None
+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=None
+wandb_project=sample_factory
+wandb_group=None
+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=None
+timelimit=None
+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
+[2023-07-04 15:41:59,887][18333] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2023-07-04 15:41:59,893][18333] Rollout worker 0 uses device cpu
+[2023-07-04 15:41:59,896][18333] Rollout worker 1 uses device cpu
+[2023-07-04 15:41:59,897][18333] Rollout worker 2 uses device cpu
+[2023-07-04 15:41:59,898][18333] Rollout worker 3 uses device cpu
+[2023-07-04 15:41:59,899][18333] Rollout worker 4 uses device cpu
+[2023-07-04 15:41:59,900][18333] Rollout worker 5 uses device cpu
+[2023-07-04 15:41:59,901][18333] Rollout worker 6 uses device cpu
+[2023-07-04 15:41:59,903][18333] Rollout worker 7 uses device cpu
+[2023-07-04 15:42:00,023][18333] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-04 15:42:00,029][18333] InferenceWorker_p0-w0: min num requests: 2
+[2023-07-04 15:42:00,068][18333] Starting all processes...
+[2023-07-04 15:42:00,073][18333] Starting process learner_proc0
+[2023-07-04 15:42:00,141][18333] Starting all processes...
+[2023-07-04 15:42:00,150][18333] Starting process inference_proc0-0
+[2023-07-04 15:42:00,150][18333] Starting process rollout_proc0
+[2023-07-04 15:42:00,151][18333] Starting process rollout_proc1
+[2023-07-04 15:42:00,151][18333] Starting process rollout_proc2
+[2023-07-04 15:42:00,151][18333] Starting process rollout_proc3
+[2023-07-04 15:42:00,151][18333] Starting process rollout_proc4
+[2023-07-04 15:42:00,151][18333] Starting process rollout_proc5
+[2023-07-04 15:42:00,151][18333] Starting process rollout_proc6
+[2023-07-04 15:42:00,151][18333] Starting process rollout_proc7
+[2023-07-04 15:42:12,217][22133] Worker 1 uses CPU cores [1]
+[2023-07-04 15:42:12,582][22113] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-04 15:42:12,585][22113] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-07-04 15:42:12,593][22135] Worker 4 uses CPU cores [0]
+[2023-07-04 15:42:12,595][22126] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-04 15:42:12,597][22126] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-07-04 15:42:12,630][22113] Num visible devices: 1
+[2023-07-04 15:42:12,657][22126] Num visible devices: 1
+[2023-07-04 15:42:12,668][22113] Starting seed is not provided
+[2023-07-04 15:42:12,668][22113] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-04 15:42:12,669][22113] Initializing actor-critic model on device cuda:0
+[2023-07-04 15:42:12,670][22113] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-04 15:42:12,671][22113] RunningMeanStd input shape: (1,)
+[2023-07-04 15:42:12,685][22138] Worker 7 uses CPU cores [1]
+[2023-07-04 15:42:12,686][22132] Worker 3 uses CPU cores [1]
+[2023-07-04 15:42:12,691][22137] Worker 6 uses CPU cores [0]
+[2023-07-04 15:42:12,703][22113] ConvEncoder: input_channels=3
+[2023-07-04 15:42:12,717][22130] Worker 0 uses CPU cores [0]
+[2023-07-04 15:42:12,739][22136] Worker 5 uses CPU cores [1]
+[2023-07-04 15:42:12,742][22134] Worker 2 uses CPU cores [0]
+[2023-07-04 15:42:12,832][22113] Conv encoder output size: 512
+[2023-07-04 15:42:12,833][22113] Policy head output size: 512
+[2023-07-04 15:42:12,848][22113] Created Actor Critic model with architecture:
+[2023-07-04 15:42:12,848][22113] 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)
+  )
+)
+[2023-07-04 15:42:14,186][22113] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-07-04 15:42:14,187][22113] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000490_2007040.pth...
+[2023-07-04 15:42:14,218][22113] Loading model from checkpoint
+[2023-07-04 15:42:14,222][22113] Loaded experiment state at self.train_step=490, self.env_steps=2007040
+[2023-07-04 15:42:14,222][22113] Initialized policy 0 weights for model version 490
+[2023-07-04 15:42:14,225][22113] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-07-04 15:42:14,238][22113] LearnerWorker_p0 finished initialization!
+[2023-07-04 15:42:14,414][22126] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-04 15:42:14,415][22126] RunningMeanStd input shape: (1,)
+[2023-07-04 15:42:14,427][22126] ConvEncoder: input_channels=3
+[2023-07-04 15:42:14,530][22126] Conv encoder output size: 512
+[2023-07-04 15:42:14,530][22126] Policy head output size: 512
+[2023-07-04 15:42:15,731][18333] Inference worker 0-0 is ready!
+[2023-07-04 15:42:15,733][18333] All inference workers are ready! Signal rollout workers to start!
+[2023-07-04 15:42:15,833][22136] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-04 15:42:15,834][22138] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-04 15:42:15,836][22133] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-04 15:42:15,837][22132] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-04 15:42:15,829][22134] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-04 15:42:15,840][22135] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-04 15:42:15,837][22137] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-04 15:42:15,838][22130] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-07-04 15:42:16,364][22134] Decorrelating experience for 0 frames...
+[2023-07-04 15:42:16,789][22135] Decorrelating experience for 0 frames...
+[2023-07-04 15:42:17,197][22132] Decorrelating experience for 0 frames...
+[2023-07-04 15:42:17,199][22133] Decorrelating experience for 0 frames...
+[2023-07-04 15:42:17,201][22136] Decorrelating experience for 0 frames...
+[2023-07-04 15:42:17,205][22138] Decorrelating experience for 0 frames...
+[2023-07-04 15:42:18,447][18333] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 2007040. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-07-04 15:42:18,787][22130] Decorrelating experience for 0 frames...
+[2023-07-04 15:42:18,793][22136] Decorrelating experience for 32 frames...
+[2023-07-04 15:42:18,799][22133] Decorrelating experience for 32 frames...
+[2023-07-04 15:42:18,804][22138] Decorrelating experience for 32 frames...
+[2023-07-04 15:42:18,819][22134] Decorrelating experience for 32 frames...
+[2023-07-04 15:42:18,872][22135] Decorrelating experience for 32 frames...
+[2023-07-04 15:42:20,014][18333] Heartbeat connected on Batcher_0
+[2023-07-04 15:42:20,019][18333] Heartbeat connected on LearnerWorker_p0
+[2023-07-04 15:42:20,073][18333] Heartbeat connected on InferenceWorker_p0-w0
+[2023-07-04 15:42:20,499][22137] Decorrelating experience for 0 frames...
+[2023-07-04 15:42:20,531][22130] Decorrelating experience for 32 frames...
+[2023-07-04 15:42:20,759][22135] Decorrelating experience for 64 frames...
+[2023-07-04 15:42:21,358][22132] Decorrelating experience for 32 frames...
+[2023-07-04 15:42:21,673][22136] Decorrelating experience for 64 frames...
+[2023-07-04 15:42:21,685][22133] Decorrelating experience for 64 frames...
+[2023-07-04 15:42:22,606][22138] Decorrelating experience for 64 frames...
+[2023-07-04 15:42:22,860][22130] Decorrelating experience for 64 frames...
+[2023-07-04 15:42:22,874][22137] Decorrelating experience for 32 frames...
+[2023-07-04 15:42:23,443][18333] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2007040. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-07-04 15:42:23,493][22136] Decorrelating experience for 96 frames...
+[2023-07-04 15:42:23,661][22134] Decorrelating experience for 64 frames...
+[2023-07-04 15:42:23,829][18333] Heartbeat connected on RolloutWorker_w5
+[2023-07-04 15:42:24,876][22132] Decorrelating experience for 64 frames...
+[2023-07-04 15:42:25,138][22138] Decorrelating experience for 96 frames...
+[2023-07-04 15:42:25,516][22137] Decorrelating experience for 64 frames...
+[2023-07-04 15:42:25,520][18333] Heartbeat connected on RolloutWorker_w7
+[2023-07-04 15:42:26,625][22130] Decorrelating experience for 96 frames...
+[2023-07-04 15:42:27,023][22135] Decorrelating experience for 96 frames...
+[2023-07-04 15:42:27,323][18333] Heartbeat connected on RolloutWorker_w0
+[2023-07-04 15:42:27,403][22134] Decorrelating experience for 96 frames...
+[2023-07-04 15:42:27,426][22133] Decorrelating experience for 96 frames...
+[2023-07-04 15:42:27,727][18333] Heartbeat connected on RolloutWorker_w4
+[2023-07-04 15:42:27,884][18333] Heartbeat connected on RolloutWorker_w2
+[2023-07-04 15:42:28,014][18333] Heartbeat connected on RolloutWorker_w1
+[2023-07-04 15:42:28,444][18333] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2007040. Throughput: 0: 104.4. Samples: 1044. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-07-04 15:42:28,450][18333] Avg episode reward: [(0, '5.920')]
+[2023-07-04 15:42:30,105][22137] Decorrelating experience for 96 frames...
+[2023-07-04 15:42:30,522][22113] Signal inference workers to stop experience collection...
+[2023-07-04 15:42:30,544][22126] InferenceWorker_p0-w0: stopping experience collection
+[2023-07-04 15:42:30,576][18333] Heartbeat connected on RolloutWorker_w6
+[2023-07-04 15:42:30,706][22132] Decorrelating experience for 96 frames...
+[2023-07-04 15:42:30,763][18333] Heartbeat connected on RolloutWorker_w3
+[2023-07-04 15:42:31,213][22113] Signal inference workers to resume experience collection...
+[2023-07-04 15:42:31,213][22126] InferenceWorker_p0-w0: resuming experience collection
+[2023-07-04 15:42:33,444][18333] Fps is (10 sec: 1228.8, 60 sec: 819.4, 300 sec: 819.4). Total num frames: 2019328. Throughput: 0: 161.6. Samples: 2424. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2023-07-04 15:42:33,448][18333] Avg episode reward: [(0, '6.131')]
+[2023-07-04 15:42:38,444][18333] Fps is (10 sec: 3277.0, 60 sec: 1638.7, 300 sec: 1638.7). Total num frames: 2039808. Throughput: 0: 379.1. Samples: 7580. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:42:38,446][18333] Avg episode reward: [(0, '10.472')]
+[2023-07-04 15:42:39,885][22126] Updated weights for policy 0, policy_version 500 (0.0364)
+[2023-07-04 15:42:43,444][18333] Fps is (10 sec: 3686.4, 60 sec: 1966.4, 300 sec: 1966.4). Total num frames: 2056192. Throughput: 0: 513.3. Samples: 12830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:42:43,448][18333] Avg episode reward: [(0, '12.881')]
+[2023-07-04 15:42:48,444][18333] Fps is (10 sec: 2867.2, 60 sec: 2048.3, 300 sec: 2048.3). Total num frames: 2068480. Throughput: 0: 491.9. Samples: 14756. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:42:48,454][18333] Avg episode reward: [(0, '15.054')]
+[2023-07-04 15:42:53,443][18333] Fps is (10 sec: 2867.2, 60 sec: 2223.8, 300 sec: 2223.8). Total num frames: 2084864. Throughput: 0: 537.4. Samples: 18808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:42:53,446][18333] Avg episode reward: [(0, '15.502')]
+[2023-07-04 15:42:54,028][22126] Updated weights for policy 0, policy_version 510 (0.0012)
+[2023-07-04 15:42:58,444][18333] Fps is (10 sec: 3686.4, 60 sec: 2457.8, 300 sec: 2457.8). Total num frames: 2105344. Throughput: 0: 631.0. Samples: 25236. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:42:58,450][18333] Avg episode reward: [(0, '16.713')]
+[2023-07-04 15:43:03,444][18333] Fps is (10 sec: 4095.9, 60 sec: 2639.9, 300 sec: 2639.9). Total num frames: 2125824. Throughput: 0: 636.5. Samples: 28642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:43:03,447][18333] Avg episode reward: [(0, '20.677')]
+[2023-07-04 15:43:03,667][22126] Updated weights for policy 0, policy_version 520 (0.0018)
+[2023-07-04 15:43:08,444][18333] Fps is (10 sec: 3686.4, 60 sec: 2703.6, 300 sec: 2703.6). Total num frames: 2142208. Throughput: 0: 738.4. Samples: 33228. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:43:08,455][18333] Avg episode reward: [(0, '20.643')]
+[2023-07-04 15:43:13,444][18333] Fps is (10 sec: 2867.2, 60 sec: 2681.2, 300 sec: 2681.2). Total num frames: 2154496. Throughput: 0: 811.4. Samples: 37556. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:43:13,449][18333] Avg episode reward: [(0, '20.266')]
+[2023-07-04 15:43:16,601][22126] Updated weights for policy 0, policy_version 530 (0.0027)
+[2023-07-04 15:43:18,444][18333] Fps is (10 sec: 3276.8, 60 sec: 2799.1, 300 sec: 2799.1). Total num frames: 2174976. Throughput: 0: 844.5. Samples: 40426. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:43:18,446][18333] Avg episode reward: [(0, '19.739')]
+[2023-07-04 15:43:23,449][18333] Fps is (10 sec: 4503.0, 60 sec: 3208.2, 300 sec: 2961.6). Total num frames: 2199552. Throughput: 0: 876.5. Samples: 47026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:43:23,456][18333] Avg episode reward: [(0, '19.858')]
+[2023-07-04 15:43:26,881][22126] Updated weights for policy 0, policy_version 540 (0.0017)
+[2023-07-04 15:43:28,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 2984.4). Total num frames: 2215936. Throughput: 0: 874.7. Samples: 52192. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:43:28,447][18333] Avg episode reward: [(0, '18.952')]
+[2023-07-04 15:43:33,444][18333] Fps is (10 sec: 2868.7, 60 sec: 3481.6, 300 sec: 2949.2). Total num frames: 2228224. Throughput: 0: 878.7. Samples: 54300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:43:33,449][18333] Avg episode reward: [(0, '18.617')]
+[2023-07-04 15:43:38,444][18333] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 2969.7). Total num frames: 2244608. Throughput: 0: 883.5. Samples: 58564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:43:38,446][18333] Avg episode reward: [(0, '19.696')]
+[2023-07-04 15:43:39,910][22126] Updated weights for policy 0, policy_version 550 (0.0015)
+[2023-07-04 15:43:43,445][18333] Fps is (10 sec: 3686.3, 60 sec: 3481.5, 300 sec: 3036.0). Total num frames: 2265088. Throughput: 0: 888.3. Samples: 65212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:43:43,450][18333] Avg episode reward: [(0, '20.749')]
+[2023-07-04 15:43:48,448][18333] Fps is (10 sec: 4094.1, 60 sec: 3617.9, 300 sec: 3094.7). Total num frames: 2285568. Throughput: 0: 886.9. Samples: 68558. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:43:48,451][18333] Avg episode reward: [(0, '20.008')]
+[2023-07-04 15:43:50,566][22126] Updated weights for policy 0, policy_version 560 (0.0015)
+[2023-07-04 15:43:53,444][18333] Fps is (10 sec: 3277.2, 60 sec: 3549.9, 300 sec: 3061.3). Total num frames: 2297856. Throughput: 0: 883.6. Samples: 72990. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:43:53,450][18333] Avg episode reward: [(0, '20.912')]
+[2023-07-04 15:43:58,444][18333] Fps is (10 sec: 2868.5, 60 sec: 3481.6, 300 sec: 3072.1). Total num frames: 2314240. Throughput: 0: 878.1. Samples: 77072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:43:58,453][18333] Avg episode reward: [(0, '21.782')]
+[2023-07-04 15:43:58,465][22113] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000565_2314240.pth...
+[2023-07-04 15:43:58,661][22113] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000448_1835008.pth
+[2023-07-04 15:43:58,681][22113] Saving new best policy, reward=21.782!
+[2023-07-04 15:44:03,276][22126] Updated weights for policy 0, policy_version 570 (0.0027)
+[2023-07-04 15:44:03,443][18333] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3120.9). Total num frames: 2334720. Throughput: 0: 873.0. Samples: 79712. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:44:03,450][18333] Avg episode reward: [(0, '21.747')]
+[2023-07-04 15:44:08,444][18333] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3165.2). Total num frames: 2355200. Throughput: 0: 876.9. Samples: 86482. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:44:08,446][18333] Avg episode reward: [(0, '22.334')]
+[2023-07-04 15:44:08,461][22113] Saving new best policy, reward=22.334!
+[2023-07-04 15:44:13,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3170.1). Total num frames: 2371584. Throughput: 0: 877.7. Samples: 91688. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:44:13,447][18333] Avg episode reward: [(0, '22.763')]
+[2023-07-04 15:44:13,454][22113] Saving new best policy, reward=22.763!
+[2023-07-04 15:44:14,147][22126] Updated weights for policy 0, policy_version 580 (0.0021)
+[2023-07-04 15:44:18,444][18333] Fps is (10 sec: 2867.0, 60 sec: 3481.6, 300 sec: 3140.3). Total num frames: 2383872. Throughput: 0: 873.9. Samples: 93626. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:44:18,448][18333] Avg episode reward: [(0, '23.183')]
+[2023-07-04 15:44:18,460][22113] Saving new best policy, reward=23.183!
+[2023-07-04 15:44:23,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3345.4, 300 sec: 3145.8). Total num frames: 2400256. Throughput: 0: 870.7. Samples: 97744. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:44:23,446][18333] Avg episode reward: [(0, '21.347')]
+[2023-07-04 15:44:26,586][22126] Updated weights for policy 0, policy_version 590 (0.0015)
+[2023-07-04 15:44:28,444][18333] Fps is (10 sec: 3686.6, 60 sec: 3413.3, 300 sec: 3182.4). Total num frames: 2420736. Throughput: 0: 869.7. Samples: 104346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:44:28,445][18333] Avg episode reward: [(0, '21.713')]
+[2023-07-04 15:44:33,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3216.2). Total num frames: 2441216. Throughput: 0: 868.1. Samples: 107620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-07-04 15:44:33,446][18333] Avg episode reward: [(0, '20.100')]
+[2023-07-04 15:44:38,163][22126] Updated weights for policy 0, policy_version 600 (0.0012)
+[2023-07-04 15:44:38,445][18333] Fps is (10 sec: 3686.0, 60 sec: 3549.8, 300 sec: 3218.3). Total num frames: 2457600. Throughput: 0: 866.4. Samples: 111978. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:44:38,454][18333] Avg episode reward: [(0, '20.039')]
+[2023-07-04 15:44:43,444][18333] Fps is (10 sec: 2867.0, 60 sec: 3413.4, 300 sec: 3192.1). Total num frames: 2469888. Throughput: 0: 870.0. Samples: 116222. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:44:43,449][18333] Avg episode reward: [(0, '19.196')]
+[2023-07-04 15:44:48,443][18333] Fps is (10 sec: 3686.8, 60 sec: 3481.9, 300 sec: 3249.6). Total num frames: 2494464. Throughput: 0: 875.0. Samples: 119086. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
+[2023-07-04 15:44:48,446][18333] Avg episode reward: [(0, '19.491')]
+[2023-07-04 15:44:49,316][22126] Updated weights for policy 0, policy_version 610 (0.0022)
+[2023-07-04 15:44:53,444][18333] Fps is (10 sec: 4505.8, 60 sec: 3618.1, 300 sec: 3276.9). Total num frames: 2514944. Throughput: 0: 873.4. Samples: 125786. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:44:53,446][18333] Avg episode reward: [(0, '19.441')]
+[2023-07-04 15:44:58,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3251.3). Total num frames: 2527232. Throughput: 0: 868.0. Samples: 130746. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
+[2023-07-04 15:44:58,446][18333] Avg episode reward: [(0, '20.312')]
+[2023-07-04 15:45:01,652][22126] Updated weights for policy 0, policy_version 620 (0.0012)
+[2023-07-04 15:45:03,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3252.1). Total num frames: 2543616. Throughput: 0: 870.8. Samples: 132812. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:45:03,446][18333] Avg episode reward: [(0, '20.249')]
+[2023-07-04 15:45:08,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3252.8). Total num frames: 2560000. Throughput: 0: 875.5. Samples: 137142. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:45:08,446][18333] Avg episode reward: [(0, '19.822')]
+[2023-07-04 15:45:12,866][22126] Updated weights for policy 0, policy_version 630 (0.0017)
+[2023-07-04 15:45:13,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3276.9). Total num frames: 2580480. Throughput: 0: 875.6. Samples: 143748. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:45:13,446][18333] Avg episode reward: [(0, '20.569')]
+[2023-07-04 15:45:18,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3299.6). Total num frames: 2600960. Throughput: 0: 875.8. Samples: 147032. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:45:18,446][18333] Avg episode reward: [(0, '21.334')]
+[2023-07-04 15:45:23,445][18333] Fps is (10 sec: 3276.2, 60 sec: 3549.8, 300 sec: 3276.8). Total num frames: 2613248. Throughput: 0: 881.4. Samples: 151640. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:45:23,447][18333] Avg episode reward: [(0, '21.972')]
+[2023-07-04 15:45:25,316][22126] Updated weights for policy 0, policy_version 640 (0.0026)
+[2023-07-04 15:45:28,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3276.9). Total num frames: 2629632. Throughput: 0: 877.9. Samples: 155728. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:45:28,447][18333] Avg episode reward: [(0, '21.312')]
+[2023-07-04 15:45:33,444][18333] Fps is (10 sec: 3687.0, 60 sec: 3481.6, 300 sec: 3297.9). Total num frames: 2650112. Throughput: 0: 875.6. Samples: 158490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:45:33,446][18333] Avg episode reward: [(0, '21.985')]
+[2023-07-04 15:45:36,100][22126] Updated weights for policy 0, policy_version 650 (0.0019)
+[2023-07-04 15:45:38,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3317.8). Total num frames: 2670592. Throughput: 0: 874.2. Samples: 165124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-07-04 15:45:38,446][18333] Avg episode reward: [(0, '21.232')]
+[2023-07-04 15:45:43,446][18333] Fps is (10 sec: 3685.4, 60 sec: 3618.0, 300 sec: 3316.8). Total num frames: 2686976. Throughput: 0: 876.4. Samples: 170188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:45:43,449][18333] Avg episode reward: [(0, '20.670')]
+[2023-07-04 15:45:48,444][18333] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3296.4). Total num frames: 2699264. Throughput: 0: 877.1. Samples: 172282. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:45:48,449][18333] Avg episode reward: [(0, '19.693')]
+[2023-07-04 15:45:49,212][22126] Updated weights for policy 0, policy_version 660 (0.0027)
+[2023-07-04 15:45:53,444][18333] Fps is (10 sec: 2867.9, 60 sec: 3345.1, 300 sec: 3295.9). Total num frames: 2715648. Throughput: 0: 876.9. Samples: 176604. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:45:53,446][18333] Avg episode reward: [(0, '18.681')]
+[2023-07-04 15:45:58,444][18333] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3332.7). Total num frames: 2740224. Throughput: 0: 877.8. Samples: 183250. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:45:58,453][18333] Avg episode reward: [(0, '17.263')]
+[2023-07-04 15:45:58,465][22113] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000669_2740224.pth...
+[2023-07-04 15:45:58,593][22113] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000490_2007040.pth
+[2023-07-04 15:45:59,224][22126] Updated weights for policy 0, policy_version 670 (0.0013)
+[2023-07-04 15:46:03,446][18333] Fps is (10 sec: 4094.9, 60 sec: 3549.7, 300 sec: 3331.4). Total num frames: 2756608. Throughput: 0: 878.6. Samples: 186570. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:46:03,451][18333] Avg episode reward: [(0, '17.009')]
+[2023-07-04 15:46:08,443][18333] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3330.3). Total num frames: 2772992. Throughput: 0: 872.7. Samples: 190908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:46:08,445][18333] Avg episode reward: [(0, '17.890')]
+[2023-07-04 15:46:12,802][22126] Updated weights for policy 0, policy_version 680 (0.0017)
+[2023-07-04 15:46:13,444][18333] Fps is (10 sec: 2868.0, 60 sec: 3413.3, 300 sec: 3311.7). Total num frames: 2785280. Throughput: 0: 874.4. Samples: 195076. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:46:13,447][18333] Avg episode reward: [(0, '18.755')]
+[2023-07-04 15:46:18,444][18333] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3328.0). Total num frames: 2805760. Throughput: 0: 880.7. Samples: 198124. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:46:18,451][18333] Avg episode reward: [(0, '19.946')]
+[2023-07-04 15:46:22,319][22126] Updated weights for policy 0, policy_version 690 (0.0015)
+[2023-07-04 15:46:23,444][18333] Fps is (10 sec: 4505.7, 60 sec: 3618.2, 300 sec: 3360.4). Total num frames: 2830336. Throughput: 0: 881.1. Samples: 204772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:46:23,446][18333] Avg episode reward: [(0, '21.407')]
+[2023-07-04 15:46:28,444][18333] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 3342.4). Total num frames: 2842624. Throughput: 0: 875.4. Samples: 209578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:46:28,446][18333] Avg episode reward: [(0, '21.690')]
+[2023-07-04 15:46:33,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3341.1). Total num frames: 2859008. Throughput: 0: 875.0. Samples: 211656. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:46:33,446][18333] Avg episode reward: [(0, '23.014')]
+[2023-07-04 15:46:36,290][22126] Updated weights for policy 0, policy_version 700 (0.0014)
+[2023-07-04 15:46:38,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3339.9). Total num frames: 2875392. Throughput: 0: 881.8. Samples: 216284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:46:38,449][18333] Avg episode reward: [(0, '22.682')]
+[2023-07-04 15:46:43,443][18333] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3354.1). Total num frames: 2895872. Throughput: 0: 880.4. Samples: 222870. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:46:43,447][18333] Avg episode reward: [(0, '23.860')]
+[2023-07-04 15:46:43,454][22113] Saving new best policy, reward=23.860!
+[2023-07-04 15:46:45,418][22126] Updated weights for policy 0, policy_version 710 (0.0012)
+[2023-07-04 15:46:48,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3367.9). Total num frames: 2916352. Throughput: 0: 876.8. Samples: 226024. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:46:48,446][18333] Avg episode reward: [(0, '24.045')]
+[2023-07-04 15:46:48,452][22113] Saving new best policy, reward=24.045!
+[2023-07-04 15:46:53,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3351.3). Total num frames: 2928640. Throughput: 0: 873.4. Samples: 230210. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:46:53,446][18333] Avg episode reward: [(0, '23.673')]
+[2023-07-04 15:46:58,444][18333] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3350.0). Total num frames: 2945024. Throughput: 0: 874.7. Samples: 234436. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:46:58,449][18333] Avg episode reward: [(0, '23.703')]
+[2023-07-04 15:46:59,263][22126] Updated weights for policy 0, policy_version 720 (0.0019)
+[2023-07-04 15:47:03,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3363.1). Total num frames: 2965504. Throughput: 0: 879.2. Samples: 237686. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:47:03,449][18333] Avg episode reward: [(0, '24.067')]
+[2023-07-04 15:47:03,454][22113] Saving new best policy, reward=24.067!
+[2023-07-04 15:47:08,444][18333] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3375.7). Total num frames: 2985984. Throughput: 0: 878.6. Samples: 244308. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:47:08,453][18333] Avg episode reward: [(0, '23.020')]
+[2023-07-04 15:47:08,772][22126] Updated weights for policy 0, policy_version 730 (0.0014)
+[2023-07-04 15:47:13,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3374.0). Total num frames: 3002368. Throughput: 0: 878.3. Samples: 249102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:47:13,451][18333] Avg episode reward: [(0, '23.164')]
+[2023-07-04 15:47:18,444][18333] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 3014656. Throughput: 0: 878.1. Samples: 251172. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:47:18,447][18333] Avg episode reward: [(0, '23.238')]
+[2023-07-04 15:47:22,534][22126] Updated weights for policy 0, policy_version 740 (0.0022)
+[2023-07-04 15:47:23,443][18333] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3485.1). Total num frames: 3035136. Throughput: 0: 878.0. Samples: 255792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:47:23,449][18333] Avg episode reward: [(0, '22.522')]
+[2023-07-04 15:47:28,444][18333] Fps is (10 sec: 4096.2, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3055616. Throughput: 0: 880.2. Samples: 262480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:47:28,446][18333] Avg episode reward: [(0, '23.105')]
+[2023-07-04 15:47:32,139][22126] Updated weights for policy 0, policy_version 750 (0.0012)
+[2023-07-04 15:47:33,446][18333] Fps is (10 sec: 3685.6, 60 sec: 3549.7, 300 sec: 3498.9). Total num frames: 3072000. Throughput: 0: 881.4. Samples: 265690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:47:33,454][18333] Avg episode reward: [(0, '22.716')]
+[2023-07-04 15:47:38,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 3088384. Throughput: 0: 881.5. Samples: 269878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:47:38,450][18333] Avg episode reward: [(0, '23.030')]
+[2023-07-04 15:47:43,443][18333] Fps is (10 sec: 3277.5, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3104768. Throughput: 0: 884.0. Samples: 274216. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:47:43,451][18333] Avg episode reward: [(0, '22.901')]
+[2023-07-04 15:47:45,377][22126] Updated weights for policy 0, policy_version 760 (0.0024)
+[2023-07-04 15:47:48,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3125248. Throughput: 0: 885.2. Samples: 277518. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:47:48,451][18333] Avg episode reward: [(0, '22.048')]
+[2023-07-04 15:47:53,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3145728. Throughput: 0: 885.5. Samples: 284154. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:47:53,449][18333] Avg episode reward: [(0, '22.074')]
+[2023-07-04 15:47:55,522][22126] Updated weights for policy 0, policy_version 770 (0.0012)
+[2023-07-04 15:47:58,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 3158016. Throughput: 0: 882.9. Samples: 288832. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-07-04 15:47:58,448][18333] Avg episode reward: [(0, '22.513')]
+[2023-07-04 15:47:58,459][22113] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000771_3158016.pth...
+[2023-07-04 15:47:58,641][22113] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000565_2314240.pth
+[2023-07-04 15:48:03,444][18333] Fps is (10 sec: 2867.0, 60 sec: 3481.6, 300 sec: 3498.9). Total num frames: 3174400. Throughput: 0: 880.9. Samples: 290812. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:48:03,454][18333] Avg episode reward: [(0, '22.144')]
+[2023-07-04 15:48:08,381][22126] Updated weights for policy 0, policy_version 780 (0.0017)
+[2023-07-04 15:48:08,443][18333] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3194880. Throughput: 0: 881.0. Samples: 295436. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:48:08,448][18333] Avg episode reward: [(0, '21.483')]
+[2023-07-04 15:48:13,444][18333] Fps is (10 sec: 4096.3, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3215360. Throughput: 0: 884.0. Samples: 302262. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:48:13,445][18333] Avg episode reward: [(0, '22.172')]
+[2023-07-04 15:48:18,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3499.0). Total num frames: 3231744. Throughput: 0: 885.5. Samples: 305536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:48:18,446][18333] Avg episode reward: [(0, '23.374')]
+[2023-07-04 15:48:18,935][22126] Updated weights for policy 0, policy_version 790 (0.0021)
+[2023-07-04 15:48:23,443][18333] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 3248128. Throughput: 0: 885.7. Samples: 309734. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:48:23,446][18333] Avg episode reward: [(0, '23.333')]
+[2023-07-04 15:48:28,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3499.0). Total num frames: 3260416. Throughput: 0: 884.2. Samples: 314006. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:48:28,447][18333] Avg episode reward: [(0, '23.753')]
+[2023-07-04 15:48:31,688][22126] Updated weights for policy 0, policy_version 800 (0.0014)
+[2023-07-04 15:48:33,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3512.8). Total num frames: 3280896. Throughput: 0: 876.0. Samples: 316940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:48:33,446][18333] Avg episode reward: [(0, '23.964')]
+[2023-07-04 15:48:38,444][18333] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3305472. Throughput: 0: 873.5. Samples: 323462. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:48:38,446][18333] Avg episode reward: [(0, '24.770')]
+[2023-07-04 15:48:38,458][22113] Saving new best policy, reward=24.770!
+[2023-07-04 15:48:42,139][22126] Updated weights for policy 0, policy_version 810 (0.0017)
+[2023-07-04 15:48:43,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 3317760. Throughput: 0: 879.9. Samples: 328428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:48:43,446][18333] Avg episode reward: [(0, '24.421')]
+[2023-07-04 15:48:48,444][18333] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3334144. Throughput: 0: 882.4. Samples: 330520. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
+[2023-07-04 15:48:48,449][18333] Avg episode reward: [(0, '23.703')]
+[2023-07-04 15:48:53,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 3350528. Throughput: 0: 882.3. Samples: 335138. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:48:53,448][18333] Avg episode reward: [(0, '23.282')]
+[2023-07-04 15:48:54,630][22126] Updated weights for policy 0, policy_version 820 (0.0031)
+[2023-07-04 15:48:58,444][18333] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3371008. Throughput: 0: 876.4. Samples: 341698. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
+[2023-07-04 15:48:58,447][18333] Avg episode reward: [(0, '23.090')]
+[2023-07-04 15:49:03,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3512.8). Total num frames: 3391488. Throughput: 0: 879.3. Samples: 345104. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:49:03,448][18333] Avg episode reward: [(0, '22.572')]
+[2023-07-04 15:49:05,498][22126] Updated weights for policy 0, policy_version 830 (0.0012)
+[2023-07-04 15:49:08,448][18333] Fps is (10 sec: 3275.2, 60 sec: 3481.3, 300 sec: 3498.9). Total num frames: 3403776. Throughput: 0: 883.2. Samples: 349484. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:49:08,451][18333] Avg episode reward: [(0, '23.881')]
+[2023-07-04 15:49:13,444][18333] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 3420160. Throughput: 0: 883.4. Samples: 353758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:49:13,447][18333] Avg episode reward: [(0, '23.167')]
+[2023-07-04 15:49:17,533][22126] Updated weights for policy 0, policy_version 840 (0.0022)
+[2023-07-04 15:49:18,444][18333] Fps is (10 sec: 3688.1, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3440640. Throughput: 0: 883.9. Samples: 356714. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:49:18,450][18333] Avg episode reward: [(0, '23.383')]
+[2023-07-04 15:49:23,444][18333] Fps is (10 sec: 4505.9, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 3465216. Throughput: 0: 889.1. Samples: 363470. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:49:23,450][18333] Avg episode reward: [(0, '22.627')]
+[2023-07-04 15:49:28,447][18333] Fps is (10 sec: 3685.1, 60 sec: 3617.9, 300 sec: 3512.8). Total num frames: 3477504. Throughput: 0: 890.7. Samples: 368512. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:49:28,450][18333] Avg episode reward: [(0, '22.567')]
+[2023-07-04 15:49:28,852][22126] Updated weights for policy 0, policy_version 850 (0.0016)
+[2023-07-04 15:49:33,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 3493888. Throughput: 0: 889.2. Samples: 370536. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:49:33,449][18333] Avg episode reward: [(0, '21.095')]
+[2023-07-04 15:49:38,444][18333] Fps is (10 sec: 3278.0, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 3510272. Throughput: 0: 886.3. Samples: 375020. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:49:38,446][18333] Avg episode reward: [(0, '19.977')]
+[2023-07-04 15:49:40,792][22126] Updated weights for policy 0, policy_version 860 (0.0012)
+[2023-07-04 15:49:43,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3530752. Throughput: 0: 888.2. Samples: 381666. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:49:43,448][18333] Avg episode reward: [(0, '21.107')]
+[2023-07-04 15:49:48,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 3551232. Throughput: 0: 888.3. Samples: 385078. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:49:48,450][18333] Avg episode reward: [(0, '21.707')]
+[2023-07-04 15:49:52,023][22126] Updated weights for policy 0, policy_version 870 (0.0027)
+[2023-07-04 15:49:53,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3563520. Throughput: 0: 889.1. Samples: 389490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:49:53,449][18333] Avg episode reward: [(0, '22.408')]
+[2023-07-04 15:49:58,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3579904. Throughput: 0: 890.4. Samples: 393826. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:49:58,450][18333] Avg episode reward: [(0, '22.977')]
+[2023-07-04 15:49:58,463][22113] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000874_3579904.pth...
+[2023-07-04 15:49:58,653][22113] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000669_2740224.pth
+[2023-07-04 15:50:03,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3600384. Throughput: 0: 886.4. Samples: 396600. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:50:03,450][18333] Avg episode reward: [(0, '23.005')]
+[2023-07-04 15:50:03,827][22126] Updated weights for policy 0, policy_version 880 (0.0014)
+[2023-07-04 15:50:08,445][18333] Fps is (10 sec: 4095.3, 60 sec: 3618.3, 300 sec: 3526.7). Total num frames: 3620864. Throughput: 0: 881.2. Samples: 403124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:50:08,448][18333] Avg episode reward: [(0, '24.137')]
+[2023-07-04 15:50:13,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3512.8). Total num frames: 3637248. Throughput: 0: 884.1. Samples: 408292. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:50:13,449][18333] Avg episode reward: [(0, '24.242')]
+[2023-07-04 15:50:15,313][22126] Updated weights for policy 0, policy_version 890 (0.0015)
+[2023-07-04 15:50:18,444][18333] Fps is (10 sec: 3277.4, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3653632. Throughput: 0: 886.8. Samples: 410444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:50:18,450][18333] Avg episode reward: [(0, '23.530')]
+[2023-07-04 15:50:23,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 3670016. Throughput: 0: 883.8. Samples: 414790. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:50:23,448][18333] Avg episode reward: [(0, '22.577')]
+[2023-07-04 15:50:26,894][22126] Updated weights for policy 0, policy_version 900 (0.0023)
+[2023-07-04 15:50:28,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3550.1, 300 sec: 3526.7). Total num frames: 3690496. Throughput: 0: 880.9. Samples: 421306. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:50:28,446][18333] Avg episode reward: [(0, '23.107')]
+[2023-07-04 15:50:33,444][18333] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3710976. Throughput: 0: 878.8. Samples: 424622. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:50:33,446][18333] Avg episode reward: [(0, '24.071')]
+[2023-07-04 15:50:38,425][22126] Updated weights for policy 0, policy_version 910 (0.0012)
+[2023-07-04 15:50:38,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3526.8). Total num frames: 3727360. Throughput: 0: 882.0. Samples: 429182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-07-04 15:50:38,445][18333] Avg episode reward: [(0, '23.988')]
+[2023-07-04 15:50:43,445][18333] Fps is (10 sec: 2866.7, 60 sec: 3481.5, 300 sec: 3526.7). Total num frames: 3739648. Throughput: 0: 882.1. Samples: 433522. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:50:43,448][18333] Avg episode reward: [(0, '23.037')]
+[2023-07-04 15:50:48,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 3760128. Throughput: 0: 879.2. Samples: 436166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:50:48,451][18333] Avg episode reward: [(0, '24.210')]
+[2023-07-04 15:50:49,985][22126] Updated weights for policy 0, policy_version 920 (0.0040)
+[2023-07-04 15:50:53,444][18333] Fps is (10 sec: 4096.7, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3780608. Throughput: 0: 883.6. Samples: 442886. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:50:53,452][18333] Avg episode reward: [(0, '25.008')]
+[2023-07-04 15:50:53,455][22113] Saving new best policy, reward=25.008!
+[2023-07-04 15:50:58,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3526.8). Total num frames: 3796992. Throughput: 0: 882.3. Samples: 447996. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:50:58,450][18333] Avg episode reward: [(0, '24.569')]
+[2023-07-04 15:51:02,192][22126] Updated weights for policy 0, policy_version 930 (0.0018)
+[2023-07-04 15:51:03,444][18333] Fps is (10 sec: 2867.0, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3809280. Throughput: 0: 880.2. Samples: 450052. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-07-04 15:51:03,449][18333] Avg episode reward: [(0, '24.889')]
+[2023-07-04 15:51:08,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3540.6). Total num frames: 3829760. Throughput: 0: 878.9. Samples: 454340. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:51:08,446][18333] Avg episode reward: [(0, '23.066')]
+[2023-07-04 15:51:13,187][22126] Updated weights for policy 0, policy_version 940 (0.0021)
+[2023-07-04 15:51:13,444][18333] Fps is (10 sec: 4096.3, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 3850240. Throughput: 0: 883.0. Samples: 461040. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:51:13,446][18333] Avg episode reward: [(0, '21.575')]
+[2023-07-04 15:51:18,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3870720. Throughput: 0: 884.0. Samples: 464404. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:51:18,450][18333] Avg episode reward: [(0, '21.145')]
+[2023-07-04 15:51:23,444][18333] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3883008. Throughput: 0: 887.0. Samples: 469096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-07-04 15:51:23,450][18333] Avg episode reward: [(0, '21.746')]
+[2023-07-04 15:51:25,562][22126] Updated weights for policy 0, policy_version 950 (0.0019)
+[2023-07-04 15:51:28,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3899392. Throughput: 0: 883.7. Samples: 473286. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:51:28,445][18333] Avg episode reward: [(0, '20.778')]
+[2023-07-04 15:51:33,443][18333] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 3919872. Throughput: 0: 882.5. Samples: 475878. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-07-04 15:51:33,447][18333] Avg episode reward: [(0, '22.279')]
+[2023-07-04 15:51:36,134][22126] Updated weights for policy 0, policy_version 960 (0.0030)
+[2023-07-04 15:51:38,444][18333] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 3940352. Throughput: 0: 883.6. Samples: 482650. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:51:38,446][18333] Avg episode reward: [(0, '22.723')]
+[2023-07-04 15:51:43,444][18333] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3526.7). Total num frames: 3956736. Throughput: 0: 889.6. Samples: 488030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-07-04 15:51:43,449][18333] Avg episode reward: [(0, '23.297')]
+[2023-07-04 15:51:48,444][18333] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3969024. Throughput: 0: 890.3. Samples: 490116. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-07-04 15:51:48,450][18333] Avg episode reward: [(0, '24.658')]
+[2023-07-04 15:51:48,604][22126] Updated weights for policy 0, policy_version 970 (0.0014)
+[2023-07-04 15:51:53,444][18333] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 3989504. Throughput: 0: 890.2. Samples: 494398. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-07-04 15:51:53,446][18333] Avg episode reward: [(0, '23.262')]
+[2023-07-04 15:51:57,392][22113] Stopping Batcher_0...
+[2023-07-04 15:51:57,394][22113] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-07-04 15:51:57,395][18333] Component Batcher_0 stopped!
+[2023-07-04 15:51:57,395][22113] Loop batcher_evt_loop terminating...
+[2023-07-04 15:51:57,459][18333] Component RolloutWorker_w0 stopped!
+[2023-07-04 15:51:57,460][22138] Stopping RolloutWorker_w7...
+[2023-07-04 15:51:57,465][18333] Component RolloutWorker_w7 stopped!
+[2023-07-04 15:51:57,473][22138] Loop rollout_proc7_evt_loop terminating...
+[2023-07-04 15:51:57,470][22130] Stopping RolloutWorker_w0...
+[2023-07-04 15:51:57,479][18333] Component RolloutWorker_w2 stopped!
+[2023-07-04 15:51:57,484][22134] Stopping RolloutWorker_w2...
+[2023-07-04 15:51:57,478][22126] Weights refcount: 2 0
+[2023-07-04 15:51:57,474][22130] Loop rollout_proc0_evt_loop terminating...
+[2023-07-04 15:51:57,492][22136] Stopping RolloutWorker_w5...
+[2023-07-04 15:51:57,491][18333] Component InferenceWorker_p0-w0 stopped!
+[2023-07-04 15:51:57,496][22132] Stopping RolloutWorker_w3...
+[2023-07-04 15:51:57,496][18333] Component RolloutWorker_w5 stopped!
+[2023-07-04 15:51:57,500][18333] Component RolloutWorker_w3 stopped!
+[2023-07-04 15:51:57,493][22136] Loop rollout_proc5_evt_loop terminating...
+[2023-07-04 15:51:57,497][22132] Loop rollout_proc3_evt_loop terminating...
+[2023-07-04 15:51:57,505][22126] Stopping InferenceWorker_p0-w0...
+[2023-07-04 15:51:57,506][18333] Component RolloutWorker_w1 stopped!
+[2023-07-04 15:51:57,506][22133] Stopping RolloutWorker_w1...
+[2023-07-04 15:51:57,505][22126] Loop inference_proc0-0_evt_loop terminating...
+[2023-07-04 15:51:57,485][22134] Loop rollout_proc2_evt_loop terminating...
+[2023-07-04 15:51:57,510][22133] Loop rollout_proc1_evt_loop terminating...
+[2023-07-04 15:51:57,520][18333] Component RolloutWorker_w4 stopped!
+[2023-07-04 15:51:57,524][22135] Stopping RolloutWorker_w4...
+[2023-07-04 15:51:57,525][18333] Component RolloutWorker_w6 stopped!
+[2023-07-04 15:51:57,531][22137] Stopping RolloutWorker_w6...
+[2023-07-04 15:51:57,538][22135] Loop rollout_proc4_evt_loop terminating...
+[2023-07-04 15:51:57,532][22137] Loop rollout_proc6_evt_loop terminating...
+[2023-07-04 15:51:57,552][22113] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000771_3158016.pth
+[2023-07-04 15:51:57,564][22113] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-07-04 15:51:57,729][18333] Component LearnerWorker_p0 stopped!
+[2023-07-04 15:51:57,736][18333] Waiting for process learner_proc0 to stop...
+[2023-07-04 15:51:57,741][22113] Stopping LearnerWorker_p0...
+[2023-07-04 15:51:57,741][22113] Loop learner_proc0_evt_loop terminating...
+[2023-07-04 15:51:58,816][18333] Waiting for process inference_proc0-0 to join...
+[2023-07-04 15:51:58,821][18333] Waiting for process rollout_proc0 to join...
+[2023-07-04 15:52:00,036][18333] Waiting for process rollout_proc1 to join...
+[2023-07-04 15:52:00,199][18333] Waiting for process rollout_proc2 to join...
+[2023-07-04 15:52:00,201][18333] Waiting for process rollout_proc3 to join...
+[2023-07-04 15:52:00,205][18333] Waiting for process rollout_proc4 to join...
+[2023-07-04 15:52:00,208][18333] Waiting for process rollout_proc5 to join...
+[2023-07-04 15:52:00,211][18333] Waiting for process rollout_proc6 to join...
+[2023-07-04 15:52:00,215][18333] Waiting for process rollout_proc7 to join...
+[2023-07-04 15:52:00,217][18333] Batcher 0 profile tree view:
+batching: 13.2010, releasing_batches: 0.0137
+[2023-07-04 15:52:00,228][18333] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0055
+  wait_policy_total: 279.2133
+update_model: 4.1925
+  weight_update: 0.0025
+one_step: 0.0025
+  handle_policy_step: 276.3185
+    deserialize: 7.4829, stack: 1.5020, obs_to_device_normalize: 59.2136, forward: 138.0503, send_messages: 14.2878
+    prepare_outputs: 42.0752
+      to_cpu: 25.6465
+[2023-07-04 15:52:00,230][18333] Learner 0 profile tree view:
+misc: 0.0025, prepare_batch: 9.8375
+train: 39.7930
+  epoch_init: 0.0146, minibatch_init: 0.0032, losses_postprocess: 0.2770, kl_divergence: 0.3191, after_optimizer: 1.9968
+  calculate_losses: 12.3821
+    losses_init: 0.0018, forward_head: 1.0349, bptt_initial: 7.7057, tail: 0.5452, advantages_returns: 0.1694, losses: 1.6271
+    bptt: 1.1473
+      bptt_forward_core: 1.0992
+  update: 24.4481
+    clip: 0.7666
+[2023-07-04 15:52:00,231][18333] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.2117, enqueue_policy_requests: 75.9103, env_step: 429.9611, overhead: 11.8503, complete_rollouts: 3.8320
+save_policy_outputs: 10.6986
+  split_output_tensors: 5.2931
+[2023-07-04 15:52:00,234][18333] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.1973, enqueue_policy_requests: 80.5694, env_step: 427.3777, overhead: 11.8470, complete_rollouts: 3.6744
+save_policy_outputs: 10.4136
+  split_output_tensors: 5.1270
+[2023-07-04 15:52:00,236][18333] Loop Runner_EvtLoop terminating...
+[2023-07-04 15:52:00,239][18333] Runner profile tree view:
+main_loop: 600.1708
+[2023-07-04 15:52:00,244][18333] Collected {0: 4005888}, FPS: 3330.5
+[2023-07-04 15:52:13,757][18333] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-07-04 15:52:13,759][18333] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-07-04 15:52:13,761][18333] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-07-04 15:52:13,763][18333] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-07-04 15:52:13,764][18333] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-07-04 15:52:13,766][18333] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-07-04 15:52:13,768][18333] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-07-04 15:52:13,770][18333] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-07-04 15:52:13,771][18333] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-07-04 15:52:13,772][18333] Adding new argument 'hf_repository'='HilbertS/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-07-04 15:52:13,773][18333] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-07-04 15:52:13,775][18333] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-07-04 15:52:13,776][18333] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-07-04 15:52:13,777][18333] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-07-04 15:52:13,778][18333] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-07-04 15:52:13,801][18333] RunningMeanStd input shape: (3, 72, 128)
+[2023-07-04 15:52:13,803][18333] RunningMeanStd input shape: (1,)
+[2023-07-04 15:52:13,817][18333] ConvEncoder: input_channels=3
+[2023-07-04 15:52:13,852][18333] Conv encoder output size: 512
+[2023-07-04 15:52:13,853][18333] Policy head output size: 512
+[2023-07-04 15:52:13,874][18333] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-07-04 15:52:14,537][18333] Num frames 100...
+[2023-07-04 15:52:14,657][18333] Num frames 200...
+[2023-07-04 15:52:14,787][18333] Num frames 300...
+[2023-07-04 15:52:14,937][18333] Num frames 400...
+[2023-07-04 15:52:15,068][18333] Num frames 500...
+[2023-07-04 15:52:15,218][18333] Num frames 600...
+[2023-07-04 15:52:15,353][18333] Num frames 700...
+[2023-07-04 15:52:15,493][18333] Num frames 800...
+[2023-07-04 15:52:15,632][18333] Num frames 900...
+[2023-07-04 15:52:15,754][18333] Num frames 1000...
+[2023-07-04 15:52:15,938][18333] Num frames 1100...
+[2023-07-04 15:52:16,144][18333] Num frames 1200...
+[2023-07-04 15:52:16,329][18333] Num frames 1300...
+[2023-07-04 15:52:16,515][18333] Num frames 1400...
+[2023-07-04 15:52:16,694][18333] Num frames 1500...
+[2023-07-04 15:52:16,885][18333] Num frames 1600...
+[2023-07-04 15:52:17,064][18333] Num frames 1700...
+[2023-07-04 15:52:17,250][18333] Num frames 1800...
+[2023-07-04 15:52:17,430][18333] Num frames 1900...
+[2023-07-04 15:52:17,609][18333] Num frames 2000...
+[2023-07-04 15:52:17,785][18333] Num frames 2100...
+[2023-07-04 15:52:17,840][18333] Avg episode rewards: #0: 54.999, true rewards: #0: 21.000
+[2023-07-04 15:52:17,843][18333] Avg episode reward: 54.999, avg true_objective: 21.000
+[2023-07-04 15:52:18,019][18333] Num frames 2200...
+[2023-07-04 15:52:18,202][18333] Num frames 2300...
+[2023-07-04 15:52:18,390][18333] Num frames 2400...
+[2023-07-04 15:52:18,579][18333] Num frames 2500...
+[2023-07-04 15:52:18,764][18333] Num frames 2600...
+[2023-07-04 15:52:18,945][18333] Num frames 2700...
+[2023-07-04 15:52:19,127][18333] Num frames 2800...
+[2023-07-04 15:52:19,311][18333] Num frames 2900...
+[2023-07-04 15:52:19,510][18333] Num frames 3000...
+[2023-07-04 15:52:19,694][18333] Num frames 3100...
+[2023-07-04 15:52:19,882][18333] Num frames 3200...
+[2023-07-04 15:52:20,067][18333] Num frames 3300...
+[2023-07-04 15:52:20,251][18333] Num frames 3400...
+[2023-07-04 15:52:20,436][18333] Num frames 3500...
+[2023-07-04 15:52:20,617][18333] Num frames 3600...
+[2023-07-04 15:52:20,802][18333] Num frames 3700...
+[2023-07-04 15:52:21,035][18333] Avg episode rewards: #0: 48.979, true rewards: #0: 18.980
+[2023-07-04 15:52:21,037][18333] Avg episode reward: 48.979, avg true_objective: 18.980
+[2023-07-04 15:52:21,047][18333] Num frames 3800...
+[2023-07-04 15:52:21,222][18333] Num frames 3900...
+[2023-07-04 15:52:21,353][18333] Num frames 4000...
+[2023-07-04 15:52:21,484][18333] Avg episode rewards: #0: 33.506, true rewards: #0: 13.507
+[2023-07-04 15:52:21,486][18333] Avg episode reward: 33.506, avg true_objective: 13.507
+[2023-07-04 15:52:21,552][18333] Num frames 4100...
+[2023-07-04 15:52:21,678][18333] Num frames 4200...
+[2023-07-04 15:52:21,808][18333] Num frames 4300...
+[2023-07-04 15:52:21,935][18333] Num frames 4400...
+[2023-07-04 15:52:22,072][18333] Num frames 4500...
+[2023-07-04 15:52:22,198][18333] Num frames 4600...
+[2023-07-04 15:52:22,332][18333] Num frames 4700...
+[2023-07-04 15:52:22,462][18333] Num frames 4800...
+[2023-07-04 15:52:22,603][18333] Num frames 4900...
+[2023-07-04 15:52:22,735][18333] Num frames 5000...
+[2023-07-04 15:52:22,869][18333] Num frames 5100...
+[2023-07-04 15:52:23,009][18333] Num frames 5200...
+[2023-07-04 15:52:23,142][18333] Num frames 5300...
+[2023-07-04 15:52:23,285][18333] Num frames 5400...
+[2023-07-04 15:52:23,422][18333] Num frames 5500...
+[2023-07-04 15:52:23,551][18333] Num frames 5600...
+[2023-07-04 15:52:23,632][18333] Avg episode rewards: #0: 35.050, true rewards: #0: 14.050
+[2023-07-04 15:52:23,634][18333] Avg episode reward: 35.050, avg true_objective: 14.050
+[2023-07-04 15:52:23,740][18333] Num frames 5700...
+[2023-07-04 15:52:23,866][18333] Num frames 5800...
+[2023-07-04 15:52:23,992][18333] Num frames 5900...
+[2023-07-04 15:52:24,140][18333] Avg episode rewards: #0: 28.944, true rewards: #0: 11.944
+[2023-07-04 15:52:24,145][18333] Avg episode reward: 28.944, avg true_objective: 11.944
+[2023-07-04 15:52:24,180][18333] Num frames 6000...
+[2023-07-04 15:52:24,305][18333] Num frames 6100...
+[2023-07-04 15:52:24,485][18333] Avg episode rewards: #0: 24.493, true rewards: #0: 10.327
+[2023-07-04 15:52:24,487][18333] Avg episode reward: 24.493, avg true_objective: 10.327
+[2023-07-04 15:52:24,497][18333] Num frames 6200...
+[2023-07-04 15:52:24,632][18333] Num frames 6300...
+[2023-07-04 15:52:24,754][18333] Num frames 6400...
+[2023-07-04 15:52:24,880][18333] Num frames 6500...
+[2023-07-04 15:52:24,999][18333] Num frames 6600...
+[2023-07-04 15:52:25,128][18333] Num frames 6700...
+[2023-07-04 15:52:25,257][18333] Num frames 6800...
+[2023-07-04 15:52:25,402][18333] Num frames 6900...
+[2023-07-04 15:52:25,545][18333] Num frames 7000...
+[2023-07-04 15:52:25,669][18333] Num frames 7100...
+[2023-07-04 15:52:25,796][18333] Num frames 7200...
+[2023-07-04 15:52:25,922][18333] Num frames 7300...
+[2023-07-04 15:52:26,053][18333] Num frames 7400...
+[2023-07-04 15:52:26,199][18333] Num frames 7500...
+[2023-07-04 15:52:26,327][18333] Num frames 7600...
+[2023-07-04 15:52:26,475][18333] Avg episode rewards: #0: 26.954, true rewards: #0: 10.954
+[2023-07-04 15:52:26,478][18333] Avg episode reward: 26.954, avg true_objective: 10.954
+[2023-07-04 15:52:26,517][18333] Num frames 7700...
+[2023-07-04 15:52:26,643][18333] Num frames 7800...
+[2023-07-04 15:52:26,774][18333] Num frames 7900...
+[2023-07-04 15:52:26,895][18333] Num frames 8000...
+[2023-07-04 15:52:27,014][18333] Num frames 8100...
+[2023-07-04 15:52:27,138][18333] Num frames 8200...
+[2023-07-04 15:52:27,258][18333] Num frames 8300...
+[2023-07-04 15:52:27,380][18333] Num frames 8400...
+[2023-07-04 15:52:27,517][18333] Num frames 8500...
+[2023-07-04 15:52:27,656][18333] Avg episode rewards: #0: 25.955, true rewards: #0: 10.705
+[2023-07-04 15:52:27,658][18333] Avg episode reward: 25.955, avg true_objective: 10.705
+[2023-07-04 15:52:27,703][18333] Num frames 8600...
+[2023-07-04 15:52:27,870][18333] Avg episode rewards: #0: 23.213, true rewards: #0: 9.658
+[2023-07-04 15:52:27,872][18333] Avg episode reward: 23.213, avg true_objective: 9.658
+[2023-07-04 15:52:27,885][18333] Num frames 8700...
+[2023-07-04 15:52:28,010][18333] Num frames 8800...
+[2023-07-04 15:52:28,130][18333] Num frames 8900...
+[2023-07-04 15:52:28,258][18333] Num frames 9000...
+[2023-07-04 15:52:28,381][18333] Num frames 9100...
+[2023-07-04 15:52:28,518][18333] Num frames 9200...
+[2023-07-04 15:52:28,579][18333] Avg episode rewards: #0: 21.704, true rewards: #0: 9.204
+[2023-07-04 15:52:28,581][18333] Avg episode reward: 21.704, avg true_objective: 9.204
+[2023-07-04 15:53:26,952][18333] Replay video saved to /content/train_dir/default_experiment/replay.mp4!