Ditrip commited on
Commit
d163348
1 Parent(s): fd82096

Upload folder using huggingface_hub

Browse files
.summary/0/events.out.tfevents.1687185373.ef5da5cad0fc ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0726bff962eaadb3aa4b8947bf39bce6f48e7b337940a5a019d19884f54c1f9b
3
+ size 377220
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 10.79 +/- 6.11
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 12.30 +/- 5.13
19
  name: mean_reward
20
  verified: false
21
  ---
checkpoint_p0/best_000001434_5873664_reward_32.907.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ee5d9c59ccb4599623a1a1f4a6bc125a21be0fca8d914f73f46a78952bc91de
3
+ size 34928806
checkpoint_p0/checkpoint_000001391_5697536.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55cce6f97c0fb78b2dd3262726bab94f0057f94d5db7ef745bb3ddab6234df06
3
+ size 34929220
checkpoint_p0/checkpoint_000001466_6004736.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5e11039190ba8d79d6b1f2c57075ae5e02f88a26283feadf385aeeedc7d0d6
3
+ size 34929220
config.json CHANGED
@@ -15,7 +15,7 @@
15
  "worker_num_splits": 2,
16
  "policy_workers_per_policy": 1,
17
  "max_policy_lag": 1000,
18
- "num_workers": 8,
19
  "num_envs_per_worker": 4,
20
  "batch_size": 1024,
21
  "num_batches_per_epoch": 1,
@@ -65,7 +65,7 @@
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
- "train_for_env_steps": 4000000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
 
15
  "worker_num_splits": 2,
16
  "policy_workers_per_policy": 1,
17
  "max_policy_lag": 1000,
18
+ "num_workers": 12,
19
  "num_envs_per_worker": 4,
20
  "batch_size": 1024,
21
  "num_batches_per_epoch": 1,
 
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 6000000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f3d32a9b3bcd239b2551c8f5e850dff4f90cc538c3034ced7426cfecc206b3c
3
- size 21267616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc33ef7087242f543de77a26e7e628509f453921dd653ee7ebbbe6803d9d30c5
3
+ size 24051363
sf_log.txt CHANGED
@@ -1697,3 +1697,887 @@ main_loop: 1130.5358
1697
  [2023-06-19 14:34:04,916][00753] Avg episode rewards: #0: 25.293, true rewards: #0: 10.793
1698
  [2023-06-19 14:34:04,918][00753] Avg episode reward: 25.293, avg true_objective: 10.793
1699
  [2023-06-19 14:35:11,109][00753] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1697
  [2023-06-19 14:34:04,916][00753] Avg episode rewards: #0: 25.293, true rewards: #0: 10.793
1698
  [2023-06-19 14:34:04,918][00753] Avg episode reward: 25.293, avg true_objective: 10.793
1699
  [2023-06-19 14:35:11,109][00753] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
1700
+ [2023-06-19 14:35:14,170][00753] The model has been pushed to https://huggingface.co/Ditrip/rl_course_vizdoom_health_gathering_supreme
1701
+ [2023-06-19 14:36:13,295][00753] Environment doom_basic already registered, overwriting...
1702
+ [2023-06-19 14:36:13,298][00753] Environment doom_two_colors_easy already registered, overwriting...
1703
+ [2023-06-19 14:36:13,299][00753] Environment doom_two_colors_hard already registered, overwriting...
1704
+ [2023-06-19 14:36:13,300][00753] Environment doom_dm already registered, overwriting...
1705
+ [2023-06-19 14:36:13,302][00753] Environment doom_dwango5 already registered, overwriting...
1706
+ [2023-06-19 14:36:13,303][00753] Environment doom_my_way_home_flat_actions already registered, overwriting...
1707
+ [2023-06-19 14:36:13,304][00753] Environment doom_defend_the_center_flat_actions already registered, overwriting...
1708
+ [2023-06-19 14:36:13,306][00753] Environment doom_my_way_home already registered, overwriting...
1709
+ [2023-06-19 14:36:13,307][00753] Environment doom_deadly_corridor already registered, overwriting...
1710
+ [2023-06-19 14:36:13,308][00753] Environment doom_defend_the_center already registered, overwriting...
1711
+ [2023-06-19 14:36:13,310][00753] Environment doom_defend_the_line already registered, overwriting...
1712
+ [2023-06-19 14:36:13,311][00753] Environment doom_health_gathering already registered, overwriting...
1713
+ [2023-06-19 14:36:13,312][00753] Environment doom_health_gathering_supreme already registered, overwriting...
1714
+ [2023-06-19 14:36:13,314][00753] Environment doom_battle already registered, overwriting...
1715
+ [2023-06-19 14:36:13,315][00753] Environment doom_battle2 already registered, overwriting...
1716
+ [2023-06-19 14:36:13,316][00753] Environment doom_duel_bots already registered, overwriting...
1717
+ [2023-06-19 14:36:13,318][00753] Environment doom_deathmatch_bots already registered, overwriting...
1718
+ [2023-06-19 14:36:13,319][00753] Environment doom_duel already registered, overwriting...
1719
+ [2023-06-19 14:36:13,320][00753] Environment doom_deathmatch_full already registered, overwriting...
1720
+ [2023-06-19 14:36:13,322][00753] Environment doom_benchmark already registered, overwriting...
1721
+ [2023-06-19 14:36:13,323][00753] register_encoder_factory: <function make_vizdoom_encoder at 0x7f1cb360c4c0>
1722
+ [2023-06-19 14:36:13,349][00753] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
1723
+ [2023-06-19 14:36:13,351][00753] Overriding arg 'num_workers' with value 12 passed from command line
1724
+ [2023-06-19 14:36:13,352][00753] Overriding arg 'train_for_env_steps' with value 6000000 passed from command line
1725
+ [2023-06-19 14:36:13,357][00753] Experiment dir /content/train_dir/default_experiment already exists!
1726
+ [2023-06-19 14:36:13,362][00753] Resuming existing experiment from /content/train_dir/default_experiment...
1727
+ [2023-06-19 14:36:13,363][00753] Weights and Biases integration disabled
1728
+ [2023-06-19 14:36:13,366][00753] Environment var CUDA_VISIBLE_DEVICES is 0
1729
+
1730
+ [2023-06-19 14:36:15,416][00753] Starting experiment with the following configuration:
1731
+ help=False
1732
+ algo=APPO
1733
+ env=doom_health_gathering_supreme
1734
+ experiment=default_experiment
1735
+ train_dir=/content/train_dir
1736
+ restart_behavior=resume
1737
+ device=gpu
1738
+ seed=None
1739
+ num_policies=1
1740
+ async_rl=True
1741
+ serial_mode=False
1742
+ batched_sampling=False
1743
+ num_batches_to_accumulate=2
1744
+ worker_num_splits=2
1745
+ policy_workers_per_policy=1
1746
+ max_policy_lag=1000
1747
+ num_workers=12
1748
+ num_envs_per_worker=4
1749
+ batch_size=1024
1750
+ num_batches_per_epoch=1
1751
+ num_epochs=1
1752
+ rollout=32
1753
+ recurrence=32
1754
+ shuffle_minibatches=False
1755
+ gamma=0.99
1756
+ reward_scale=1.0
1757
+ reward_clip=1000.0
1758
+ value_bootstrap=False
1759
+ normalize_returns=True
1760
+ exploration_loss_coeff=0.001
1761
+ value_loss_coeff=0.5
1762
+ kl_loss_coeff=0.0
1763
+ exploration_loss=symmetric_kl
1764
+ gae_lambda=0.95
1765
+ ppo_clip_ratio=0.1
1766
+ ppo_clip_value=0.2
1767
+ with_vtrace=False
1768
+ vtrace_rho=1.0
1769
+ vtrace_c=1.0
1770
+ optimizer=adam
1771
+ adam_eps=1e-06
1772
+ adam_beta1=0.9
1773
+ adam_beta2=0.999
1774
+ max_grad_norm=4.0
1775
+ learning_rate=0.0001
1776
+ lr_schedule=constant
1777
+ lr_schedule_kl_threshold=0.008
1778
+ lr_adaptive_min=1e-06
1779
+ lr_adaptive_max=0.01
1780
+ obs_subtract_mean=0.0
1781
+ obs_scale=255.0
1782
+ normalize_input=True
1783
+ normalize_input_keys=None
1784
+ decorrelate_experience_max_seconds=0
1785
+ decorrelate_envs_on_one_worker=True
1786
+ actor_worker_gpus=[]
1787
+ set_workers_cpu_affinity=True
1788
+ force_envs_single_thread=False
1789
+ default_niceness=0
1790
+ log_to_file=True
1791
+ experiment_summaries_interval=10
1792
+ flush_summaries_interval=30
1793
+ stats_avg=100
1794
+ summaries_use_frameskip=True
1795
+ heartbeat_interval=20
1796
+ heartbeat_reporting_interval=600
1797
+ train_for_env_steps=6000000
1798
+ train_for_seconds=10000000000
1799
+ save_every_sec=120
1800
+ keep_checkpoints=2
1801
+ load_checkpoint_kind=latest
1802
+ save_milestones_sec=-1
1803
+ save_best_every_sec=5
1804
+ save_best_metric=reward
1805
+ save_best_after=100000
1806
+ benchmark=False
1807
+ encoder_mlp_layers=[512, 512]
1808
+ encoder_conv_architecture=convnet_simple
1809
+ encoder_conv_mlp_layers=[512]
1810
+ use_rnn=True
1811
+ rnn_size=512
1812
+ rnn_type=gru
1813
+ rnn_num_layers=1
1814
+ decoder_mlp_layers=[]
1815
+ nonlinearity=elu
1816
+ policy_initialization=orthogonal
1817
+ policy_init_gain=1.0
1818
+ actor_critic_share_weights=True
1819
+ adaptive_stddev=True
1820
+ continuous_tanh_scale=0.0
1821
+ initial_stddev=1.0
1822
+ use_env_info_cache=False
1823
+ env_gpu_actions=False
1824
+ env_gpu_observations=True
1825
+ env_frameskip=4
1826
+ env_framestack=1
1827
+ pixel_format=CHW
1828
+ use_record_episode_statistics=False
1829
+ with_wandb=False
1830
+ wandb_user=None
1831
+ wandb_project=sample_factory
1832
+ wandb_group=None
1833
+ wandb_job_type=SF
1834
+ wandb_tags=[]
1835
+ with_pbt=False
1836
+ pbt_mix_policies_in_one_env=True
1837
+ pbt_period_env_steps=5000000
1838
+ pbt_start_mutation=20000000
1839
+ pbt_replace_fraction=0.3
1840
+ pbt_mutation_rate=0.15
1841
+ pbt_replace_reward_gap=0.1
1842
+ pbt_replace_reward_gap_absolute=1e-06
1843
+ pbt_optimize_gamma=False
1844
+ pbt_target_objective=true_objective
1845
+ pbt_perturb_min=1.1
1846
+ pbt_perturb_max=1.5
1847
+ num_agents=-1
1848
+ num_humans=0
1849
+ num_bots=-1
1850
+ start_bot_difficulty=None
1851
+ timelimit=None
1852
+ res_w=128
1853
+ res_h=72
1854
+ wide_aspect_ratio=False
1855
+ eval_env_frameskip=1
1856
+ fps=35
1857
+ command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
1858
+ cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
1859
+ git_hash=unknown
1860
+ git_repo_name=not a git repository
1861
+ [2023-06-19 14:36:15,418][00753] Saving configuration to /content/train_dir/default_experiment/config.json...
1862
+ [2023-06-19 14:36:15,423][00753] Rollout worker 0 uses device cpu
1863
+ [2023-06-19 14:36:15,425][00753] Rollout worker 1 uses device cpu
1864
+ [2023-06-19 14:36:15,427][00753] Rollout worker 2 uses device cpu
1865
+ [2023-06-19 14:36:15,429][00753] Rollout worker 3 uses device cpu
1866
+ [2023-06-19 14:36:15,430][00753] Rollout worker 4 uses device cpu
1867
+ [2023-06-19 14:36:15,431][00753] Rollout worker 5 uses device cpu
1868
+ [2023-06-19 14:36:15,432][00753] Rollout worker 6 uses device cpu
1869
+ [2023-06-19 14:36:15,434][00753] Rollout worker 7 uses device cpu
1870
+ [2023-06-19 14:36:15,435][00753] Rollout worker 8 uses device cpu
1871
+ [2023-06-19 14:36:15,436][00753] Rollout worker 9 uses device cpu
1872
+ [2023-06-19 14:36:15,437][00753] Rollout worker 10 uses device cpu
1873
+ [2023-06-19 14:36:15,439][00753] Rollout worker 11 uses device cpu
1874
+ [2023-06-19 14:36:15,557][00753] Using GPUs [0] for process 0 (actually maps to GPUs [0])
1875
+ [2023-06-19 14:36:15,560][00753] InferenceWorker_p0-w0: min num requests: 4
1876
+ [2023-06-19 14:36:15,607][00753] Starting all processes...
1877
+ [2023-06-19 14:36:15,608][00753] Starting process learner_proc0
1878
+ [2023-06-19 14:36:15,657][00753] Starting all processes...
1879
+ [2023-06-19 14:36:15,663][00753] Starting process inference_proc0-0
1880
+ [2023-06-19 14:36:15,665][00753] Starting process rollout_proc0
1881
+ [2023-06-19 14:36:15,679][00753] Starting process rollout_proc1
1882
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc2
1883
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc3
1884
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc4
1885
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc5
1886
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc6
1887
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc7
1888
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc8
1889
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc9
1890
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc10
1891
+ [2023-06-19 14:36:15,680][00753] Starting process rollout_proc11
1892
+ [2023-06-19 14:36:39,488][22299] Worker 3 uses CPU cores [1]
1893
+ [2023-06-19 14:36:39,604][00753] Heartbeat connected on RolloutWorker_w3
1894
+ [2023-06-19 14:36:39,792][22310] Worker 9 uses CPU cores [1]
1895
+ [2023-06-19 14:36:39,977][22295] Using GPUs [0] for process 0 (actually maps to GPUs [0])
1896
+ [2023-06-19 14:36:39,981][22295] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
1897
+ [2023-06-19 14:36:40,008][22303] Worker 8 uses CPU cores [0]
1898
+ [2023-06-19 14:36:40,015][22311] Worker 11 uses CPU cores [1]
1899
+ [2023-06-19 14:36:40,044][00753] Heartbeat connected on RolloutWorker_w9
1900
+ [2023-06-19 14:36:40,062][22295] Num visible devices: 1
1901
+ [2023-06-19 14:36:40,068][22300] Worker 4 uses CPU cores [0]
1902
+ [2023-06-19 14:36:40,079][22297] Worker 1 uses CPU cores [1]
1903
+ [2023-06-19 14:36:40,084][00753] Heartbeat connected on InferenceWorker_p0-w0
1904
+ [2023-06-19 14:36:40,083][22278] Using GPUs [0] for process 0 (actually maps to GPUs [0])
1905
+ [2023-06-19 14:36:40,087][22278] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
1906
+ [2023-06-19 14:36:40,088][22296] Worker 0 uses CPU cores [0]
1907
+ [2023-06-19 14:36:40,116][22309] Worker 10 uses CPU cores [0]
1908
+ [2023-06-19 14:36:40,119][22304] Worker 7 uses CPU cores [1]
1909
+ [2023-06-19 14:36:40,127][00753] Heartbeat connected on RolloutWorker_w8
1910
+ [2023-06-19 14:36:40,132][22298] Worker 2 uses CPU cores [0]
1911
+ [2023-06-19 14:36:40,135][22278] Num visible devices: 1
1912
+ [2023-06-19 14:36:40,151][22302] Worker 6 uses CPU cores [0]
1913
+ [2023-06-19 14:36:40,156][00753] Heartbeat connected on RolloutWorker_w0
1914
+ [2023-06-19 14:36:40,157][00753] Heartbeat connected on RolloutWorker_w4
1915
+ [2023-06-19 14:36:40,161][00753] Heartbeat connected on RolloutWorker_w10
1916
+ [2023-06-19 14:36:40,169][00753] Heartbeat connected on RolloutWorker_w11
1917
+ [2023-06-19 14:36:40,176][22278] Starting seed is not provided
1918
+ [2023-06-19 14:36:40,177][22278] Using GPUs [0] for process 0 (actually maps to GPUs [0])
1919
+ [2023-06-19 14:36:40,178][22278] Initializing actor-critic model on device cuda:0
1920
+ [2023-06-19 14:36:40,176][00753] Heartbeat connected on RolloutWorker_w2
1921
+ [2023-06-19 14:36:40,178][22278] RunningMeanStd input shape: (3, 72, 128)
1922
+ [2023-06-19 14:36:40,182][22278] RunningMeanStd input shape: (1,)
1923
+ [2023-06-19 14:36:40,181][00753] Heartbeat connected on RolloutWorker_w6
1924
+ [2023-06-19 14:36:40,183][00753] Heartbeat connected on RolloutWorker_w7
1925
+ [2023-06-19 14:36:40,187][00753] Heartbeat connected on RolloutWorker_w1
1926
+ [2023-06-19 14:36:40,194][00753] Heartbeat connected on Batcher_0
1927
+ [2023-06-19 14:36:40,213][22278] ConvEncoder: input_channels=3
1928
+ [2023-06-19 14:36:40,248][22301] Worker 5 uses CPU cores [1]
1929
+ [2023-06-19 14:36:40,259][00753] Heartbeat connected on RolloutWorker_w5
1930
+ [2023-06-19 14:36:40,355][22278] Conv encoder output size: 512
1931
+ [2023-06-19 14:36:40,356][22278] Policy head output size: 512
1932
+ [2023-06-19 14:36:40,375][22278] Created Actor Critic model with architecture:
1933
+ [2023-06-19 14:36:40,376][22278] ActorCriticSharedWeights(
1934
+ (obs_normalizer): ObservationNormalizer(
1935
+ (running_mean_std): RunningMeanStdDictInPlace(
1936
+ (running_mean_std): ModuleDict(
1937
+ (obs): RunningMeanStdInPlace()
1938
+ )
1939
+ )
1940
+ )
1941
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
1942
+ (encoder): VizdoomEncoder(
1943
+ (basic_encoder): ConvEncoder(
1944
+ (enc): RecursiveScriptModule(
1945
+ original_name=ConvEncoderImpl
1946
+ (conv_head): RecursiveScriptModule(
1947
+ original_name=Sequential
1948
+ (0): RecursiveScriptModule(original_name=Conv2d)
1949
+ (1): RecursiveScriptModule(original_name=ELU)
1950
+ (2): RecursiveScriptModule(original_name=Conv2d)
1951
+ (3): RecursiveScriptModule(original_name=ELU)
1952
+ (4): RecursiveScriptModule(original_name=Conv2d)
1953
+ (5): RecursiveScriptModule(original_name=ELU)
1954
+ )
1955
+ (mlp_layers): RecursiveScriptModule(
1956
+ original_name=Sequential
1957
+ (0): RecursiveScriptModule(original_name=Linear)
1958
+ (1): RecursiveScriptModule(original_name=ELU)
1959
+ )
1960
+ )
1961
+ )
1962
+ )
1963
+ (core): ModelCoreRNN(
1964
+ (core): GRU(512, 512)
1965
+ )
1966
+ (decoder): MlpDecoder(
1967
+ (mlp): Identity()
1968
+ )
1969
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
1970
+ (action_parameterization): ActionParameterizationDefault(
1971
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
1972
+ )
1973
+ )
1974
+ [2023-06-19 14:36:40,600][22278] Using optimizer <class 'torch.optim.adam.Adam'>
1975
+ [2023-06-19 14:36:40,601][22278] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
1976
+ [2023-06-19 14:36:40,636][22278] Loading model from checkpoint
1977
+ [2023-06-19 14:36:40,641][22278] Loaded experiment state at self.train_step=978, self.env_steps=4005888
1978
+ [2023-06-19 14:36:40,641][22278] Initialized policy 0 weights for model version 978
1979
+ [2023-06-19 14:36:40,648][22278] LearnerWorker_p0 finished initialization!
1980
+ [2023-06-19 14:36:40,649][22278] Using GPUs [0] for process 0 (actually maps to GPUs [0])
1981
+ [2023-06-19 14:36:40,650][00753] Heartbeat connected on LearnerWorker_p0
1982
+ [2023-06-19 14:36:40,856][22295] RunningMeanStd input shape: (3, 72, 128)
1983
+ [2023-06-19 14:36:40,857][22295] RunningMeanStd input shape: (1,)
1984
+ [2023-06-19 14:36:40,870][22295] ConvEncoder: input_channels=3
1985
+ [2023-06-19 14:36:40,978][22295] Conv encoder output size: 512
1986
+ [2023-06-19 14:36:40,979][22295] Policy head output size: 512
1987
+ [2023-06-19 14:36:41,041][00753] Inference worker 0-0 is ready!
1988
+ [2023-06-19 14:36:41,042][00753] All inference workers are ready! Signal rollout workers to start!
1989
+ [2023-06-19 14:36:41,214][22309] Doom resolution: 160x120, resize resolution: (128, 72)
1990
+ [2023-06-19 14:36:41,233][22297] Doom resolution: 160x120, resize resolution: (128, 72)
1991
+ [2023-06-19 14:36:41,241][22301] Doom resolution: 160x120, resize resolution: (128, 72)
1992
+ [2023-06-19 14:36:41,243][22304] Doom resolution: 160x120, resize resolution: (128, 72)
1993
+ [2023-06-19 14:36:41,246][22311] Doom resolution: 160x120, resize resolution: (128, 72)
1994
+ [2023-06-19 14:36:41,243][22296] Doom resolution: 160x120, resize resolution: (128, 72)
1995
+ [2023-06-19 14:36:41,247][22298] Doom resolution: 160x120, resize resolution: (128, 72)
1996
+ [2023-06-19 14:36:41,259][22300] Doom resolution: 160x120, resize resolution: (128, 72)
1997
+ [2023-06-19 14:36:41,264][22310] Doom resolution: 160x120, resize resolution: (128, 72)
1998
+ [2023-06-19 14:36:41,258][22302] Doom resolution: 160x120, resize resolution: (128, 72)
1999
+ [2023-06-19 14:36:41,266][22299] Doom resolution: 160x120, resize resolution: (128, 72)
2000
+ [2023-06-19 14:36:41,263][22303] Doom resolution: 160x120, resize resolution: (128, 72)
2001
+ [2023-06-19 14:36:43,083][22298] Decorrelating experience for 0 frames...
2002
+ [2023-06-19 14:36:43,087][22300] Decorrelating experience for 0 frames...
2003
+ [2023-06-19 14:36:43,088][22309] Decorrelating experience for 0 frames...
2004
+ [2023-06-19 14:36:43,247][22310] Decorrelating experience for 0 frames...
2005
+ [2023-06-19 14:36:43,249][22304] Decorrelating experience for 0 frames...
2006
+ [2023-06-19 14:36:43,254][22301] Decorrelating experience for 0 frames...
2007
+ [2023-06-19 14:36:43,257][22297] Decorrelating experience for 0 frames...
2008
+ [2023-06-19 14:36:43,259][22299] Decorrelating experience for 0 frames...
2009
+ [2023-06-19 14:36:43,367][00753] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
2010
+ [2023-06-19 14:36:44,486][22299] Decorrelating experience for 32 frames...
2011
+ [2023-06-19 14:36:44,488][22297] Decorrelating experience for 32 frames...
2012
+ [2023-06-19 14:36:44,495][22310] Decorrelating experience for 32 frames...
2013
+ [2023-06-19 14:36:44,539][22300] Decorrelating experience for 32 frames...
2014
+ [2023-06-19 14:36:44,537][22309] Decorrelating experience for 32 frames...
2015
+ [2023-06-19 14:36:44,992][22302] Decorrelating experience for 0 frames...
2016
+ [2023-06-19 14:36:44,995][22303] Decorrelating experience for 0 frames...
2017
+ [2023-06-19 14:36:46,139][22304] Decorrelating experience for 32 frames...
2018
+ [2023-06-19 14:36:46,160][22301] Decorrelating experience for 32 frames...
2019
+ [2023-06-19 14:36:46,208][22296] Decorrelating experience for 0 frames...
2020
+ [2023-06-19 14:36:46,406][22297] Decorrelating experience for 64 frames...
2021
+ [2023-06-19 14:36:46,417][22310] Decorrelating experience for 64 frames...
2022
+ [2023-06-19 14:36:46,457][22300] Decorrelating experience for 64 frames...
2023
+ [2023-06-19 14:36:46,646][22303] Decorrelating experience for 32 frames...
2024
+ [2023-06-19 14:36:46,648][22298] Decorrelating experience for 32 frames...
2025
+ [2023-06-19 14:36:47,782][22311] Decorrelating experience for 0 frames...
2026
+ [2023-06-19 14:36:47,868][22296] Decorrelating experience for 32 frames...
2027
+ [2023-06-19 14:36:48,045][22310] Decorrelating experience for 96 frames...
2028
+ [2023-06-19 14:36:48,108][22302] Decorrelating experience for 32 frames...
2029
+ [2023-06-19 14:36:48,207][22304] Decorrelating experience for 64 frames...
2030
+ [2023-06-19 14:36:48,270][22299] Decorrelating experience for 64 frames...
2031
+ [2023-06-19 14:36:48,367][00753] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
2032
+ [2023-06-19 14:36:48,555][22298] Decorrelating experience for 64 frames...
2033
+ [2023-06-19 14:36:48,556][22303] Decorrelating experience for 64 frames...
2034
+ [2023-06-19 14:36:49,352][22311] Decorrelating experience for 32 frames...
2035
+ [2023-06-19 14:36:49,587][22304] Decorrelating experience for 96 frames...
2036
+ [2023-06-19 14:36:49,707][22300] Decorrelating experience for 96 frames...
2037
+ [2023-06-19 14:36:49,714][22296] Decorrelating experience for 64 frames...
2038
+ [2023-06-19 14:36:50,839][22298] Decorrelating experience for 96 frames...
2039
+ [2023-06-19 14:36:52,493][22302] Decorrelating experience for 64 frames...
2040
+ [2023-06-19 14:36:53,370][00753] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 125.2. Samples: 1252. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
2041
+ [2023-06-19 14:36:53,372][00753] Avg episode reward: [(0, '4.357')]
2042
+ [2023-06-19 14:36:53,446][22299] Decorrelating experience for 96 frames...
2043
+ [2023-06-19 14:36:54,089][22311] Decorrelating experience for 64 frames...
2044
+ [2023-06-19 14:36:54,305][22303] Decorrelating experience for 96 frames...
2045
+ [2023-06-19 14:36:54,934][22296] Decorrelating experience for 96 frames...
2046
+ [2023-06-19 14:36:58,366][00753] Fps is (10 sec: 409.6, 60 sec: 273.1, 300 sec: 273.1). Total num frames: 4009984. Throughput: 0: 131.5. Samples: 1972. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
2047
+ [2023-06-19 14:36:58,373][00753] Avg episode reward: [(0, '6.364')]
2048
+ [2023-06-19 14:36:58,720][22301] Decorrelating experience for 64 frames...
2049
+ [2023-06-19 14:37:00,102][22278] Signal inference workers to stop experience collection...
2050
+ [2023-06-19 14:37:00,136][22295] InferenceWorker_p0-w0: stopping experience collection
2051
+ [2023-06-19 14:37:00,246][22278] Signal inference workers to resume experience collection...
2052
+ [2023-06-19 14:37:00,248][22295] InferenceWorker_p0-w0: resuming experience collection
2053
+ [2023-06-19 14:37:00,881][22311] Decorrelating experience for 96 frames...
2054
+ [2023-06-19 14:37:01,859][22309] Decorrelating experience for 64 frames...
2055
+ [2023-06-19 14:37:02,338][22302] Decorrelating experience for 96 frames...
2056
+ [2023-06-19 14:37:03,369][00753] Fps is (10 sec: 2048.2, 60 sec: 1023.9, 300 sec: 1023.9). Total num frames: 4026368. Throughput: 0: 228.6. Samples: 4572. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2057
+ [2023-06-19 14:37:03,372][00753] Avg episode reward: [(0, '7.372')]
2058
+ [2023-06-19 14:37:06,350][22309] Decorrelating experience for 96 frames...
2059
+ [2023-06-19 14:37:06,391][22297] Decorrelating experience for 96 frames...
2060
+ [2023-06-19 14:37:07,239][22301] Decorrelating experience for 96 frames...
2061
+ [2023-06-19 14:37:08,366][00753] Fps is (10 sec: 3276.8, 60 sec: 1474.6, 300 sec: 1474.6). Total num frames: 4042752. Throughput: 0: 388.1. Samples: 9702. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
2062
+ [2023-06-19 14:37:08,371][00753] Avg episode reward: [(0, '10.755')]
2063
+ [2023-06-19 14:37:09,179][22295] Updated weights for policy 0, policy_version 988 (0.0024)
2064
+ [2023-06-19 14:37:13,366][00753] Fps is (10 sec: 3687.3, 60 sec: 1911.5, 300 sec: 1911.5). Total num frames: 4063232. Throughput: 0: 442.4. Samples: 13272. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2065
+ [2023-06-19 14:37:13,373][00753] Avg episode reward: [(0, '12.563')]
2066
+ [2023-06-19 14:37:18,366][00753] Fps is (10 sec: 3686.4, 60 sec: 2106.5, 300 sec: 2106.5). Total num frames: 4079616. Throughput: 0: 521.0. Samples: 18236. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2067
+ [2023-06-19 14:37:18,369][00753] Avg episode reward: [(0, '14.803')]
2068
+ [2023-06-19 14:37:20,866][22295] Updated weights for policy 0, policy_version 998 (0.0012)
2069
+ [2023-06-19 14:37:23,367][00753] Fps is (10 sec: 2867.1, 60 sec: 2150.4, 300 sec: 2150.4). Total num frames: 4091904. Throughput: 0: 576.4. Samples: 23056. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2070
+ [2023-06-19 14:37:23,374][00753] Avg episode reward: [(0, '18.143')]
2071
+ [2023-06-19 14:37:28,366][00753] Fps is (10 sec: 3686.4, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 4116480. Throughput: 0: 577.7. Samples: 25996. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2072
+ [2023-06-19 14:37:28,369][00753] Avg episode reward: [(0, '19.802')]
2073
+ [2023-06-19 14:37:30,628][22295] Updated weights for policy 0, policy_version 1008 (0.0013)
2074
+ [2023-06-19 14:37:33,367][00753] Fps is (10 sec: 4915.3, 60 sec: 2703.4, 300 sec: 2703.4). Total num frames: 4141056. Throughput: 0: 738.5. Samples: 33232. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2075
+ [2023-06-19 14:37:33,373][00753] Avg episode reward: [(0, '22.458')]
2076
+ [2023-06-19 14:37:38,366][00753] Fps is (10 sec: 4096.0, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 4157440. Throughput: 0: 837.6. Samples: 38942. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2077
+ [2023-06-19 14:37:38,376][00753] Avg episode reward: [(0, '23.440')]
2078
+ [2023-06-19 14:37:41,628][22295] Updated weights for policy 0, policy_version 1018 (0.0027)
2079
+ [2023-06-19 14:37:43,366][00753] Fps is (10 sec: 3276.8, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 4173824. Throughput: 0: 875.1. Samples: 41350. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2080
+ [2023-06-19 14:37:43,374][00753] Avg episode reward: [(0, '24.698')]
2081
+ [2023-06-19 14:37:48,366][00753] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 4190208. Throughput: 0: 922.5. Samples: 46084. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2082
+ [2023-06-19 14:37:48,376][00753] Avg episode reward: [(0, '27.588')]
2083
+ [2023-06-19 14:37:51,962][22295] Updated weights for policy 0, policy_version 1028 (0.0016)
2084
+ [2023-06-19 14:37:53,367][00753] Fps is (10 sec: 4096.0, 60 sec: 3481.8, 300 sec: 2984.2). Total num frames: 4214784. Throughput: 0: 967.2. Samples: 53226. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2085
+ [2023-06-19 14:37:53,380][00753] Avg episode reward: [(0, '25.768')]
2086
+ [2023-06-19 14:37:58,369][00753] Fps is (10 sec: 4504.5, 60 sec: 3754.5, 300 sec: 3058.2). Total num frames: 4235264. Throughput: 0: 967.6. Samples: 56816. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2087
+ [2023-06-19 14:37:58,371][00753] Avg episode reward: [(0, '25.108')]
2088
+ [2023-06-19 14:38:02,515][22295] Updated weights for policy 0, policy_version 1038 (0.0011)
2089
+ [2023-06-19 14:38:03,367][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 3072.0). Total num frames: 4251648. Throughput: 0: 971.7. Samples: 61964. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2090
+ [2023-06-19 14:38:03,373][00753] Avg episode reward: [(0, '25.022')]
2091
+ [2023-06-19 14:38:08,366][00753] Fps is (10 sec: 3277.6, 60 sec: 3754.7, 300 sec: 3084.0). Total num frames: 4268032. Throughput: 0: 969.5. Samples: 66682. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2092
+ [2023-06-19 14:38:08,371][00753] Avg episode reward: [(0, '25.362')]
2093
+ [2023-06-19 14:38:13,367][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3140.3). Total num frames: 4288512. Throughput: 0: 965.4. Samples: 69440. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2094
+ [2023-06-19 14:38:13,374][00753] Avg episode reward: [(0, '24.075')]
2095
+ [2023-06-19 14:38:13,384][22278] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001047_4288512.pth...
2096
+ [2023-06-19 14:38:13,516][22278] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000933_3821568.pth
2097
+ [2023-06-19 14:38:13,731][22295] Updated weights for policy 0, policy_version 1048 (0.0035)
2098
+ [2023-06-19 14:38:18,366][00753] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3233.7). Total num frames: 4313088. Throughput: 0: 962.4. Samples: 76540. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2099
+ [2023-06-19 14:38:18,368][00753] Avg episode reward: [(0, '25.057')]
2100
+ [2023-06-19 14:38:23,350][22295] Updated weights for policy 0, policy_version 1058 (0.0020)
2101
+ [2023-06-19 14:38:23,367][00753] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3276.8). Total num frames: 4333568. Throughput: 0: 968.5. Samples: 82526. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2102
+ [2023-06-19 14:38:23,369][00753] Avg episode reward: [(0, '25.397')]
2103
+ [2023-06-19 14:38:28,366][00753] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3237.8). Total num frames: 4345856. Throughput: 0: 967.2. Samples: 84874. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2104
+ [2023-06-19 14:38:28,372][00753] Avg episode reward: [(0, '25.798')]
2105
+ [2023-06-19 14:38:33,366][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3239.6). Total num frames: 4362240. Throughput: 0: 968.5. Samples: 89666. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2106
+ [2023-06-19 14:38:33,369][00753] Avg episode reward: [(0, '26.800')]
2107
+ [2023-06-19 14:38:34,887][22295] Updated weights for policy 0, policy_version 1068 (0.0021)
2108
+ [2023-06-19 14:38:38,366][00753] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3312.4). Total num frames: 4386816. Throughput: 0: 966.7. Samples: 96728. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2109
+ [2023-06-19 14:38:38,373][00753] Avg episode reward: [(0, '26.468')]
2110
+ [2023-06-19 14:38:43,367][00753] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3379.2). Total num frames: 4411392. Throughput: 0: 967.6. Samples: 100356. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2111
+ [2023-06-19 14:38:43,373][00753] Avg episode reward: [(0, '28.813')]
2112
+ [2023-06-19 14:38:44,016][22295] Updated weights for policy 0, policy_version 1078 (0.0012)
2113
+ [2023-06-19 14:38:48,366][00753] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3375.1). Total num frames: 4427776. Throughput: 0: 972.0. Samples: 105706. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2114
+ [2023-06-19 14:38:48,373][00753] Avg episode reward: [(0, '29.018')]
2115
+ [2023-06-19 14:38:53,369][00753] Fps is (10 sec: 3275.9, 60 sec: 3822.8, 300 sec: 3371.3). Total num frames: 4444160. Throughput: 0: 973.0. Samples: 110472. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2116
+ [2023-06-19 14:38:53,374][00753] Avg episode reward: [(0, '27.659')]
2117
+ [2023-06-19 14:38:56,289][22295] Updated weights for policy 0, policy_version 1088 (0.0022)
2118
+ [2023-06-19 14:38:58,367][00753] Fps is (10 sec: 3686.4, 60 sec: 3823.1, 300 sec: 3398.2). Total num frames: 4464640. Throughput: 0: 970.4. Samples: 113108. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2119
+ [2023-06-19 14:38:58,372][00753] Avg episode reward: [(0, '28.410')]
2120
+ [2023-06-19 14:39:03,367][00753] Fps is (10 sec: 4506.9, 60 sec: 3959.5, 300 sec: 3452.3). Total num frames: 4489216. Throughput: 0: 971.8. Samples: 120270. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2121
+ [2023-06-19 14:39:03,373][00753] Avg episode reward: [(0, '27.645')]
2122
+ [2023-06-19 14:39:04,933][22295] Updated weights for policy 0, policy_version 1098 (0.0017)
2123
+ [2023-06-19 14:39:08,367][00753] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3446.3). Total num frames: 4505600. Throughput: 0: 973.9. Samples: 126350. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2124
+ [2023-06-19 14:39:08,373][00753] Avg episode reward: [(0, '24.769')]
2125
+ [2023-06-19 14:39:13,368][00753] Fps is (10 sec: 3276.5, 60 sec: 3891.1, 300 sec: 3440.6). Total num frames: 4521984. Throughput: 0: 973.1. Samples: 128664. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2126
+ [2023-06-19 14:39:13,371][00753] Avg episode reward: [(0, '24.195')]
2127
+ [2023-06-19 14:39:17,415][22295] Updated weights for policy 0, policy_version 1108 (0.0025)
2128
+ [2023-06-19 14:39:18,367][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3435.4). Total num frames: 4538368. Throughput: 0: 973.0. Samples: 133452. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2129
+ [2023-06-19 14:39:18,369][00753] Avg episode reward: [(0, '23.530')]
2130
+ [2023-06-19 14:39:23,367][00753] Fps is (10 sec: 4096.4, 60 sec: 3822.9, 300 sec: 3481.6). Total num frames: 4562944. Throughput: 0: 974.4. Samples: 140578. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2131
+ [2023-06-19 14:39:23,373][00753] Avg episode reward: [(0, '22.835')]
2132
+ [2023-06-19 14:39:26,090][22295] Updated weights for policy 0, policy_version 1118 (0.0020)
2133
+ [2023-06-19 14:39:28,367][00753] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3525.0). Total num frames: 4587520. Throughput: 0: 974.7. Samples: 144218. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2134
+ [2023-06-19 14:39:28,375][00753] Avg episode reward: [(0, '23.982')]
2135
+ [2023-06-19 14:39:33,367][00753] Fps is (10 sec: 4095.9, 60 sec: 4027.7, 300 sec: 3517.7). Total num frames: 4603904. Throughput: 0: 978.8. Samples: 149754. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2136
+ [2023-06-19 14:39:33,369][00753] Avg episode reward: [(0, '24.738')]
2137
+ [2023-06-19 14:39:38,103][22295] Updated weights for policy 0, policy_version 1128 (0.0012)
2138
+ [2023-06-19 14:39:38,366][00753] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3510.9). Total num frames: 4620288. Throughput: 0: 979.4. Samples: 154540. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2139
+ [2023-06-19 14:39:38,369][00753] Avg episode reward: [(0, '24.929')]
2140
+ [2023-06-19 14:39:43,367][00753] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3527.1). Total num frames: 4640768. Throughput: 0: 981.4. Samples: 157270. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2141
+ [2023-06-19 14:39:43,373][00753] Avg episode reward: [(0, '24.468')]
2142
+ [2023-06-19 14:39:47,183][22295] Updated weights for policy 0, policy_version 1138 (0.0033)
2143
+ [2023-06-19 14:39:48,366][00753] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3564.6). Total num frames: 4665344. Throughput: 0: 983.2. Samples: 164512. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2144
+ [2023-06-19 14:39:48,369][00753] Avg episode reward: [(0, '26.204')]
2145
+ [2023-06-19 14:39:53,367][00753] Fps is (10 sec: 4505.6, 60 sec: 4027.9, 300 sec: 3578.6). Total num frames: 4685824. Throughput: 0: 987.2. Samples: 170774. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2146
+ [2023-06-19 14:39:53,373][00753] Avg episode reward: [(0, '26.814')]
2147
+ [2023-06-19 14:39:57,949][22295] Updated weights for policy 0, policy_version 1148 (0.0058)
2148
+ [2023-06-19 14:39:58,366][00753] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3570.9). Total num frames: 4702208. Throughput: 0: 987.9. Samples: 173120. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2149
+ [2023-06-19 14:39:58,372][00753] Avg episode reward: [(0, '25.868')]
2150
+ [2023-06-19 14:40:03,367][00753] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3563.5). Total num frames: 4718592. Throughput: 0: 989.6. Samples: 177984. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
2151
+ [2023-06-19 14:40:03,369][00753] Avg episode reward: [(0, '26.029')]
2152
+ [2023-06-19 14:40:08,366][00753] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3576.5). Total num frames: 4739072. Throughput: 0: 983.1. Samples: 184818. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2153
+ [2023-06-19 14:40:08,370][00753] Avg episode reward: [(0, '27.939')]
2154
+ [2023-06-19 14:40:08,387][22295] Updated weights for policy 0, policy_version 1158 (0.0032)
2155
+ [2023-06-19 14:40:13,367][00753] Fps is (10 sec: 4505.5, 60 sec: 4027.8, 300 sec: 3608.4). Total num frames: 4763648. Throughput: 0: 981.5. Samples: 188384. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
2156
+ [2023-06-19 14:40:13,376][00753] Avg episode reward: [(0, '27.435')]
2157
+ [2023-06-19 14:40:13,386][22278] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001163_4763648.pth...
2158
+ [2023-06-19 14:40:13,564][22278] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
2159
+ [2023-06-19 14:40:18,366][00753] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3600.7). Total num frames: 4780032. Throughput: 0: 980.7. Samples: 193886. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2160
+ [2023-06-19 14:40:18,372][00753] Avg episode reward: [(0, '26.868')]
2161
+ [2023-06-19 14:40:19,029][22295] Updated weights for policy 0, policy_version 1168 (0.0032)
2162
+ [2023-06-19 14:40:23,367][00753] Fps is (10 sec: 3276.9, 60 sec: 3891.2, 300 sec: 3593.3). Total num frames: 4796416. Throughput: 0: 979.8. Samples: 198632. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2163
+ [2023-06-19 14:40:23,368][00753] Avg episode reward: [(0, '27.007')]
2164
+ [2023-06-19 14:40:28,367][00753] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3604.5). Total num frames: 4816896. Throughput: 0: 978.0. Samples: 201278. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2165
+ [2023-06-19 14:40:28,370][00753] Avg episode reward: [(0, '28.959')]
2166
+ [2023-06-19 14:40:29,866][22295] Updated weights for policy 0, policy_version 1178 (0.0017)
2167
+ [2023-06-19 14:40:33,366][00753] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3633.0). Total num frames: 4841472. Throughput: 0: 979.7. Samples: 208600. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2168
+ [2023-06-19 14:40:33,369][00753] Avg episode reward: [(0, '27.656')]
2169
+ [2023-06-19 14:40:38,366][00753] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3625.4). Total num frames: 4857856. Throughput: 0: 977.2. Samples: 214746. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
2170
+ [2023-06-19 14:40:38,369][00753] Avg episode reward: [(0, '27.204')]
2171
+ [2023-06-19 14:40:39,109][22295] Updated weights for policy 0, policy_version 1188 (0.0026)
2172
+ [2023-06-19 14:40:43,370][00753] Fps is (10 sec: 3685.1, 60 sec: 3959.2, 300 sec: 3635.1). Total num frames: 4878336. Throughput: 0: 979.5. Samples: 217200. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
2173
+ [2023-06-19 14:40:43,372][00753] Avg episode reward: [(0, '27.556')]
2174
+ [2023-06-19 14:40:48,366][00753] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3627.9). Total num frames: 4894720. Throughput: 0: 978.4. Samples: 222010. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2175
+ [2023-06-19 14:40:48,371][00753] Avg episode reward: [(0, '27.730')]
2176
+ [2023-06-19 14:40:50,756][22295] Updated weights for policy 0, policy_version 1198 (0.0012)
2177
+ [2023-06-19 14:40:53,366][00753] Fps is (10 sec: 4097.4, 60 sec: 3891.2, 300 sec: 3653.6). Total num frames: 4919296. Throughput: 0: 979.2. Samples: 228884. Policy #0 lag: (min: 0.0, avg: 0.8, max: 3.0)
2178
+ [2023-06-19 14:40:53,374][00753] Avg episode reward: [(0, '26.206')]
2179
+ [2023-06-19 14:40:58,366][00753] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3678.4). Total num frames: 4943872. Throughput: 0: 980.9. Samples: 232526. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
2180
+ [2023-06-19 14:40:58,374][00753] Avg episode reward: [(0, '25.497')]
2181
+ [2023-06-19 14:40:59,940][22295] Updated weights for policy 0, policy_version 1208 (0.0022)
2182
+ [2023-06-19 14:41:03,366][00753] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3654.9). Total num frames: 4956160. Throughput: 0: 985.7. Samples: 238242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
2183
+ [2023-06-19 14:41:03,369][00753] Avg episode reward: [(0, '25.035')]
2184
+ [2023-06-19 14:41:08,367][00753] Fps is (10 sec: 2867.2, 60 sec: 3891.2, 300 sec: 3647.8). Total num frames: 4972544. Throughput: 0: 988.7. Samples: 243124. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
2185
+ [2023-06-19 14:41:08,373][00753] Avg episode reward: [(0, '25.931')]
2186
+ [2023-06-19 14:41:11,788][22295] Updated weights for policy 0, policy_version 1218 (0.0042)
2187
+ [2023-06-19 14:41:13,366][00753] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3656.1). Total num frames: 4993024. Throughput: 0: 985.4. Samples: 245620. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2188
+ [2023-06-19 14:41:13,374][00753] Avg episode reward: [(0, '24.143')]
2189
+ [2023-06-19 14:41:18,367][00753] Fps is (10 sec: 4505.4, 60 sec: 3959.4, 300 sec: 3678.9). Total num frames: 5017600. Throughput: 0: 983.4. Samples: 252852. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2190
+ [2023-06-19 14:41:18,369][00753] Avg episode reward: [(0, '25.066')]
2191
+ [2023-06-19 14:41:20,436][22295] Updated weights for policy 0, policy_version 1228 (0.0012)
2192
+ [2023-06-19 14:41:23,367][00753] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3686.4). Total num frames: 5038080. Throughput: 0: 990.6. Samples: 259322. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2193
+ [2023-06-19 14:41:23,369][00753] Avg episode reward: [(0, '26.740')]
2194
+ [2023-06-19 14:41:28,367][00753] Fps is (10 sec: 3686.5, 60 sec: 3959.5, 300 sec: 3679.2). Total num frames: 5054464. Throughput: 0: 990.0. Samples: 261748. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2195
+ [2023-06-19 14:41:28,369][00753] Avg episode reward: [(0, '26.941')]
2196
+ [2023-06-19 14:41:32,587][22295] Updated weights for policy 0, policy_version 1238 (0.0012)
2197
+ [2023-06-19 14:41:33,367][00753] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3672.3). Total num frames: 5070848. Throughput: 0: 990.0. Samples: 266560. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2198
+ [2023-06-19 14:41:33,369][00753] Avg episode reward: [(0, '28.274')]
2199
+ [2023-06-19 14:41:38,367][00753] Fps is (10 sec: 4095.9, 60 sec: 3959.4, 300 sec: 3693.3). Total num frames: 5095424. Throughput: 0: 983.9. Samples: 273160. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2200
+ [2023-06-19 14:41:38,369][00753] Avg episode reward: [(0, '27.551')]
2201
+ [2023-06-19 14:41:41,510][22295] Updated weights for policy 0, policy_version 1248 (0.0012)
2202
+ [2023-06-19 14:41:43,367][00753] Fps is (10 sec: 4915.2, 60 sec: 4028.0, 300 sec: 3776.7). Total num frames: 5120000. Throughput: 0: 983.6. Samples: 276786. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
2203
+ [2023-06-19 14:41:43,371][00753] Avg episode reward: [(0, '28.989')]
2204
+ [2023-06-19 14:41:48,366][00753] Fps is (10 sec: 3686.5, 60 sec: 3959.5, 300 sec: 3818.3). Total num frames: 5132288. Throughput: 0: 982.9. Samples: 282472. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2205
+ [2023-06-19 14:41:48,369][00753] Avg episode reward: [(0, '27.900')]
2206
+ [2023-06-19 14:41:53,367][00753] Fps is (10 sec: 2867.1, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 5148672. Throughput: 0: 981.1. Samples: 287272. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2207
+ [2023-06-19 14:41:53,374][00753] Avg episode reward: [(0, '27.637')]
2208
+ [2023-06-19 14:41:53,413][22295] Updated weights for policy 0, policy_version 1258 (0.0012)
2209
+ [2023-06-19 14:41:58,367][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3873.9). Total num frames: 5169152. Throughput: 0: 979.7. Samples: 289706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
2210
+ [2023-06-19 14:41:58,371][00753] Avg episode reward: [(0, '27.081')]
2211
+ [2023-06-19 14:42:02,707][22295] Updated weights for policy 0, policy_version 1268 (0.0021)
2212
+ [2023-06-19 14:42:03,366][00753] Fps is (10 sec: 4505.8, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 5193728. Throughput: 0: 978.9. Samples: 296904. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2213
+ [2023-06-19 14:42:03,371][00753] Avg episode reward: [(0, '27.350')]
2214
+ [2023-06-19 14:42:08,366][00753] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3901.6). Total num frames: 5214208. Throughput: 0: 974.8. Samples: 303186. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2215
+ [2023-06-19 14:42:08,370][00753] Avg episode reward: [(0, '27.132')]
2216
+ [2023-06-19 14:42:13,367][00753] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 5230592. Throughput: 0: 974.4. Samples: 305596. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2217
+ [2023-06-19 14:42:13,369][00753] Avg episode reward: [(0, '28.582')]
2218
+ [2023-06-19 14:42:13,387][22278] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001277_5230592.pth...
2219
+ [2023-06-19 14:42:13,551][22278] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001047_4288512.pth
2220
+ [2023-06-19 14:42:14,268][22295] Updated weights for policy 0, policy_version 1278 (0.0012)
2221
+ [2023-06-19 14:42:18,367][00753] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3915.5). Total num frames: 5246976. Throughput: 0: 972.5. Samples: 310324. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2222
+ [2023-06-19 14:42:18,372][00753] Avg episode reward: [(0, '28.962')]
2223
+ [2023-06-19 14:42:23,367][00753] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 5271552. Throughput: 0: 976.2. Samples: 317088. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2224
+ [2023-06-19 14:42:23,368][00753] Avg episode reward: [(0, '28.250')]
2225
+ [2023-06-19 14:42:24,003][22295] Updated weights for policy 0, policy_version 1288 (0.0019)
2226
+ [2023-06-19 14:42:28,366][00753] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 5296128. Throughput: 0: 976.3. Samples: 320718. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2227
+ [2023-06-19 14:42:28,371][00753] Avg episode reward: [(0, '29.213')]
2228
+ [2023-06-19 14:42:33,366][00753] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 5312512. Throughput: 0: 978.7. Samples: 326514. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2229
+ [2023-06-19 14:42:33,373][00753] Avg episode reward: [(0, '28.213')]
2230
+ [2023-06-19 14:42:34,383][22295] Updated weights for policy 0, policy_version 1298 (0.0031)
2231
+ [2023-06-19 14:42:38,367][00753] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 5328896. Throughput: 0: 980.9. Samples: 331412. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2232
+ [2023-06-19 14:42:38,375][00753] Avg episode reward: [(0, '28.573')]
2233
+ [2023-06-19 14:42:43,367][00753] Fps is (10 sec: 3276.7, 60 sec: 3754.6, 300 sec: 3915.5). Total num frames: 5345280. Throughput: 0: 981.5. Samples: 333876. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2234
+ [2023-06-19 14:42:43,369][00753] Avg episode reward: [(0, '27.184')]
2235
+ [2023-06-19 14:42:45,049][22295] Updated weights for policy 0, policy_version 1308 (0.0027)
2236
+ [2023-06-19 14:42:48,366][00753] Fps is (10 sec: 4096.2, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 5369856. Throughput: 0: 983.1. Samples: 341142. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2237
+ [2023-06-19 14:42:48,368][00753] Avg episode reward: [(0, '28.363')]
2238
+ [2023-06-19 14:42:53,369][00753] Fps is (10 sec: 4504.6, 60 sec: 4027.6, 300 sec: 3915.5). Total num frames: 5390336. Throughput: 0: 988.2. Samples: 347658. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2239
+ [2023-06-19 14:42:53,373][00753] Avg episode reward: [(0, '27.651')]
2240
+ [2023-06-19 14:42:54,792][22295] Updated weights for policy 0, policy_version 1318 (0.0014)
2241
+ [2023-06-19 14:42:58,366][00753] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 5406720. Throughput: 0: 987.3. Samples: 350024. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2242
+ [2023-06-19 14:42:58,372][00753] Avg episode reward: [(0, '27.618')]
2243
+ [2023-06-19 14:43:03,366][00753] Fps is (10 sec: 3277.6, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 5423104. Throughput: 0: 992.0. Samples: 354964. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2244
+ [2023-06-19 14:43:03,374][00753] Avg episode reward: [(0, '27.952')]
2245
+ [2023-06-19 14:43:06,170][22295] Updated weights for policy 0, policy_version 1328 (0.0032)
2246
+ [2023-06-19 14:43:08,366][00753] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 5447680. Throughput: 0: 989.9. Samples: 361634. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2247
+ [2023-06-19 14:43:08,372][00753] Avg episode reward: [(0, '28.384')]
2248
+ [2023-06-19 14:43:13,367][00753] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 5472256. Throughput: 0: 989.8. Samples: 365260. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2249
+ [2023-06-19 14:43:13,372][00753] Avg episode reward: [(0, '27.141')]
2250
+ [2023-06-19 14:43:15,087][22295] Updated weights for policy 0, policy_version 1338 (0.0014)
2251
+ [2023-06-19 14:43:18,366][00753] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 5488640. Throughput: 0: 990.6. Samples: 371090. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2252
+ [2023-06-19 14:43:18,369][00753] Avg episode reward: [(0, '26.356')]
2253
+ [2023-06-19 14:43:23,370][00753] Fps is (10 sec: 3275.6, 60 sec: 3891.0, 300 sec: 3929.3). Total num frames: 5505024. Throughput: 0: 987.7. Samples: 375862. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2254
+ [2023-06-19 14:43:23,377][00753] Avg episode reward: [(0, '26.087')]
2255
+ [2023-06-19 14:43:27,190][22295] Updated weights for policy 0, policy_version 1348 (0.0021)
2256
+ [2023-06-19 14:43:28,366][00753] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3943.3). Total num frames: 5525504. Throughput: 0: 987.3. Samples: 378306. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2257
+ [2023-06-19 14:43:28,374][00753] Avg episode reward: [(0, '24.648')]
2258
+ [2023-06-19 14:43:33,370][00753] Fps is (10 sec: 4505.8, 60 sec: 3959.3, 300 sec: 3943.2). Total num frames: 5550080. Throughput: 0: 982.6. Samples: 385362. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2259
+ [2023-06-19 14:43:33,372][00753] Avg episode reward: [(0, '24.712')]
2260
+ [2023-06-19 14:43:35,812][22295] Updated weights for policy 0, policy_version 1358 (0.0012)
2261
+ [2023-06-19 14:43:38,367][00753] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 5566464. Throughput: 0: 979.1. Samples: 391716. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2262
+ [2023-06-19 14:43:38,378][00753] Avg episode reward: [(0, '26.031')]
2263
+ [2023-06-19 14:43:43,367][00753] Fps is (10 sec: 3277.9, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 5582848. Throughput: 0: 979.2. Samples: 394090. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2264
+ [2023-06-19 14:43:43,369][00753] Avg episode reward: [(0, '26.289')]
2265
+ [2023-06-19 14:43:48,366][00753] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 5599232. Throughput: 0: 975.5. Samples: 398862. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2266
+ [2023-06-19 14:43:48,376][00753] Avg episode reward: [(0, '25.812')]
2267
+ [2023-06-19 14:43:48,815][22295] Updated weights for policy 0, policy_version 1368 (0.0032)
2268
+ [2023-06-19 14:43:53,367][00753] Fps is (10 sec: 4096.0, 60 sec: 3891.4, 300 sec: 3929.4). Total num frames: 5623808. Throughput: 0: 971.7. Samples: 405362. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2269
+ [2023-06-19 14:43:53,369][00753] Avg episode reward: [(0, '27.435')]
2270
+ [2023-06-19 14:43:57,357][22295] Updated weights for policy 0, policy_version 1378 (0.0022)
2271
+ [2023-06-19 14:43:58,366][00753] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 5648384. Throughput: 0: 971.3. Samples: 408968. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2272
+ [2023-06-19 14:43:58,375][00753] Avg episode reward: [(0, '29.401')]
2273
+ [2023-06-19 14:43:58,379][22278] Saving new best policy, reward=29.401!
2274
+ [2023-06-19 14:44:03,366][00753] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 5664768. Throughput: 0: 969.6. Samples: 414722. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2275
+ [2023-06-19 14:44:03,371][00753] Avg episode reward: [(0, '28.680')]
2276
+ [2023-06-19 14:44:08,369][00753] Fps is (10 sec: 3275.9, 60 sec: 3891.0, 300 sec: 3929.4). Total num frames: 5681152. Throughput: 0: 969.4. Samples: 419484. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2277
+ [2023-06-19 14:44:08,376][00753] Avg episode reward: [(0, '29.090')]
2278
+ [2023-06-19 14:44:09,491][22295] Updated weights for policy 0, policy_version 1388 (0.0011)
2279
+ [2023-06-19 14:44:13,367][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3929.4). Total num frames: 5697536. Throughput: 0: 967.4. Samples: 421838. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2280
+ [2023-06-19 14:44:13,373][00753] Avg episode reward: [(0, '28.578')]
2281
+ [2023-06-19 14:44:13,384][22278] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001391_5697536.pth...
2282
+ [2023-06-19 14:44:13,573][22278] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001163_4763648.pth
2283
+ [2023-06-19 14:44:18,367][00753] Fps is (10 sec: 4097.0, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 5722112. Throughput: 0: 965.4. Samples: 428802. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
2284
+ [2023-06-19 14:44:18,370][00753] Avg episode reward: [(0, '30.459')]
2285
+ [2023-06-19 14:44:18,382][22278] Saving new best policy, reward=30.459!
2286
+ [2023-06-19 14:44:19,022][22295] Updated weights for policy 0, policy_version 1398 (0.0016)
2287
+ [2023-06-19 14:44:23,368][00753] Fps is (10 sec: 4505.1, 60 sec: 3959.6, 300 sec: 3915.5). Total num frames: 5742592. Throughput: 0: 969.9. Samples: 435362. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2288
+ [2023-06-19 14:44:23,373][00753] Avg episode reward: [(0, '28.421')]
2289
+ [2023-06-19 14:44:28,367][00753] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 5758976. Throughput: 0: 970.5. Samples: 437764. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2290
+ [2023-06-19 14:44:28,369][00753] Avg episode reward: [(0, '27.132')]
2291
+ [2023-06-19 14:44:30,114][22295] Updated weights for policy 0, policy_version 1408 (0.0033)
2292
+ [2023-06-19 14:44:33,367][00753] Fps is (10 sec: 3277.2, 60 sec: 3754.9, 300 sec: 3915.5). Total num frames: 5775360. Throughput: 0: 970.1. Samples: 442518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
2293
+ [2023-06-19 14:44:33,371][00753] Avg episode reward: [(0, '28.250')]
2294
+ [2023-06-19 14:44:38,367][00753] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 5795840. Throughput: 0: 963.1. Samples: 448702. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2295
+ [2023-06-19 14:44:38,368][00753] Avg episode reward: [(0, '29.758')]
2296
+ [2023-06-19 14:44:40,242][22295] Updated weights for policy 0, policy_version 1418 (0.0012)
2297
+ [2023-06-19 14:44:43,367][00753] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 5820416. Throughput: 0: 962.8. Samples: 452296. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2298
+ [2023-06-19 14:44:43,369][00753] Avg episode reward: [(0, '29.920')]
2299
+ [2023-06-19 14:44:48,368][00753] Fps is (10 sec: 4504.9, 60 sec: 4027.6, 300 sec: 3915.5). Total num frames: 5840896. Throughput: 0: 971.1. Samples: 458424. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2300
+ [2023-06-19 14:44:48,378][00753] Avg episode reward: [(0, '30.304')]
2301
+ [2023-06-19 14:44:51,347][22295] Updated weights for policy 0, policy_version 1428 (0.0017)
2302
+ [2023-06-19 14:44:53,366][00753] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 5853184. Throughput: 0: 970.2. Samples: 463140. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
2303
+ [2023-06-19 14:44:53,372][00753] Avg episode reward: [(0, '30.202')]
2304
+ [2023-06-19 14:44:58,367][00753] Fps is (10 sec: 2867.6, 60 sec: 3686.4, 300 sec: 3901.6). Total num frames: 5869568. Throughput: 0: 970.2. Samples: 465498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
2305
+ [2023-06-19 14:44:58,369][00753] Avg episode reward: [(0, '32.907')]
2306
+ [2023-06-19 14:44:58,385][22278] Saving new best policy, reward=32.907!
2307
+ [2023-06-19 14:45:01,667][22295] Updated weights for policy 0, policy_version 1438 (0.0031)
2308
+ [2023-06-19 14:45:03,369][00753] Fps is (10 sec: 4504.3, 60 sec: 3891.0, 300 sec: 3929.3). Total num frames: 5898240. Throughput: 0: 965.5. Samples: 472250. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2309
+ [2023-06-19 14:45:03,372][00753] Avg episode reward: [(0, '30.852')]
2310
+ [2023-06-19 14:45:08,366][00753] Fps is (10 sec: 4915.2, 60 sec: 3959.7, 300 sec: 3915.5). Total num frames: 5918720. Throughput: 0: 972.4. Samples: 479118. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2311
+ [2023-06-19 14:45:08,370][00753] Avg episode reward: [(0, '27.310')]
2312
+ [2023-06-19 14:45:11,909][22295] Updated weights for policy 0, policy_version 1448 (0.0016)
2313
+ [2023-06-19 14:45:13,367][00753] Fps is (10 sec: 3687.4, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 5935104. Throughput: 0: 972.5. Samples: 481526. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
2314
+ [2023-06-19 14:45:13,370][00753] Avg episode reward: [(0, '27.353')]
2315
+ [2023-06-19 14:45:18,374][00753] Fps is (10 sec: 3274.4, 60 sec: 3822.5, 300 sec: 3915.4). Total num frames: 5951488. Throughput: 0: 973.3. Samples: 486322. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
2316
+ [2023-06-19 14:45:18,377][00753] Avg episode reward: [(0, '25.210')]
2317
+ [2023-06-19 14:45:22,942][22295] Updated weights for policy 0, policy_version 1458 (0.0021)
2318
+ [2023-06-19 14:45:23,366][00753] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3915.5). Total num frames: 5971968. Throughput: 0: 975.9. Samples: 492618. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2319
+ [2023-06-19 14:45:23,369][00753] Avg episode reward: [(0, '22.058')]
2320
+ [2023-06-19 14:45:28,367][00753] Fps is (10 sec: 4508.7, 60 sec: 3959.4, 300 sec: 3915.5). Total num frames: 5996544. Throughput: 0: 977.9. Samples: 496300. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
2321
+ [2023-06-19 14:45:28,369][00753] Avg episode reward: [(0, '22.318')]
2322
+ [2023-06-19 14:45:29,568][22278] Stopping Batcher_0...
2323
+ [2023-06-19 14:45:29,569][22278] Loop batcher_evt_loop terminating...
2324
+ [2023-06-19 14:45:29,570][00753] Component Batcher_0 stopped!
2325
+ [2023-06-19 14:45:29,572][22278] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth...
2326
+ [2023-06-19 14:45:29,671][22301] Stopping RolloutWorker_w5...
2327
+ [2023-06-19 14:45:29,671][22301] Loop rollout_proc5_evt_loop terminating...
2328
+ [2023-06-19 14:45:29,668][00753] Component RolloutWorker_w5 stopped!
2329
+ [2023-06-19 14:45:29,684][22302] Stopping RolloutWorker_w6...
2330
+ [2023-06-19 14:45:29,687][22296] Stopping RolloutWorker_w0...
2331
+ [2023-06-19 14:45:29,688][00753] Component RolloutWorker_w6 stopped!
2332
+ [2023-06-19 14:45:29,692][00753] Component RolloutWorker_w0 stopped!
2333
+ [2023-06-19 14:45:29,699][22309] Stopping RolloutWorker_w10...
2334
+ [2023-06-19 14:45:29,700][00753] Component RolloutWorker_w10 stopped!
2335
+ [2023-06-19 14:45:29,714][22296] Loop rollout_proc0_evt_loop terminating...
2336
+ [2023-06-19 14:45:29,718][22303] Stopping RolloutWorker_w8...
2337
+ [2023-06-19 14:45:29,719][00753] Component RolloutWorker_w8 stopped!
2338
+ [2023-06-19 14:45:29,722][22299] Stopping RolloutWorker_w3...
2339
+ [2023-06-19 14:45:29,720][22309] Loop rollout_proc10_evt_loop terminating...
2340
+ [2023-06-19 14:45:29,723][22299] Loop rollout_proc3_evt_loop terminating...
2341
+ [2023-06-19 14:45:29,722][00753] Component RolloutWorker_w3 stopped!
2342
+ [2023-06-19 14:45:29,689][22302] Loop rollout_proc6_evt_loop terminating...
2343
+ [2023-06-19 14:45:29,730][22310] Stopping RolloutWorker_w9...
2344
+ [2023-06-19 14:45:29,731][22310] Loop rollout_proc9_evt_loop terminating...
2345
+ [2023-06-19 14:45:29,730][00753] Component RolloutWorker_w9 stopped!
2346
+ [2023-06-19 14:45:29,718][22303] Loop rollout_proc8_evt_loop terminating...
2347
+ [2023-06-19 14:45:29,740][22297] Stopping RolloutWorker_w1...
2348
+ [2023-06-19 14:45:29,740][22297] Loop rollout_proc1_evt_loop terminating...
2349
+ [2023-06-19 14:45:29,738][00753] Component RolloutWorker_w1 stopped!
2350
+ [2023-06-19 14:45:29,744][22304] Stopping RolloutWorker_w7...
2351
+ [2023-06-19 14:45:29,743][00753] Component RolloutWorker_w7 stopped!
2352
+ [2023-06-19 14:45:29,751][22300] Stopping RolloutWorker_w4...
2353
+ [2023-06-19 14:45:29,752][22300] Loop rollout_proc4_evt_loop terminating...
2354
+ [2023-06-19 14:45:29,753][22298] Stopping RolloutWorker_w2...
2355
+ [2023-06-19 14:45:29,754][22298] Loop rollout_proc2_evt_loop terminating...
2356
+ [2023-06-19 14:45:29,753][00753] Component RolloutWorker_w4 stopped!
2357
+ [2023-06-19 14:45:29,762][00753] Component RolloutWorker_w2 stopped!
2358
+ [2023-06-19 14:45:29,748][22304] Loop rollout_proc7_evt_loop terminating...
2359
+ [2023-06-19 14:45:29,781][22295] Weights refcount: 2 0
2360
+ [2023-06-19 14:45:29,782][22295] Stopping InferenceWorker_p0-w0...
2361
+ [2023-06-19 14:45:29,782][22295] Loop inference_proc0-0_evt_loop terminating...
2362
+ [2023-06-19 14:45:29,783][00753] Component InferenceWorker_p0-w0 stopped!
2363
+ [2023-06-19 14:45:29,795][00753] Component RolloutWorker_w11 stopped!
2364
+ [2023-06-19 14:45:29,796][22311] Stopping RolloutWorker_w11...
2365
+ [2023-06-19 14:45:29,797][22311] Loop rollout_proc11_evt_loop terminating...
2366
+ [2023-06-19 14:45:29,823][22278] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001277_5230592.pth
2367
+ [2023-06-19 14:45:29,840][22278] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth...
2368
+ [2023-06-19 14:45:30,054][00753] Component LearnerWorker_p0 stopped!
2369
+ [2023-06-19 14:45:30,056][00753] Waiting for process learner_proc0 to stop...
2370
+ [2023-06-19 14:45:30,059][22278] Stopping LearnerWorker_p0...
2371
+ [2023-06-19 14:45:30,060][22278] Loop learner_proc0_evt_loop terminating...
2372
+ [2023-06-19 14:45:31,937][00753] Waiting for process inference_proc0-0 to join...
2373
+ [2023-06-19 14:45:32,377][00753] Waiting for process rollout_proc0 to join...
2374
+ [2023-06-19 14:45:36,938][00753] Waiting for process rollout_proc1 to join...
2375
+ [2023-06-19 14:45:36,968][00753] Waiting for process rollout_proc2 to join...
2376
+ [2023-06-19 14:45:36,970][00753] Waiting for process rollout_proc3 to join...
2377
+ [2023-06-19 14:45:36,971][00753] Waiting for process rollout_proc4 to join...
2378
+ [2023-06-19 14:45:36,973][00753] Waiting for process rollout_proc5 to join...
2379
+ [2023-06-19 14:45:36,977][00753] Waiting for process rollout_proc6 to join...
2380
+ [2023-06-19 14:45:36,982][00753] Waiting for process rollout_proc7 to join...
2381
+ [2023-06-19 14:45:36,983][00753] Waiting for process rollout_proc8 to join...
2382
+ [2023-06-19 14:45:36,985][00753] Waiting for process rollout_proc9 to join...
2383
+ [2023-06-19 14:45:36,987][00753] Waiting for process rollout_proc10 to join...
2384
+ [2023-06-19 14:45:36,989][00753] Waiting for process rollout_proc11 to join...
2385
+ [2023-06-19 14:45:36,991][00753] Batcher 0 profile tree view:
2386
+ batching: 15.1503, releasing_batches: 0.0120
2387
+ [2023-06-19 14:45:36,992][00753] InferenceWorker_p0-w0 profile tree view:
2388
+ wait_policy: 0.0108
2389
+ wait_policy_total: 324.6077
2390
+ update_model: 2.7738
2391
+ weight_update: 0.0024
2392
+ one_step: 0.0033
2393
+ handle_policy_step: 187.4206
2394
+ deserialize: 6.1076, stack: 0.9300, obs_to_device_normalize: 37.4810, forward: 98.0533, send_messages: 13.2084
2395
+ prepare_outputs: 23.5951
2396
+ to_cpu: 13.3490
2397
+ [2023-06-19 14:45:36,994][00753] Learner 0 profile tree view:
2398
+ misc: 0.0026, prepare_batch: 11.4592
2399
+ train: 39.3034
2400
+ epoch_init: 0.0029, minibatch_init: 0.0054, losses_postprocess: 0.2337, kl_divergence: 0.3921, after_optimizer: 1.6729
2401
+ calculate_losses: 14.1472
2402
+ losses_init: 0.0015, forward_head: 0.9955, bptt_initial: 8.6592, tail: 0.6937, advantages_returns: 0.1729, losses: 2.3929
2403
+ bptt: 1.0778
2404
+ bptt_forward_core: 1.0180
2405
+ update: 22.4473
2406
+ clip: 16.4902
2407
+ [2023-06-19 14:45:36,995][00753] RolloutWorker_w0 profile tree view:
2408
+ wait_for_trajectories: 0.2178, enqueue_policy_requests: 80.0690, env_step: 372.0584, overhead: 8.8974, complete_rollouts: 2.6271
2409
+ save_policy_outputs: 6.8942
2410
+ split_output_tensors: 3.4991
2411
+ [2023-06-19 14:45:36,997][00753] RolloutWorker_w11 profile tree view:
2412
+ wait_for_trajectories: 0.1147, enqueue_policy_requests: 81.5770, env_step: 366.0075, overhead: 8.1784, complete_rollouts: 2.7526
2413
+ save_policy_outputs: 6.5695
2414
+ split_output_tensors: 3.0774
2415
+ [2023-06-19 14:45:36,998][00753] Loop Runner_EvtLoop terminating...
2416
+ [2023-06-19 14:45:36,999][00753] Runner profile tree view:
2417
+ main_loop: 561.3929
2418
+ [2023-06-19 14:45:37,001][00753] Collected {0: 6004736}, FPS: 3560.5
2419
+ [2023-06-19 14:45:47,199][00753] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
2420
+ [2023-06-19 14:45:47,201][00753] Overriding arg 'num_workers' with value 1 passed from command line
2421
+ [2023-06-19 14:45:47,202][00753] Adding new argument 'no_render'=True that is not in the saved config file!
2422
+ [2023-06-19 14:45:47,204][00753] Adding new argument 'save_video'=True that is not in the saved config file!
2423
+ [2023-06-19 14:45:47,205][00753] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
2424
+ [2023-06-19 14:45:47,206][00753] Adding new argument 'video_name'=None that is not in the saved config file!
2425
+ [2023-06-19 14:45:47,207][00753] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
2426
+ [2023-06-19 14:45:47,208][00753] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
2427
+ [2023-06-19 14:45:47,209][00753] Adding new argument 'push_to_hub'=True that is not in the saved config file!
2428
+ [2023-06-19 14:45:47,210][00753] Adding new argument 'hf_repository'='Ditrip/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
2429
+ [2023-06-19 14:45:47,211][00753] Adding new argument 'policy_index'=0 that is not in the saved config file!
2430
+ [2023-06-19 14:45:47,212][00753] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
2431
+ [2023-06-19 14:45:47,213][00753] Adding new argument 'train_script'=None that is not in the saved config file!
2432
+ [2023-06-19 14:45:47,214][00753] Adding new argument 'enjoy_script'=None that is not in the saved config file!
2433
+ [2023-06-19 14:45:47,215][00753] Using frameskip 1 and render_action_repeat=4 for evaluation
2434
+ [2023-06-19 14:45:47,241][00753] RunningMeanStd input shape: (3, 72, 128)
2435
+ [2023-06-19 14:45:47,246][00753] RunningMeanStd input shape: (1,)
2436
+ [2023-06-19 14:45:47,266][00753] ConvEncoder: input_channels=3
2437
+ [2023-06-19 14:45:47,322][00753] Conv encoder output size: 512
2438
+ [2023-06-19 14:45:47,324][00753] Policy head output size: 512
2439
+ [2023-06-19 14:45:47,351][00753] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth...
2440
+ [2023-06-19 14:45:48,057][00753] Num frames 100...
2441
+ [2023-06-19 14:45:48,243][00753] Num frames 200...
2442
+ [2023-06-19 14:45:48,422][00753] Num frames 300...
2443
+ [2023-06-19 14:45:48,615][00753] Num frames 400...
2444
+ [2023-06-19 14:45:48,793][00753] Num frames 500...
2445
+ [2023-06-19 14:45:48,991][00753] Num frames 600...
2446
+ [2023-06-19 14:45:49,171][00753] Num frames 700...
2447
+ [2023-06-19 14:45:49,355][00753] Num frames 800...
2448
+ [2023-06-19 14:45:49,545][00753] Num frames 900...
2449
+ [2023-06-19 14:45:49,730][00753] Num frames 1000...
2450
+ [2023-06-19 14:45:49,918][00753] Num frames 1100...
2451
+ [2023-06-19 14:45:50,114][00753] Num frames 1200...
2452
+ [2023-06-19 14:45:50,301][00753] Num frames 1300...
2453
+ [2023-06-19 14:45:50,486][00753] Num frames 1400...
2454
+ [2023-06-19 14:45:50,672][00753] Num frames 1500...
2455
+ [2023-06-19 14:45:50,856][00753] Num frames 1600...
2456
+ [2023-06-19 14:45:50,986][00753] Num frames 1700...
2457
+ [2023-06-19 14:45:51,114][00753] Num frames 1800...
2458
+ [2023-06-19 14:45:51,243][00753] Num frames 1900...
2459
+ [2023-06-19 14:45:51,367][00753] Num frames 2000...
2460
+ [2023-06-19 14:45:51,496][00753] Num frames 2100...
2461
+ [2023-06-19 14:45:51,548][00753] Avg episode rewards: #0: 59.999, true rewards: #0: 21.000
2462
+ [2023-06-19 14:45:51,549][00753] Avg episode reward: 59.999, avg true_objective: 21.000
2463
+ [2023-06-19 14:45:51,672][00753] Num frames 2200...
2464
+ [2023-06-19 14:45:51,789][00753] Num frames 2300...
2465
+ [2023-06-19 14:45:51,918][00753] Num frames 2400...
2466
+ [2023-06-19 14:45:52,040][00753] Num frames 2500...
2467
+ [2023-06-19 14:45:52,181][00753] Num frames 2600...
2468
+ [2023-06-19 14:45:52,305][00753] Num frames 2700...
2469
+ [2023-06-19 14:45:52,425][00753] Num frames 2800...
2470
+ [2023-06-19 14:45:52,550][00753] Num frames 2900...
2471
+ [2023-06-19 14:45:52,670][00753] Num frames 3000...
2472
+ [2023-06-19 14:45:52,796][00753] Num frames 3100...
2473
+ [2023-06-19 14:45:52,936][00753] Avg episode rewards: #0: 42.854, true rewards: #0: 15.855
2474
+ [2023-06-19 14:45:52,937][00753] Avg episode reward: 42.854, avg true_objective: 15.855
2475
+ [2023-06-19 14:45:52,978][00753] Num frames 3200...
2476
+ [2023-06-19 14:45:53,113][00753] Num frames 3300...
2477
+ [2023-06-19 14:45:53,236][00753] Num frames 3400...
2478
+ [2023-06-19 14:45:53,362][00753] Num frames 3500...
2479
+ [2023-06-19 14:45:53,483][00753] Num frames 3600...
2480
+ [2023-06-19 14:45:53,608][00753] Num frames 3700...
2481
+ [2023-06-19 14:45:53,731][00753] Num frames 3800...
2482
+ [2023-06-19 14:45:53,859][00753] Num frames 3900...
2483
+ [2023-06-19 14:45:53,982][00753] Num frames 4000...
2484
+ [2023-06-19 14:45:54,115][00753] Num frames 4100...
2485
+ [2023-06-19 14:45:54,238][00753] Num frames 4200...
2486
+ [2023-06-19 14:45:54,366][00753] Num frames 4300...
2487
+ [2023-06-19 14:45:54,490][00753] Num frames 4400...
2488
+ [2023-06-19 14:45:54,616][00753] Num frames 4500...
2489
+ [2023-06-19 14:45:54,737][00753] Num frames 4600...
2490
+ [2023-06-19 14:45:54,861][00753] Num frames 4700...
2491
+ [2023-06-19 14:45:55,009][00753] Avg episode rewards: #0: 40.913, true rewards: #0: 15.913
2492
+ [2023-06-19 14:45:55,010][00753] Avg episode reward: 40.913, avg true_objective: 15.913
2493
+ [2023-06-19 14:45:55,043][00753] Num frames 4800...
2494
+ [2023-06-19 14:45:55,176][00753] Num frames 4900...
2495
+ [2023-06-19 14:45:55,295][00753] Num frames 5000...
2496
+ [2023-06-19 14:45:55,417][00753] Num frames 5100...
2497
+ [2023-06-19 14:45:55,539][00753] Num frames 5200...
2498
+ [2023-06-19 14:45:55,620][00753] Avg episode rewards: #0: 32.055, true rewards: #0: 13.055
2499
+ [2023-06-19 14:45:55,622][00753] Avg episode reward: 32.055, avg true_objective: 13.055
2500
+ [2023-06-19 14:45:55,716][00753] Num frames 5300...
2501
+ [2023-06-19 14:45:55,842][00753] Num frames 5400...
2502
+ [2023-06-19 14:45:55,963][00753] Num frames 5500...
2503
+ [2023-06-19 14:45:56,086][00753] Num frames 5600...
2504
+ [2023-06-19 14:45:56,221][00753] Num frames 5700...
2505
+ [2023-06-19 14:45:56,344][00753] Num frames 5800...
2506
+ [2023-06-19 14:45:56,468][00753] Num frames 5900...
2507
+ [2023-06-19 14:45:56,629][00753] Avg episode rewards: #0: 28.780, true rewards: #0: 11.980
2508
+ [2023-06-19 14:45:56,630][00753] Avg episode reward: 28.780, avg true_objective: 11.980
2509
+ [2023-06-19 14:45:56,648][00753] Num frames 6000...
2510
+ [2023-06-19 14:45:56,770][00753] Num frames 6100...
2511
+ [2023-06-19 14:45:56,889][00753] Num frames 6200...
2512
+ [2023-06-19 14:45:57,012][00753] Num frames 6300...
2513
+ [2023-06-19 14:45:57,139][00753] Num frames 6400...
2514
+ [2023-06-19 14:45:57,271][00753] Num frames 6500...
2515
+ [2023-06-19 14:45:57,398][00753] Num frames 6600...
2516
+ [2023-06-19 14:45:57,520][00753] Num frames 6700...
2517
+ [2023-06-19 14:45:57,642][00753] Num frames 6800...
2518
+ [2023-06-19 14:45:57,774][00753] Num frames 6900...
2519
+ [2023-06-19 14:45:57,852][00753] Avg episode rewards: #0: 28.030, true rewards: #0: 11.530
2520
+ [2023-06-19 14:45:57,853][00753] Avg episode reward: 28.030, avg true_objective: 11.530
2521
+ [2023-06-19 14:45:57,957][00753] Num frames 7000...
2522
+ [2023-06-19 14:45:58,086][00753] Num frames 7100...
2523
+ [2023-06-19 14:45:58,217][00753] Num frames 7200...
2524
+ [2023-06-19 14:45:58,344][00753] Num frames 7300...
2525
+ [2023-06-19 14:45:58,469][00753] Num frames 7400...
2526
+ [2023-06-19 14:45:58,591][00753] Num frames 7500...
2527
+ [2023-06-19 14:45:58,714][00753] Num frames 7600...
2528
+ [2023-06-19 14:45:58,838][00753] Num frames 7700...
2529
+ [2023-06-19 14:45:58,965][00753] Num frames 7800...
2530
+ [2023-06-19 14:45:59,091][00753] Num frames 7900...
2531
+ [2023-06-19 14:45:59,247][00753] Avg episode rewards: #0: 28.248, true rewards: #0: 11.391
2532
+ [2023-06-19 14:45:59,248][00753] Avg episode reward: 28.248, avg true_objective: 11.391
2533
+ [2023-06-19 14:45:59,284][00753] Num frames 8000...
2534
+ [2023-06-19 14:45:59,406][00753] Num frames 8100...
2535
+ [2023-06-19 14:45:59,537][00753] Num frames 8200...
2536
+ [2023-06-19 14:45:59,660][00753] Num frames 8300...
2537
+ [2023-06-19 14:45:59,783][00753] Num frames 8400...
2538
+ [2023-06-19 14:45:59,909][00753] Num frames 8500...
2539
+ [2023-06-19 14:46:00,033][00753] Num frames 8600...
2540
+ [2023-06-19 14:46:00,169][00753] Num frames 8700...
2541
+ [2023-06-19 14:46:00,297][00753] Num frames 8800...
2542
+ [2023-06-19 14:46:00,419][00753] Num frames 8900...
2543
+ [2023-06-19 14:46:00,545][00753] Num frames 9000...
2544
+ [2023-06-19 14:46:00,667][00753] Num frames 9100...
2545
+ [2023-06-19 14:46:00,791][00753] Num frames 9200...
2546
+ [2023-06-19 14:46:00,946][00753] Num frames 9300...
2547
+ [2023-06-19 14:46:01,140][00753] Num frames 9400...
2548
+ [2023-06-19 14:46:01,330][00753] Num frames 9500...
2549
+ [2023-06-19 14:46:01,505][00753] Num frames 9600...
2550
+ [2023-06-19 14:46:01,690][00753] Num frames 9700...
2551
+ [2023-06-19 14:46:01,817][00753] Avg episode rewards: #0: 30.667, true rewards: #0: 12.167
2552
+ [2023-06-19 14:46:01,823][00753] Avg episode reward: 30.667, avg true_objective: 12.167
2553
+ [2023-06-19 14:46:01,959][00753] Num frames 9800...
2554
+ [2023-06-19 14:46:02,157][00753] Num frames 9900...
2555
+ [2023-06-19 14:46:02,354][00753] Num frames 10000...
2556
+ [2023-06-19 14:46:02,541][00753] Num frames 10100...
2557
+ [2023-06-19 14:46:02,721][00753] Num frames 10200...
2558
+ [2023-06-19 14:46:02,905][00753] Num frames 10300...
2559
+ [2023-06-19 14:46:03,086][00753] Num frames 10400...
2560
+ [2023-06-19 14:46:03,268][00753] Num frames 10500...
2561
+ [2023-06-19 14:46:03,454][00753] Num frames 10600...
2562
+ [2023-06-19 14:46:03,636][00753] Num frames 10700...
2563
+ [2023-06-19 14:46:03,822][00753] Num frames 10800...
2564
+ [2023-06-19 14:46:04,017][00753] Num frames 10900...
2565
+ [2023-06-19 14:46:04,199][00753] Num frames 11000...
2566
+ [2023-06-19 14:46:04,390][00753] Num frames 11100...
2567
+ [2023-06-19 14:46:04,573][00753] Num frames 11200...
2568
+ [2023-06-19 14:46:04,757][00753] Num frames 11300...
2569
+ [2023-06-19 14:46:04,923][00753] Num frames 11400...
2570
+ [2023-06-19 14:46:05,054][00753] Num frames 11500...
2571
+ [2023-06-19 14:46:05,120][00753] Avg episode rewards: #0: 32.230, true rewards: #0: 12.786
2572
+ [2023-06-19 14:46:05,121][00753] Avg episode reward: 32.230, avg true_objective: 12.786
2573
+ [2023-06-19 14:46:05,246][00753] Num frames 11600...
2574
+ [2023-06-19 14:46:05,372][00753] Num frames 11700...
2575
+ [2023-06-19 14:46:05,505][00753] Num frames 11800...
2576
+ [2023-06-19 14:46:05,627][00753] Num frames 11900...
2577
+ [2023-06-19 14:46:05,750][00753] Num frames 12000...
2578
+ [2023-06-19 14:46:05,872][00753] Num frames 12100...
2579
+ [2023-06-19 14:46:06,003][00753] Num frames 12200...
2580
+ [2023-06-19 14:46:06,127][00753] Num frames 12300...
2581
+ [2023-06-19 14:46:06,187][00753] Avg episode rewards: #0: 30.603, true rewards: #0: 12.303
2582
+ [2023-06-19 14:46:06,189][00753] Avg episode reward: 30.603, avg true_objective: 12.303
2583
+ [2023-06-19 14:47:20,286][00753] Replay video saved to /content/train_dir/default_experiment/replay.mp4!