Hugging Face's logo

Christian90
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
rl_course_vizdoom_health_gathering_supreme
File size: 77,364 Bytes 
bfc8c85
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
 
[2023-03-17 10:54:05,152][24380] Saving configuration to /home/ckahmann/RL/train_dir/default_experiment/config.json...
[2023-03-17 10:54:05,155][24380] Rollout worker 0 uses device cpu
[2023-03-17 10:54:05,156][24380] Rollout worker 1 uses device cpu
[2023-03-17 10:54:05,157][24380] Rollout worker 2 uses device cpu
[2023-03-17 10:54:05,159][24380] Rollout worker 3 uses device cpu
[2023-03-17 10:54:05,160][24380] Rollout worker 4 uses device cpu
[2023-03-17 10:54:05,161][24380] Rollout worker 5 uses device cpu
[2023-03-17 10:54:05,162][24380] Rollout worker 6 uses device cpu
[2023-03-17 10:54:05,163][24380] Rollout worker 7 uses device cpu
[2023-03-17 10:54:05,210][24380] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:05,211][24380] InferenceWorker_p0-w0: min num requests: 2
[2023-03-17 10:54:05,232][24380] Starting all processes...
[2023-03-17 10:54:05,233][24380] Starting process learner_proc0
[2023-03-17 10:54:05,282][24380] Starting all processes...
[2023-03-17 10:54:05,293][24380] Starting process inference_proc0-0
[2023-03-17 10:54:05,293][24380] Starting process rollout_proc0
[2023-03-17 10:54:05,294][24380] Starting process rollout_proc1
[2023-03-17 10:54:05,294][24380] Starting process rollout_proc2
[2023-03-17 10:54:05,294][24380] Starting process rollout_proc3
[2023-03-17 10:54:05,295][24380] Starting process rollout_proc4
[2023-03-17 10:54:05,295][24380] Starting process rollout_proc5
[2023-03-17 10:54:05,296][24380] Starting process rollout_proc6
[2023-03-17 10:54:05,297][24380] Starting process rollout_proc7
[2023-03-17 10:54:06,789][32549] Worker 0 uses CPU cores [0, 1]
[2023-03-17 10:54:06,820][32535] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:06,820][32535] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2023-03-17 10:54:06,833][32535] Num visible devices: 1
[2023-03-17 10:54:06,847][32568] Worker 1 uses CPU cores [2, 3]
[2023-03-17 10:54:06,860][32571] Worker 6 uses CPU cores [12, 13]
[2023-03-17 10:54:06,880][32572] Worker 7 uses CPU cores [14, 15]
[2023-03-17 10:54:06,892][32535] Starting seed is not provided
[2023-03-17 10:54:06,893][32535] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:06,893][32535] Initializing actor-critic model on device cuda:0
[2023-03-17 10:54:06,893][32535] RunningMeanStd input shape: (3, 72, 128)
[2023-03-17 10:54:06,894][32535] RunningMeanStd input shape: (1,)
[2023-03-17 10:54:06,904][32535] ConvEncoder: input_channels=3
[2023-03-17 10:54:06,995][32535] Conv encoder output size: 512
[2023-03-17 10:54:06,996][32535] Policy head output size: 512
[2023-03-17 10:54:07,006][32535] Created Actor Critic model with architecture:
[2023-03-17 10:54:07,006][32535] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2023-03-17 10:54:07,011][32570] Worker 5 uses CPU cores [10, 11]
[2023-03-17 10:54:07,020][32548] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:07,020][32548] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2023-03-17 10:54:07,035][32567] Worker 3 uses CPU cores [6, 7]
[2023-03-17 10:54:07,042][32548] Num visible devices: 1
[2023-03-17 10:54:07,165][32550] Worker 2 uses CPU cores [4, 5]
[2023-03-17 10:54:07,197][32569] Worker 4 uses CPU cores [8, 9]
[2023-03-17 10:54:08,475][32535] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-03-17 10:54:08,476][32535] No checkpoints found
[2023-03-17 10:54:08,476][32535] Did not load from checkpoint, starting from scratch!
[2023-03-17 10:54:08,476][32535] Initialized policy 0 weights for model version 0
[2023-03-17 10:54:08,478][32535] LearnerWorker_p0 finished initialization!
[2023-03-17 10:54:08,478][32535] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:08,577][32548] RunningMeanStd input shape: (3, 72, 128)
[2023-03-17 10:54:08,578][32548] RunningMeanStd input shape: (1,)
[2023-03-17 10:54:08,586][32548] ConvEncoder: input_channels=3
[2023-03-17 10:54:08,657][32548] Conv encoder output size: 512
[2023-03-17 10:54:08,657][32548] Policy head output size: 512
[2023-03-17 10:54:10,077][24380] Inference worker 0-0 is ready!
[2023-03-17 10:54:10,079][24380] All inference workers are ready! Signal rollout workers to start!
[2023-03-17 10:54:10,106][32549] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:10,106][32569] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:10,111][32572] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:10,111][32550] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:10,111][32571] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:10,111][32567] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:10,112][32568] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:10,112][32570] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:10,368][32569] Decorrelating experience for 0 frames...
[2023-03-17 10:54:10,368][32567] Decorrelating experience for 0 frames...
[2023-03-17 10:54:10,368][32550] Decorrelating experience for 0 frames...
[2023-03-17 10:54:10,369][32568] Decorrelating experience for 0 frames...
[2023-03-17 10:54:10,395][32549] Decorrelating experience for 0 frames...
[2023-03-17 10:54:10,580][32550] Decorrelating experience for 32 frames...
[2023-03-17 10:54:10,586][32567] Decorrelating experience for 32 frames...
[2023-03-17 10:54:10,592][32569] Decorrelating experience for 32 frames...
[2023-03-17 10:54:10,862][32568] Decorrelating experience for 32 frames...
[2023-03-17 10:54:10,879][32571] Decorrelating experience for 0 frames...
[2023-03-17 10:54:10,880][32567] Decorrelating experience for 64 frames...
[2023-03-17 10:54:10,921][32549] Decorrelating experience for 32 frames...
[2023-03-17 10:54:10,980][32569] Decorrelating experience for 64 frames...
[2023-03-17 10:54:11,112][32572] Decorrelating experience for 0 frames...
[2023-03-17 10:54:11,122][32571] Decorrelating experience for 32 frames...
[2023-03-17 10:54:11,128][32568] Decorrelating experience for 64 frames...
[2023-03-17 10:54:11,154][32550] Decorrelating experience for 64 frames...
[2023-03-17 10:54:11,215][32567] Decorrelating experience for 96 frames...
[2023-03-17 10:54:11,347][32569] Decorrelating experience for 96 frames...
[2023-03-17 10:54:11,396][32571] Decorrelating experience for 64 frames...
[2023-03-17 10:54:11,428][32568] Decorrelating experience for 96 frames...
[2023-03-17 10:54:11,430][32572] Decorrelating experience for 32 frames...
[2023-03-17 10:54:11,475][32550] Decorrelating experience for 96 frames...
[2023-03-17 10:54:11,640][32570] Decorrelating experience for 0 frames...
[2023-03-17 10:54:11,659][32549] Decorrelating experience for 64 frames...
[2023-03-17 10:54:11,690][32571] Decorrelating experience for 96 frames...
[2023-03-17 10:54:11,893][32570] Decorrelating experience for 32 frames...
[2023-03-17 10:54:11,952][32572] Decorrelating experience for 64 frames...
[2023-03-17 10:54:12,005][32549] Decorrelating experience for 96 frames...
[2023-03-17 10:54:12,218][32570] Decorrelating experience for 64 frames...
[2023-03-17 10:54:12,333][32572] Decorrelating experience for 96 frames...
[2023-03-17 10:54:12,422][32535] Signal inference workers to stop experience collection...
[2023-03-17 10:54:12,434][32548] InferenceWorker_p0-w0: stopping experience collection
[2023-03-17 10:54:12,554][32570] Decorrelating experience for 96 frames...
[2023-03-17 10:54:12,902][24380] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-03-17 10:54:12,904][24380] Avg episode reward: [(0, '2.711')]
[2023-03-17 10:54:13,106][32535] Signal inference workers to resume experience collection...
[2023-03-17 10:54:13,107][32548] InferenceWorker_p0-w0: resuming experience collection
[2023-03-17 10:54:15,446][32548] Updated weights for policy 0, policy_version 10 (0.0263)
[2023-03-17 10:54:17,635][32548] Updated weights for policy 0, policy_version 20 (0.0007)
[2023-03-17 10:54:17,902][24380] Fps is (10 sec: 17203.9, 60 sec: 17203.9, 300 sec: 17203.9). Total num frames: 86016. Throughput: 0: 2777.3. Samples: 13886. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-03-17 10:54:17,903][24380] Avg episode reward: [(0, '4.460')]
[2023-03-17 10:54:19,874][32548] Updated weights for policy 0, policy_version 30 (0.0008)
[2023-03-17 10:54:22,150][32548] Updated weights for policy 0, policy_version 40 (0.0008)
[2023-03-17 10:54:22,902][24380] Fps is (10 sec: 17612.5, 60 sec: 17612.5, 300 sec: 17612.5). Total num frames: 176128. Throughput: 0: 4135.1. Samples: 41352. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-03-17 10:54:22,904][24380] Avg episode reward: [(0, '4.468')]
[2023-03-17 10:54:22,912][32535] Saving new best policy, reward=4.468!
[2023-03-17 10:54:23,494][24380] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 24380], exiting...
[2023-03-17 10:54:23,497][32535] Stopping Batcher_0...
[2023-03-17 10:54:23,498][32535] Loop batcher_evt_loop terminating...
[2023-03-17 10:54:23,497][24380] Runner profile tree view:
main_loop: 18.2648
[2023-03-17 10:54:23,499][32535] Saving /home/ckahmann/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000045_184320.pth...
[2023-03-17 10:54:23,499][24380] Collected {0: 184320}, FPS: 10091.5
[2023-03-17 10:54:23,505][32549] Stopping RolloutWorker_w0...
[2023-03-17 10:54:23,506][32569] Stopping RolloutWorker_w4...
[2023-03-17 10:54:23,506][32549] Loop rollout_proc0_evt_loop terminating...
[2023-03-17 10:54:23,506][32569] Loop rollout_proc4_evt_loop terminating...
[2023-03-17 10:54:23,509][32570] Stopping RolloutWorker_w5...
[2023-03-17 10:54:23,509][32568] Stopping RolloutWorker_w1...
[2023-03-17 10:54:23,510][32570] Loop rollout_proc5_evt_loop terminating...
[2023-03-17 10:54:23,510][32568] Loop rollout_proc1_evt_loop terminating...
[2023-03-17 10:54:23,510][32548] Weights refcount: 2 0
[2023-03-17 10:54:23,511][32548] Stopping InferenceWorker_p0-w0...
[2023-03-17 10:54:23,512][32548] Loop inference_proc0-0_evt_loop terminating...
[2023-03-17 10:54:23,512][32550] Stopping RolloutWorker_w2...
[2023-03-17 10:54:23,513][32550] Loop rollout_proc2_evt_loop terminating...
[2023-03-17 10:54:23,515][32571] Stopping RolloutWorker_w6...
[2023-03-17 10:54:23,516][32571] Loop rollout_proc6_evt_loop terminating...
[2023-03-17 10:54:23,516][32567] Stopping RolloutWorker_w3...
[2023-03-17 10:54:23,517][32567] Loop rollout_proc3_evt_loop terminating...
[2023-03-17 10:54:23,525][32572] Stopping RolloutWorker_w7...
[2023-03-17 10:54:23,525][32572] Loop rollout_proc7_evt_loop terminating...
[2023-03-17 10:54:23,561][32535] Stopping LearnerWorker_p0...
[2023-03-17 10:54:23,562][32535] Loop learner_proc0_evt_loop terminating...
[2023-03-17 10:54:29,677][24380] Environment doom_basic already registered, overwriting...
[2023-03-17 10:54:29,680][24380] Environment doom_two_colors_easy already registered, overwriting...
[2023-03-17 10:54:29,682][24380] Environment doom_two_colors_hard already registered, overwriting...
[2023-03-17 10:54:29,684][24380] Environment doom_dm already registered, overwriting...
[2023-03-17 10:54:29,686][24380] Environment doom_dwango5 already registered, overwriting...
[2023-03-17 10:54:29,687][24380] Environment doom_my_way_home_flat_actions already registered, overwriting...
[2023-03-17 10:54:29,689][24380] Environment doom_defend_the_center_flat_actions already registered, overwriting...
[2023-03-17 10:54:29,690][24380] Environment doom_my_way_home already registered, overwriting...
[2023-03-17 10:54:29,692][24380] Environment doom_deadly_corridor already registered, overwriting...
[2023-03-17 10:54:29,693][24380] Environment doom_defend_the_center already registered, overwriting...
[2023-03-17 10:54:29,694][24380] Environment doom_defend_the_line already registered, overwriting...
[2023-03-17 10:54:29,695][24380] Environment doom_health_gathering already registered, overwriting...
[2023-03-17 10:54:29,695][24380] Environment doom_health_gathering_supreme already registered, overwriting...
[2023-03-17 10:54:29,696][24380] Environment doom_battle already registered, overwriting...
[2023-03-17 10:54:29,698][24380] Environment doom_battle2 already registered, overwriting...
[2023-03-17 10:54:29,699][24380] Environment doom_duel_bots already registered, overwriting...
[2023-03-17 10:54:29,699][24380] Environment doom_deathmatch_bots already registered, overwriting...
[2023-03-17 10:54:29,701][24380] Environment doom_duel already registered, overwriting...
[2023-03-17 10:54:29,701][24380] Environment doom_deathmatch_full already registered, overwriting...
[2023-03-17 10:54:29,702][24380] Environment doom_benchmark already registered, overwriting...
[2023-03-17 10:54:29,703][24380] register_encoder_factory: <function make_vizdoom_encoder at 0x7f2990bd61f0>
[2023-03-17 10:54:29,721][24380] Loading existing experiment configuration from /home/ckahmann/RL/train_dir/default_experiment/config.json
[2023-03-17 10:54:29,722][24380] Overriding arg 'num_workers' with value 16 passed from command line
[2023-03-17 10:54:29,729][24380] Experiment dir /home/ckahmann/RL/train_dir/default_experiment already exists!
[2023-03-17 10:54:29,730][24380] Resuming existing experiment from /home/ckahmann/RL/train_dir/default_experiment...
[2023-03-17 10:54:29,731][24380] Weights and Biases integration disabled
[2023-03-17 10:54:29,863][24380] Environment var CUDA_VISIBLE_DEVICES is 0,1

[2023-03-17 10:54:31,128][24380] Starting experiment with the following configuration:
help=False
algo=APPO
env=doom_health_gathering_supreme
experiment=default_experiment
train_dir=/home/ckahmann/RL/train_dir
restart_behavior=resume
device=gpu
seed=None
num_policies=1
async_rl=True
serial_mode=False
batched_sampling=False
num_batches_to_accumulate=2
worker_num_splits=2
policy_workers_per_policy=1
max_policy_lag=1000
num_workers=16
num_envs_per_worker=4
batch_size=1024
num_batches_per_epoch=1
num_epochs=1
rollout=32
recurrence=32
shuffle_minibatches=False
gamma=0.99
reward_scale=1.0
reward_clip=1000.0
value_bootstrap=False
normalize_returns=True
exploration_loss_coeff=0.001
value_loss_coeff=0.5
kl_loss_coeff=0.0
exploration_loss=symmetric_kl
gae_lambda=0.95
ppo_clip_ratio=0.1
ppo_clip_value=0.2
with_vtrace=False
vtrace_rho=1.0
vtrace_c=1.0
optimizer=adam
adam_eps=1e-06
adam_beta1=0.9
adam_beta2=0.999
max_grad_norm=4.0
learning_rate=0.0001
lr_schedule=constant
lr_schedule_kl_threshold=0.008
lr_adaptive_min=1e-06
lr_adaptive_max=0.01
obs_subtract_mean=0.0
obs_scale=255.0
normalize_input=True
normalize_input_keys=None
decorrelate_experience_max_seconds=0
decorrelate_envs_on_one_worker=True
actor_worker_gpus=[]
set_workers_cpu_affinity=True
force_envs_single_thread=False
default_niceness=0
log_to_file=True
experiment_summaries_interval=10
flush_summaries_interval=30
stats_avg=100
summaries_use_frameskip=True
heartbeat_interval=20
heartbeat_reporting_interval=600
train_for_env_steps=4000000
train_for_seconds=10000000000
save_every_sec=120
keep_checkpoints=2
load_checkpoint_kind=latest
save_milestones_sec=-1
save_best_every_sec=5
save_best_metric=reward
save_best_after=100000
benchmark=False
encoder_mlp_layers=[512, 512]
encoder_conv_architecture=convnet_simple
encoder_conv_mlp_layers=[512]
use_rnn=True
rnn_size=512
rnn_type=gru
rnn_num_layers=1
decoder_mlp_layers=[]
nonlinearity=elu
policy_initialization=orthogonal
policy_init_gain=1.0
actor_critic_share_weights=True
adaptive_stddev=True
continuous_tanh_scale=0.0
initial_stddev=1.0
use_env_info_cache=False
env_gpu_actions=False
env_gpu_observations=True
env_frameskip=4
env_framestack=1
pixel_format=CHW
use_record_episode_statistics=False
with_wandb=False
wandb_user=None
wandb_project=sample_factory
wandb_group=None
wandb_job_type=SF
wandb_tags=[]
with_pbt=False
pbt_mix_policies_in_one_env=True
pbt_period_env_steps=5000000
pbt_start_mutation=20000000
pbt_replace_fraction=0.3
pbt_mutation_rate=0.15
pbt_replace_reward_gap=0.1
pbt_replace_reward_gap_absolute=1e-06
pbt_optimize_gamma=False
pbt_target_objective=true_objective
pbt_perturb_min=1.1
pbt_perturb_max=1.5
num_agents=-1
num_humans=0
num_bots=-1
start_bot_difficulty=None
timelimit=None
res_w=128
res_h=72
wide_aspect_ratio=False
eval_env_frameskip=1
fps=35
command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
git_hash=unknown
git_repo_name=not a git repository
[2023-03-17 10:54:31,130][24380] Saving configuration to /home/ckahmann/RL/train_dir/default_experiment/config.json...
[2023-03-17 10:54:31,132][24380] Rollout worker 0 uses device cpu
[2023-03-17 10:54:31,132][24380] Rollout worker 1 uses device cpu
[2023-03-17 10:54:31,133][24380] Rollout worker 2 uses device cpu
[2023-03-17 10:54:31,134][24380] Rollout worker 3 uses device cpu
[2023-03-17 10:54:31,134][24380] Rollout worker 4 uses device cpu
[2023-03-17 10:54:31,135][24380] Rollout worker 5 uses device cpu
[2023-03-17 10:54:31,136][24380] Rollout worker 6 uses device cpu
[2023-03-17 10:54:31,137][24380] Rollout worker 7 uses device cpu
[2023-03-17 10:54:31,137][24380] Rollout worker 8 uses device cpu
[2023-03-17 10:54:31,138][24380] Rollout worker 9 uses device cpu
[2023-03-17 10:54:31,139][24380] Rollout worker 10 uses device cpu
[2023-03-17 10:54:31,139][24380] Rollout worker 11 uses device cpu
[2023-03-17 10:54:31,140][24380] Rollout worker 12 uses device cpu
[2023-03-17 10:54:31,141][24380] Rollout worker 13 uses device cpu
[2023-03-17 10:54:31,141][24380] Rollout worker 14 uses device cpu
[2023-03-17 10:54:31,142][24380] Rollout worker 15 uses device cpu
[2023-03-17 10:54:31,206][24380] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:31,207][24380] InferenceWorker_p0-w0: min num requests: 5
[2023-03-17 10:54:31,243][24380] Starting all processes...
[2023-03-17 10:54:31,244][24380] Starting process learner_proc0
[2023-03-17 10:54:31,297][24380] Starting all processes...
[2023-03-17 10:54:31,305][24380] Starting process inference_proc0-0
[2023-03-17 10:54:31,306][24380] Starting process rollout_proc0
[2023-03-17 10:54:31,306][24380] Starting process rollout_proc1
[2023-03-17 10:54:31,307][24380] Starting process rollout_proc2
[2023-03-17 10:54:31,307][24380] Starting process rollout_proc3
[2023-03-17 10:54:31,307][24380] Starting process rollout_proc4
[2023-03-17 10:54:31,308][24380] Starting process rollout_proc5
[2023-03-17 10:54:31,308][24380] Starting process rollout_proc6
[2023-03-17 10:54:31,309][24380] Starting process rollout_proc7
[2023-03-17 10:54:31,310][24380] Starting process rollout_proc8
[2023-03-17 10:54:31,310][24380] Starting process rollout_proc9
[2023-03-17 10:54:31,311][24380] Starting process rollout_proc10
[2023-03-17 10:54:31,312][24380] Starting process rollout_proc11
[2023-03-17 10:54:31,312][24380] Starting process rollout_proc12
[2023-03-17 10:54:31,318][24380] Starting process rollout_proc13
[2023-03-17 10:54:31,318][24380] Starting process rollout_proc14
[2023-03-17 10:54:31,378][24380] Starting process rollout_proc15
[2023-03-17 10:54:33,386][01277] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:33,386][01277] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2023-03-17 10:54:33,400][01277] Num visible devices: 1
[2023-03-17 10:54:33,448][01301] Worker 1 uses CPU cores [1]
[2023-03-17 10:54:33,448][01277] Starting seed is not provided
[2023-03-17 10:54:33,448][01277] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:33,449][01277] Initializing actor-critic model on device cuda:0
[2023-03-17 10:54:33,449][01277] RunningMeanStd input shape: (3, 72, 128)
[2023-03-17 10:54:33,450][01277] RunningMeanStd input shape: (1,)
[2023-03-17 10:54:33,466][01277] ConvEncoder: input_channels=3
[2023-03-17 10:54:33,524][01299] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:33,524][01299] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2023-03-17 10:54:33,536][01324] Worker 6 uses CPU cores [6]
[2023-03-17 10:54:33,550][01299] Num visible devices: 1
[2023-03-17 10:54:33,552][01325] Worker 8 uses CPU cores [8]
[2023-03-17 10:54:33,580][01300] Worker 0 uses CPU cores [0]
[2023-03-17 10:54:33,596][01323] Worker 5 uses CPU cores [5]
[2023-03-17 10:54:33,604][01321] Worker 4 uses CPU cores [4]
[2023-03-17 10:54:33,648][01320] Worker 3 uses CPU cores [3]
[2023-03-17 10:54:33,676][01328] Worker 10 uses CPU cores [10]
[2023-03-17 10:54:33,685][01277] Conv encoder output size: 512
[2023-03-17 10:54:33,686][01277] Policy head output size: 512
[2023-03-17 10:54:33,696][01326] Worker 7 uses CPU cores [7]
[2023-03-17 10:54:33,704][01277] Created Actor Critic model with architecture:
[2023-03-17 10:54:33,704][01277] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2023-03-17 10:54:33,752][01319] Worker 2 uses CPU cores [2]
[2023-03-17 10:54:33,775][01329] Worker 11 uses CPU cores [11]
[2023-03-17 10:54:33,824][01335] Worker 13 uses CPU cores [13]
[2023-03-17 10:54:33,840][01332] Worker 15 uses CPU cores [15]
[2023-03-17 10:54:33,876][01327] Worker 9 uses CPU cores [9]
[2023-03-17 10:54:33,990][01331] Worker 12 uses CPU cores [12]
[2023-03-17 10:54:33,993][01334] Worker 14 uses CPU cores [14]
[2023-03-17 10:54:35,256][01277] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-03-17 10:54:35,257][01277] Loading state from checkpoint /home/ckahmann/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000045_184320.pth...
[2023-03-17 10:54:35,278][01277] Loading model from checkpoint
[2023-03-17 10:54:35,281][01277] Loaded experiment state at self.train_step=45, self.env_steps=184320
[2023-03-17 10:54:35,281][01277] Initialized policy 0 weights for model version 45
[2023-03-17 10:54:35,283][01277] LearnerWorker_p0 finished initialization!
[2023-03-17 10:54:35,283][01277] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-03-17 10:54:35,387][01299] RunningMeanStd input shape: (3, 72, 128)
[2023-03-17 10:54:35,388][01299] RunningMeanStd input shape: (1,)
[2023-03-17 10:54:35,396][01299] ConvEncoder: input_channels=3
[2023-03-17 10:54:35,467][01299] Conv encoder output size: 512
[2023-03-17 10:54:35,467][01299] Policy head output size: 512
[2023-03-17 10:54:36,963][24380] Inference worker 0-0 is ready!
[2023-03-17 10:54:36,965][24380] All inference workers are ready! Signal rollout workers to start!
[2023-03-17 10:54:36,987][01301] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:36,987][01327] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:36,998][01323] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:36,998][01334] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:36,998][01335] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:36,998][01324] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:36,999][01326] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:36,999][01320] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,000][01329] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,000][01319] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,001][01321] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,001][01331] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,001][01328] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,001][01300] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,002][01325] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,005][01332] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:54:37,233][01324] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,234][01319] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,235][01326] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,340][01301] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,340][01327] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,437][01319] Decorrelating experience for 32 frames...
[2023-03-17 10:54:37,470][01324] Decorrelating experience for 32 frames...
[2023-03-17 10:54:37,489][01335] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,496][01320] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,496][01321] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,544][01301] Decorrelating experience for 32 frames...
[2023-03-17 10:54:37,631][01334] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,692][01335] Decorrelating experience for 32 frames...
[2023-03-17 10:54:37,698][01321] Decorrelating experience for 32 frames...
[2023-03-17 10:54:37,717][01326] Decorrelating experience for 32 frames...
[2023-03-17 10:54:37,764][01327] Decorrelating experience for 32 frames...
[2023-03-17 10:54:37,820][01332] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,851][01325] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,929][01335] Decorrelating experience for 64 frames...
[2023-03-17 10:54:37,948][01328] Decorrelating experience for 0 frames...
[2023-03-17 10:54:37,967][01320] Decorrelating experience for 32 frames...
[2023-03-17 10:54:38,061][01301] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,067][01334] Decorrelating experience for 32 frames...
[2023-03-17 10:54:38,153][01321] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,164][01324] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,252][01326] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,327][01320] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,354][01332] Decorrelating experience for 32 frames...
[2023-03-17 10:54:38,378][01321] Decorrelating experience for 96 frames...
[2023-03-17 10:54:38,395][01319] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,447][01324] Decorrelating experience for 96 frames...
[2023-03-17 10:54:38,560][01334] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,571][01327] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,653][01335] Decorrelating experience for 96 frames...
[2023-03-17 10:54:38,654][01329] Decorrelating experience for 0 frames...
[2023-03-17 10:54:38,705][01332] Decorrelating experience for 64 frames...
[2023-03-17 10:54:38,716][01326] Decorrelating experience for 96 frames...
[2023-03-17 10:54:38,797][01301] Decorrelating experience for 96 frames...
[2023-03-17 10:54:38,805][01331] Decorrelating experience for 0 frames...
[2023-03-17 10:54:38,913][01300] Decorrelating experience for 0 frames...
[2023-03-17 10:54:38,982][01334] Decorrelating experience for 96 frames...
[2023-03-17 10:54:38,992][01332] Decorrelating experience for 96 frames...
[2023-03-17 10:54:39,016][01319] Decorrelating experience for 96 frames...
[2023-03-17 10:54:39,059][01331] Decorrelating experience for 32 frames...
[2023-03-17 10:54:39,112][01328] Decorrelating experience for 32 frames...
[2023-03-17 10:54:39,244][01323] Decorrelating experience for 0 frames...
[2023-03-17 10:54:39,278][01300] Decorrelating experience for 32 frames...
[2023-03-17 10:54:39,359][01329] Decorrelating experience for 32 frames...
[2023-03-17 10:54:39,411][01320] Decorrelating experience for 96 frames...
[2023-03-17 10:54:39,431][01331] Decorrelating experience for 64 frames...
[2023-03-17 10:54:39,459][01325] Decorrelating experience for 32 frames...
[2023-03-17 10:54:39,647][01300] Decorrelating experience for 64 frames...
[2023-03-17 10:54:39,650][01277] Signal inference workers to stop experience collection...
[2023-03-17 10:54:39,654][01299] InferenceWorker_p0-w0: stopping experience collection
[2023-03-17 10:54:39,690][01323] Decorrelating experience for 32 frames...
[2023-03-17 10:54:39,715][01327] Decorrelating experience for 96 frames...
[2023-03-17 10:54:39,718][01328] Decorrelating experience for 64 frames...
[2023-03-17 10:54:39,734][24380] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 184320. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-03-17 10:54:39,736][24380] Avg episode reward: [(0, '2.928')]
[2023-03-17 10:54:39,808][01325] Decorrelating experience for 64 frames...
[2023-03-17 10:54:39,927][01331] Decorrelating experience for 96 frames...
[2023-03-17 10:54:39,930][01323] Decorrelating experience for 64 frames...
[2023-03-17 10:54:39,947][01329] Decorrelating experience for 64 frames...
[2023-03-17 10:54:40,043][01300] Decorrelating experience for 96 frames...
[2023-03-17 10:54:40,080][01328] Decorrelating experience for 96 frames...
[2023-03-17 10:54:40,145][01325] Decorrelating experience for 96 frames...
[2023-03-17 10:54:40,156][01323] Decorrelating experience for 96 frames...
[2023-03-17 10:54:40,287][01329] Decorrelating experience for 96 frames...
[2023-03-17 10:54:40,479][01277] Signal inference workers to resume experience collection...
[2023-03-17 10:54:40,480][01299] InferenceWorker_p0-w0: resuming experience collection
[2023-03-17 10:54:42,279][01299] Updated weights for policy 0, policy_version 55 (0.0267)
[2023-03-17 10:54:43,568][01299] Updated weights for policy 0, policy_version 65 (0.0010)
[2023-03-17 10:54:44,734][24380] Fps is (10 sec: 23757.4, 60 sec: 23757.4, 300 sec: 23757.4). Total num frames: 303104. Throughput: 0: 3473.3. Samples: 17366. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
[2023-03-17 10:54:44,735][24380] Avg episode reward: [(0, '4.797')]
[2023-03-17 10:54:44,843][01299] Updated weights for policy 0, policy_version 75 (0.0011)
[2023-03-17 10:54:44,884][01277] Saving new best policy, reward=4.827!
[2023-03-17 10:54:46,123][01299] Updated weights for policy 0, policy_version 85 (0.0010)
[2023-03-17 10:54:47,363][01299] Updated weights for policy 0, policy_version 95 (0.0012)
[2023-03-17 10:54:48,642][01299] Updated weights for policy 0, policy_version 105 (0.0010)
[2023-03-17 10:54:49,734][24380] Fps is (10 sec: 27853.3, 60 sec: 27853.3, 300 sec: 27853.3). Total num frames: 462848. Throughput: 0: 6522.7. Samples: 65226. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
[2023-03-17 10:54:49,735][24380] Avg episode reward: [(0, '4.902')]
[2023-03-17 10:54:49,920][01299] Updated weights for policy 0, policy_version 115 (0.0014)
[2023-03-17 10:54:51,201][01299] Updated weights for policy 0, policy_version 125 (0.0012)
[2023-03-17 10:54:51,201][24380] Heartbeat connected on Batcher_0
[2023-03-17 10:54:51,203][24380] Heartbeat connected on LearnerWorker_p0
[2023-03-17 10:54:51,211][24380] Heartbeat connected on InferenceWorker_p0-w0
[2023-03-17 10:54:51,212][24380] Heartbeat connected on RolloutWorker_w0
[2023-03-17 10:54:51,213][24380] Heartbeat connected on RolloutWorker_w1
[2023-03-17 10:54:51,219][24380] Heartbeat connected on RolloutWorker_w3
[2023-03-17 10:54:51,220][24380] Heartbeat connected on RolloutWorker_w2
[2023-03-17 10:54:51,222][24380] Heartbeat connected on RolloutWorker_w4
[2023-03-17 10:54:51,223][24380] Heartbeat connected on RolloutWorker_w5
[2023-03-17 10:54:51,225][24380] Heartbeat connected on RolloutWorker_w6
[2023-03-17 10:54:51,226][24380] Heartbeat connected on RolloutWorker_w7
[2023-03-17 10:54:51,232][24380] Heartbeat connected on RolloutWorker_w9
[2023-03-17 10:54:51,233][24380] Heartbeat connected on RolloutWorker_w8
[2023-03-17 10:54:51,234][24380] Heartbeat connected on RolloutWorker_w10
[2023-03-17 10:54:51,238][24380] Heartbeat connected on RolloutWorker_w12
[2023-03-17 10:54:51,239][24380] Heartbeat connected on RolloutWorker_w13
[2023-03-17 10:54:51,241][24380] Heartbeat connected on RolloutWorker_w11
[2023-03-17 10:54:51,241][24380] Heartbeat connected on RolloutWorker_w14
[2023-03-17 10:54:51,245][24380] Heartbeat connected on RolloutWorker_w15
[2023-03-17 10:54:52,537][01299] Updated weights for policy 0, policy_version 135 (0.0014)
[2023-03-17 10:54:53,836][01299] Updated weights for policy 0, policy_version 145 (0.0010)
[2023-03-17 10:54:54,734][24380] Fps is (10 sec: 31949.1, 60 sec: 29218.5, 300 sec: 29218.5). Total num frames: 622592. Throughput: 0: 5924.1. Samples: 88860. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
[2023-03-17 10:54:54,735][24380] Avg episode reward: [(0, '5.518')]
[2023-03-17 10:54:54,881][01277] Saving new best policy, reward=5.635!
[2023-03-17 10:54:55,142][01299] Updated weights for policy 0, policy_version 155 (0.0012)
[2023-03-17 10:54:56,424][01299] Updated weights for policy 0, policy_version 165 (0.0010)
[2023-03-17 10:54:57,687][01299] Updated weights for policy 0, policy_version 175 (0.0015)
[2023-03-17 10:54:58,936][01299] Updated weights for policy 0, policy_version 185 (0.0009)
[2023-03-17 10:54:59,734][24380] Fps is (10 sec: 31948.6, 60 sec: 29901.0, 300 sec: 29901.0). Total num frames: 782336. Throughput: 0: 6841.6. Samples: 136832. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
[2023-03-17 10:54:59,735][24380] Avg episode reward: [(0, '6.663')]
[2023-03-17 10:54:59,864][01277] Saving new best policy, reward=6.669!
[2023-03-17 10:55:00,226][01299] Updated weights for policy 0, policy_version 195 (0.0011)
[2023-03-17 10:55:01,473][01299] Updated weights for policy 0, policy_version 205 (0.0011)
[2023-03-17 10:55:02,736][01299] Updated weights for policy 0, policy_version 215 (0.0010)
[2023-03-17 10:55:04,018][01299] Updated weights for policy 0, policy_version 225 (0.0013)
[2023-03-17 10:55:04,734][24380] Fps is (10 sec: 31948.6, 60 sec: 30310.6, 300 sec: 30310.6). Total num frames: 942080. Throughput: 0: 7402.4. Samples: 185058. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
[2023-03-17 10:55:04,735][24380] Avg episode reward: [(0, '7.065')]
[2023-03-17 10:55:04,863][01277] Saving new best policy, reward=7.036!
[2023-03-17 10:55:05,319][01299] Updated weights for policy 0, policy_version 235 (0.0009)
[2023-03-17 10:55:06,589][01299] Updated weights for policy 0, policy_version 245 (0.0010)
[2023-03-17 10:55:07,846][01299] Updated weights for policy 0, policy_version 255 (0.0011)
[2023-03-17 10:55:09,162][01299] Updated weights for policy 0, policy_version 265 (0.0010)
[2023-03-17 10:55:09,734][24380] Fps is (10 sec: 31948.6, 60 sec: 30583.5, 300 sec: 30583.5). Total num frames: 1101824. Throughput: 0: 6968.3. Samples: 209050. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
[2023-03-17 10:55:09,736][24380] Avg episode reward: [(0, '8.389')]
[2023-03-17 10:55:09,863][01277] Saving new best policy, reward=8.525!
[2023-03-17 10:55:10,439][01299] Updated weights for policy 0, policy_version 275 (0.0014)
[2023-03-17 10:55:11,734][01299] Updated weights for policy 0, policy_version 285 (0.0010)
[2023-03-17 10:55:13,008][01299] Updated weights for policy 0, policy_version 295 (0.0014)
[2023-03-17 10:55:14,302][01299] Updated weights for policy 0, policy_version 305 (0.0012)
[2023-03-17 10:55:14,734][24380] Fps is (10 sec: 31948.7, 60 sec: 30778.6, 300 sec: 30778.6). Total num frames: 1261568. Throughput: 0: 7341.9. Samples: 256964. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
[2023-03-17 10:55:14,735][24380] Avg episode reward: [(0, '10.328')]
[2023-03-17 10:55:14,863][01277] Saving new best policy, reward=10.279!
[2023-03-17 10:55:15,612][01299] Updated weights for policy 0, policy_version 315 (0.0011)
[2023-03-17 10:55:16,888][01299] Updated weights for policy 0, policy_version 325 (0.0013)
[2023-03-17 10:55:18,147][01299] Updated weights for policy 0, policy_version 335 (0.0010)
[2023-03-17 10:55:19,395][01299] Updated weights for policy 0, policy_version 345 (0.0015)
[2023-03-17 10:55:19,734][24380] Fps is (10 sec: 31949.0, 60 sec: 30924.9, 300 sec: 30924.9). Total num frames: 1421312. Throughput: 0: 7627.8. Samples: 305112. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
[2023-03-17 10:55:19,735][24380] Avg episode reward: [(0, '12.270')]
[2023-03-17 10:55:19,863][01277] Saving new best policy, reward=12.489!
[2023-03-17 10:55:20,693][01299] Updated weights for policy 0, policy_version 355 (0.0009)
[2023-03-17 10:55:21,936][01299] Updated weights for policy 0, policy_version 365 (0.0013)
[2023-03-17 10:55:23,234][01299] Updated weights for policy 0, policy_version 375 (0.0016)
[2023-03-17 10:55:24,533][01299] Updated weights for policy 0, policy_version 385 (0.0013)
[2023-03-17 10:55:24,735][24380] Fps is (10 sec: 31947.2, 60 sec: 31038.3, 300 sec: 31038.3). Total num frames: 1581056. Throughput: 0: 7309.9. Samples: 328948. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
[2023-03-17 10:55:24,736][24380] Avg episode reward: [(0, '12.939')]
[2023-03-17 10:55:24,863][01277] Saving new best policy, reward=13.697!
[2023-03-17 10:55:25,807][01299] Updated weights for policy 0, policy_version 395 (0.0011)
[2023-03-17 10:55:27,094][01299] Updated weights for policy 0, policy_version 405 (0.0013)
[2023-03-17 10:55:28,354][01299] Updated weights for policy 0, policy_version 415 (0.0010)
[2023-03-17 10:55:29,639][01299] Updated weights for policy 0, policy_version 425 (0.0011)
[2023-03-17 10:55:29,734][24380] Fps is (10 sec: 31949.0, 60 sec: 31129.7, 300 sec: 31129.7). Total num frames: 1740800. Throughput: 0: 7994.3. Samples: 377110. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
[2023-03-17 10:55:29,735][24380] Avg episode reward: [(0, '13.684')]
[2023-03-17 10:55:30,934][01299] Updated weights for policy 0, policy_version 435 (0.0016)
[2023-03-17 10:55:32,233][01299] Updated weights for policy 0, policy_version 445 (0.0011)
[2023-03-17 10:55:33,489][01299] Updated weights for policy 0, policy_version 455 (0.0011)
[2023-03-17 10:55:34,734][24380] Fps is (10 sec: 31950.5, 60 sec: 31204.2, 300 sec: 31204.2). Total num frames: 1900544. Throughput: 0: 8000.2. Samples: 425234. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0)
[2023-03-17 10:55:34,735][24380] Avg episode reward: [(0, '16.289')]
[2023-03-17 10:55:34,772][01299] Updated weights for policy 0, policy_version 465 (0.0012)
[2023-03-17 10:55:34,863][01277] Saving new best policy, reward=16.870!
[2023-03-17 10:55:36,008][01299] Updated weights for policy 0, policy_version 475 (0.0013)
[2023-03-17 10:55:37,281][01299] Updated weights for policy 0, policy_version 485 (0.0009)
[2023-03-17 10:55:38,525][01299] Updated weights for policy 0, policy_version 495 (0.0011)
[2023-03-17 10:55:39,734][24380] Fps is (10 sec: 32358.4, 60 sec: 31334.5, 300 sec: 31334.5). Total num frames: 2064384. Throughput: 0: 8013.5. Samples: 449468. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
[2023-03-17 10:55:39,735][24380] Avg episode reward: [(0, '18.133')]
[2023-03-17 10:55:39,804][01299] Updated weights for policy 0, policy_version 505 (0.0010)
[2023-03-17 10:55:39,863][01277] Saving new best policy, reward=17.945!
[2023-03-17 10:55:41,090][01299] Updated weights for policy 0, policy_version 515 (0.0010)
[2023-03-17 10:55:42,364][01299] Updated weights for policy 0, policy_version 525 (0.0011)
[2023-03-17 10:55:43,627][01299] Updated weights for policy 0, policy_version 535 (0.0012)
[2023-03-17 10:55:44,734][24380] Fps is (10 sec: 32358.4, 60 sec: 32017.1, 300 sec: 31381.7). Total num frames: 2224128. Throughput: 0: 8018.6. Samples: 497668. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
[2023-03-17 10:55:44,735][24380] Avg episode reward: [(0, '17.323')]
[2023-03-17 10:55:44,892][01299] Updated weights for policy 0, policy_version 545 (0.0012)
[2023-03-17 10:55:46,183][01299] Updated weights for policy 0, policy_version 555 (0.0011)
[2023-03-17 10:55:47,442][01299] Updated weights for policy 0, policy_version 565 (0.0015)
[2023-03-17 10:55:48,670][01299] Updated weights for policy 0, policy_version 575 (0.0009)
[2023-03-17 10:55:49,734][24380] Fps is (10 sec: 32358.2, 60 sec: 32085.3, 300 sec: 31480.7). Total num frames: 2387968. Throughput: 0: 8031.5. Samples: 546474. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
[2023-03-17 10:55:49,735][24380] Avg episode reward: [(0, '18.752')]
[2023-03-17 10:55:49,863][01277] Saving new best policy, reward=18.918!
[2023-03-17 10:55:49,969][01299] Updated weights for policy 0, policy_version 585 (0.0011)
[2023-03-17 10:55:51,171][01299] Updated weights for policy 0, policy_version 595 (0.0010)
[2023-03-17 10:55:52,434][01299] Updated weights for policy 0, policy_version 605 (0.0009)
[2023-03-17 10:55:53,704][01299] Updated weights for policy 0, policy_version 615 (0.0012)
[2023-03-17 10:55:54,734][24380] Fps is (10 sec: 32767.9, 60 sec: 32153.6, 300 sec: 31566.6). Total num frames: 2551808. Throughput: 0: 8037.4. Samples: 570730. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
[2023-03-17 10:55:54,735][24380] Avg episode reward: [(0, '17.902')]
[2023-03-17 10:55:54,984][01299] Updated weights for policy 0, policy_version 625 (0.0010)
[2023-03-17 10:55:56,291][01299] Updated weights for policy 0, policy_version 635 (0.0012)
[2023-03-17 10:55:57,564][01299] Updated weights for policy 0, policy_version 645 (0.0013)
[2023-03-17 10:55:58,843][01299] Updated weights for policy 0, policy_version 655 (0.0014)
[2023-03-17 10:55:59,734][24380] Fps is (10 sec: 31949.0, 60 sec: 32085.4, 300 sec: 31539.3). Total num frames: 2707456. Throughput: 0: 8041.9. Samples: 618848. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
[2023-03-17 10:55:59,735][24380] Avg episode reward: [(0, '19.811')]
[2023-03-17 10:55:59,863][01277] Saving new best policy, reward=19.975!
[2023-03-17 10:56:00,116][01299] Updated weights for policy 0, policy_version 665 (0.0015)
[2023-03-17 10:56:01,390][01299] Updated weights for policy 0, policy_version 675 (0.0010)
[2023-03-17 10:56:02,654][01299] Updated weights for policy 0, policy_version 685 (0.0012)
[2023-03-17 10:56:03,932][01299] Updated weights for policy 0, policy_version 695 (0.0012)
[2023-03-17 10:56:04,734][24380] Fps is (10 sec: 31949.0, 60 sec: 32153.6, 300 sec: 31611.6). Total num frames: 2871296. Throughput: 0: 8045.4. Samples: 667156. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
[2023-03-17 10:56:04,735][24380] Avg episode reward: [(0, '20.363')]
[2023-03-17 10:56:04,863][01277] Saving new best policy, reward=20.373!
[2023-03-17 10:56:05,206][01299] Updated weights for policy 0, policy_version 705 (0.0009)
[2023-03-17 10:56:06,462][01299] Updated weights for policy 0, policy_version 715 (0.0012)
[2023-03-17 10:56:07,751][01299] Updated weights for policy 0, policy_version 725 (0.0013)
[2023-03-17 10:56:09,058][01299] Updated weights for policy 0, policy_version 735 (0.0011)
[2023-03-17 10:56:09,734][24380] Fps is (10 sec: 32358.4, 60 sec: 32153.7, 300 sec: 31630.3). Total num frames: 3031040. Throughput: 0: 8050.5. Samples: 691216. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
[2023-03-17 10:56:09,735][24380] Avg episode reward: [(0, '22.248')]
[2023-03-17 10:56:09,863][01277] Saving new best policy, reward=22.610!
[2023-03-17 10:56:10,354][01299] Updated weights for policy 0, policy_version 745 (0.0014)
[2023-03-17 10:56:11,597][01299] Updated weights for policy 0, policy_version 755 (0.0009)
[2023-03-17 10:56:12,894][01299] Updated weights for policy 0, policy_version 765 (0.0010)
[2023-03-17 10:56:14,193][01299] Updated weights for policy 0, policy_version 775 (0.0011)
[2023-03-17 10:56:14,734][24380] Fps is (10 sec: 31948.8, 60 sec: 32153.6, 300 sec: 31647.1). Total num frames: 3190784. Throughput: 0: 8051.2. Samples: 739416. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
[2023-03-17 10:56:14,735][24380] Avg episode reward: [(0, '22.320')]
[2023-03-17 10:56:15,457][01299] Updated weights for policy 0, policy_version 785 (0.0011)
[2023-03-17 10:56:16,726][01299] Updated weights for policy 0, policy_version 795 (0.0014)
[2023-03-17 10:56:17,985][01299] Updated weights for policy 0, policy_version 805 (0.0010)
[2023-03-17 10:56:19,278][01299] Updated weights for policy 0, policy_version 815 (0.0010)
[2023-03-17 10:56:19,734][24380] Fps is (10 sec: 31948.6, 60 sec: 32153.6, 300 sec: 31662.1). Total num frames: 3350528. Throughput: 0: 8047.0. Samples: 787348. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0)
[2023-03-17 10:56:19,735][24380] Avg episode reward: [(0, '24.349')]
[2023-03-17 10:56:19,863][01277] Saving new best policy, reward=24.642!
[2023-03-17 10:56:20,556][01299] Updated weights for policy 0, policy_version 825 (0.0010)
[2023-03-17 10:56:21,799][01299] Updated weights for policy 0, policy_version 835 (0.0012)
[2023-03-17 10:56:23,077][01299] Updated weights for policy 0, policy_version 845 (0.0015)
[2023-03-17 10:56:24,359][01299] Updated weights for policy 0, policy_version 855 (0.0012)
[2023-03-17 10:56:24,734][24380] Fps is (10 sec: 32358.4, 60 sec: 32222.2, 300 sec: 31714.8). Total num frames: 3514368. Throughput: 0: 8045.7. Samples: 811526. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
[2023-03-17 10:56:24,735][24380] Avg episode reward: [(0, '22.221')]
[2023-03-17 10:56:25,633][01299] Updated weights for policy 0, policy_version 865 (0.0010)
[2023-03-17 10:56:26,920][01299] Updated weights for policy 0, policy_version 875 (0.0011)
[2023-03-17 10:56:28,186][01299] Updated weights for policy 0, policy_version 885 (0.0012)
[2023-03-17 10:56:29,474][01299] Updated weights for policy 0, policy_version 895 (0.0010)
[2023-03-17 10:56:29,739][24380] Fps is (10 sec: 32342.2, 60 sec: 32219.2, 300 sec: 31724.0). Total num frames: 3674112. Throughput: 0: 8048.2. Samples: 859876. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
[2023-03-17 10:56:29,741][24380] Avg episode reward: [(0, '24.978')]
[2023-03-17 10:56:29,746][01277] Saving /home/ckahmann/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000897_3674112.pth...
[2023-03-17 10:56:29,863][01277] Saving new best policy, reward=26.247!
[2023-03-17 10:56:30,766][01299] Updated weights for policy 0, policy_version 905 (0.0009)
[2023-03-17 10:56:32,032][01299] Updated weights for policy 0, policy_version 915 (0.0010)
[2023-03-17 10:56:33,354][01299] Updated weights for policy 0, policy_version 925 (0.0010)
[2023-03-17 10:56:34,610][01299] Updated weights for policy 0, policy_version 935 (0.0012)
[2023-03-17 10:56:34,734][24380] Fps is (10 sec: 31948.6, 60 sec: 32221.9, 300 sec: 31735.1). Total num frames: 3833856. Throughput: 0: 8028.9. Samples: 907774. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
[2023-03-17 10:56:34,735][24380] Avg episode reward: [(0, '24.749')]
[2023-03-17 10:56:35,882][01299] Updated weights for policy 0, policy_version 945 (0.0013)
[2023-03-17 10:56:37,173][01299] Updated weights for policy 0, policy_version 955 (0.0011)
[2023-03-17 10:56:38,451][01299] Updated weights for policy 0, policy_version 965 (0.0011)
[2023-03-17 10:56:39,707][01299] Updated weights for policy 0, policy_version 975 (0.0012)
[2023-03-17 10:56:39,734][24380] Fps is (10 sec: 31964.8, 60 sec: 32153.6, 300 sec: 31744.0). Total num frames: 3993600. Throughput: 0: 8021.1. Samples: 931680. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0)
[2023-03-17 10:56:39,735][24380] Avg episode reward: [(0, '24.199')]
[2023-03-17 10:56:40,085][01277] Stopping Batcher_0...
[2023-03-17 10:56:40,086][01277] Loop batcher_evt_loop terminating...
[2023-03-17 10:56:40,087][01277] Saving /home/ckahmann/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-03-17 10:56:40,085][24380] Component Batcher_0 stopped!
[2023-03-17 10:56:40,096][01334] Stopping RolloutWorker_w14...
[2023-03-17 10:56:40,097][01328] Stopping RolloutWorker_w10...
[2023-03-17 10:56:40,097][01334] Loop rollout_proc14_evt_loop terminating...
[2023-03-17 10:56:40,097][01328] Loop rollout_proc10_evt_loop terminating...
[2023-03-17 10:56:40,097][01319] Stopping RolloutWorker_w2...
[2023-03-17 10:56:40,097][24380] Component RolloutWorker_w14 stopped!
[2023-03-17 10:56:40,098][01301] Stopping RolloutWorker_w1...
[2023-03-17 10:56:40,098][01323] Stopping RolloutWorker_w5...
[2023-03-17 10:56:40,099][01326] Stopping RolloutWorker_w7...
[2023-03-17 10:56:40,098][01324] Stopping RolloutWorker_w6...
[2023-03-17 10:56:40,099][01319] Loop rollout_proc2_evt_loop terminating...
[2023-03-17 10:56:40,099][01301] Loop rollout_proc1_evt_loop terminating...
[2023-03-17 10:56:40,099][01323] Loop rollout_proc5_evt_loop terminating...
[2023-03-17 10:56:40,099][01332] Stopping RolloutWorker_w15...
[2023-03-17 10:56:40,099][01326] Loop rollout_proc7_evt_loop terminating...
[2023-03-17 10:56:40,099][01324] Loop rollout_proc6_evt_loop terminating...
[2023-03-17 10:56:40,099][01332] Loop rollout_proc15_evt_loop terminating...
[2023-03-17 10:56:40,099][01335] Stopping RolloutWorker_w13...
[2023-03-17 10:56:40,100][01335] Loop rollout_proc13_evt_loop terminating...
[2023-03-17 10:56:40,100][01325] Stopping RolloutWorker_w8...
[2023-03-17 10:56:40,099][24380] Component RolloutWorker_w10 stopped!
[2023-03-17 10:56:40,100][01321] Stopping RolloutWorker_w4...
[2023-03-17 10:56:40,101][01320] Stopping RolloutWorker_w3...
[2023-03-17 10:56:40,101][01325] Loop rollout_proc8_evt_loop terminating...
[2023-03-17 10:56:40,101][01320] Loop rollout_proc3_evt_loop terminating...
[2023-03-17 10:56:40,101][01321] Loop rollout_proc4_evt_loop terminating...
[2023-03-17 10:56:40,101][01329] Stopping RolloutWorker_w11...
[2023-03-17 10:56:40,102][24380] Component RolloutWorker_w2 stopped!
[2023-03-17 10:56:40,103][24380] Component RolloutWorker_w1 stopped!
[2023-03-17 10:56:40,104][24380] Component RolloutWorker_w6 stopped!
[2023-03-17 10:56:40,105][24380] Component RolloutWorker_w5 stopped!
[2023-03-17 10:56:40,106][24380] Component RolloutWorker_w7 stopped!
[2023-03-17 10:56:40,107][24380] Component RolloutWorker_w15 stopped!
[2023-03-17 10:56:40,108][24380] Component RolloutWorker_w13 stopped!
[2023-03-17 10:56:40,109][01331] Stopping RolloutWorker_w12...
[2023-03-17 10:56:40,109][24380] Component RolloutWorker_w8 stopped!
[2023-03-17 10:56:40,109][01331] Loop rollout_proc12_evt_loop terminating...
[2023-03-17 10:56:40,110][24380] Component RolloutWorker_w4 stopped!
[2023-03-17 10:56:40,110][24380] Component RolloutWorker_w3 stopped!
[2023-03-17 10:56:40,111][24380] Component RolloutWorker_w11 stopped!
[2023-03-17 10:56:40,112][24380] Component RolloutWorker_w12 stopped!
[2023-03-17 10:56:40,102][01329] Loop rollout_proc11_evt_loop terminating...
[2023-03-17 10:56:40,116][01327] Stopping RolloutWorker_w9...
[2023-03-17 10:56:40,116][01327] Loop rollout_proc9_evt_loop terminating...
[2023-03-17 10:56:40,116][24380] Component RolloutWorker_w9 stopped!
[2023-03-17 10:56:40,117][01300] Stopping RolloutWorker_w0...
[2023-03-17 10:56:40,118][01300] Loop rollout_proc0_evt_loop terminating...
[2023-03-17 10:56:40,117][24380] Component RolloutWorker_w0 stopped!
[2023-03-17 10:56:40,126][01299] Weights refcount: 2 0
[2023-03-17 10:56:40,127][01299] Stopping InferenceWorker_p0-w0...
[2023-03-17 10:56:40,128][01299] Loop inference_proc0-0_evt_loop terminating...
[2023-03-17 10:56:40,128][24380] Component InferenceWorker_p0-w0 stopped!
[2023-03-17 10:56:40,158][01277] Removing /home/ckahmann/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000045_184320.pth
[2023-03-17 10:56:40,165][01277] Saving /home/ckahmann/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-03-17 10:56:40,243][01277] Stopping LearnerWorker_p0...
[2023-03-17 10:56:40,243][01277] Loop learner_proc0_evt_loop terminating...
[2023-03-17 10:56:40,243][24380] Component LearnerWorker_p0 stopped!
[2023-03-17 10:56:40,245][24380] Waiting for process learner_proc0 to stop...
[2023-03-17 10:56:40,965][24380] Waiting for process inference_proc0-0 to join...
[2023-03-17 10:56:40,967][24380] Waiting for process rollout_proc0 to join...
[2023-03-17 10:56:40,968][24380] Waiting for process rollout_proc1 to join...
[2023-03-17 10:56:40,970][24380] Waiting for process rollout_proc2 to join...
[2023-03-17 10:56:40,971][24380] Waiting for process rollout_proc3 to join...
[2023-03-17 10:56:40,972][24380] Waiting for process rollout_proc4 to join...
[2023-03-17 10:56:40,974][24380] Waiting for process rollout_proc5 to join...
[2023-03-17 10:56:40,975][24380] Waiting for process rollout_proc6 to join...
[2023-03-17 10:56:40,976][24380] Waiting for process rollout_proc7 to join...
[2023-03-17 10:56:40,978][24380] Waiting for process rollout_proc8 to join...
[2023-03-17 10:56:40,979][24380] Waiting for process rollout_proc9 to join...
[2023-03-17 10:56:40,980][24380] Waiting for process rollout_proc10 to join...
[2023-03-17 10:56:40,982][24380] Waiting for process rollout_proc11 to join...
[2023-03-17 10:56:40,983][24380] Waiting for process rollout_proc12 to join...
[2023-03-17 10:56:40,984][24380] Waiting for process rollout_proc13 to join...
[2023-03-17 10:56:40,986][24380] Waiting for process rollout_proc14 to join...
[2023-03-17 10:56:40,987][24380] Waiting for process rollout_proc15 to join...
[2023-03-17 10:56:40,988][24380] Batcher 0 profile tree view:
batching: 12.2211, releasing_batches: 0.0246
[2023-03-17 10:56:40,989][24380] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0001
  wait_policy_total: 5.2569
update_model: 2.5986
  weight_update: 0.0012
one_step: 0.0036
  handle_policy_step: 107.7825
    deserialize: 7.7872, stack: 0.7211, obs_to_device_normalize: 31.9304, forward: 37.9525, send_messages: 9.9044
    prepare_outputs: 14.9006
      to_cpu: 9.4684
[2023-03-17 10:56:40,990][24380] Learner 0 profile tree view:
misc: 0.0056, prepare_batch: 7.4842
train: 28.2527
  epoch_init: 0.0042, minibatch_init: 0.0061, losses_postprocess: 0.1527, kl_divergence: 0.1730, after_optimizer: 0.3012
  calculate_losses: 8.7205
    losses_init: 0.0027, forward_head: 0.7555, bptt_initial: 5.6775, tail: 0.4340, advantages_returns: 0.1187, losses: 0.6629
    bptt: 0.9171
      bptt_forward_core: 0.8796
  update: 18.5538
    clip: 0.8257
[2023-03-17 10:56:40,992][24380] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.0611, enqueue_policy_requests: 4.1572, env_step: 51.2831, overhead: 4.9311, complete_rollouts: 0.1200
save_policy_outputs: 4.2128
  split_output_tensors: 2.0315
[2023-03-17 10:56:40,993][24380] RolloutWorker_w15 profile tree view:
wait_for_trajectories: 0.0640, enqueue_policy_requests: 4.2558, env_step: 53.0790, overhead: 5.1241, complete_rollouts: 0.1230
save_policy_outputs: 4.2865
  split_output_tensors: 2.0872
[2023-03-17 10:56:40,995][24380] Loop Runner_EvtLoop terminating...
[2023-03-17 10:56:40,996][24380] Runner profile tree view:
main_loop: 129.7535
[2023-03-17 10:56:40,998][24380] Collected {0: 4005888}, FPS: 29452.5
[2023-03-17 10:58:47,379][24380] Loading existing experiment configuration from /home/ckahmann/RL/train_dir/default_experiment/config.json
[2023-03-17 10:58:47,380][24380] Overriding arg 'num_workers' with value 1 passed from command line
[2023-03-17 10:58:47,381][24380] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-03-17 10:58:47,381][24380] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-03-17 10:58:47,382][24380] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-03-17 10:58:47,382][24380] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-03-17 10:58:47,383][24380] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2023-03-17 10:58:47,384][24380] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-03-17 10:58:47,384][24380] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2023-03-17 10:58:47,385][24380] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2023-03-17 10:58:47,385][24380] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-03-17 10:58:47,386][24380] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-03-17 10:58:47,387][24380] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-03-17 10:58:47,387][24380] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-03-17 10:58:47,388][24380] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-03-17 10:58:47,404][24380] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-03-17 10:58:47,406][24380] RunningMeanStd input shape: (3, 72, 128)
[2023-03-17 10:58:47,407][24380] RunningMeanStd input shape: (1,)
[2023-03-17 10:58:47,419][24380] ConvEncoder: input_channels=3
[2023-03-17 10:58:47,538][24380] Conv encoder output size: 512
[2023-03-17 10:58:47,539][24380] Policy head output size: 512
[2023-03-17 10:58:49,022][24380] Loading state from checkpoint /home/ckahmann/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-03-17 10:58:49,781][24380] Num frames 100...
[2023-03-17 10:58:49,931][24380] Num frames 200...
[2023-03-17 10:58:50,058][24380] Num frames 300...
[2023-03-17 10:58:50,169][24380] Num frames 400...
[2023-03-17 10:58:50,290][24380] Num frames 500...
[2023-03-17 10:58:50,397][24380] Num frames 600...
[2023-03-17 10:58:50,508][24380] Num frames 700...
[2023-03-17 10:58:50,619][24380] Num frames 800...
[2023-03-17 10:58:50,731][24380] Num frames 900...
[2023-03-17 10:58:50,841][24380] Num frames 1000...
[2023-03-17 10:58:50,956][24380] Num frames 1100...
[2023-03-17 10:58:51,077][24380] Num frames 1200...
[2023-03-17 10:58:51,193][24380] Avg episode rewards: #0: 27.480, true rewards: #0: 12.480
[2023-03-17 10:58:51,195][24380] Avg episode reward: 27.480, avg true_objective: 12.480
[2023-03-17 10:58:51,292][24380] Num frames 1300...
[2023-03-17 10:58:51,422][24380] Num frames 1400...
[2023-03-17 10:58:51,579][24380] Num frames 1500...
[2023-03-17 10:58:51,702][24380] Num frames 1600...
[2023-03-17 10:58:51,863][24380] Avg episode rewards: #0: 17.405, true rewards: #0: 8.405
[2023-03-17 10:58:51,865][24380] Avg episode reward: 17.405, avg true_objective: 8.405
[2023-03-17 10:58:51,906][24380] Num frames 1700...
[2023-03-17 10:58:52,054][24380] Num frames 1800...
[2023-03-17 10:58:52,167][24380] Num frames 1900...
[2023-03-17 10:58:52,273][24380] Avg episode rewards: #0: 12.457, true rewards: #0: 6.457
[2023-03-17 10:58:52,275][24380] Avg episode reward: 12.457, avg true_objective: 6.457
[2023-03-17 10:58:52,380][24380] Num frames 2000...
[2023-03-17 10:58:52,503][24380] Num frames 2100...
[2023-03-17 10:58:52,627][24380] Num frames 2200...
[2023-03-17 10:58:52,753][24380] Num frames 2300...
[2023-03-17 10:58:52,874][24380] Num frames 2400...
[2023-03-17 10:58:53,011][24380] Num frames 2500...
[2023-03-17 10:58:53,176][24380] Num frames 2600...
[2023-03-17 10:58:53,288][24380] Num frames 2700...
[2023-03-17 10:58:53,369][24380] Num frames 2800...
[2023-03-17 10:58:53,476][24380] Avg episode rewards: #0: 14.173, true rewards: #0: 7.172
[2023-03-17 10:58:53,478][24380] Avg episode reward: 14.173, avg true_objective: 7.172
[2023-03-17 10:58:53,523][24380] Num frames 2900...
[2023-03-17 10:58:53,607][24380] Num frames 3000...
[2023-03-17 10:58:53,690][24380] Num frames 3100...
[2023-03-17 10:58:53,808][24380] Num frames 3200...
[2023-03-17 10:58:53,936][24380] Num frames 3300...
[2023-03-17 10:58:54,055][24380] Num frames 3400...
[2023-03-17 10:58:54,190][24380] Num frames 3500...
[2023-03-17 10:58:54,288][24380] Num frames 3600...
[2023-03-17 10:58:54,368][24380] Num frames 3700...
[2023-03-17 10:58:54,444][24380] Num frames 3800...
[2023-03-17 10:58:54,520][24380] Num frames 3900...
[2023-03-17 10:58:54,596][24380] Num frames 4000...
[2023-03-17 10:58:54,674][24380] Num frames 4100...
[2023-03-17 10:58:54,802][24380] Avg episode rewards: #0: 16.590, true rewards: #0: 8.390
[2023-03-17 10:58:54,803][24380] Avg episode reward: 16.590, avg true_objective: 8.390
[2023-03-17 10:58:54,816][24380] Num frames 4200...
[2023-03-17 10:58:54,914][24380] Num frames 4300...
[2023-03-17 10:58:54,995][24380] Num frames 4400...
[2023-03-17 10:58:55,071][24380] Num frames 4500...
[2023-03-17 10:58:55,147][24380] Num frames 4600...
[2023-03-17 10:58:55,224][24380] Num frames 4700...
[2023-03-17 10:58:55,301][24380] Num frames 4800...
[2023-03-17 10:58:55,358][24380] Avg episode rewards: #0: 15.338, true rewards: #0: 8.005
[2023-03-17 10:58:55,359][24380] Avg episode reward: 15.338, avg true_objective: 8.005
[2023-03-17 10:58:55,457][24380] Num frames 4900...
[2023-03-17 10:58:55,539][24380] Num frames 5000...
[2023-03-17 10:58:55,621][24380] Num frames 5100...
[2023-03-17 10:58:55,702][24380] Num frames 5200...
[2023-03-17 10:58:55,786][24380] Num frames 5300...
[2023-03-17 10:58:55,868][24380] Num frames 5400...
[2023-03-17 10:58:55,950][24380] Num frames 5500...
[2023-03-17 10:58:56,032][24380] Num frames 5600...
[2023-03-17 10:58:56,115][24380] Num frames 5700...
[2023-03-17 10:58:56,199][24380] Num frames 5800...
[2023-03-17 10:58:56,328][24380] Num frames 5900...
[2023-03-17 10:58:56,458][24380] Num frames 6000...
[2023-03-17 10:58:56,592][24380] Num frames 6100...
[2023-03-17 10:58:56,721][24380] Num frames 6200...
[2023-03-17 10:58:56,860][24380] Num frames 6300...
[2023-03-17 10:58:56,995][24380] Num frames 6400...
[2023-03-17 10:58:57,127][24380] Num frames 6500...
[2023-03-17 10:58:57,249][24380] Num frames 6600...
[2023-03-17 10:58:57,333][24380] Num frames 6700...
[2023-03-17 10:58:57,411][24380] Num frames 6800...
[2023-03-17 10:58:57,489][24380] Num frames 6900...
[2023-03-17 10:58:57,546][24380] Avg episode rewards: #0: 21.861, true rewards: #0: 9.861
[2023-03-17 10:58:57,547][24380] Avg episode reward: 21.861, avg true_objective: 9.861
[2023-03-17 10:58:57,644][24380] Num frames 7000...
[2023-03-17 10:58:57,748][24380] Num frames 7100...
[2023-03-17 10:58:57,876][24380] Num frames 7200...
[2023-03-17 10:58:57,992][24380] Num frames 7300...
[2023-03-17 10:58:58,072][24380] Avg episode rewards: #0: 19.899, true rewards: #0: 9.149
[2023-03-17 10:58:58,074][24380] Avg episode reward: 19.899, avg true_objective: 9.149
[2023-03-17 10:58:58,196][24380] Num frames 7400...
[2023-03-17 10:58:58,399][24380] Num frames 7500...
[2023-03-17 10:58:58,543][24380] Num frames 7600...
[2023-03-17 10:58:58,673][24380] Num frames 7700...
[2023-03-17 10:58:58,776][24380] Num frames 7800...
[2023-03-17 10:58:58,908][24380] Num frames 7900...
[2023-03-17 10:58:59,066][24380] Num frames 8000...
[2023-03-17 10:58:59,182][24380] Num frames 8100...
[2023-03-17 10:58:59,294][24380] Num frames 8200...
[2023-03-17 10:58:59,427][24380] Num frames 8300...
[2023-03-17 10:58:59,546][24380] Num frames 8400...
[2023-03-17 10:58:59,665][24380] Num frames 8500...
[2023-03-17 10:58:59,797][24380] Num frames 8600...
[2023-03-17 10:58:59,917][24380] Num frames 8700...
[2023-03-17 10:59:00,031][24380] Num frames 8800...
[2023-03-17 10:59:00,161][24380] Num frames 8900...
[2023-03-17 10:59:00,323][24380] Num frames 9000...
[2023-03-17 10:59:00,458][24380] Num frames 9100...
[2023-03-17 10:59:00,596][24380] Num frames 9200...
[2023-03-17 10:59:00,665][24380] Avg episode rewards: #0: 22.674, true rewards: #0: 10.230
[2023-03-17 10:59:00,667][24380] Avg episode reward: 22.674, avg true_objective: 10.230
[2023-03-17 10:59:00,847][24380] Num frames 9300...
[2023-03-17 10:59:00,983][24380] Num frames 9400...
[2023-03-17 10:59:01,101][24380] Num frames 9500...
[2023-03-17 10:59:01,238][24380] Num frames 9600...
[2023-03-17 10:59:01,396][24380] Num frames 9700...
[2023-03-17 10:59:01,527][24380] Num frames 9800...
[2023-03-17 10:59:01,665][24380] Num frames 9900...
[2023-03-17 10:59:01,806][24380] Num frames 10000...
[2023-03-17 10:59:01,927][24380] Num frames 10100...
[2023-03-17 10:59:02,057][24380] Num frames 10200...
[2023-03-17 10:59:02,180][24380] Num frames 10300...
[2023-03-17 10:59:02,343][24380] Num frames 10400...
[2023-03-17 10:59:02,541][24380] Num frames 10500...
[2023-03-17 10:59:02,701][24380] Avg episode rewards: #0: 23.768, true rewards: #0: 10.568
[2023-03-17 10:59:02,703][24380] Avg episode reward: 23.768, avg true_objective: 10.568
[2023-03-17 10:59:30,255][24380] Replay video saved to /home/ckahmann/RL/train_dir/default_experiment/replay.mp4!
[2023-03-17 11:02:12,760][24380] Loading existing experiment configuration from /home/ckahmann/RL/train_dir/default_experiment/config.json
[2023-03-17 11:02:12,761][24380] Overriding arg 'num_workers' with value 1 passed from command line
[2023-03-17 11:02:12,762][24380] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-03-17 11:02:12,762][24380] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-03-17 11:02:12,763][24380] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-03-17 11:02:12,764][24380] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-03-17 11:02:12,764][24380] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2023-03-17 11:02:12,765][24380] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-03-17 11:02:12,766][24380] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-03-17 11:02:12,766][24380] Adding new argument 'hf_repository'='Christian90/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-03-17 11:02:12,767][24380] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-03-17 11:02:12,767][24380] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-03-17 11:02:12,768][24380] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-03-17 11:02:12,769][24380] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-03-17 11:02:12,769][24380] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-03-17 11:02:12,788][24380] RunningMeanStd input shape: (3, 72, 128)
[2023-03-17 11:02:12,790][24380] RunningMeanStd input shape: (1,)
[2023-03-17 11:02:12,800][24380] ConvEncoder: input_channels=3
[2023-03-17 11:02:12,828][24380] Conv encoder output size: 512
[2023-03-17 11:02:12,829][24380] Policy head output size: 512
[2023-03-17 11:02:12,863][24380] Loading state from checkpoint /home/ckahmann/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-03-17 11:02:13,294][24380] Num frames 100...
[2023-03-17 11:02:13,426][24380] Num frames 200...
[2023-03-17 11:02:13,543][24380] Num frames 300...
[2023-03-17 11:02:13,650][24380] Num frames 400...
[2023-03-17 11:02:13,770][24380] Num frames 500...
[2023-03-17 11:02:13,905][24380] Num frames 600...
[2023-03-17 11:02:14,026][24380] Num frames 700...
[2023-03-17 11:02:14,133][24380] Num frames 800...
[2023-03-17 11:02:14,262][24380] Avg episode rewards: #0: 20.640, true rewards: #0: 8.640
[2023-03-17 11:02:14,263][24380] Avg episode reward: 20.640, avg true_objective: 8.640
[2023-03-17 11:02:14,334][24380] Num frames 900...
[2023-03-17 11:02:14,461][24380] Num frames 1000...
[2023-03-17 11:02:14,598][24380] Num frames 1100...
[2023-03-17 11:02:14,723][24380] Num frames 1200...
[2023-03-17 11:02:14,888][24380] Num frames 1300...
[2023-03-17 11:02:15,068][24380] Num frames 1400...
[2023-03-17 11:02:15,252][24380] Num frames 1500...
[2023-03-17 11:02:15,427][24380] Num frames 1600...
[2023-03-17 11:02:15,554][24380] Num frames 1700...
[2023-03-17 11:02:15,688][24380] Num frames 1800...
[2023-03-17 11:02:15,828][24380] Num frames 1900...
[2023-03-17 11:02:15,969][24380] Num frames 2000...
[2023-03-17 11:02:16,097][24380] Num frames 2100...
[2023-03-17 11:02:16,221][24380] Num frames 2200...
[2023-03-17 11:02:16,361][24380] Num frames 2300...
[2023-03-17 11:02:16,472][24380] Num frames 2400...
[2023-03-17 11:02:16,599][24380] Num frames 2500...
[2023-03-17 11:02:16,701][24380] Avg episode rewards: #0: 31.140, true rewards: #0: 12.640
[2023-03-17 11:02:16,703][24380] Avg episode reward: 31.140, avg true_objective: 12.640
[2023-03-17 11:02:16,836][24380] Num frames 2600...
[2023-03-17 11:02:16,977][24380] Num frames 2700...
[2023-03-17 11:02:17,108][24380] Num frames 2800...
[2023-03-17 11:02:17,235][24380] Num frames 2900...
[2023-03-17 11:02:17,353][24380] Num frames 3000...
[2023-03-17 11:02:17,480][24380] Num frames 3100...
[2023-03-17 11:02:17,601][24380] Num frames 3200...
[2023-03-17 11:02:17,731][24380] Num frames 3300...
[2023-03-17 11:02:17,850][24380] Num frames 3400...
[2023-03-17 11:02:17,991][24380] Num frames 3500...
[2023-03-17 11:02:18,135][24380] Num frames 3600...
[2023-03-17 11:02:18,286][24380] Num frames 3700...
[2023-03-17 11:02:18,405][24380] Num frames 3800...
[2023-03-17 11:02:18,555][24380] Num frames 3900...
[2023-03-17 11:02:18,677][24380] Num frames 4000...
[2023-03-17 11:02:18,795][24380] Num frames 4100...
[2023-03-17 11:02:18,932][24380] Num frames 4200...
[2023-03-17 11:02:19,128][24380] Avg episode rewards: #0: 36.960, true rewards: #0: 14.293
[2023-03-17 11:02:19,130][24380] Avg episode reward: 36.960, avg true_objective: 14.293
[2023-03-17 11:02:19,160][24380] Num frames 4300...
[2023-03-17 11:02:19,297][24380] Num frames 4400...
[2023-03-17 11:02:19,439][24380] Num frames 4500...
[2023-03-17 11:02:19,577][24380] Num frames 4600...
[2023-03-17 11:02:19,698][24380] Num frames 4700...
[2023-03-17 11:02:19,832][24380] Num frames 4800...
[2023-03-17 11:02:19,884][24380] Avg episode rewards: #0: 29.750, true rewards: #0: 12.000
[2023-03-17 11:02:19,886][24380] Avg episode reward: 29.750, avg true_objective: 12.000
[2023-03-17 11:02:20,021][24380] Num frames 4900...
[2023-03-17 11:02:20,140][24380] Num frames 5000...
[2023-03-17 11:02:20,255][24380] Num frames 5100...
[2023-03-17 11:02:20,373][24380] Num frames 5200...
[2023-03-17 11:02:20,492][24380] Num frames 5300...
[2023-03-17 11:02:20,635][24380] Num frames 5400...
[2023-03-17 11:02:20,764][24380] Num frames 5500...
[2023-03-17 11:02:20,892][24380] Num frames 5600...
[2023-03-17 11:02:21,008][24380] Num frames 5700...
[2023-03-17 11:02:21,126][24380] Avg episode rewards: #0: 28.088, true rewards: #0: 11.488
[2023-03-17 11:02:21,128][24380] Avg episode reward: 28.088, avg true_objective: 11.488
[2023-03-17 11:02:21,232][24380] Num frames 5800...
[2023-03-17 11:02:21,376][24380] Num frames 5900...
[2023-03-17 11:02:21,540][24380] Num frames 6000...
[2023-03-17 11:02:21,661][24380] Num frames 6100...
[2023-03-17 11:02:21,809][24380] Num frames 6200...
[2023-03-17 11:02:21,940][24380] Num frames 6300...
[2023-03-17 11:02:22,059][24380] Num frames 6400...
[2023-03-17 11:02:22,172][24380] Num frames 6500...
[2023-03-17 11:02:22,285][24380] Num frames 6600...
[2023-03-17 11:02:22,414][24380] Num frames 6700...
[2023-03-17 11:02:22,534][24380] Num frames 6800...
[2023-03-17 11:02:22,647][24380] Num frames 6900...
[2023-03-17 11:02:22,762][24380] Num frames 7000...
[2023-03-17 11:02:22,885][24380] Num frames 7100...
[2023-03-17 11:02:23,036][24380] Num frames 7200...
[2023-03-17 11:02:23,152][24380] Num frames 7300...
[2023-03-17 11:02:23,292][24380] Num frames 7400...
[2023-03-17 11:02:23,418][24380] Num frames 7500...
[2023-03-17 11:02:23,504][24380] Num frames 7600...
[2023-03-17 11:02:23,589][24380] Num frames 7700...
[2023-03-17 11:02:23,717][24380] Num frames 7800...
[2023-03-17 11:02:23,830][24380] Avg episode rewards: #0: 32.406, true rewards: #0: 13.073
[2023-03-17 11:02:23,832][24380] Avg episode reward: 32.406, avg true_objective: 13.073
[2023-03-17 11:02:23,947][24380] Num frames 7900...
[2023-03-17 11:02:24,092][24380] Num frames 8000...
[2023-03-17 11:02:24,247][24380] Num frames 8100...
[2023-03-17 11:02:24,367][24380] Num frames 8200...
[2023-03-17 11:02:24,487][24380] Num frames 8300...
[2023-03-17 11:02:24,609][24380] Num frames 8400...
[2023-03-17 11:02:24,724][24380] Num frames 8500...
[2023-03-17 11:02:24,835][24380] Num frames 8600...
[2023-03-17 11:02:24,998][24380] Avg episode rewards: #0: 29.965, true rewards: #0: 12.394
[2023-03-17 11:02:25,000][24380] Avg episode reward: 29.965, avg true_objective: 12.394
[2023-03-17 11:02:25,050][24380] Num frames 8700...
[2023-03-17 11:02:25,182][24380] Num frames 8800...
[2023-03-17 11:02:25,289][24380] Num frames 8900...
[2023-03-17 11:02:25,402][24380] Num frames 9000...
[2023-03-17 11:02:25,569][24380] Num frames 9100...
[2023-03-17 11:02:25,681][24380] Num frames 9200...
[2023-03-17 11:02:25,829][24380] Num frames 9300...
[2023-03-17 11:02:26,014][24380] Num frames 9400...
[2023-03-17 11:02:26,142][24380] Num frames 9500...
[2023-03-17 11:02:26,264][24380] Num frames 9600...
[2023-03-17 11:02:26,370][24380] Avg episode rewards: #0: 28.929, true rewards: #0: 12.054
[2023-03-17 11:02:26,372][24380] Avg episode reward: 28.929, avg true_objective: 12.054
[2023-03-17 11:02:26,492][24380] Num frames 9700...
[2023-03-17 11:02:26,650][24380] Num frames 9800...
[2023-03-17 11:02:26,798][24380] Num frames 9900...
[2023-03-17 11:02:26,914][24380] Num frames 10000...
[2023-03-17 11:02:27,105][24380] Num frames 10100...
[2023-03-17 11:02:27,295][24380] Num frames 10200...
[2023-03-17 11:02:27,483][24380] Num frames 10300...
[2023-03-17 11:02:27,662][24380] Num frames 10400...
[2023-03-17 11:02:27,784][24380] Num frames 10500...
[2023-03-17 11:02:27,902][24380] Num frames 10600...
[2023-03-17 11:02:27,963][24380] Avg episode rewards: #0: 28.670, true rewards: #0: 11.781
[2023-03-17 11:02:27,965][24380] Avg episode reward: 28.670, avg true_objective: 11.781
[2023-03-17 11:02:28,112][24380] Num frames 10700...
[2023-03-17 11:02:28,238][24380] Num frames 10800...
[2023-03-17 11:02:28,364][24380] Num frames 10900...
[2023-03-17 11:02:28,495][24380] Num frames 11000...
[2023-03-17 11:02:28,621][24380] Num frames 11100...
[2023-03-17 11:02:28,756][24380] Num frames 11200...
[2023-03-17 11:02:28,887][24380] Num frames 11300...
[2023-03-17 11:02:29,022][24380] Num frames 11400...
[2023-03-17 11:02:29,149][24380] Num frames 11500...
[2023-03-17 11:02:29,269][24380] Num frames 11600...
[2023-03-17 11:02:29,429][24380] Avg episode rewards: #0: 28.480, true rewards: #0: 11.680
[2023-03-17 11:02:29,431][24380] Avg episode reward: 28.480, avg true_objective: 11.680
[2023-03-17 11:02:59,990][24380] Replay video saved to /home/ckahmann/RL/train_dir/default_experiment/replay.mp4!