MalyO2 commited on
Commit
ff03d28
·
verified ·
1 Parent(s): 14b4e13

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. replay.mp4 +2 -2
  3. sf_log.txt +272 -0
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 9.69 +/- 5.23
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 6.60 +/- 0.20
19
  name: mean_reward
20
  verified: false
21
  ---
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1fad9eea012f5cb044a37654742a8a5f859a3b6d5cb43b2dcc8468443cae6a7
3
- size 18672988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3afd7d77362e065459f94b368950f93b7d507f1d890faf2156200a54972c266
3
+ size 1905150
sf_log.txt CHANGED
@@ -854,3 +854,275 @@ main_loop: 508.8147
854
  [2024-10-09 18:26:29,786][00030] Avg episode rewards: #0: 21.893, true rewards: #0: 9.693
855
  [2024-10-09 18:26:29,787][00030] Avg episode reward: 21.893, avg true_objective: 9.693
856
  [2024-10-09 18:27:03,077][00030] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
854
  [2024-10-09 18:26:29,786][00030] Avg episode rewards: #0: 21.893, true rewards: #0: 9.693
855
  [2024-10-09 18:26:29,787][00030] Avg episode reward: 21.893, avg true_objective: 9.693
856
  [2024-10-09 18:27:03,077][00030] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!
857
+ [2024-10-09 18:27:06,720][00030] The model has been pushed to https://huggingface.co/MalyO2/rl_course_vizdoom_health_gathering_supreme
858
+ [2024-10-09 18:32:17,316][00030] Loading legacy config file train_dir/doom_health_gathering_supreme_2222/cfg.json instead of train_dir/doom_health_gathering_supreme_2222/config.json
859
+ [2024-10-09 18:32:17,318][00030] Loading existing experiment configuration from train_dir/doom_health_gathering_supreme_2222/config.json
860
+ [2024-10-09 18:32:17,320][00030] Overriding arg 'experiment' with value 'doom_health_gathering_supreme_2222' passed from command line
861
+ [2024-10-09 18:32:17,321][00030] Overriding arg 'train_dir' with value 'train_dir' passed from command line
862
+ [2024-10-09 18:32:17,322][00030] Overriding arg 'num_workers' with value 1 passed from command line
863
+ [2024-10-09 18:32:17,323][00030] Adding new argument 'lr_adaptive_min'=1e-06 that is not in the saved config file!
864
+ [2024-10-09 18:32:17,324][00030] Adding new argument 'lr_adaptive_max'=0.01 that is not in the saved config file!
865
+ [2024-10-09 18:32:17,325][00030] Adding new argument 'env_gpu_observations'=True that is not in the saved config file!
866
+ [2024-10-09 18:32:17,326][00030] Adding new argument 'no_render'=True that is not in the saved config file!
867
+ [2024-10-09 18:32:17,327][00030] Adding new argument 'save_video'=True that is not in the saved config file!
868
+ [2024-10-09 18:32:17,328][00030] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
869
+ [2024-10-09 18:32:17,329][00030] Adding new argument 'video_name'=None that is not in the saved config file!
870
+ [2024-10-09 18:32:17,331][00030] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
871
+ [2024-10-09 18:32:17,332][00030] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
872
+ [2024-10-09 18:32:17,333][00030] Adding new argument 'push_to_hub'=False that is not in the saved config file!
873
+ [2024-10-09 18:32:17,334][00030] Adding new argument 'hf_repository'=None that is not in the saved config file!
874
+ [2024-10-09 18:32:17,335][00030] Adding new argument 'policy_index'=0 that is not in the saved config file!
875
+ [2024-10-09 18:32:17,336][00030] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
876
+ [2024-10-09 18:32:17,337][00030] Adding new argument 'train_script'=None that is not in the saved config file!
877
+ [2024-10-09 18:32:17,338][00030] Adding new argument 'enjoy_script'=None that is not in the saved config file!
878
+ [2024-10-09 18:32:17,339][00030] Using frameskip 1 and render_action_repeat=4 for evaluation
879
+ [2024-10-09 18:32:17,368][00030] RunningMeanStd input shape: (3, 72, 128)
880
+ [2024-10-09 18:32:17,369][00030] RunningMeanStd input shape: (1,)
881
+ [2024-10-09 18:32:17,386][00030] ConvEncoder: input_channels=3
882
+ [2024-10-09 18:32:17,448][00030] Conv encoder output size: 512
883
+ [2024-10-09 18:32:17,449][00030] Policy head output size: 512
884
+ [2024-10-09 18:32:17,475][00030] Loading state from checkpoint train_dir/doom_health_gathering_supreme_2222/checkpoint_p0/checkpoint_000539850_4422451200.pth...
885
+ [2024-10-09 18:32:18,017][00030] Num frames 100...
886
+ [2024-10-09 18:32:18,165][00030] Num frames 200...
887
+ [2024-10-09 18:32:18,308][00030] Num frames 300...
888
+ [2024-10-09 18:32:18,458][00030] Num frames 400...
889
+ [2024-10-09 18:32:18,601][00030] Num frames 500...
890
+ [2024-10-09 18:32:18,742][00030] Num frames 600...
891
+ [2024-10-09 18:32:18,890][00030] Num frames 700...
892
+ [2024-10-09 18:32:19,033][00030] Num frames 800...
893
+ [2024-10-09 18:32:19,172][00030] Num frames 900...
894
+ [2024-10-09 18:32:19,313][00030] Num frames 1000...
895
+ [2024-10-09 18:32:19,465][00030] Num frames 1100...
896
+ [2024-10-09 18:32:19,609][00030] Num frames 1200...
897
+ [2024-10-09 18:32:19,688][00030] Avg episode rewards: #0: 25.160, true rewards: #0: 12.160
898
+ [2024-10-09 18:32:19,689][00030] Avg episode reward: 25.160, avg true_objective: 12.160
899
+ [2024-10-09 18:32:19,825][00030] Num frames 1300...
900
+ [2024-10-09 18:32:19,972][00030] Num frames 1400...
901
+ [2024-10-09 18:32:20,113][00030] Num frames 1500...
902
+ [2024-10-09 18:32:20,254][00030] Num frames 1600...
903
+ [2024-10-09 18:32:20,394][00030] Num frames 1700...
904
+ [2024-10-09 18:32:20,532][00030] Num frames 1800...
905
+ [2024-10-09 18:32:20,683][00030] Num frames 1900...
906
+ [2024-10-09 18:32:20,830][00030] Num frames 2000...
907
+ [2024-10-09 18:32:20,972][00030] Num frames 2100...
908
+ [2024-10-09 18:32:21,111][00030] Num frames 2200...
909
+ [2024-10-09 18:32:21,255][00030] Num frames 2300...
910
+ [2024-10-09 18:32:21,398][00030] Num frames 2400...
911
+ [2024-10-09 18:32:21,544][00030] Num frames 2500...
912
+ [2024-10-09 18:32:21,685][00030] Num frames 2600...
913
+ [2024-10-09 18:32:21,831][00030] Num frames 2700...
914
+ [2024-10-09 18:32:21,975][00030] Num frames 2800...
915
+ [2024-10-09 18:32:22,119][00030] Num frames 2900...
916
+ [2024-10-09 18:32:22,259][00030] Num frames 3000...
917
+ [2024-10-09 18:32:22,406][00030] Num frames 3100...
918
+ [2024-10-09 18:32:22,556][00030] Num frames 3200...
919
+ [2024-10-09 18:32:22,698][00030] Num frames 3300...
920
+ [2024-10-09 18:32:22,777][00030] Avg episode rewards: #0: 43.579, true rewards: #0: 16.580
921
+ [2024-10-09 18:32:22,778][00030] Avg episode reward: 43.579, avg true_objective: 16.580
922
+ [2024-10-09 18:32:22,898][00030] Num frames 3400...
923
+ [2024-10-09 18:32:23,037][00030] Num frames 3500...
924
+ [2024-10-09 18:32:23,175][00030] Num frames 3600...
925
+ [2024-10-09 18:32:23,326][00030] Num frames 3700...
926
+ [2024-10-09 18:32:23,474][00030] Num frames 3800...
927
+ [2024-10-09 18:32:23,619][00030] Num frames 3900...
928
+ [2024-10-09 18:32:23,765][00030] Num frames 4000...
929
+ [2024-10-09 18:32:23,910][00030] Num frames 4100...
930
+ [2024-10-09 18:32:24,057][00030] Num frames 4200...
931
+ [2024-10-09 18:32:24,206][00030] Num frames 4300...
932
+ [2024-10-09 18:32:24,348][00030] Num frames 4400...
933
+ [2024-10-09 18:32:24,493][00030] Num frames 4500...
934
+ [2024-10-09 18:32:24,636][00030] Num frames 4600...
935
+ [2024-10-09 18:32:24,782][00030] Num frames 4700...
936
+ [2024-10-09 18:32:24,961][00030] Num frames 4800...
937
+ [2024-10-09 18:32:25,123][00030] Num frames 4900...
938
+ [2024-10-09 18:32:25,270][00030] Num frames 5000...
939
+ [2024-10-09 18:32:25,419][00030] Num frames 5100...
940
+ [2024-10-09 18:32:25,566][00030] Num frames 5200...
941
+ [2024-10-09 18:32:25,713][00030] Num frames 5300...
942
+ [2024-10-09 18:32:25,864][00030] Num frames 5400...
943
+ [2024-10-09 18:32:25,942][00030] Avg episode rewards: #0: 48.719, true rewards: #0: 18.053
944
+ [2024-10-09 18:32:25,943][00030] Avg episode reward: 48.719, avg true_objective: 18.053
945
+ [2024-10-09 18:32:26,061][00030] Num frames 5500...
946
+ [2024-10-09 18:32:26,204][00030] Num frames 5600...
947
+ [2024-10-09 18:32:26,346][00030] Num frames 5700...
948
+ [2024-10-09 18:32:26,487][00030] Num frames 5800...
949
+ [2024-10-09 18:32:26,636][00030] Num frames 5900...
950
+ [2024-10-09 18:32:26,784][00030] Num frames 6000...
951
+ [2024-10-09 18:32:26,935][00030] Num frames 6100...
952
+ [2024-10-09 18:32:27,079][00030] Num frames 6200...
953
+ [2024-10-09 18:32:27,224][00030] Num frames 6300...
954
+ [2024-10-09 18:32:27,367][00030] Num frames 6400...
955
+ [2024-10-09 18:32:27,518][00030] Num frames 6500...
956
+ [2024-10-09 18:32:27,670][00030] Num frames 6600...
957
+ [2024-10-09 18:32:27,821][00030] Num frames 6700...
958
+ [2024-10-09 18:32:27,962][00030] Num frames 6800...
959
+ [2024-10-09 18:32:28,104][00030] Num frames 6900...
960
+ [2024-10-09 18:32:28,247][00030] Num frames 7000...
961
+ [2024-10-09 18:32:28,398][00030] Num frames 7100...
962
+ [2024-10-09 18:32:28,542][00030] Num frames 7200...
963
+ [2024-10-09 18:32:28,690][00030] Num frames 7300...
964
+ [2024-10-09 18:32:28,836][00030] Num frames 7400...
965
+ [2024-10-09 18:32:28,984][00030] Num frames 7500...
966
+ [2024-10-09 18:32:29,062][00030] Avg episode rewards: #0: 53.039, true rewards: #0: 18.790
967
+ [2024-10-09 18:32:29,064][00030] Avg episode reward: 53.039, avg true_objective: 18.790
968
+ [2024-10-09 18:32:29,182][00030] Num frames 7600...
969
+ [2024-10-09 18:32:29,332][00030] Num frames 7700...
970
+ [2024-10-09 18:32:29,471][00030] Num frames 7800...
971
+ [2024-10-09 18:32:29,608][00030] Num frames 7900...
972
+ [2024-10-09 18:32:29,749][00030] Num frames 8000...
973
+ [2024-10-09 18:32:29,899][00030] Num frames 8100...
974
+ [2024-10-09 18:32:30,049][00030] Num frames 8200...
975
+ [2024-10-09 18:32:30,191][00030] Num frames 8300...
976
+ [2024-10-09 18:32:30,337][00030] Num frames 8400...
977
+ [2024-10-09 18:32:30,483][00030] Num frames 8500...
978
+ [2024-10-09 18:32:30,630][00030] Num frames 8600...
979
+ [2024-10-09 18:32:30,775][00030] Num frames 8700...
980
+ [2024-10-09 18:32:30,925][00030] Num frames 8800...
981
+ [2024-10-09 18:32:31,073][00030] Num frames 8900...
982
+ [2024-10-09 18:32:31,221][00030] Num frames 9000...
983
+ [2024-10-09 18:32:31,282][00030] Avg episode rewards: #0: 51.005, true rewards: #0: 18.006
984
+ [2024-10-09 18:32:31,284][00030] Avg episode reward: 51.005, avg true_objective: 18.006
985
+ [2024-10-09 18:32:31,420][00030] Num frames 9100...
986
+ [2024-10-09 18:32:31,559][00030] Num frames 9200...
987
+ [2024-10-09 18:32:31,698][00030] Num frames 9300...
988
+ [2024-10-09 18:32:31,845][00030] Num frames 9400...
989
+ [2024-10-09 18:32:31,986][00030] Num frames 9500...
990
+ [2024-10-09 18:32:32,131][00030] Num frames 9600...
991
+ [2024-10-09 18:32:32,284][00030] Num frames 9700...
992
+ [2024-10-09 18:32:32,425][00030] Num frames 9800...
993
+ [2024-10-09 18:32:32,565][00030] Num frames 9900...
994
+ [2024-10-09 18:32:32,710][00030] Num frames 10000...
995
+ [2024-10-09 18:32:32,851][00030] Num frames 10100...
996
+ [2024-10-09 18:32:32,992][00030] Num frames 10200...
997
+ [2024-10-09 18:32:33,135][00030] Num frames 10300...
998
+ [2024-10-09 18:32:33,278][00030] Num frames 10400...
999
+ [2024-10-09 18:32:33,420][00030] Num frames 10500...
1000
+ [2024-10-09 18:32:33,562][00030] Num frames 10600...
1001
+ [2024-10-09 18:32:33,737][00030] Num frames 10700...
1002
+ [2024-10-09 18:32:33,906][00030] Num frames 10800...
1003
+ [2024-10-09 18:32:34,080][00030] Num frames 10900...
1004
+ [2024-10-09 18:32:34,230][00030] Num frames 11000...
1005
+ [2024-10-09 18:32:34,390][00030] Num frames 11100...
1006
+ [2024-10-09 18:32:34,451][00030] Avg episode rewards: #0: 52.837, true rewards: #0: 18.505
1007
+ [2024-10-09 18:32:34,452][00030] Avg episode reward: 52.837, avg true_objective: 18.505
1008
+ [2024-10-09 18:32:34,591][00030] Num frames 11200...
1009
+ [2024-10-09 18:32:34,735][00030] Num frames 11300...
1010
+ [2024-10-09 18:32:34,889][00030] Num frames 11400...
1011
+ [2024-10-09 18:32:35,044][00030] Num frames 11500...
1012
+ [2024-10-09 18:32:35,198][00030] Num frames 11600...
1013
+ [2024-10-09 18:32:35,347][00030] Num frames 11700...
1014
+ [2024-10-09 18:32:35,487][00030] Num frames 11800...
1015
+ [2024-10-09 18:32:35,625][00030] Num frames 11900...
1016
+ [2024-10-09 18:32:35,763][00030] Num frames 12000...
1017
+ [2024-10-09 18:32:35,912][00030] Num frames 12100...
1018
+ [2024-10-09 18:32:36,063][00030] Num frames 12200...
1019
+ [2024-10-09 18:32:36,200][00030] Avg episode rewards: #0: 49.364, true rewards: #0: 17.507
1020
+ [2024-10-09 18:32:36,202][00030] Avg episode reward: 49.364, avg true_objective: 17.507
1021
+ [2024-10-09 18:32:36,265][00030] Num frames 12300...
1022
+ [2024-10-09 18:32:36,403][00030] Num frames 12400...
1023
+ [2024-10-09 18:32:36,541][00030] Num frames 12500...
1024
+ [2024-10-09 18:32:36,689][00030] Num frames 12600...
1025
+ [2024-10-09 18:32:36,835][00030] Num frames 12700...
1026
+ [2024-10-09 18:32:36,988][00030] Num frames 12800...
1027
+ [2024-10-09 18:32:37,134][00030] Num frames 12900...
1028
+ [2024-10-09 18:32:37,279][00030] Num frames 13000...
1029
+ [2024-10-09 18:32:37,426][00030] Num frames 13100...
1030
+ [2024-10-09 18:32:37,567][00030] Num frames 13200...
1031
+ [2024-10-09 18:32:37,710][00030] Num frames 13300...
1032
+ [2024-10-09 18:32:37,859][00030] Num frames 13400...
1033
+ [2024-10-09 18:32:38,001][00030] Num frames 13500...
1034
+ [2024-10-09 18:32:38,142][00030] Num frames 13600...
1035
+ [2024-10-09 18:32:38,288][00030] Num frames 13700...
1036
+ [2024-10-09 18:32:38,434][00030] Num frames 13800...
1037
+ [2024-10-09 18:32:38,574][00030] Num frames 13900...
1038
+ [2024-10-09 18:32:38,718][00030] Num frames 14000...
1039
+ [2024-10-09 18:32:38,862][00030] Num frames 14100...
1040
+ [2024-10-09 18:32:39,012][00030] Num frames 14200...
1041
+ [2024-10-09 18:32:39,159][00030] Num frames 14300...
1042
+ [2024-10-09 18:32:39,292][00030] Avg episode rewards: #0: 50.693, true rewards: #0: 17.944
1043
+ [2024-10-09 18:32:39,293][00030] Avg episode reward: 50.693, avg true_objective: 17.944
1044
+ [2024-10-09 18:32:39,358][00030] Num frames 14400...
1045
+ [2024-10-09 18:32:39,500][00030] Num frames 14500...
1046
+ [2024-10-09 18:32:39,643][00030] Num frames 14600...
1047
+ [2024-10-09 18:32:39,784][00030] Num frames 14700...
1048
+ [2024-10-09 18:32:39,928][00030] Num frames 14800...
1049
+ [2024-10-09 18:32:40,077][00030] Num frames 14900...
1050
+ [2024-10-09 18:32:40,219][00030] Num frames 15000...
1051
+ [2024-10-09 18:32:40,367][00030] Num frames 15100...
1052
+ [2024-10-09 18:32:40,510][00030] Num frames 15200...
1053
+ [2024-10-09 18:32:40,654][00030] Num frames 15300...
1054
+ [2024-10-09 18:32:40,794][00030] Num frames 15400...
1055
+ [2024-10-09 18:32:40,936][00030] Num frames 15500...
1056
+ [2024-10-09 18:32:41,074][00030] Num frames 15600...
1057
+ [2024-10-09 18:32:41,219][00030] Num frames 15700...
1058
+ [2024-10-09 18:32:41,363][00030] Num frames 15800...
1059
+ [2024-10-09 18:32:41,504][00030] Num frames 15900...
1060
+ [2024-10-09 18:32:41,645][00030] Num frames 16000...
1061
+ [2024-10-09 18:32:41,784][00030] Num frames 16100...
1062
+ [2024-10-09 18:32:41,928][00030] Num frames 16200...
1063
+ [2024-10-09 18:32:42,080][00030] Num frames 16300...
1064
+ [2024-10-09 18:32:42,230][00030] Num frames 16400...
1065
+ [2024-10-09 18:32:42,366][00030] Avg episode rewards: #0: 52.282, true rewards: #0: 18.283
1066
+ [2024-10-09 18:32:42,367][00030] Avg episode reward: 52.282, avg true_objective: 18.283
1067
+ [2024-10-09 18:32:42,430][00030] Num frames 16500...
1068
+ [2024-10-09 18:32:42,567][00030] Num frames 16600...
1069
+ [2024-10-09 18:32:42,710][00030] Num frames 16700...
1070
+ [2024-10-09 18:32:42,852][00030] Num frames 16800...
1071
+ [2024-10-09 18:32:43,002][00030] Num frames 16900...
1072
+ [2024-10-09 18:32:43,146][00030] Num frames 17000...
1073
+ [2024-10-09 18:32:43,292][00030] Num frames 17100...
1074
+ [2024-10-09 18:32:43,442][00030] Num frames 17200...
1075
+ [2024-10-09 18:32:43,588][00030] Num frames 17300...
1076
+ [2024-10-09 18:32:43,734][00030] Num frames 17400...
1077
+ [2024-10-09 18:32:43,883][00030] Num frames 17500...
1078
+ [2024-10-09 18:32:44,023][00030] Num frames 17600...
1079
+ [2024-10-09 18:32:44,164][00030] Num frames 17700...
1080
+ [2024-10-09 18:32:44,306][00030] Num frames 17800...
1081
+ [2024-10-09 18:32:44,454][00030] Num frames 17900...
1082
+ [2024-10-09 18:32:44,602][00030] Num frames 18000...
1083
+ [2024-10-09 18:32:44,756][00030] Num frames 18100...
1084
+ [2024-10-09 18:32:44,909][00030] Num frames 18200...
1085
+ [2024-10-09 18:32:45,070][00030] Num frames 18300...
1086
+ [2024-10-09 18:32:45,219][00030] Num frames 18400...
1087
+ [2024-10-09 18:32:45,313][00030] Avg episode rewards: #0: 53.226, true rewards: #0: 18.427
1088
+ [2024-10-09 18:32:45,314][00030] Avg episode reward: 53.226, avg true_objective: 18.427
1089
+ [2024-10-09 18:33:48,569][00030] Replay video saved to train_dir/doom_health_gathering_supreme_2222/replay.mp4!
1090
+ [2024-10-09 18:35:53,331][00030] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
1091
+ [2024-10-09 18:35:53,332][00030] Overriding arg 'num_workers' with value 1 passed from command line
1092
+ [2024-10-09 18:35:53,333][00030] Adding new argument 'no_render'=True that is not in the saved config file!
1093
+ [2024-10-09 18:35:53,334][00030] Adding new argument 'save_video'=True that is not in the saved config file!
1094
+ [2024-10-09 18:35:53,336][00030] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
1095
+ [2024-10-09 18:35:53,337][00030] Adding new argument 'video_name'=None that is not in the saved config file!
1096
+ [2024-10-09 18:35:53,338][00030] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
1097
+ [2024-10-09 18:35:53,339][00030] Adding new argument 'max_num_episodes'=2 that is not in the saved config file!
1098
+ [2024-10-09 18:35:53,340][00030] Adding new argument 'push_to_hub'=True that is not in the saved config file!
1099
+ [2024-10-09 18:35:53,341][00030] Adding new argument 'hf_repository'='MalyO2/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
1100
+ [2024-10-09 18:35:53,342][00030] Adding new argument 'policy_index'=0 that is not in the saved config file!
1101
+ [2024-10-09 18:35:53,343][00030] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
1102
+ [2024-10-09 18:35:53,344][00030] Adding new argument 'train_script'=None that is not in the saved config file!
1103
+ [2024-10-09 18:35:53,344][00030] Adding new argument 'enjoy_script'=None that is not in the saved config file!
1104
+ [2024-10-09 18:35:53,345][00030] Using frameskip 1 and render_action_repeat=4 for evaluation
1105
+ [2024-10-09 18:35:53,368][00030] RunningMeanStd input shape: (3, 72, 128)
1106
+ [2024-10-09 18:35:53,369][00030] RunningMeanStd input shape: (1,)
1107
+ [2024-10-09 18:35:53,385][00030] ConvEncoder: input_channels=3
1108
+ [2024-10-09 18:35:53,433][00030] Conv encoder output size: 512
1109
+ [2024-10-09 18:35:53,434][00030] Policy head output size: 512
1110
+ [2024-10-09 18:35:53,454][00030] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
1111
+ [2024-10-09 18:35:53,987][00030] Num frames 100...
1112
+ [2024-10-09 18:35:54,128][00030] Num frames 200...
1113
+ [2024-10-09 18:35:54,265][00030] Num frames 300...
1114
+ [2024-10-09 18:35:54,404][00030] Num frames 400...
1115
+ [2024-10-09 18:35:54,539][00030] Num frames 500...
1116
+ [2024-10-09 18:35:54,676][00030] Num frames 600...
1117
+ [2024-10-09 18:35:54,845][00030] Avg episode rewards: #0: 10.810, true rewards: #0: 6.810
1118
+ [2024-10-09 18:35:54,847][00030] Avg episode reward: 10.810, avg true_objective: 6.810
1119
+ [2024-10-09 18:35:54,881][00030] Num frames 700...
1120
+ [2024-10-09 18:35:55,041][00030] Num frames 800...
1121
+ [2024-10-09 18:35:55,194][00030] Num frames 900...
1122
+ [2024-10-09 18:35:55,336][00030] Num frames 1000...
1123
+ [2024-10-09 18:35:55,479][00030] Num frames 1100...
1124
+ [2024-10-09 18:35:55,621][00030] Num frames 1200...
1125
+ [2024-10-09 18:35:55,762][00030] Num frames 1300...
1126
+ [2024-10-09 18:35:55,847][00030] Avg episode rewards: #0: 12.605, true rewards: #0: 6.605
1127
+ [2024-10-09 18:35:55,848][00030] Avg episode reward: 12.605, avg true_objective: 6.605
1128
+ [2024-10-09 18:36:00,081][00030] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!