Upload . with huggingface_hub

.summary/0/events.out.tfevents.1677226122.pop-os

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee1a1ceac24b1cdd5511470eba4f682f4a31b2f1c5a5f77abee92d119944a3c
+size 226374

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 8.70 +/- 5.10
+      value: 12.47 +/- 6.32
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000001131_4632576_reward_31.137.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6572c07a4e95d77ce151d2fb8f63327845b28353c7651a6e48320251fe81e3e7
+size 34928806

checkpoint_p0/checkpoint_000001284_5259264.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd558f9840d8b908cbebd30bb7769592f04d00dd63108e4e38da21a4a257775
+size 34929220

checkpoint_p0/checkpoint_000001361_5574656.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b462b48f3f461d4c1b5463f1bdc60d6fccb151fcc820851e31ed4e9ac9f170
+size 34929220

sf_log.txt

@@ -831,3 +831,724 @@ main_loop: 47.3880
 [2023-02-24 08:07:49,763][795538] Avg episode rewards: #0: 18.704, true rewards: #0: 8.704
 [2023-02-24 08:07:49,764][795538] Avg episode reward: 18.704, avg true_objective: 8.704
 [2023-02-24 08:07:53,791][795538] Replay video saved to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!
+[2023-02-24 08:08:19,273][795538] The model has been pushed to https://huggingface.co/chqmatteo/rl_course_vizdoom_health_gathering_supreme
+[2023-02-24 08:08:42,140][795538] Environment doom_basic already registered, overwriting...
+[2023-02-24 08:08:42,141][795538] Environment doom_two_colors_easy already registered, overwriting...
+[2023-02-24 08:08:42,142][795538] Environment doom_two_colors_hard already registered, overwriting...
+[2023-02-24 08:08:42,142][795538] Environment doom_dm already registered, overwriting...
+[2023-02-24 08:08:42,142][795538] Environment doom_dwango5 already registered, overwriting...
+[2023-02-24 08:08:42,143][795538] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2023-02-24 08:08:42,143][795538] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2023-02-24 08:08:42,143][795538] Environment doom_my_way_home already registered, overwriting...
+[2023-02-24 08:08:42,144][795538] Environment doom_deadly_corridor already registered, overwriting...
+[2023-02-24 08:08:42,144][795538] Environment doom_defend_the_center already registered, overwriting...
+[2023-02-24 08:08:42,144][795538] Environment doom_defend_the_line already registered, overwriting...
+[2023-02-24 08:08:42,145][795538] Environment doom_health_gathering already registered, overwriting...
+[2023-02-24 08:08:42,145][795538] Environment doom_health_gathering_supreme already registered, overwriting...
+[2023-02-24 08:08:42,145][795538] Environment doom_battle already registered, overwriting...
+[2023-02-24 08:08:42,146][795538] Environment doom_battle2 already registered, overwriting...
+[2023-02-24 08:08:42,146][795538] Environment doom_duel_bots already registered, overwriting...
+[2023-02-24 08:08:42,146][795538] Environment doom_deathmatch_bots already registered, overwriting...
+[2023-02-24 08:08:42,147][795538] Environment doom_duel already registered, overwriting...
+[2023-02-24 08:08:42,147][795538] Environment doom_deathmatch_full already registered, overwriting...
+[2023-02-24 08:08:42,148][795538] Environment doom_benchmark already registered, overwriting...
+[2023-02-24 08:08:42,148][795538] register_encoder_factory: <function make_vizdoom_encoder at 0x7efd09ae12d0>
+[2023-02-24 08:08:42,156][795538] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
+[2023-02-24 08:08:42,157][795538] Experiment dir /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment already exists!
+[2023-02-24 08:08:42,158][795538] Resuming existing experiment from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment...
+[2023-02-24 08:08:42,158][795538] Weights and Biases integration disabled
+[2023-02-24 08:08:42,159][795538] Environment var CUDA_VISIBLE_DEVICES is 1
+[2023-02-24 08:08:43,053][795538] Starting experiment with the following configuration:
+help=False
+algo=APPO
+env=doom_health_gathering_supreme
+experiment=default_experiment
+train_dir=/mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/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=40000000
+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=1a2374cbd09490752b14aee6fdecfe64db411550
+git_repo_name=https://github.com/huggingface/deep-rl-class.git
+[2023-02-24 08:08:43,053][795538] Saving configuration to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json...
+[2023-02-24 08:08:43,222][795538] Rollout worker 0 uses device cpu
+[2023-02-24 08:08:43,223][795538] Rollout worker 1 uses device cpu
+[2023-02-24 08:08:43,223][795538] Rollout worker 2 uses device cpu
+[2023-02-24 08:08:43,223][795538] Rollout worker 3 uses device cpu
+[2023-02-24 08:08:43,224][795538] Rollout worker 4 uses device cpu
+[2023-02-24 08:08:43,224][795538] Rollout worker 5 uses device cpu
+[2023-02-24 08:08:43,225][795538] Rollout worker 6 uses device cpu
+[2023-02-24 08:08:43,225][795538] Rollout worker 7 uses device cpu
+[2023-02-24 08:08:43,257][795538] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:08:43,258][795538] InferenceWorker_p0-w0: min num requests: 2
+[2023-02-24 08:08:43,278][795538] Starting all processes...
+[2023-02-24 08:08:43,278][795538] Starting process learner_proc0
+[2023-02-24 08:08:43,328][795538] Starting all processes...
+[2023-02-24 08:08:43,329][795538] Starting process inference_proc0-0
+[2023-02-24 08:08:43,330][795538] Starting process rollout_proc0
+[2023-02-24 08:08:43,330][795538] Starting process rollout_proc1
+[2023-02-24 08:08:43,330][795538] Starting process rollout_proc2
+[2023-02-24 08:08:43,331][795538] Starting process rollout_proc3
+[2023-02-24 08:08:43,331][795538] Starting process rollout_proc4
+[2023-02-24 08:08:43,331][795538] Starting process rollout_proc5
+[2023-02-24 08:08:43,331][795538] Starting process rollout_proc6
+[2023-02-24 08:08:43,331][795538] Starting process rollout_proc7
+[2023-02-24 08:08:44,462][796098] Low niceness requires sudo!
+[2023-02-24 08:08:44,463][796098] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:08:44,463][796098] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for learning process 0
+[2023-02-24 08:08:44,484][796098] Num visible devices: 1
+[2023-02-24 08:08:44,522][796098] Starting seed is not provided
+[2023-02-24 08:08:44,522][796098] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:08:44,523][796098] Initializing actor-critic model on device cuda:0
+[2023-02-24 08:08:44,523][796098] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 08:08:44,524][796098] RunningMeanStd input shape: (1,)
+[2023-02-24 08:08:44,549][796098] ConvEncoder: input_channels=3
+[2023-02-24 08:08:44,706][796112] Low niceness requires sudo!
+[2023-02-24 08:08:44,707][796112] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:08:44,707][796112] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for inference process 0
+[2023-02-24 08:08:44,724][796112] Num visible devices: 1
+[2023-02-24 08:08:44,767][796113] Worker 2 uses CPU cores [2]
+[2023-02-24 08:08:44,802][796098] Conv encoder output size: 512
+[2023-02-24 08:08:44,810][796098] Policy head output size: 512
+[2023-02-24 08:08:44,842][796098] Created Actor Critic model with architecture:
+[2023-02-24 08:08:44,843][796098] 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)
+  )
+)
+[2023-02-24 08:08:44,946][796119] Worker 6 uses CPU cores [6]
+[2023-02-24 08:08:44,948][796117] Worker 5 uses CPU cores [5]
+[2023-02-24 08:08:45,059][796114] Worker 1 uses CPU cores [1]
+[2023-02-24 08:08:45,108][796115] Worker 3 uses CPU cores [3]
+[2023-02-24 08:08:45,108][796111] Worker 0 uses CPU cores [0]
+[2023-02-24 08:08:45,114][796118] Worker 4 uses CPU cores [4]
+[2023-02-24 08:08:45,164][796116] Worker 7 uses CPU cores [7]
+[2023-02-24 08:08:46,945][796098] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-02-24 08:08:46,945][796098] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000403_1650688.pth...
+[2023-02-24 08:08:47,005][796098] Loading model from checkpoint
+[2023-02-24 08:08:47,007][796098] Loaded experiment state at self.train_step=403, self.env_steps=1650688
+[2023-02-24 08:08:47,007][796098] Initialized policy 0 weights for model version 403
+[2023-02-24 08:08:47,008][796098] LearnerWorker_p0 finished initialization!
+[2023-02-24 08:08:47,008][796098] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:08:47,160][795538] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 1650688. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-24 08:08:48,101][796112] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 08:08:48,101][796112] RunningMeanStd input shape: (1,)
+[2023-02-24 08:08:48,108][796112] ConvEncoder: input_channels=3
+[2023-02-24 08:08:48,178][796112] Conv encoder output size: 512
+[2023-02-24 08:08:48,178][796112] Policy head output size: 512
+[2023-02-24 08:08:49,152][795538] Inference worker 0-0 is ready!
+[2023-02-24 08:08:49,152][795538] All inference workers are ready! Signal rollout workers to start!
+[2023-02-24 08:08:49,171][796116] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:08:49,171][796118] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:08:49,170][796115] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:08:49,171][796119] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:08:49,175][796111] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:08:49,176][796117] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:08:49,204][796113] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:08:49,205][796114] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:08:49,421][796115] Decorrelating experience for 0 frames...
+[2023-02-24 08:08:49,457][796116] Decorrelating experience for 0 frames...
+[2023-02-24 08:08:49,467][796114] Decorrelating experience for 0 frames...
+[2023-02-24 08:08:49,471][796118] Decorrelating experience for 0 frames...
+[2023-02-24 08:08:49,475][796117] Decorrelating experience for 0 frames...
+[2023-02-24 08:08:49,653][796115] Decorrelating experience for 32 frames...
+[2023-02-24 08:08:49,732][796116] Decorrelating experience for 32 frames...
+[2023-02-24 08:08:49,752][796118] Decorrelating experience for 32 frames...
+[2023-02-24 08:08:49,758][796117] Decorrelating experience for 32 frames...
+[2023-02-24 08:08:49,795][796119] Decorrelating experience for 0 frames...
+[2023-02-24 08:08:49,932][796114] Decorrelating experience for 32 frames...
+[2023-02-24 08:08:50,017][796111] Decorrelating experience for 0 frames...
+[2023-02-24 08:08:50,033][796116] Decorrelating experience for 64 frames...
+[2023-02-24 08:08:50,071][796119] Decorrelating experience for 32 frames...
+[2023-02-24 08:08:50,078][796115] Decorrelating experience for 64 frames...
+[2023-02-24 08:08:50,109][796113] Decorrelating experience for 0 frames...
+[2023-02-24 08:08:50,145][796118] Decorrelating experience for 64 frames...
+[2023-02-24 08:08:50,241][796111] Decorrelating experience for 32 frames...
+[2023-02-24 08:08:50,325][796116] Decorrelating experience for 96 frames...
+[2023-02-24 08:08:50,338][796115] Decorrelating experience for 96 frames...
+[2023-02-24 08:08:50,377][796117] Decorrelating experience for 64 frames...
+[2023-02-24 08:08:50,445][796118] Decorrelating experience for 96 frames...
+[2023-02-24 08:08:50,502][796111] Decorrelating experience for 64 frames...
+[2023-02-24 08:08:50,527][796119] Decorrelating experience for 64 frames...
+[2023-02-24 08:08:50,669][796117] Decorrelating experience for 96 frames...
+[2023-02-24 08:08:50,704][796113] Decorrelating experience for 32 frames...
+[2023-02-24 08:08:50,716][796114] Decorrelating experience for 64 frames...
+[2023-02-24 08:08:50,804][796111] Decorrelating experience for 96 frames...
+[2023-02-24 08:08:50,833][796119] Decorrelating experience for 96 frames...
+[2023-02-24 08:08:50,958][796113] Decorrelating experience for 64 frames...
+[2023-02-24 08:08:50,977][796114] Decorrelating experience for 96 frames...
+[2023-02-24 08:08:51,210][796113] Decorrelating experience for 96 frames...
+[2023-02-24 08:08:52,160][795538] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 1650688. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-24 08:08:52,161][795538] Avg episode reward: [(0, '0.903')]
+[2023-02-24 08:08:52,586][796098] Signal inference workers to stop experience collection...
+[2023-02-24 08:08:52,593][796112] InferenceWorker_p0-w0: stopping experience collection
+[2023-02-24 08:08:54,537][796098] Signal inference workers to resume experience collection...
+[2023-02-24 08:08:54,538][796112] InferenceWorker_p0-w0: resuming experience collection
+[2023-02-24 08:08:57,090][796112] Updated weights for policy 0, policy_version 413 (0.0247)
+[2023-02-24 08:08:57,160][795538] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 1691648. Throughput: 0: 332.8. Samples: 3328. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-24 08:08:57,161][795538] Avg episode reward: [(0, '8.033')]
+[2023-02-24 08:08:59,657][796112] Updated weights for policy 0, policy_version 423 (0.0013)
+[2023-02-24 08:09:02,160][795538] Fps is (10 sec: 11878.4, 60 sec: 7918.9, 300 sec: 7918.9). Total num frames: 1769472. Throughput: 0: 1818.4. Samples: 27276. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:09:02,161][795538] Avg episode reward: [(0, '21.201')]
+[2023-02-24 08:09:02,163][796098] Saving new best policy, reward=21.201!
+[2023-02-24 08:09:02,326][796112] Updated weights for policy 0, policy_version 433 (0.0009)
+[2023-02-24 08:09:03,254][795538] Heartbeat connected on LearnerWorker_p0
+[2023-02-24 08:09:03,262][795538] Heartbeat connected on InferenceWorker_p0-w0
+[2023-02-24 08:09:03,263][795538] Heartbeat connected on Batcher_0
+[2023-02-24 08:09:03,264][795538] Heartbeat connected on RolloutWorker_w1
+[2023-02-24 08:09:03,266][795538] Heartbeat connected on RolloutWorker_w2
+[2023-02-24 08:09:03,269][795538] Heartbeat connected on RolloutWorker_w3
+[2023-02-24 08:09:03,271][795538] Heartbeat connected on RolloutWorker_w0
+[2023-02-24 08:09:03,275][795538] Heartbeat connected on RolloutWorker_w5
+[2023-02-24 08:09:03,276][795538] Heartbeat connected on RolloutWorker_w4
+[2023-02-24 08:09:03,280][795538] Heartbeat connected on RolloutWorker_w7
+[2023-02-24 08:09:03,282][795538] Heartbeat connected on RolloutWorker_w6
+[2023-02-24 08:09:04,840][796112] Updated weights for policy 0, policy_version 443 (0.0007)
+[2023-02-24 08:09:07,160][795538] Fps is (10 sec: 15974.5, 60 sec: 10035.2, 300 sec: 10035.2). Total num frames: 1851392. Throughput: 0: 2569.2. Samples: 51384. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:09:07,161][795538] Avg episode reward: [(0, '18.568')]
+[2023-02-24 08:09:07,343][796112] Updated weights for policy 0, policy_version 453 (0.0007)
+[2023-02-24 08:09:09,849][796112] Updated weights for policy 0, policy_version 463 (0.0006)
+[2023-02-24 08:09:12,160][795538] Fps is (10 sec: 16384.0, 60 sec: 11304.9, 300 sec: 11304.9). Total num frames: 1933312. Throughput: 0: 2543.8. Samples: 63594. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:09:12,161][795538] Avg episode reward: [(0, '20.173')]
+[2023-02-24 08:09:12,344][796112] Updated weights for policy 0, policy_version 473 (0.0006)
+[2023-02-24 08:09:14,882][796112] Updated weights for policy 0, policy_version 483 (0.0007)
+[2023-02-24 08:09:17,160][795538] Fps is (10 sec: 16384.0, 60 sec: 12151.5, 300 sec: 12151.5). Total num frames: 2015232. Throughput: 0: 2934.7. Samples: 88042. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:09:17,161][795538] Avg episode reward: [(0, '21.495')]
+[2023-02-24 08:09:17,162][796098] Saving new best policy, reward=21.495!
+[2023-02-24 08:09:17,416][796112] Updated weights for policy 0, policy_version 493 (0.0009)
+[2023-02-24 08:09:19,892][796112] Updated weights for policy 0, policy_version 503 (0.0006)
+[2023-02-24 08:09:22,160][795538] Fps is (10 sec: 16384.0, 60 sec: 12756.1, 300 sec: 12756.1). Total num frames: 2097152. Throughput: 0: 3214.6. Samples: 112512. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-24 08:09:22,161][795538] Avg episode reward: [(0, '18.695')]
+[2023-02-24 08:09:22,364][796112] Updated weights for policy 0, policy_version 513 (0.0010)
+[2023-02-24 08:09:24,860][796112] Updated weights for policy 0, policy_version 523 (0.0007)
+[2023-02-24 08:09:27,160][795538] Fps is (10 sec: 16384.1, 60 sec: 13209.6, 300 sec: 13209.6). Total num frames: 2179072. Throughput: 0: 3120.8. Samples: 124832. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-24 08:09:27,161][795538] Avg episode reward: [(0, '21.156')]
+[2023-02-24 08:09:27,388][796112] Updated weights for policy 0, policy_version 533 (0.0006)
+[2023-02-24 08:09:29,933][796112] Updated weights for policy 0, policy_version 543 (0.0011)
+[2023-02-24 08:09:32,160][795538] Fps is (10 sec: 15974.5, 60 sec: 13471.3, 300 sec: 13471.3). Total num frames: 2256896. Throughput: 0: 3315.7. Samples: 149206. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:09:32,164][795538] Avg episode reward: [(0, '19.110')]
+[2023-02-24 08:09:32,491][796112] Updated weights for policy 0, policy_version 553 (0.0008)
+[2023-02-24 08:09:34,962][796112] Updated weights for policy 0, policy_version 563 (0.0006)
+[2023-02-24 08:09:37,160][795538] Fps is (10 sec: 15974.4, 60 sec: 13762.6, 300 sec: 13762.6). Total num frames: 2338816. Throughput: 0: 3865.1. Samples: 173928. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:09:37,160][795538] Avg episode reward: [(0, '20.430')]
+[2023-02-24 08:09:37,443][796112] Updated weights for policy 0, policy_version 573 (0.0006)
+[2023-02-24 08:09:40,104][796112] Updated weights for policy 0, policy_version 583 (0.0007)
+[2023-02-24 08:09:42,160][795538] Fps is (10 sec: 15974.4, 60 sec: 13926.4, 300 sec: 13926.4). Total num frames: 2416640. Throughput: 0: 4050.8. Samples: 185616. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:09:42,160][795538] Avg episode reward: [(0, '22.387')]
+[2023-02-24 08:09:42,172][796098] Saving new best policy, reward=22.387!
+[2023-02-24 08:09:42,735][796112] Updated weights for policy 0, policy_version 593 (0.0008)
+[2023-02-24 08:09:45,371][796112] Updated weights for policy 0, policy_version 603 (0.0006)
+[2023-02-24 08:09:47,160][795538] Fps is (10 sec: 15974.3, 60 sec: 14131.2, 300 sec: 14131.2). Total num frames: 2498560. Throughput: 0: 4036.7. Samples: 208926. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:09:47,162][795538] Avg episode reward: [(0, '23.294')]
+[2023-02-24 08:09:47,163][796098] Saving new best policy, reward=23.294!
+[2023-02-24 08:09:47,936][796112] Updated weights for policy 0, policy_version 613 (0.0009)
+[2023-02-24 08:09:50,471][796112] Updated weights for policy 0, policy_version 623 (0.0006)
+[2023-02-24 08:09:52,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15428.3, 300 sec: 14241.5). Total num frames: 2576384. Throughput: 0: 4030.0. Samples: 232734. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-24 08:09:52,161][795538] Avg episode reward: [(0, '23.526')]
+[2023-02-24 08:09:52,164][796098] Saving new best policy, reward=23.526!
+[2023-02-24 08:09:53,087][796112] Updated weights for policy 0, policy_version 633 (0.0006)
+[2023-02-24 08:09:55,707][796112] Updated weights for policy 0, policy_version 643 (0.0007)
+[2023-02-24 08:09:57,160][795538] Fps is (10 sec: 15564.8, 60 sec: 16042.7, 300 sec: 14336.0). Total num frames: 2654208. Throughput: 0: 4017.6. Samples: 244384. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:09:57,161][795538] Avg episode reward: [(0, '23.324')]
+[2023-02-24 08:09:58,316][796112] Updated weights for policy 0, policy_version 653 (0.0008)
+[2023-02-24 08:10:00,905][796112] Updated weights for policy 0, policy_version 663 (0.0006)
+[2023-02-24 08:10:02,160][795538] Fps is (10 sec: 15564.8, 60 sec: 16042.7, 300 sec: 14417.9). Total num frames: 2732032. Throughput: 0: 4002.8. Samples: 268166. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:10:02,161][795538] Avg episode reward: [(0, '23.305')]
+[2023-02-24 08:10:03,498][796112] Updated weights for policy 0, policy_version 673 (0.0006)
+[2023-02-24 08:10:06,102][796112] Updated weights for policy 0, policy_version 683 (0.0006)
+[2023-02-24 08:10:07,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15974.4, 300 sec: 14489.6). Total num frames: 2809856. Throughput: 0: 3723.8. Samples: 280082. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:10:07,162][795538] Avg episode reward: [(0, '24.939')]
+[2023-02-24 08:10:07,168][796098] Saving new best policy, reward=24.939!
+[2023-02-24 08:10:08,749][796112] Updated weights for policy 0, policy_version 693 (0.0006)
+[2023-02-24 08:10:11,316][796112] Updated weights for policy 0, policy_version 703 (0.0007)
+[2023-02-24 08:10:12,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15974.4, 300 sec: 14601.0). Total num frames: 2891776. Throughput: 0: 3972.7. Samples: 303606. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:10:12,161][795538] Avg episode reward: [(0, '27.390')]
+[2023-02-24 08:10:12,165][796098] Saving new best policy, reward=27.390!
+[2023-02-24 08:10:13,931][796112] Updated weights for policy 0, policy_version 713 (0.0006)
+[2023-02-24 08:10:16,517][796112] Updated weights for policy 0, policy_version 723 (0.0007)
+[2023-02-24 08:10:17,160][795538] Fps is (10 sec: 15974.5, 60 sec: 15906.1, 300 sec: 14654.6). Total num frames: 2969600. Throughput: 0: 3957.6. Samples: 327298. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:10:17,160][795538] Avg episode reward: [(0, '23.654')]
+[2023-02-24 08:10:19,064][796112] Updated weights for policy 0, policy_version 733 (0.0006)
+[2023-02-24 08:10:21,654][796112] Updated weights for policy 0, policy_version 743 (0.0007)
+[2023-02-24 08:10:22,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15837.9, 300 sec: 14702.5). Total num frames: 3047424. Throughput: 0: 3672.8. Samples: 339206. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:10:22,161][795538] Avg episode reward: [(0, '23.892')]
+[2023-02-24 08:10:24,239][796112] Updated weights for policy 0, policy_version 753 (0.0007)
+[2023-02-24 08:10:26,790][796112] Updated weights for policy 0, policy_version 763 (0.0007)
+[2023-02-24 08:10:27,160][795538] Fps is (10 sec: 15974.3, 60 sec: 15837.8, 300 sec: 14786.6). Total num frames: 3129344. Throughput: 0: 3942.0. Samples: 363004. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:10:27,161][795538] Avg episode reward: [(0, '24.204')]
+[2023-02-24 08:10:29,329][796112] Updated weights for policy 0, policy_version 773 (0.0007)
+[2023-02-24 08:10:31,939][796112] Updated weights for policy 0, policy_version 783 (0.0006)
+[2023-02-24 08:10:32,160][795538] Fps is (10 sec: 15974.3, 60 sec: 15837.9, 300 sec: 14823.6). Total num frames: 3207168. Throughput: 0: 3952.3. Samples: 386780. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-24 08:10:32,161][795538] Avg episode reward: [(0, '26.121')]
+[2023-02-24 08:10:34,527][796112] Updated weights for policy 0, policy_version 793 (0.0006)
+[2023-02-24 08:10:37,160][796112] Updated weights for policy 0, policy_version 803 (0.0006)
+[2023-02-24 08:10:37,160][795538] Fps is (10 sec: 15974.5, 60 sec: 15837.9, 300 sec: 14894.6). Total num frames: 3289088. Throughput: 0: 3950.8. Samples: 410518. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:10:37,161][795538] Avg episode reward: [(0, '24.946')]
+[2023-02-24 08:10:39,753][796112] Updated weights for policy 0, policy_version 813 (0.0007)
+[2023-02-24 08:10:42,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 14923.7). Total num frames: 3366912. Throughput: 0: 3957.0. Samples: 422448. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:10:42,160][795538] Avg episode reward: [(0, '24.684')]
+[2023-02-24 08:10:42,164][796098] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000822_3366912.pth...
+[2023-02-24 08:10:42,260][796098] Removing /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000268_1097728.pth
+[2023-02-24 08:10:42,367][796112] Updated weights for policy 0, policy_version 823 (0.0006)
+[2023-02-24 08:10:44,973][796112] Updated weights for policy 0, policy_version 833 (0.0006)
+[2023-02-24 08:10:47,160][795538] Fps is (10 sec: 15564.7, 60 sec: 15769.6, 300 sec: 14950.4). Total num frames: 3444736. Throughput: 0: 3949.0. Samples: 445872. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:10:47,160][795538] Avg episode reward: [(0, '26.184')]
+[2023-02-24 08:10:47,617][796112] Updated weights for policy 0, policy_version 843 (0.0006)
+[2023-02-24 08:10:50,205][796112] Updated weights for policy 0, policy_version 853 (0.0007)
+[2023-02-24 08:10:52,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15769.6, 300 sec: 14975.0). Total num frames: 3522560. Throughput: 0: 4210.3. Samples: 469546. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:10:52,161][795538] Avg episode reward: [(0, '26.862')]
+[2023-02-24 08:10:52,756][796112] Updated weights for policy 0, policy_version 863 (0.0008)
+[2023-02-24 08:10:55,295][796112] Updated weights for policy 0, policy_version 873 (0.0006)
+[2023-02-24 08:10:57,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15029.2). Total num frames: 3604480. Throughput: 0: 3953.6. Samples: 481518. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-02-24 08:10:57,161][795538] Avg episode reward: [(0, '25.390')]
+[2023-02-24 08:10:57,895][796112] Updated weights for policy 0, policy_version 883 (0.0007)
+[2023-02-24 08:11:00,550][796112] Updated weights for policy 0, policy_version 893 (0.0009)
+[2023-02-24 08:11:02,160][795538] Fps is (10 sec: 15974.2, 60 sec: 15837.8, 300 sec: 15049.0). Total num frames: 3682304. Throughput: 0: 3949.9. Samples: 505042. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:11:02,161][795538] Avg episode reward: [(0, '25.427')]
+[2023-02-24 08:11:03,150][796112] Updated weights for policy 0, policy_version 903 (0.0008)
+[2023-02-24 08:11:05,738][796112] Updated weights for policy 0, policy_version 913 (0.0008)
+[2023-02-24 08:11:07,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15837.9, 300 sec: 15067.4). Total num frames: 3760128. Throughput: 0: 4217.3. Samples: 528986. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:11:07,161][795538] Avg episode reward: [(0, '25.526')]
+[2023-02-24 08:11:08,213][796112] Updated weights for policy 0, policy_version 923 (0.0006)
+[2023-02-24 08:11:10,734][796112] Updated weights for policy 0, policy_version 933 (0.0007)
+[2023-02-24 08:11:12,160][795538] Fps is (10 sec: 15974.6, 60 sec: 15837.9, 300 sec: 15112.8). Total num frames: 3842048. Throughput: 0: 3965.5. Samples: 541452. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:11:12,160][795538] Avg episode reward: [(0, '26.175')]
+[2023-02-24 08:11:13,377][796112] Updated weights for policy 0, policy_version 943 (0.0007)
+[2023-02-24 08:11:15,931][796112] Updated weights for policy 0, policy_version 953 (0.0007)
+[2023-02-24 08:11:17,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15127.9). Total num frames: 3919872. Throughput: 0: 3960.2. Samples: 564990. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:11:17,161][795538] Avg episode reward: [(0, '26.638')]
+[2023-02-24 08:11:18,529][796112] Updated weights for policy 0, policy_version 963 (0.0008)
+[2023-02-24 08:11:21,078][796112] Updated weights for policy 0, policy_version 973 (0.0007)
+[2023-02-24 08:11:22,160][795538] Fps is (10 sec: 15974.3, 60 sec: 15906.1, 300 sec: 15168.4). Total num frames: 4001792. Throughput: 0: 3964.5. Samples: 588920. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:11:22,161][795538] Avg episode reward: [(0, '26.420')]
+[2023-02-24 08:11:23,650][796112] Updated weights for policy 0, policy_version 983 (0.0006)
+[2023-02-24 08:11:26,246][796112] Updated weights for policy 0, policy_version 993 (0.0006)
+[2023-02-24 08:11:27,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15180.8). Total num frames: 4079616. Throughput: 0: 3963.6. Samples: 600810. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:11:27,161][795538] Avg episode reward: [(0, '23.763')]
+[2023-02-24 08:11:28,856][796112] Updated weights for policy 0, policy_version 1003 (0.0006)
+[2023-02-24 08:11:31,443][796112] Updated weights for policy 0, policy_version 1013 (0.0006)
+[2023-02-24 08:11:32,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15837.9, 300 sec: 15192.4). Total num frames: 4157440. Throughput: 0: 3970.3. Samples: 624536. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:11:32,161][795538] Avg episode reward: [(0, '29.275')]
+[2023-02-24 08:11:32,165][796098] Saving new best policy, reward=29.275!
+[2023-02-24 08:11:34,059][796112] Updated weights for policy 0, policy_version 1023 (0.0007)
+[2023-02-24 08:11:36,631][796112] Updated weights for policy 0, policy_version 1033 (0.0006)
+[2023-02-24 08:11:37,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15227.5). Total num frames: 4239360. Throughput: 0: 3966.3. Samples: 648028. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
+[2023-02-24 08:11:37,161][795538] Avg episode reward: [(0, '30.081')]
+[2023-02-24 08:11:37,162][796098] Saving new best policy, reward=30.081!
+[2023-02-24 08:11:39,264][796112] Updated weights for policy 0, policy_version 1043 (0.0006)
+[2023-02-24 08:11:41,882][796112] Updated weights for policy 0, policy_version 1053 (0.0008)
+[2023-02-24 08:11:42,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15237.1). Total num frames: 4317184. Throughput: 0: 3961.7. Samples: 659794. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:11:42,162][795538] Avg episode reward: [(0, '28.237')]
+[2023-02-24 08:11:44,465][796112] Updated weights for policy 0, policy_version 1063 (0.0007)
+[2023-02-24 08:11:47,078][796112] Updated weights for policy 0, policy_version 1073 (0.0007)
+[2023-02-24 08:11:47,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15837.9, 300 sec: 15246.2). Total num frames: 4395008. Throughput: 0: 3964.2. Samples: 683430. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:11:47,160][795538] Avg episode reward: [(0, '27.334')]
+[2023-02-24 08:11:49,667][796112] Updated weights for policy 0, policy_version 1083 (0.0007)
+[2023-02-24 08:11:52,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15837.9, 300 sec: 15254.8). Total num frames: 4472832. Throughput: 0: 3957.7. Samples: 707084. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:11:52,161][795538] Avg episode reward: [(0, '27.060')]
+[2023-02-24 08:11:52,282][796112] Updated weights for policy 0, policy_version 1093 (0.0006)
+[2023-02-24 08:11:54,877][796112] Updated weights for policy 0, policy_version 1103 (0.0006)
+[2023-02-24 08:11:57,160][795538] Fps is (10 sec: 15564.7, 60 sec: 15769.6, 300 sec: 15263.0). Total num frames: 4550656. Throughput: 0: 3941.8. Samples: 718832. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:11:57,161][795538] Avg episode reward: [(0, '26.759')]
+[2023-02-24 08:11:57,461][796112] Updated weights for policy 0, policy_version 1113 (0.0006)
+[2023-02-24 08:12:00,051][796112] Updated weights for policy 0, policy_version 1123 (0.0006)
+[2023-02-24 08:12:02,160][795538] Fps is (10 sec: 15974.5, 60 sec: 15837.9, 300 sec: 15291.7). Total num frames: 4632576. Throughput: 0: 3946.0. Samples: 742562. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:12:02,161][795538] Avg episode reward: [(0, '31.137')]
+[2023-02-24 08:12:02,164][796098] Saving new best policy, reward=31.137!
+[2023-02-24 08:12:02,698][796112] Updated weights for policy 0, policy_version 1133 (0.0008)
+[2023-02-24 08:12:05,265][796112] Updated weights for policy 0, policy_version 1143 (0.0007)
+[2023-02-24 08:12:07,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15298.6). Total num frames: 4710400. Throughput: 0: 3936.4. Samples: 766056. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:12:07,161][795538] Avg episode reward: [(0, '29.446')]
+[2023-02-24 08:12:07,854][796112] Updated weights for policy 0, policy_version 1153 (0.0009)
+[2023-02-24 08:12:10,527][796112] Updated weights for policy 0, policy_version 1163 (0.0008)
+[2023-02-24 08:12:12,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15769.6, 300 sec: 15305.1). Total num frames: 4788224. Throughput: 0: 3933.4. Samples: 777814. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:12:12,161][795538] Avg episode reward: [(0, '25.534')]
+[2023-02-24 08:12:13,157][796112] Updated weights for policy 0, policy_version 1173 (0.0008)
+[2023-02-24 08:12:15,767][796112] Updated weights for policy 0, policy_version 1183 (0.0007)
+[2023-02-24 08:12:17,160][795538] Fps is (10 sec: 15564.5, 60 sec: 15769.6, 300 sec: 15311.2). Total num frames: 4866048. Throughput: 0: 3927.5. Samples: 801272. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:12:17,161][795538] Avg episode reward: [(0, '28.476')]
+[2023-02-24 08:12:18,390][796112] Updated weights for policy 0, policy_version 1193 (0.0006)
+[2023-02-24 08:12:21,010][796112] Updated weights for policy 0, policy_version 1203 (0.0008)
+[2023-02-24 08:12:22,161][795538] Fps is (10 sec: 15563.3, 60 sec: 15701.1, 300 sec: 15317.1). Total num frames: 4943872. Throughput: 0: 3926.3. Samples: 824714. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:12:22,162][795538] Avg episode reward: [(0, '29.026')]
+[2023-02-24 08:12:23,640][796112] Updated weights for policy 0, policy_version 1213 (0.0007)
+[2023-02-24 08:12:26,277][796112] Updated weights for policy 0, policy_version 1223 (0.0006)
+[2023-02-24 08:12:27,160][795538] Fps is (10 sec: 15565.1, 60 sec: 15701.3, 300 sec: 15322.8). Total num frames: 5021696. Throughput: 0: 3925.6. Samples: 836444. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:12:27,161][795538] Avg episode reward: [(0, '28.968')]
+[2023-02-24 08:12:28,839][796112] Updated weights for policy 0, policy_version 1233 (0.0008)
+[2023-02-24 08:12:31,424][796112] Updated weights for policy 0, policy_version 1243 (0.0009)
+[2023-02-24 08:12:32,160][795538] Fps is (10 sec: 15566.2, 60 sec: 15701.3, 300 sec: 15328.1). Total num frames: 5099520. Throughput: 0: 3926.8. Samples: 860134. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:12:32,161][795538] Avg episode reward: [(0, '30.627')]
+[2023-02-24 08:12:34,002][796112] Updated weights for policy 0, policy_version 1253 (0.0006)
+[2023-02-24 08:12:36,598][796112] Updated weights for policy 0, policy_version 1263 (0.0007)
+[2023-02-24 08:12:37,160][795538] Fps is (10 sec: 15974.5, 60 sec: 15701.3, 300 sec: 15351.1). Total num frames: 5181440. Throughput: 0: 3927.4. Samples: 883818. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:12:37,160][795538] Avg episode reward: [(0, '30.119')]
+[2023-02-24 08:12:39,183][796112] Updated weights for policy 0, policy_version 1273 (0.0006)
+[2023-02-24 08:12:41,827][796112] Updated weights for policy 0, policy_version 1283 (0.0006)
+[2023-02-24 08:12:42,160][795538] Fps is (10 sec: 15974.3, 60 sec: 15701.3, 300 sec: 15355.6). Total num frames: 5259264. Throughput: 0: 3932.7. Samples: 895804. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:12:42,161][795538] Avg episode reward: [(0, '28.016')]
+[2023-02-24 08:12:42,165][796098] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001284_5259264.pth...
+[2023-02-24 08:12:42,261][796098] Removing /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000403_1650688.pth
+[2023-02-24 08:12:44,477][796112] Updated weights for policy 0, policy_version 1293 (0.0006)
+[2023-02-24 08:12:47,112][796112] Updated weights for policy 0, policy_version 1303 (0.0007)
+[2023-02-24 08:12:47,160][795538] Fps is (10 sec: 15564.7, 60 sec: 15701.3, 300 sec: 15360.0). Total num frames: 5337088. Throughput: 0: 3918.7. Samples: 918904. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2023-02-24 08:12:47,161][795538] Avg episode reward: [(0, '29.296')]
+[2023-02-24 08:12:49,686][796112] Updated weights for policy 0, policy_version 1313 (0.0006)
+[2023-02-24 08:12:52,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15701.3, 300 sec: 15364.2). Total num frames: 5414912. Throughput: 0: 3658.7. Samples: 930696. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:12:52,161][795538] Avg episode reward: [(0, '29.969')]
+[2023-02-24 08:12:52,236][796112] Updated weights for policy 0, policy_version 1323 (0.0007)
+[2023-02-24 08:12:54,849][796112] Updated weights for policy 0, policy_version 1333 (0.0006)
+[2023-02-24 08:12:57,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15701.3, 300 sec: 15368.2). Total num frames: 5492736. Throughput: 0: 3924.4. Samples: 954414. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-24 08:12:57,160][795538] Avg episode reward: [(0, '26.997')]
+[2023-02-24 08:12:57,451][796112] Updated weights for policy 0, policy_version 1343 (0.0007)
+[2023-02-24 08:13:00,062][796112] Updated weights for policy 0, policy_version 1353 (0.0007)
+[2023-02-24 08:13:02,127][795538] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 795538], exiting...
+[2023-02-24 08:13:02,128][796098] Stopping Batcher_0...
+[2023-02-24 08:13:02,129][796098] Loop batcher_evt_loop terminating...
+[2023-02-24 08:13:02,130][796098] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001361_5574656.pth...
+[2023-02-24 08:13:02,130][795538] Runner profile tree view:
+main_loop: 258.8521
+[2023-02-24 08:13:02,130][795538] Collected {0: 5574656}, FPS: 15159.1
+[2023-02-24 08:13:02,136][796113] Stopping RolloutWorker_w2...
+[2023-02-24 08:13:02,137][796113] Loop rollout_proc2_evt_loop terminating...
+[2023-02-24 08:13:02,139][796118] Stopping RolloutWorker_w4...
+[2023-02-24 08:13:02,139][796118] Loop rollout_proc4_evt_loop terminating...
+[2023-02-24 08:13:02,139][796117] Stopping RolloutWorker_w5...
+[2023-02-24 08:13:02,140][796117] Loop rollout_proc5_evt_loop terminating...
+[2023-02-24 08:13:02,142][796115] Stopping RolloutWorker_w3...
+[2023-02-24 08:13:02,143][796115] Loop rollout_proc3_evt_loop terminating...
+[2023-02-24 08:13:02,143][796111] Stopping RolloutWorker_w0...
+[2023-02-24 08:13:02,144][796119] Stopping RolloutWorker_w6...
+[2023-02-24 08:13:02,144][796111] Loop rollout_proc0_evt_loop terminating...
+[2023-02-24 08:13:02,144][796119] Loop rollout_proc6_evt_loop terminating...
+[2023-02-24 08:13:02,148][796114] Stopping RolloutWorker_w1...
+[2023-02-24 08:13:02,148][796114] Loop rollout_proc1_evt_loop terminating...
+[2023-02-24 08:13:02,151][796116] Stopping RolloutWorker_w7...
+[2023-02-24 08:13:02,152][796116] Loop rollout_proc7_evt_loop terminating...
+[2023-02-24 08:13:02,163][796112] Weights refcount: 2 0
+[2023-02-24 08:13:02,171][796112] Stopping InferenceWorker_p0-w0...
+[2023-02-24 08:13:02,172][796112] Loop inference_proc0-0_evt_loop terminating...
+[2023-02-24 08:13:02,301][796098] Removing /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000822_3366912.pth
+[2023-02-24 08:13:02,305][796098] Stopping LearnerWorker_p0...
+[2023-02-24 08:13:02,314][796098] Loop learner_proc0_evt_loop terminating...
+[2023-02-24 08:13:11,768][795538] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
+[2023-02-24 08:13:11,769][795538] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-24 08:13:11,770][795538] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-24 08:13:11,770][795538] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-24 08:13:11,770][795538] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-24 08:13:11,771][795538] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-24 08:13:11,771][795538] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-02-24 08:13:11,772][795538] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-24 08:13:11,772][795538] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-02-24 08:13:11,773][795538] Adding new argument 'hf_repository'='chqmatteo/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-02-24 08:13:11,773][795538] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-24 08:13:11,773][795538] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-24 08:13:11,774][795538] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-24 08:13:11,774][795538] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-24 08:13:11,775][795538] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-24 08:13:11,779][795538] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 08:13:11,780][795538] RunningMeanStd input shape: (1,)
+[2023-02-24 08:13:11,787][795538] ConvEncoder: input_channels=3
+[2023-02-24 08:13:11,812][795538] Conv encoder output size: 512
+[2023-02-24 08:13:11,813][795538] Policy head output size: 512
+[2023-02-24 08:13:11,845][795538] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001361_5574656.pth...
+[2023-02-24 08:13:12,294][795538] Num frames 100...
+[2023-02-24 08:13:12,360][795538] Num frames 200...
+[2023-02-24 08:13:12,438][795538] Num frames 300...
+[2023-02-24 08:13:12,502][795538] Num frames 400...
+[2023-02-24 08:13:12,568][795538] Num frames 500...
+[2023-02-24 08:13:12,635][795538] Num frames 600...
+[2023-02-24 08:13:12,701][795538] Num frames 700...
+[2023-02-24 08:13:12,763][795538] Num frames 800...
+[2023-02-24 08:13:12,833][795538] Num frames 900...
+[2023-02-24 08:13:12,896][795538] Num frames 1000...
+[2023-02-24 08:13:12,971][795538] Num frames 1100...
+[2023-02-24 08:13:13,037][795538] Num frames 1200...
+[2023-02-24 08:13:13,102][795538] Avg episode rewards: #0: 29.160, true rewards: #0: 12.160
+[2023-02-24 08:13:13,102][795538] Avg episode reward: 29.160, avg true_objective: 12.160
+[2023-02-24 08:13:13,165][795538] Num frames 1300...
+[2023-02-24 08:13:13,228][795538] Num frames 1400...
+[2023-02-24 08:13:13,291][795538] Num frames 1500...
+[2023-02-24 08:13:13,362][795538] Num frames 1600...
+[2023-02-24 08:13:13,429][795538] Num frames 1700...
+[2023-02-24 08:13:13,494][795538] Num frames 1800...
+[2023-02-24 08:13:13,563][795538] Num frames 1900...
+[2023-02-24 08:13:13,627][795538] Num frames 2000...
+[2023-02-24 08:13:13,697][795538] Num frames 2100...
+[2023-02-24 08:13:13,770][795538] Num frames 2200...
+[2023-02-24 08:13:13,838][795538] Num frames 2300...
+[2023-02-24 08:13:13,919][795538] Num frames 2400...
+[2023-02-24 08:13:13,989][795538] Num frames 2500...
+[2023-02-24 08:13:14,053][795538] Num frames 2600...
+[2023-02-24 08:13:14,132][795538] Num frames 2700...
+[2023-02-24 08:13:14,205][795538] Num frames 2800...
+[2023-02-24 08:13:14,265][795538] Avg episode rewards: #0: 35.535, true rewards: #0: 14.035
+[2023-02-24 08:13:14,266][795538] Avg episode reward: 35.535, avg true_objective: 14.035
+[2023-02-24 08:13:14,332][795538] Num frames 2900...
+[2023-02-24 08:13:14,399][795538] Num frames 3000...
+[2023-02-24 08:13:14,464][795538] Num frames 3100...
+[2023-02-24 08:13:14,537][795538] Num frames 3200...
+[2023-02-24 08:13:14,627][795538] Num frames 3300...
+[2023-02-24 08:13:14,696][795538] Num frames 3400...
+[2023-02-24 08:13:14,807][795538] Avg episode rewards: #0: 28.950, true rewards: #0: 11.617
+[2023-02-24 08:13:14,808][795538] Avg episode reward: 28.950, avg true_objective: 11.617
+[2023-02-24 08:13:14,818][795538] Num frames 3500...
+[2023-02-24 08:13:14,882][795538] Num frames 3600...
+[2023-02-24 08:13:14,943][795538] Num frames 3700...
+[2023-02-24 08:13:15,002][795538] Num frames 3800...
+[2023-02-24 08:13:15,069][795538] Num frames 3900...
+[2023-02-24 08:13:15,133][795538] Num frames 4000...
+[2023-02-24 08:13:15,196][795538] Num frames 4100...
+[2023-02-24 08:13:15,259][795538] Num frames 4200...
+[2023-02-24 08:13:15,327][795538] Num frames 4300...
+[2023-02-24 08:13:15,403][795538] Num frames 4400...
+[2023-02-24 08:13:15,470][795538] Num frames 4500...
+[2023-02-24 08:13:15,534][795538] Num frames 4600...
+[2023-02-24 08:13:15,596][795538] Num frames 4700...
+[2023-02-24 08:13:15,660][795538] Num frames 4800...
+[2023-02-24 08:13:15,736][795538] Num frames 4900...
+[2023-02-24 08:13:15,804][795538] Num frames 5000...
+[2023-02-24 08:13:15,870][795538] Num frames 5100...
+[2023-02-24 08:13:15,944][795538] Num frames 5200...
+[2023-02-24 08:13:16,023][795538] Num frames 5300...
+[2023-02-24 08:13:16,098][795538] Num frames 5400...
+[2023-02-24 08:13:16,186][795538] Num frames 5500...
+[2023-02-24 08:13:16,306][795538] Avg episode rewards: #0: 35.962, true rewards: #0: 13.962
+[2023-02-24 08:13:16,307][795538] Avg episode reward: 35.962, avg true_objective: 13.962
+[2023-02-24 08:13:16,320][795538] Num frames 5600...
+[2023-02-24 08:13:16,393][795538] Num frames 5700...
+[2023-02-24 08:13:16,460][795538] Num frames 5800...
+[2023-02-24 08:13:16,524][795538] Num frames 5900...
+[2023-02-24 08:13:16,601][795538] Avg episode rewards: #0: 30.080, true rewards: #0: 11.880
+[2023-02-24 08:13:16,602][795538] Avg episode reward: 30.080, avg true_objective: 11.880
+[2023-02-24 08:13:16,640][795538] Num frames 6000...
+[2023-02-24 08:13:16,708][795538] Num frames 6100...
+[2023-02-24 08:13:16,794][795538] Num frames 6200...
+[2023-02-24 08:13:16,854][795538] Num frames 6300...
+[2023-02-24 08:13:16,920][795538] Num frames 6400...
+[2023-02-24 08:13:16,995][795538] Num frames 6500...
+[2023-02-24 08:13:17,060][795538] Num frames 6600...
+[2023-02-24 08:13:17,136][795538] Num frames 6700...
+[2023-02-24 08:13:17,202][795538] Num frames 6800...
+[2023-02-24 08:13:17,265][795538] Num frames 6900...
+[2023-02-24 08:13:17,334][795538] Num frames 7000...
+[2023-02-24 08:13:17,402][795538] Num frames 7100...
+[2023-02-24 08:13:17,467][795538] Num frames 7200...
+[2023-02-24 08:13:17,541][795538] Num frames 7300...
+[2023-02-24 08:13:17,614][795538] Num frames 7400...
+[2023-02-24 08:13:17,693][795538] Num frames 7500...
+[2023-02-24 08:13:17,761][795538] Num frames 7600...
+[2023-02-24 08:13:17,852][795538] Avg episode rewards: #0: 32.753, true rewards: #0: 12.753
+[2023-02-24 08:13:17,853][795538] Avg episode reward: 32.753, avg true_objective: 12.753
+[2023-02-24 08:13:17,891][795538] Num frames 7700...
+[2023-02-24 08:13:17,954][795538] Num frames 7800...
+[2023-02-24 08:13:18,026][795538] Num frames 7900...
+[2023-02-24 08:13:18,113][795538] Num frames 8000...
+[2023-02-24 08:13:18,178][795538] Num frames 8100...
+[2023-02-24 08:13:18,244][795538] Num frames 8200...
+[2023-02-24 08:13:18,314][795538] Num frames 8300...
+[2023-02-24 08:13:18,380][795538] Num frames 8400...
+[2023-02-24 08:13:18,452][795538] Num frames 8500...
+[2023-02-24 08:13:18,528][795538] Num frames 8600...
+[2023-02-24 08:13:18,601][795538] Num frames 8700...
+[2023-02-24 08:13:18,664][795538] Num frames 8800...
+[2023-02-24 08:13:18,732][795538] Num frames 8900...
+[2023-02-24 08:13:18,799][795538] Num frames 9000...
+[2023-02-24 08:13:18,876][795538] Num frames 9100...
+[2023-02-24 08:13:18,945][795538] Num frames 9200...
+[2023-02-24 08:13:19,017][795538] Num frames 9300...
+[2023-02-24 08:13:19,083][795538] Num frames 9400...
+[2023-02-24 08:13:19,162][795538] Num frames 9500...
+[2023-02-24 08:13:19,240][795538] Num frames 9600...
+[2023-02-24 08:13:19,308][795538] Num frames 9700...
+[2023-02-24 08:13:19,398][795538] Avg episode rewards: #0: 36.788, true rewards: #0: 13.931
+[2023-02-24 08:13:19,398][795538] Avg episode reward: 36.788, avg true_objective: 13.931
+[2023-02-24 08:13:19,431][795538] Num frames 9800...
+[2023-02-24 08:13:19,505][795538] Num frames 9900...
+[2023-02-24 08:13:19,570][795538] Num frames 10000...
+[2023-02-24 08:13:19,642][795538] Num frames 10100...
+[2023-02-24 08:13:19,704][795538] Num frames 10200...
+[2023-02-24 08:13:19,778][795538] Avg episode rewards: #0: 33.665, true rewards: #0: 12.790
+[2023-02-24 08:13:19,779][795538] Avg episode reward: 33.665, avg true_objective: 12.790
+[2023-02-24 08:13:19,831][795538] Num frames 10300...
+[2023-02-24 08:13:19,906][795538] Num frames 10400...
+[2023-02-24 08:13:20,011][795538] Num frames 10500...
+[2023-02-24 08:13:20,081][795538] Num frames 10600...
+[2023-02-24 08:13:20,144][795538] Num frames 10700...
+[2023-02-24 08:13:20,220][795538] Num frames 10800...
+[2023-02-24 08:13:20,322][795538] Avg episode rewards: #0: 31.302, true rewards: #0: 12.080
+[2023-02-24 08:13:20,322][795538] Avg episode reward: 31.302, avg true_objective: 12.080
+[2023-02-24 08:13:20,348][795538] Num frames 10900...
+[2023-02-24 08:13:20,415][795538] Num frames 11000...
+[2023-02-24 08:13:20,477][795538] Num frames 11100...
+[2023-02-24 08:13:20,537][795538] Num frames 11200...
+[2023-02-24 08:13:20,596][795538] Num frames 11300...
+[2023-02-24 08:13:20,656][795538] Num frames 11400...
+[2023-02-24 08:13:20,717][795538] Num frames 11500...
+[2023-02-24 08:13:20,774][795538] Num frames 11600...
+[2023-02-24 08:13:20,836][795538] Num frames 11700...
+[2023-02-24 08:13:20,897][795538] Num frames 11800...
+[2023-02-24 08:13:20,958][795538] Num frames 11900...
+[2023-02-24 08:13:21,028][795538] Num frames 12000...
+[2023-02-24 08:13:21,097][795538] Num frames 12100...
+[2023-02-24 08:13:21,160][795538] Num frames 12200...
+[2023-02-24 08:13:21,224][795538] Num frames 12300...
+[2023-02-24 08:13:21,292][795538] Num frames 12400...
+[2023-02-24 08:13:21,394][795538] Avg episode rewards: #0: 32.272, true rewards: #0: 12.472
+[2023-02-24 08:13:21,395][795538] Avg episode reward: 32.272, avg true_objective: 12.472
+[2023-02-24 08:13:27,245][795538] Replay video saved to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!