Hugging Face's logo

ItchyB
/
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: 130,549 Bytes 
4e2de75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a0c27d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4e2de75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10887b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4e2de75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
 
[2023-04-30 12:43:57,803][678550] Saving configuration to ./train_dir/doom_health_gathering_supreme/config.json...
[2023-04-30 12:43:57,803][678550] Rollout worker 0 uses device cpu
[2023-04-30 12:43:57,803][678550] Rollout worker 1 uses device cpu
[2023-04-30 12:43:57,804][678550] Rollout worker 2 uses device cpu
[2023-04-30 12:43:57,804][678550] Rollout worker 3 uses device cpu
[2023-04-30 12:43:57,804][678550] Rollout worker 4 uses device cpu
[2023-04-30 12:43:57,804][678550] Rollout worker 5 uses device cpu
[2023-04-30 12:43:57,804][678550] Rollout worker 6 uses device cpu
[2023-04-30 12:43:57,804][678550] Rollout worker 7 uses device cpu
[2023-04-30 12:43:57,858][678550] InferenceWorker_p0-w0: min num requests: 2
[2023-04-30 12:43:57,999][678550] Starting all processes...
[2023-04-30 12:43:57,999][678550] Starting process learner_proc0
[2023-04-30 12:43:58,808][678550] Starting all processes...
[2023-04-30 12:43:58,813][678550] Starting process inference_proc0-0
[2023-04-30 12:43:58,813][678550] Starting process rollout_proc0
[2023-04-30 12:43:58,814][678641] Starting seed is not provided
[2023-04-30 12:43:58,814][678641] Initializing actor-critic model on device cpu
[2023-04-30 12:43:58,814][678641] RunningMeanStd input shape: (3, 72, 128)
[2023-04-30 12:43:58,815][678641] RunningMeanStd input shape: (1,)
[2023-04-30 12:43:58,813][678550] Starting process rollout_proc1
[2023-04-30 12:43:58,814][678550] Starting process rollout_proc2
[2023-04-30 12:43:58,822][678641] ConvEncoder: input_channels=3
[2023-04-30 12:43:58,818][678550] Starting process rollout_proc3
[2023-04-30 12:43:58,820][678550] Starting process rollout_proc4
[2023-04-30 12:43:58,821][678550] Starting process rollout_proc5
[2023-04-30 12:43:58,824][678550] Starting process rollout_proc6
[2023-04-30 12:43:58,827][678550] Starting process rollout_proc7
[2023-04-30 12:43:58,928][678641] Conv encoder output size: 512
[2023-04-30 12:43:58,929][678641] Policy head output size: 512
[2023-04-30 12:43:58,948][678641] Created Actor Critic model with architecture:
[2023-04-30 12:43:58,948][678641] 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)
  )
)
[2023-04-30 12:43:59,297][678641] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-04-30 12:43:59,298][678641] No checkpoints found
[2023-04-30 12:43:59,299][678641] Did not load from checkpoint, starting from scratch!
[2023-04-30 12:43:59,299][678641] Initialized policy 0 weights for model version 0
[2023-04-30 12:43:59,300][678641] LearnerWorker_p0 finished initialization!
[2023-04-30 12:43:59,906][678704] Worker 0 uses CPU cores [0, 1, 2]
[2023-04-30 12:43:59,919][678703] RunningMeanStd input shape: (3, 72, 128)
[2023-04-30 12:43:59,920][678703] RunningMeanStd input shape: (1,)
[2023-04-30 12:43:59,928][678703] ConvEncoder: input_channels=3
[2023-04-30 12:43:59,932][678706] Worker 2 uses CPU cores [6, 7, 8]
[2023-04-30 12:43:59,934][678711] Worker 7 uses CPU cores [21, 22, 23]
[2023-04-30 12:43:59,935][678705] Worker 1 uses CPU cores [3, 4, 5]
[2023-04-30 12:43:59,943][678708] Worker 4 uses CPU cores [12, 13, 14]
[2023-04-30 12:43:59,948][678710] Worker 6 uses CPU cores [18, 19, 20]
[2023-04-30 12:43:59,949][678707] Worker 3 uses CPU cores [9, 10, 11]
[2023-04-30 12:43:59,953][678709] Worker 5 uses CPU cores [15, 16, 17]
[2023-04-30 12:44:00,076][678703] Conv encoder output size: 512
[2023-04-30 12:44:00,077][678703] Policy head output size: 512
[2023-04-30 12:44:00,093][678550] Inference worker 0-0 is ready!
[2023-04-30 12:44:00,093][678550] All inference workers are ready! Signal rollout workers to start!
[2023-04-30 12:44:00,109][678704] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:44:00,111][678707] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:44:00,112][678705] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:44:00,113][678710] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:44:00,113][678706] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:44:00,113][678711] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:44:00,113][678708] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:44:00,121][678709] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:44:00,516][678704] Decorrelating experience for 0 frames...
[2023-04-30 12:44:00,516][678707] Decorrelating experience for 0 frames...
[2023-04-30 12:44:00,516][678706] Decorrelating experience for 0 frames...
[2023-04-30 12:44:00,516][678708] Decorrelating experience for 0 frames...
[2023-04-30 12:44:00,516][678710] Decorrelating experience for 0 frames...
[2023-04-30 12:44:00,516][678705] Decorrelating experience for 0 frames...
[2023-04-30 12:44:00,701][678707] Decorrelating experience for 32 frames...
[2023-04-30 12:44:00,702][678704] Decorrelating experience for 32 frames...
[2023-04-30 12:44:00,702][678705] Decorrelating experience for 32 frames...
[2023-04-30 12:44:00,703][678710] Decorrelating experience for 32 frames...
[2023-04-30 12:44:00,709][678711] Decorrelating experience for 0 frames...
[2023-04-30 12:44:00,711][678706] Decorrelating experience for 32 frames...
[2023-04-30 12:44:00,740][678709] Decorrelating experience for 0 frames...
[2023-04-30 12:44:00,891][678708] Decorrelating experience for 32 frames...
[2023-04-30 12:44:00,892][678707] Decorrelating experience for 64 frames...
[2023-04-30 12:44:00,918][678704] Decorrelating experience for 64 frames...
[2023-04-30 12:44:00,936][678709] Decorrelating experience for 32 frames...
[2023-04-30 12:44:01,119][678711] Decorrelating experience for 32 frames...
[2023-04-30 12:44:01,129][678705] Decorrelating experience for 64 frames...
[2023-04-30 12:44:01,133][678706] Decorrelating experience for 64 frames...
[2023-04-30 12:44:01,173][678708] Decorrelating experience for 64 frames...
[2023-04-30 12:44:01,319][678710] Decorrelating experience for 64 frames...
[2023-04-30 12:44:01,335][678711] Decorrelating experience for 64 frames...
[2023-04-30 12:44:01,349][678704] Decorrelating experience for 96 frames...
[2023-04-30 12:44:01,368][678706] Decorrelating experience for 96 frames...
[2023-04-30 12:44:01,538][678710] Decorrelating experience for 96 frames...
[2023-04-30 12:44:01,538][678709] Decorrelating experience for 64 frames...
[2023-04-30 12:44:01,565][678708] Decorrelating experience for 96 frames...
[2023-04-30 12:44:01,590][678711] Decorrelating experience for 96 frames...
[2023-04-30 12:44:01,635][678704] Decorrelating experience for 128 frames...
[2023-04-30 12:44:01,655][678706] Decorrelating experience for 128 frames...
[2023-04-30 12:44:01,771][678705] Decorrelating experience for 96 frames...
[2023-04-30 12:44:01,840][678550] 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)
[2023-04-30 12:44:01,857][678708] Decorrelating experience for 128 frames...
[2023-04-30 12:44:01,882][678711] Decorrelating experience for 128 frames...
[2023-04-30 12:44:01,931][678709] Decorrelating experience for 96 frames...
[2023-04-30 12:44:01,939][678706] Decorrelating experience for 160 frames...
[2023-04-30 12:44:02,000][678707] Decorrelating experience for 96 frames...
[2023-04-30 12:44:02,043][678705] Decorrelating experience for 128 frames...
[2023-04-30 12:44:02,044][678704] Decorrelating experience for 160 frames...
[2023-04-30 12:44:02,142][678708] Decorrelating experience for 160 frames...
[2023-04-30 12:44:02,239][678709] Decorrelating experience for 128 frames...
[2023-04-30 12:44:02,244][678710] Decorrelating experience for 128 frames...
[2023-04-30 12:44:02,265][678706] Decorrelating experience for 192 frames...
[2023-04-30 12:44:02,275][678711] Decorrelating experience for 160 frames...
[2023-04-30 12:44:02,335][678705] Decorrelating experience for 160 frames...
[2023-04-30 12:44:02,454][678708] Decorrelating experience for 192 frames...
[2023-04-30 12:44:02,491][678707] Decorrelating experience for 128 frames...
[2023-04-30 12:44:02,502][678704] Decorrelating experience for 192 frames...
[2023-04-30 12:44:02,528][678709] Decorrelating experience for 160 frames...
[2023-04-30 12:44:02,675][678710] Decorrelating experience for 160 frames...
[2023-04-30 12:44:02,721][678711] Decorrelating experience for 192 frames...
[2023-04-30 12:44:02,749][678708] Decorrelating experience for 224 frames...
[2023-04-30 12:44:02,749][678707] Decorrelating experience for 160 frames...
[2023-04-30 12:44:02,777][678706] Decorrelating experience for 224 frames...
[2023-04-30 12:44:02,865][678709] Decorrelating experience for 192 frames...
[2023-04-30 12:44:02,917][678704] Decorrelating experience for 224 frames...
[2023-04-30 12:44:02,984][678710] Decorrelating experience for 192 frames...
[2023-04-30 12:44:03,052][678705] Decorrelating experience for 192 frames...
[2023-04-30 12:44:03,056][678711] Decorrelating experience for 224 frames...
[2023-04-30 12:44:03,067][678707] Decorrelating experience for 192 frames...
[2023-04-30 12:44:03,308][678710] Decorrelating experience for 224 frames...
[2023-04-30 12:44:03,319][678709] Decorrelating experience for 224 frames...
[2023-04-30 12:44:03,354][678707] Decorrelating experience for 224 frames...
[2023-04-30 12:44:03,354][678705] Decorrelating experience for 224 frames...
[2023-04-30 12:44:04,423][678641] Signal inference workers to stop experience collection...
[2023-04-30 12:44:04,443][678703] InferenceWorker_p0-w0: stopping experience collection
[2023-04-30 12:44:05,428][678641] Signal inference workers to resume experience collection...
[2023-04-30 12:44:05,429][678703] InferenceWorker_p0-w0: resuming experience collection
[2023-04-30 12:44:06,840][678550] Fps is (10 sec: 819.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 4096. Throughput: 0: 772.0. Samples: 3860. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-04-30 12:44:06,840][678550] Avg episode reward: [(0, '1.905')]
[2023-04-30 12:44:09,728][678641] Stopping Batcher_0...
[2023-04-30 12:44:09,728][678641] Loop batcher_evt_loop terminating...
[2023-04-30 12:44:09,734][678550] Component Batcher_0 stopped!
[2023-04-30 12:44:09,741][678708] Stopping RolloutWorker_w4...
[2023-04-30 12:44:09,741][678708] Loop rollout_proc4_evt_loop terminating...
[2023-04-30 12:44:09,741][678550] Component RolloutWorker_w4 stopped!
[2023-04-30 12:44:09,741][678706] Stopping RolloutWorker_w2...
[2023-04-30 12:44:09,741][678705] Stopping RolloutWorker_w1...
[2023-04-30 12:44:09,741][678550] Component RolloutWorker_w2 stopped!
[2023-04-30 12:44:09,741][678550] Component RolloutWorker_w1 stopped!
[2023-04-30 12:44:09,741][678706] Loop rollout_proc2_evt_loop terminating...
[2023-04-30 12:44:09,742][678550] Component RolloutWorker_w3 stopped!
[2023-04-30 12:44:09,742][678705] Loop rollout_proc1_evt_loop terminating...
[2023-04-30 12:44:09,742][678707] Stopping RolloutWorker_w3...
[2023-04-30 12:44:09,742][678550] Component RolloutWorker_w5 stopped!
[2023-04-30 12:44:09,742][678709] Stopping RolloutWorker_w5...
[2023-04-30 12:44:09,742][678704] Stopping RolloutWorker_w0...
[2023-04-30 12:44:09,742][678550] Component RolloutWorker_w0 stopped!
[2023-04-30 12:44:09,742][678711] Stopping RolloutWorker_w7...
[2023-04-30 12:44:09,742][678709] Loop rollout_proc5_evt_loop terminating...
[2023-04-30 12:44:09,742][678707] Loop rollout_proc3_evt_loop terminating...
[2023-04-30 12:44:09,743][678704] Loop rollout_proc0_evt_loop terminating...
[2023-04-30 12:44:09,743][678550] Component RolloutWorker_w7 stopped!
[2023-04-30 12:44:09,743][678711] Loop rollout_proc7_evt_loop terminating...
[2023-04-30 12:44:09,743][678550] Component RolloutWorker_w6 stopped!
[2023-04-30 12:44:09,743][678710] Stopping RolloutWorker_w6...
[2023-04-30 12:44:09,744][678710] Loop rollout_proc6_evt_loop terminating...
[2023-04-30 12:44:10,050][678703] Weights refcount: 2 0
[2023-04-30 12:44:10,050][678703] Stopping InferenceWorker_p0-w0...
[2023-04-30 12:44:10,051][678703] Loop inference_proc0-0_evt_loop terminating...
[2023-04-30 12:44:10,051][678550] Component InferenceWorker_p0-w0 stopped!
[2023-04-30 12:44:11,141][678641] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000005_20480.pth...
[2023-04-30 12:44:11,164][678641] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000005_20480.pth...
[2023-04-30 12:44:11,190][678641] Stopping LearnerWorker_p0...
[2023-04-30 12:44:11,190][678550] Component LearnerWorker_p0 stopped!
[2023-04-30 12:44:11,190][678641] Loop learner_proc0_evt_loop terminating...
[2023-04-30 12:44:11,191][678550] Waiting for process learner_proc0 to stop...
[2023-04-30 12:44:11,368][678550] Waiting for process inference_proc0-0 to join...
[2023-04-30 12:44:11,369][678550] Waiting for process rollout_proc0 to join...
[2023-04-30 12:44:11,369][678550] Waiting for process rollout_proc1 to join...
[2023-04-30 12:44:11,369][678550] Waiting for process rollout_proc2 to join...
[2023-04-30 12:44:11,369][678550] Waiting for process rollout_proc3 to join...
[2023-04-30 12:44:11,369][678550] Waiting for process rollout_proc4 to join...
[2023-04-30 12:44:11,369][678550] Waiting for process rollout_proc5 to join...
[2023-04-30 12:44:11,370][678550] Waiting for process rollout_proc6 to join...
[2023-04-30 12:44:11,370][678550] Waiting for process rollout_proc7 to join...
[2023-04-30 12:44:11,370][678550] Batcher 0 profile tree view:
batching: 0.0243, releasing_batches: 0.0008
[2023-04-30 12:44:11,370][678550] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0051
  wait_policy_total: 2.8056
update_model: 0.7312
  weight_update: 0.1811
one_step: 0.0370
  handle_policy_step: 3.0217
    deserialize: 0.0424, stack: 0.0035, obs_to_device_normalize: 0.2143, forward: 2.6394, send_messages: 0.0531
    prepare_outputs: 0.0322
      to_cpu: 0.0028
[2023-04-30 12:44:11,370][678550] Learner 0 profile tree view:
misc: 0.0000, prepare_batch: 1.5143
train: 5.6552
  epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0002, kl_divergence: 0.0007, after_optimizer: 0.0041
  calculate_losses: 1.9942
    losses_init: 0.0000, forward_head: 1.4543, bptt_initial: 0.0072, tail: 0.0036, advantages_returns: 0.0006, losses: 0.0035
    bptt: 0.5243
      bptt_forward_core: 0.5233
  update: 3.6540
    clip: 0.0070
[2023-04-30 12:44:11,370][678550] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.0006, enqueue_policy_requests: 0.0288, env_step: 0.6001, overhead: 0.0480, complete_rollouts: 0.0007
save_policy_outputs: 0.0333
  split_output_tensors: 0.0154
[2023-04-30 12:44:11,371][678550] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.0006, enqueue_policy_requests: 0.0265, env_step: 0.5396, overhead: 0.0422, complete_rollouts: 0.0007
save_policy_outputs: 0.0293
  split_output_tensors: 0.0137
[2023-04-30 12:44:11,371][678550] Loop Runner_EvtLoop terminating...
[2023-04-30 12:44:11,371][678550] Runner profile tree view:
main_loop: 13.3725
[2023-04-30 12:44:11,371][678550] Collected {0: 20480}, FPS: 1531.5
[2023-04-30 12:45:34,038][682983] Saving configuration to ./train_dir/doom_health_gathering_supreme/config.json...
[2023-04-30 12:45:34,039][682983] Rollout worker 0 uses device cpu
[2023-04-30 12:45:34,039][682983] Rollout worker 1 uses device cpu
[2023-04-30 12:45:34,039][682983] Rollout worker 2 uses device cpu
[2023-04-30 12:45:34,039][682983] Rollout worker 3 uses device cpu
[2023-04-30 12:45:34,039][682983] Rollout worker 4 uses device cpu
[2023-04-30 12:45:34,039][682983] Rollout worker 5 uses device cpu
[2023-04-30 12:45:34,039][682983] Rollout worker 6 uses device cpu
[2023-04-30 12:45:34,040][682983] Rollout worker 7 uses device cpu
[2023-04-30 12:45:34,080][682983] InferenceWorker_p0-w0: min num requests: 2
[2023-04-30 12:45:34,139][682983] Starting all processes...
[2023-04-30 12:45:34,139][682983] Starting process learner_proc0
[2023-04-30 12:45:34,957][682983] Starting all processes...
[2023-04-30 12:45:34,961][683074] Starting seed is not provided
[2023-04-30 12:45:34,961][683074] Initializing actor-critic model on device cpu
[2023-04-30 12:45:34,961][682983] Starting process inference_proc0-0
[2023-04-30 12:45:34,961][683074] RunningMeanStd input shape: (3, 72, 128)
[2023-04-30 12:45:34,961][682983] Starting process rollout_proc0
[2023-04-30 12:45:34,962][683074] RunningMeanStd input shape: (1,)
[2023-04-30 12:45:34,962][682983] Starting process rollout_proc1
[2023-04-30 12:45:34,962][682983] Starting process rollout_proc2
[2023-04-30 12:45:34,969][683074] ConvEncoder: input_channels=3
[2023-04-30 12:45:34,963][682983] Starting process rollout_proc3
[2023-04-30 12:45:34,967][682983] Starting process rollout_proc4
[2023-04-30 12:45:34,967][682983] Starting process rollout_proc5
[2023-04-30 12:45:34,967][682983] Starting process rollout_proc6
[2023-04-30 12:45:34,968][682983] Starting process rollout_proc7
[2023-04-30 12:45:35,069][683074] Conv encoder output size: 512
[2023-04-30 12:45:35,070][683074] Policy head output size: 512
[2023-04-30 12:45:35,079][683074] Created Actor Critic model with architecture:
[2023-04-30 12:45:35,079][683074] 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)
  )
)
[2023-04-30 12:45:35,350][683074] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-04-30 12:45:35,351][683074] Loading state from checkpoint ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000005_20480.pth...
[2023-04-30 12:45:35,371][683074] Loading model from checkpoint
[2023-04-30 12:45:35,395][683074] Loaded experiment state at self.train_step=5, self.env_steps=20480
[2023-04-30 12:45:35,426][683074] Initialized policy 0 weights for model version 5
[2023-04-30 12:45:35,442][683074] LearnerWorker_p0 finished initialization!
[2023-04-30 12:45:36,076][683138] Worker 0 uses CPU cores [0, 1, 2]
[2023-04-30 12:45:36,081][683137] RunningMeanStd input shape: (3, 72, 128)
[2023-04-30 12:45:36,081][683137] RunningMeanStd input shape: (1,)
[2023-04-30 12:45:36,084][683139] Worker 1 uses CPU cores [3, 4, 5]
[2023-04-30 12:45:36,088][683141] Worker 3 uses CPU cores [9, 10, 11]
[2023-04-30 12:45:36,089][683137] ConvEncoder: input_channels=3
[2023-04-30 12:45:36,103][683149] Worker 7 uses CPU cores [21, 22, 23]
[2023-04-30 12:45:36,109][683144] Worker 5 uses CPU cores [15, 16, 17]
[2023-04-30 12:45:36,115][683145] Worker 6 uses CPU cores [18, 19, 20]
[2023-04-30 12:45:36,118][683142] Worker 4 uses CPU cores [12, 13, 14]
[2023-04-30 12:45:36,119][683140] Worker 2 uses CPU cores [6, 7, 8]
[2023-04-30 12:45:36,217][683137] Conv encoder output size: 512
[2023-04-30 12:45:36,218][683137] Policy head output size: 512
[2023-04-30 12:45:36,229][682983] Inference worker 0-0 is ready!
[2023-04-30 12:45:36,229][682983] All inference workers are ready! Signal rollout workers to start!
[2023-04-30 12:45:36,241][683138] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:45:36,242][683145] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:45:36,242][683149] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:45:36,243][683144] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:45:36,243][683141] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:45:36,260][683142] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:45:36,270][683140] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:45:36,276][683139] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-04-30 12:45:36,481][683149] Decorrelating experience for 0 frames...
[2023-04-30 12:45:36,487][683138] Decorrelating experience for 0 frames...
[2023-04-30 12:45:36,497][683144] Decorrelating experience for 0 frames...
[2023-04-30 12:45:36,501][683145] Decorrelating experience for 0 frames...
[2023-04-30 12:45:36,698][683149] Decorrelating experience for 32 frames...
[2023-04-30 12:45:36,704][683139] Decorrelating experience for 0 frames...
[2023-04-30 12:45:36,745][683144] Decorrelating experience for 32 frames...
[2023-04-30 12:45:36,755][683141] Decorrelating experience for 0 frames...
[2023-04-30 12:45:36,758][683140] Decorrelating experience for 0 frames...
[2023-04-30 12:45:36,907][683139] Decorrelating experience for 32 frames...
[2023-04-30 12:45:36,940][683144] Decorrelating experience for 64 frames...
[2023-04-30 12:45:36,940][683141] Decorrelating experience for 32 frames...
[2023-04-30 12:45:36,940][683145] Decorrelating experience for 32 frames...
[2023-04-30 12:45:36,973][683149] Decorrelating experience for 64 frames...
[2023-04-30 12:45:37,117][683140] Decorrelating experience for 32 frames...
[2023-04-30 12:45:37,142][683139] Decorrelating experience for 64 frames...
[2023-04-30 12:45:37,185][683145] Decorrelating experience for 64 frames...
[2023-04-30 12:45:37,195][683144] Decorrelating experience for 96 frames...
[2023-04-30 12:45:37,197][683149] Decorrelating experience for 96 frames...
[2023-04-30 12:45:37,198][683138] Decorrelating experience for 32 frames...
[2023-04-30 12:45:37,335][683140] Decorrelating experience for 64 frames...
[2023-04-30 12:45:37,379][683139] Decorrelating experience for 96 frames...
[2023-04-30 12:45:37,404][683142] Decorrelating experience for 0 frames...
[2023-04-30 12:45:37,431][683145] Decorrelating experience for 96 frames...
[2023-04-30 12:45:37,469][683149] Decorrelating experience for 128 frames...
[2023-04-30 12:45:37,555][683140] Decorrelating experience for 96 frames...
[2023-04-30 12:45:37,555][683138] Decorrelating experience for 64 frames...
[2023-04-30 12:45:37,592][683144] Decorrelating experience for 128 frames...
[2023-04-30 12:45:37,592][683142] Decorrelating experience for 32 frames...
[2023-04-30 12:45:37,781][683149] Decorrelating experience for 160 frames...
[2023-04-30 12:45:37,781][683138] Decorrelating experience for 96 frames...
[2023-04-30 12:45:37,785][683139] Decorrelating experience for 128 frames...
[2023-04-30 12:45:37,786][683145] Decorrelating experience for 128 frames...
[2023-04-30 12:45:37,831][683141] Decorrelating experience for 64 frames...
[2023-04-30 12:45:38,044][682983] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 20480. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-04-30 12:45:38,049][683144] Decorrelating experience for 160 frames...
[2023-04-30 12:45:38,061][683140] Decorrelating experience for 128 frames...
[2023-04-30 12:45:38,067][683138] Decorrelating experience for 128 frames...
[2023-04-30 12:45:38,088][683145] Decorrelating experience for 160 frames...
[2023-04-30 12:45:38,101][683139] Decorrelating experience for 160 frames...
[2023-04-30 12:45:38,110][683141] Decorrelating experience for 96 frames...
[2023-04-30 12:45:38,271][683142] Decorrelating experience for 64 frames...
[2023-04-30 12:45:38,324][683140] Decorrelating experience for 160 frames...
[2023-04-30 12:45:38,325][683138] Decorrelating experience for 160 frames...
[2023-04-30 12:45:38,371][683144] Decorrelating experience for 192 frames...
[2023-04-30 12:45:38,385][683145] Decorrelating experience for 192 frames...
[2023-04-30 12:45:38,403][683141] Decorrelating experience for 128 frames...
[2023-04-30 12:45:38,504][683142] Decorrelating experience for 96 frames...
[2023-04-30 12:45:38,522][683149] Decorrelating experience for 192 frames...
[2023-04-30 12:45:38,596][683139] Decorrelating experience for 192 frames...
[2023-04-30 12:45:38,615][683138] Decorrelating experience for 192 frames...
[2023-04-30 12:45:38,674][683141] Decorrelating experience for 160 frames...
[2023-04-30 12:45:38,796][683142] Decorrelating experience for 128 frames...
[2023-04-30 12:45:38,815][683149] Decorrelating experience for 224 frames...
[2023-04-30 12:45:38,815][683140] Decorrelating experience for 192 frames...
[2023-04-30 12:45:38,905][683139] Decorrelating experience for 224 frames...
[2023-04-30 12:45:38,979][683141] Decorrelating experience for 192 frames...
[2023-04-30 12:45:39,050][683138] Decorrelating experience for 224 frames...
[2023-04-30 12:45:39,067][683145] Decorrelating experience for 224 frames...
[2023-04-30 12:45:39,095][683144] Decorrelating experience for 224 frames...
[2023-04-30 12:45:39,137][683142] Decorrelating experience for 160 frames...
[2023-04-30 12:45:39,138][683140] Decorrelating experience for 224 frames...
[2023-04-30 12:45:39,308][683141] Decorrelating experience for 224 frames...
[2023-04-30 12:45:39,424][683142] Decorrelating experience for 192 frames...
[2023-04-30 12:45:39,711][683142] Decorrelating experience for 224 frames...
[2023-04-30 12:45:40,485][683074] Signal inference workers to stop experience collection...
[2023-04-30 12:45:40,505][683137] InferenceWorker_p0-w0: stopping experience collection
[2023-04-30 12:45:41,493][683074] Signal inference workers to resume experience collection...
[2023-04-30 12:45:41,494][683137] InferenceWorker_p0-w0: resuming experience collection
[2023-04-30 12:45:43,044][682983] Fps is (10 sec: 819.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 24576. Throughput: 0: 784.0. Samples: 3920. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-04-30 12:45:43,045][682983] Avg episode reward: [(0, '1.796')]
[2023-04-30 12:45:48,044][682983] Fps is (10 sec: 2048.0, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 40960. Throughput: 0: 616.0. Samples: 6160. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:45:48,044][682983] Avg episode reward: [(0, '3.036')]
[2023-04-30 12:45:53,044][682983] Fps is (10 sec: 3276.8, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 57344. Throughput: 0: 685.9. Samples: 10288. Policy #0 lag: (min: 1.0, avg: 1.8, max: 3.0)
[2023-04-30 12:45:53,044][682983] Avg episode reward: [(0, '3.679')]
[2023-04-30 12:45:54,030][683137] Updated weights for policy 0, policy_version 15 (0.1495)
[2023-04-30 12:45:54,076][682983] Heartbeat connected on Batcher_0
[2023-04-30 12:45:54,082][682983] Heartbeat connected on RolloutWorker_w0
[2023-04-30 12:45:54,084][682983] Heartbeat connected on RolloutWorker_w1
[2023-04-30 12:45:54,086][682983] Heartbeat connected on RolloutWorker_w2
[2023-04-30 12:45:54,087][682983] Heartbeat connected on RolloutWorker_w3
[2023-04-30 12:45:54,089][682983] Heartbeat connected on RolloutWorker_w4
[2023-04-30 12:45:54,091][682983] Heartbeat connected on RolloutWorker_w5
[2023-04-30 12:45:54,092][682983] Heartbeat connected on RolloutWorker_w6
[2023-04-30 12:45:54,101][682983] Heartbeat connected on InferenceWorker_p0-w0
[2023-04-30 12:45:54,138][682983] Heartbeat connected on RolloutWorker_w7
[2023-04-30 12:45:56,743][682983] Heartbeat connected on LearnerWorker_p0
[2023-04-30 12:45:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 69632. Throughput: 0: 759.4. Samples: 15188. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:45:58,044][682983] Avg episode reward: [(0, '4.419')]
[2023-04-30 12:46:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 86016. Throughput: 0: 689.9. Samples: 17248. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:46:03,045][682983] Avg episode reward: [(0, '4.396')]
[2023-04-30 12:46:08,044][682983] Fps is (10 sec: 3276.8, 60 sec: 2730.7, 300 sec: 2730.7). Total num frames: 102400. Throughput: 0: 710.4. Samples: 21312. Policy #0 lag: (min: 1.0, avg: 1.8, max: 3.0)
[2023-04-30 12:46:08,044][682983] Avg episode reward: [(0, '4.337')]
[2023-04-30 12:46:08,115][683137] Updated weights for policy 0, policy_version 25 (0.0839)
[2023-04-30 12:46:09,338][683074] Saving new best policy, reward=4.337!
[2023-04-30 12:46:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2691.7, 300 sec: 2691.7). Total num frames: 114688. Throughput: 0: 737.0. Samples: 25796. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:46:13,044][682983] Avg episode reward: [(0, '4.517')]
[2023-04-30 12:46:14,840][683074] Saving new best policy, reward=4.517!
[2023-04-30 12:46:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2764.8, 300 sec: 2764.8). Total num frames: 131072. Throughput: 0: 707.9. Samples: 28316. Policy #0 lag: (min: 1.0, avg: 1.8, max: 3.0)
[2023-04-30 12:46:18,044][682983] Avg episode reward: [(0, '4.532')]
[2023-04-30 12:46:18,990][683074] Saving new best policy, reward=4.532!
[2023-04-30 12:46:21,984][683137] Updated weights for policy 0, policy_version 35 (0.0410)
[2023-04-30 12:46:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2730.7, 300 sec: 2730.7). Total num frames: 143360. Throughput: 0: 729.9. Samples: 32844. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:46:23,045][682983] Avg episode reward: [(0, '4.647')]
[2023-04-30 12:46:24,537][683074] Saving new best policy, reward=4.647!
[2023-04-30 12:46:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2785.3, 300 sec: 2785.3). Total num frames: 159744. Throughput: 0: 734.3. Samples: 36964. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 12:46:28,044][682983] Avg episode reward: [(0, '4.552')]
[2023-04-30 12:46:33,044][682983] Fps is (10 sec: 3276.8, 60 sec: 2830.0, 300 sec: 2830.0). Total num frames: 176128. Throughput: 0: 731.1. Samples: 39060. Policy #0 lag: (min: 1.0, avg: 1.8, max: 3.0)
[2023-04-30 12:46:33,044][682983] Avg episode reward: [(0, '4.594')]
[2023-04-30 12:46:35,701][683137] Updated weights for policy 0, policy_version 45 (0.1014)
[2023-04-30 12:46:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 188416. Throughput: 0: 746.7. Samples: 43888. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 12:46:38,044][682983] Avg episode reward: [(0, '4.432')]
[2023-04-30 12:46:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2835.7). Total num frames: 204800. Throughput: 0: 729.8. Samples: 48028. Policy #0 lag: (min: 1.0, avg: 1.8, max: 3.0)
[2023-04-30 12:46:43,044][682983] Avg episode reward: [(0, '4.388')]
[2023-04-30 12:46:48,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2867.2). Total num frames: 221184. Throughput: 0: 737.7. Samples: 50444. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:46:48,045][682983] Avg episode reward: [(0, '4.381')]
[2023-04-30 12:46:49,451][683137] Updated weights for policy 0, policy_version 55 (0.0613)
[2023-04-30 12:46:49,856][683074] Signal inference workers to stop experience collection... (50 times)
[2023-04-30 12:46:49,880][683137] InferenceWorker_p0-w0: stopping experience collection (50 times)
[2023-04-30 12:46:50,622][683074] Signal inference workers to resume experience collection... (50 times)
[2023-04-30 12:46:50,622][683137] InferenceWorker_p0-w0: resuming experience collection (50 times)
[2023-04-30 12:46:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2839.9). Total num frames: 233472. Throughput: 0: 752.2. Samples: 55160. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 12:46:53,044][682983] Avg episode reward: [(0, '4.521')]
[2023-04-30 12:46:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2867.2). Total num frames: 249856. Throughput: 0: 748.9. Samples: 59496. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:46:58,044][682983] Avg episode reward: [(0, '4.531')]
[2023-04-30 12:47:03,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2891.3). Total num frames: 266240. Throughput: 0: 739.8. Samples: 61608. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 12:47:03,044][682983] Avg episode reward: [(0, '4.595')]
[2023-04-30 12:47:03,122][683137] Updated weights for policy 0, policy_version 65 (0.1207)
[2023-04-30 12:47:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2867.2). Total num frames: 278528. Throughput: 0: 748.1. Samples: 66508. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:47:08,044][682983] Avg episode reward: [(0, '4.550')]
[2023-04-30 12:47:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2888.8). Total num frames: 294912. Throughput: 0: 748.4. Samples: 70644. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:47:13,044][682983] Avg episode reward: [(0, '4.613')]
[2023-04-30 12:47:16,479][683137] Updated weights for policy 0, policy_version 75 (0.0409)
[2023-04-30 12:47:18,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2908.2). Total num frames: 311296. Throughput: 0: 753.7. Samples: 72976. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:47:18,044][682983] Avg episode reward: [(0, '4.541')]
[2023-04-30 12:47:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2886.7). Total num frames: 323584. Throughput: 0: 757.2. Samples: 77960. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:47:23,044][682983] Avg episode reward: [(0, '4.580')]
[2023-04-30 12:47:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2904.4). Total num frames: 339968. Throughput: 0: 756.4. Samples: 82068. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:47:28,044][682983] Avg episode reward: [(0, '4.510')]
[2023-04-30 12:47:30,039][683137] Updated weights for policy 0, policy_version 85 (0.0411)
[2023-04-30 12:47:33,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2920.6). Total num frames: 356352. Throughput: 0: 758.0. Samples: 84552. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:47:33,044][682983] Avg episode reward: [(0, '4.608')]
[2023-04-30 12:47:34,084][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000088_360448.pth...
[2023-04-30 12:47:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2901.3). Total num frames: 368640. Throughput: 0: 751.5. Samples: 88976. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:47:38,045][682983] Avg episode reward: [(0, '4.517')]
[2023-04-30 12:47:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2916.4). Total num frames: 385024. Throughput: 0: 745.7. Samples: 93052. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 12:47:43,044][682983] Avg episode reward: [(0, '4.462')]
[2023-04-30 12:47:43,749][683137] Updated weights for policy 0, policy_version 95 (0.0606)
[2023-04-30 12:47:48,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2930.2). Total num frames: 401408. Throughput: 0: 751.3. Samples: 95416. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:47:48,044][682983] Avg episode reward: [(0, '4.606')]
[2023-04-30 12:47:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2912.7). Total num frames: 413696. Throughput: 0: 754.9. Samples: 100480. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 12:47:53,044][682983] Avg episode reward: [(0, '4.601')]
[2023-04-30 12:47:57,422][683137] Updated weights for policy 0, policy_version 105 (0.0408)
[2023-04-30 12:47:57,749][683074] Signal inference workers to stop experience collection... (100 times)
[2023-04-30 12:47:57,772][683137] InferenceWorker_p0-w0: stopping experience collection (100 times)
[2023-04-30 12:47:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2925.7). Total num frames: 430080. Throughput: 0: 754.7. Samples: 104604. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 12:47:58,044][682983] Avg episode reward: [(0, '4.597')]
[2023-04-30 12:47:58,760][683074] Signal inference workers to resume experience collection... (100 times)
[2023-04-30 12:47:58,761][683137] InferenceWorker_p0-w0: resuming experience collection (100 times)
[2023-04-30 12:48:03,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2937.8). Total num frames: 446464. Throughput: 0: 750.0. Samples: 106724. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:48:03,044][682983] Avg episode reward: [(0, '4.543')]
[2023-04-30 12:48:08,044][682983] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 2921.8). Total num frames: 458752. Throughput: 0: 747.2. Samples: 111584. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:48:08,045][682983] Avg episode reward: [(0, '4.516')]
[2023-04-30 12:48:11,302][683137] Updated weights for policy 0, policy_version 115 (0.0814)
[2023-04-30 12:48:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2933.3). Total num frames: 475136. Throughput: 0: 746.0. Samples: 115636. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:48:13,044][682983] Avg episode reward: [(0, '4.398')]
[2023-04-30 12:48:18,044][682983] Fps is (10 sec: 3276.9, 60 sec: 3003.7, 300 sec: 2944.0). Total num frames: 491520. Throughput: 0: 736.6. Samples: 117700. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:48:18,044][682983] Avg episode reward: [(0, '4.413')]
[2023-04-30 12:48:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2929.3). Total num frames: 503808. Throughput: 0: 754.4. Samples: 122924. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:48:23,044][682983] Avg episode reward: [(0, '4.453')]
[2023-04-30 12:48:24,751][683137] Updated weights for policy 0, policy_version 125 (0.0214)
[2023-04-30 12:48:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2939.5). Total num frames: 520192. Throughput: 0: 755.1. Samples: 127032. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:48:28,044][682983] Avg episode reward: [(0, '4.499')]
[2023-04-30 12:48:33,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2949.1). Total num frames: 536576. Throughput: 0: 752.6. Samples: 129284. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:48:33,044][682983] Avg episode reward: [(0, '4.464')]
[2023-04-30 12:48:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2935.5). Total num frames: 548864. Throughput: 0: 744.0. Samples: 133960. Policy #0 lag: (min: 1.0, avg: 1.8, max: 3.0)
[2023-04-30 12:48:38,044][682983] Avg episode reward: [(0, '4.435')]
[2023-04-30 12:48:38,317][683137] Updated weights for policy 0, policy_version 135 (0.1005)
[2023-04-30 12:48:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2944.7). Total num frames: 565248. Throughput: 0: 744.3. Samples: 138096. Policy #0 lag: (min: 1.0, avg: 1.8, max: 3.0)
[2023-04-30 12:48:43,044][682983] Avg episode reward: [(0, '4.505')]
[2023-04-30 12:48:48,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2953.4). Total num frames: 581632. Throughput: 0: 748.4. Samples: 140404. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:48:48,044][682983] Avg episode reward: [(0, '4.554')]
[2023-04-30 12:48:52,091][683137] Updated weights for policy 0, policy_version 145 (0.0613)
[2023-04-30 12:48:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2940.7). Total num frames: 593920. Throughput: 0: 753.0. Samples: 145468. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:48:53,044][682983] Avg episode reward: [(0, '4.515')]
[2023-04-30 12:48:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2949.1). Total num frames: 610304. Throughput: 0: 754.0. Samples: 149564. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:48:58,045][682983] Avg episode reward: [(0, '4.678')]
[2023-04-30 12:49:00,070][683074] Saving new best policy, reward=4.678!
[2023-04-30 12:49:03,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2957.1). Total num frames: 626688. Throughput: 0: 763.2. Samples: 152044. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:49:03,045][682983] Avg episode reward: [(0, '4.617')]
[2023-04-30 12:49:05,532][683137] Updated weights for policy 0, policy_version 155 (0.0806)
[2023-04-30 12:49:05,871][683074] Signal inference workers to stop experience collection... (150 times)
[2023-04-30 12:49:05,892][683137] InferenceWorker_p0-w0: stopping experience collection (150 times)
[2023-04-30 12:49:06,865][683074] Signal inference workers to resume experience collection... (150 times)
[2023-04-30 12:49:06,865][683137] InferenceWorker_p0-w0: resuming experience collection (150 times)
[2023-04-30 12:49:08,044][682983] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 2945.2). Total num frames: 638976. Throughput: 0: 747.5. Samples: 156560. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:49:08,044][682983] Avg episode reward: [(0, '4.339')]
[2023-04-30 12:49:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2952.9). Total num frames: 655360. Throughput: 0: 747.6. Samples: 160676. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:49:13,044][682983] Avg episode reward: [(0, '4.342')]
[2023-04-30 12:49:18,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2960.3). Total num frames: 671744. Throughput: 0: 748.9. Samples: 162984. Policy #0 lag: (min: 1.0, avg: 1.9, max: 3.0)
[2023-04-30 12:49:18,045][682983] Avg episode reward: [(0, '4.469')]
[2023-04-30 12:49:19,236][683137] Updated weights for policy 0, policy_version 165 (0.0610)
[2023-04-30 12:49:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2949.1). Total num frames: 684032. Throughput: 0: 754.4. Samples: 167908. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:49:23,044][682983] Avg episode reward: [(0, '4.478')]
[2023-04-30 12:49:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2956.2). Total num frames: 700416. Throughput: 0: 754.9. Samples: 172068. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:49:28,044][682983] Avg episode reward: [(0, '4.447')]
[2023-04-30 12:49:33,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2963.1). Total num frames: 716800. Throughput: 0: 755.5. Samples: 174400. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:49:33,045][682983] Avg episode reward: [(0, '4.556')]
[2023-04-30 12:49:33,045][683137] Updated weights for policy 0, policy_version 175 (0.1202)
[2023-04-30 12:49:34,206][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000176_720896.pth...
[2023-04-30 12:49:34,229][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000005_20480.pth
[2023-04-30 12:49:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2952.5). Total num frames: 729088. Throughput: 0: 750.7. Samples: 179248. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:49:38,044][682983] Avg episode reward: [(0, '4.596')]
[2023-04-30 12:49:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2959.2). Total num frames: 745472. Throughput: 0: 751.1. Samples: 183364. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:49:43,044][682983] Avg episode reward: [(0, '4.718')]
[2023-04-30 12:49:45,166][683074] Saving new best policy, reward=4.718!
[2023-04-30 12:49:46,754][683137] Updated weights for policy 0, policy_version 185 (0.0422)
[2023-04-30 12:49:48,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2965.5). Total num frames: 761856. Throughput: 0: 744.6. Samples: 185552. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:49:48,044][682983] Avg episode reward: [(0, '4.742')]
[2023-04-30 12:49:49,242][683074] Saving new best policy, reward=4.742!
[2023-04-30 12:49:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2955.5). Total num frames: 774144. Throughput: 0: 753.5. Samples: 190468. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:49:53,044][682983] Avg episode reward: [(0, '4.708')]
[2023-04-30 12:49:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2961.7). Total num frames: 790528. Throughput: 0: 754.8. Samples: 194640. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:49:58,044][682983] Avg episode reward: [(0, '4.632')]
[2023-04-30 12:50:00,153][683137] Updated weights for policy 0, policy_version 195 (0.0414)
[2023-04-30 12:50:03,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2967.7). Total num frames: 806912. Throughput: 0: 753.2. Samples: 196876. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:50:03,044][682983] Avg episode reward: [(0, '4.682')]
[2023-04-30 12:50:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2958.2). Total num frames: 819200. Throughput: 0: 753.2. Samples: 201800. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:50:08,044][682983] Avg episode reward: [(0, '4.626')]
[2023-04-30 12:50:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2964.0). Total num frames: 835584. Throughput: 0: 751.4. Samples: 205880. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:50:13,044][682983] Avg episode reward: [(0, '4.827')]
[2023-04-30 12:50:13,785][683137] Updated weights for policy 0, policy_version 205 (0.0413)
[2023-04-30 12:50:14,272][683074] Signal inference workers to stop experience collection... (200 times)
[2023-04-30 12:50:14,295][683137] InferenceWorker_p0-w0: stopping experience collection (200 times)
[2023-04-30 12:50:15,184][683074] Signal inference workers to resume experience collection... (200 times)
[2023-04-30 12:50:15,184][683074] Saving new best policy, reward=4.827!
[2023-04-30 12:50:15,185][683137] InferenceWorker_p0-w0: resuming experience collection (200 times)
[2023-04-30 12:50:18,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2969.6). Total num frames: 851968. Throughput: 0: 748.1. Samples: 208064. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:50:18,044][682983] Avg episode reward: [(0, '4.745')]
[2023-04-30 12:50:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2960.6). Total num frames: 864256. Throughput: 0: 744.4. Samples: 212744. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:50:23,044][682983] Avg episode reward: [(0, '4.879')]
[2023-04-30 12:50:24,786][683074] Saving new best policy, reward=4.879!
[2023-04-30 12:50:27,549][683137] Updated weights for policy 0, policy_version 215 (0.0813)
[2023-04-30 12:50:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2966.1). Total num frames: 880640. Throughput: 0: 753.0. Samples: 217248. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:50:28,044][682983] Avg episode reward: [(0, '4.850')]
[2023-04-30 12:50:33,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2971.3). Total num frames: 897024. Throughput: 0: 749.5. Samples: 219280. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:50:33,044][682983] Avg episode reward: [(0, '4.836')]
[2023-04-30 12:50:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 909312. Throughput: 0: 750.9. Samples: 224260. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:50:38,044][682983] Avg episode reward: [(0, '5.016')]
[2023-04-30 12:50:39,740][683074] Saving new best policy, reward=5.016!
[2023-04-30 12:50:41,149][683137] Updated weights for policy 0, policy_version 225 (0.0609)
[2023-04-30 12:50:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 925696. Throughput: 0: 749.5. Samples: 228368. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:50:43,044][682983] Avg episode reward: [(0, '4.806')]
[2023-04-30 12:50:48,044][682983] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 942080. Throughput: 0: 745.7. Samples: 230432. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:50:48,045][682983] Avg episode reward: [(0, '4.703')]
[2023-04-30 12:50:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 954368. Throughput: 0: 741.8. Samples: 235180. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:50:53,044][682983] Avg episode reward: [(0, '4.671')]
[2023-04-30 12:50:54,910][683137] Updated weights for policy 0, policy_version 235 (0.0817)
[2023-04-30 12:50:58,044][682983] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 970752. Throughput: 0: 751.2. Samples: 239684. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:50:58,044][682983] Avg episode reward: [(0, '4.748')]
[2023-04-30 12:51:03,044][682983] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 987136. Throughput: 0: 747.6. Samples: 241704. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:51:03,045][682983] Avg episode reward: [(0, '4.837')]
[2023-04-30 12:51:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 999424. Throughput: 0: 753.6. Samples: 246656. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:51:08,044][682983] Avg episode reward: [(0, '4.646')]
[2023-04-30 12:51:08,584][683137] Updated weights for policy 0, policy_version 245 (0.1015)
[2023-04-30 12:51:13,044][682983] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1015808. Throughput: 0: 747.6. Samples: 250888. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:51:13,044][682983] Avg episode reward: [(0, '4.586')]
[2023-04-30 12:51:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 1028096. Throughput: 0: 747.6. Samples: 252924. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:51:18,044][682983] Avg episode reward: [(0, '4.674')]
[2023-04-30 12:51:22,505][683137] Updated weights for policy 0, policy_version 255 (0.1620)
[2023-04-30 12:51:22,914][683074] Signal inference workers to stop experience collection... (250 times)
[2023-04-30 12:51:22,934][683137] InferenceWorker_p0-w0: stopping experience collection (250 times)
[2023-04-30 12:51:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1044480. Throughput: 0: 735.7. Samples: 257368. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:51:23,044][682983] Avg episode reward: [(0, '4.714')]
[2023-04-30 12:51:23,675][683074] Signal inference workers to resume experience collection... (250 times)
[2023-04-30 12:51:23,675][683137] InferenceWorker_p0-w0: resuming experience collection (250 times)
[2023-04-30 12:51:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1060864. Throughput: 0: 751.4. Samples: 262180. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:51:28,044][682983] Avg episode reward: [(0, '4.826')]
[2023-04-30 12:51:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 1073152. Throughput: 0: 750.2. Samples: 264192. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:51:33,044][682983] Avg episode reward: [(0, '4.848')]
[2023-04-30 12:51:34,628][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000264_1081344.pth...
[2023-04-30 12:51:34,652][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000088_360448.pth
[2023-04-30 12:51:36,018][683137] Updated weights for policy 0, policy_version 265 (0.1428)
[2023-04-30 12:51:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1089536. Throughput: 0: 748.1. Samples: 268844. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:51:38,044][682983] Avg episode reward: [(0, '4.826')]
[2023-04-30 12:51:43,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1105920. Throughput: 0: 750.0. Samples: 273436. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:51:43,044][682983] Avg episode reward: [(0, '4.918')]
[2023-04-30 12:51:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 1118208. Throughput: 0: 751.0. Samples: 275500. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:51:48,045][682983] Avg episode reward: [(0, '5.068')]
[2023-04-30 12:51:49,648][683074] Saving new best policy, reward=5.068!
[2023-04-30 12:51:49,650][683137] Updated weights for policy 0, policy_version 275 (0.0210)
[2023-04-30 12:51:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1134592. Throughput: 0: 744.5. Samples: 280160. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:51:53,044][682983] Avg episode reward: [(0, '5.125')]
[2023-04-30 12:51:55,065][683074] Saving new best policy, reward=5.125!
[2023-04-30 12:51:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1150976. Throughput: 0: 751.6. Samples: 284712. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:51:58,045][682983] Avg episode reward: [(0, '5.239')]
[2023-04-30 12:51:59,156][683074] Saving new best policy, reward=5.239!
[2023-04-30 12:52:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 1163264. Throughput: 0: 752.4. Samples: 286780. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:52:03,045][682983] Avg episode reward: [(0, '5.155')]
[2023-04-30 12:52:03,447][683137] Updated weights for policy 0, policy_version 285 (0.0602)
[2023-04-30 12:52:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1179648. Throughput: 0: 748.1. Samples: 291032. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:52:08,044][682983] Avg episode reward: [(0, '5.415')]
[2023-04-30 12:52:10,023][683074] Saving new best policy, reward=5.415!
[2023-04-30 12:52:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1196032. Throughput: 0: 751.9. Samples: 296016. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:52:13,044][682983] Avg episode reward: [(0, '5.217')]
[2023-04-30 12:52:16,848][683137] Updated weights for policy 0, policy_version 295 (0.0811)
[2023-04-30 12:52:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1208320. Throughput: 0: 753.1. Samples: 298080. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:52:18,044][682983] Avg episode reward: [(0, '5.206')]
[2023-04-30 12:52:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1224704. Throughput: 0: 746.6. Samples: 302440. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:52:23,044][682983] Avg episode reward: [(0, '5.253')]
[2023-04-30 12:52:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1241088. Throughput: 0: 750.8. Samples: 307224. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:52:28,044][682983] Avg episode reward: [(0, '5.301')]
[2023-04-30 12:52:30,677][683137] Updated weights for policy 0, policy_version 305 (0.0817)
[2023-04-30 12:52:31,162][683074] Signal inference workers to stop experience collection... (300 times)
[2023-04-30 12:52:31,182][683137] InferenceWorker_p0-w0: stopping experience collection (300 times)
[2023-04-30 12:52:31,828][683074] Signal inference workers to resume experience collection... (300 times)
[2023-04-30 12:52:31,828][683137] InferenceWorker_p0-w0: resuming experience collection (300 times)
[2023-04-30 12:52:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1253376. Throughput: 0: 750.2. Samples: 309260. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:52:33,044][682983] Avg episode reward: [(0, '5.249')]
[2023-04-30 12:52:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1269760. Throughput: 0: 754.3. Samples: 314104. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:52:38,044][682983] Avg episode reward: [(0, '5.004')]
[2023-04-30 12:52:43,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1286144. Throughput: 0: 753.2. Samples: 318604. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:52:43,044][682983] Avg episode reward: [(0, '5.045')]
[2023-04-30 12:52:44,046][683137] Updated weights for policy 0, policy_version 315 (0.0601)
[2023-04-30 12:52:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1298432. Throughput: 0: 752.8. Samples: 320656. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:52:48,044][682983] Avg episode reward: [(0, '5.310')]
[2023-04-30 12:52:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1314816. Throughput: 0: 768.7. Samples: 325624. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:52:53,044][682983] Avg episode reward: [(0, '5.363')]
[2023-04-30 12:52:57,551][683137] Updated weights for policy 0, policy_version 325 (0.0429)
[2023-04-30 12:52:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1331200. Throughput: 0: 748.9. Samples: 329716. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:52:58,044][682983] Avg episode reward: [(0, '5.291')]
[2023-04-30 12:53:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1343488. Throughput: 0: 748.3. Samples: 331752. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:53:03,044][682983] Avg episode reward: [(0, '5.053')]
[2023-04-30 12:53:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1359872. Throughput: 0: 763.5. Samples: 336796. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:53:08,044][682983] Avg episode reward: [(0, '4.972')]
[2023-04-30 12:53:11,249][683137] Updated weights for policy 0, policy_version 335 (0.0454)
[2023-04-30 12:53:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1376256. Throughput: 0: 755.7. Samples: 341232. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:53:13,044][682983] Avg episode reward: [(0, '4.880')]
[2023-04-30 12:53:18,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 1392640. Throughput: 0: 756.0. Samples: 343280. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:53:18,044][682983] Avg episode reward: [(0, '4.801')]
[2023-04-30 12:53:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1404928. Throughput: 0: 752.9. Samples: 347984. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:53:23,044][682983] Avg episode reward: [(0, '5.042')]
[2023-04-30 12:53:24,765][683137] Updated weights for policy 0, policy_version 345 (0.0415)
[2023-04-30 12:53:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1421312. Throughput: 0: 743.2. Samples: 352048. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:53:28,044][682983] Avg episode reward: [(0, '5.282')]
[2023-04-30 12:53:33,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 1437696. Throughput: 0: 742.1. Samples: 354052. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:53:33,044][682983] Avg episode reward: [(0, '5.448')]
[2023-04-30 12:53:34,319][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000352_1441792.pth...
[2023-04-30 12:53:34,341][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000176_720896.pth
[2023-04-30 12:53:34,344][683074] Saving new best policy, reward=5.448!
[2023-04-30 12:53:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1449984. Throughput: 0: 747.9. Samples: 359280. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:53:38,044][682983] Avg episode reward: [(0, '5.482')]
[2023-04-30 12:53:38,485][683137] Updated weights for policy 0, policy_version 355 (0.0409)
[2023-04-30 12:53:39,146][683074] Signal inference workers to stop experience collection... (350 times)
[2023-04-30 12:53:39,165][683137] InferenceWorker_p0-w0: stopping experience collection (350 times)
[2023-04-30 12:53:39,866][683074] Signal inference workers to resume experience collection... (350 times)
[2023-04-30 12:53:39,866][683074] Saving new best policy, reward=5.482!
[2023-04-30 12:53:39,866][683137] InferenceWorker_p0-w0: resuming experience collection (350 times)
[2023-04-30 12:53:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1466368. Throughput: 0: 757.7. Samples: 363812. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:53:43,045][682983] Avg episode reward: [(0, '5.618')]
[2023-04-30 12:53:45,355][683074] Saving new best policy, reward=5.618!
[2023-04-30 12:53:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1478656. Throughput: 0: 757.0. Samples: 365816. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:53:48,044][682983] Avg episode reward: [(0, '5.825')]
[2023-04-30 12:53:49,444][683074] Saving new best policy, reward=5.825!
[2023-04-30 12:53:52,366][683137] Updated weights for policy 0, policy_version 365 (0.1196)
[2023-04-30 12:53:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1495040. Throughput: 0: 745.8. Samples: 370356. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:53:53,045][682983] Avg episode reward: [(0, '5.970')]
[2023-04-30 12:53:54,847][683074] Saving new best policy, reward=5.970!
[2023-04-30 12:53:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1511424. Throughput: 0: 741.2. Samples: 374588. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:53:58,044][682983] Avg episode reward: [(0, '5.866')]
[2023-04-30 12:54:03,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 1527808. Throughput: 0: 741.8. Samples: 376660. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:54:03,045][682983] Avg episode reward: [(0, '6.063')]
[2023-04-30 12:54:04,424][683074] Saving new best policy, reward=6.063!
[2023-04-30 12:54:05,786][683137] Updated weights for policy 0, policy_version 375 (0.0217)
[2023-04-30 12:54:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1540096. Throughput: 0: 751.2. Samples: 381788. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:08,044][682983] Avg episode reward: [(0, '5.935')]
[2023-04-30 12:54:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1556480. Throughput: 0: 763.1. Samples: 386388. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:54:13,044][682983] Avg episode reward: [(0, '6.127')]
[2023-04-30 12:54:15,286][683074] Saving new best policy, reward=6.127!
[2023-04-30 12:54:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 1568768. Throughput: 0: 764.4. Samples: 388448. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:18,044][682983] Avg episode reward: [(0, '6.191')]
[2023-04-30 12:54:19,419][683074] Saving new best policy, reward=6.191!
[2023-04-30 12:54:19,421][683137] Updated weights for policy 0, policy_version 385 (0.0608)
[2023-04-30 12:54:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1585152. Throughput: 0: 749.6. Samples: 393012. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:23,044][682983] Avg episode reward: [(0, '6.146')]
[2023-04-30 12:54:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1601536. Throughput: 0: 741.1. Samples: 397160. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:28,044][682983] Avg episode reward: [(0, '6.405')]
[2023-04-30 12:54:28,989][683074] Saving new best policy, reward=6.405!
[2023-04-30 12:54:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 1613824. Throughput: 0: 741.6. Samples: 399188. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:33,044][682983] Avg episode reward: [(0, '6.330')]
[2023-04-30 12:54:33,079][683137] Updated weights for policy 0, policy_version 395 (0.1200)
[2023-04-30 12:54:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1630208. Throughput: 0: 753.6. Samples: 404268. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:38,044][682983] Avg episode reward: [(0, '6.762')]
[2023-04-30 12:54:39,881][683074] Saving new best policy, reward=6.762!
[2023-04-30 12:54:43,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1646592. Throughput: 0: 763.1. Samples: 408928. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:43,045][682983] Avg episode reward: [(0, '6.827')]
[2023-04-30 12:54:44,066][683074] Saving new best policy, reward=6.827!
[2023-04-30 12:54:46,847][683137] Updated weights for policy 0, policy_version 405 (0.0817)
[2023-04-30 12:54:47,522][683074] Signal inference workers to stop experience collection... (400 times)
[2023-04-30 12:54:47,542][683137] InferenceWorker_p0-w0: stopping experience collection (400 times)
[2023-04-30 12:54:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1658880. Throughput: 0: 763.1. Samples: 411000. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:48,044][682983] Avg episode reward: [(0, '7.411')]
[2023-04-30 12:54:48,229][683074] Signal inference workers to resume experience collection... (400 times)
[2023-04-30 12:54:48,229][683137] InferenceWorker_p0-w0: resuming experience collection (400 times)
[2023-04-30 12:54:49,578][683074] Saving new best policy, reward=7.411!
[2023-04-30 12:54:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1675264. Throughput: 0: 744.5. Samples: 415292. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:54:53,044][682983] Avg episode reward: [(0, '7.622')]
[2023-04-30 12:54:53,699][683074] Saving new best policy, reward=7.622!
[2023-04-30 12:54:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1691648. Throughput: 0: 740.4. Samples: 419704. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:54:58,044][682983] Avg episode reward: [(0, '7.770')]
[2023-04-30 12:54:59,139][683074] Saving new best policy, reward=7.770!
[2023-04-30 12:55:00,740][683137] Updated weights for policy 0, policy_version 415 (0.0822)
[2023-04-30 12:55:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 1703936. Throughput: 0: 740.4. Samples: 421768. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:55:03,044][682983] Avg episode reward: [(0, '7.646')]
[2023-04-30 12:55:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1720320. Throughput: 0: 738.8. Samples: 426256. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:55:08,044][682983] Avg episode reward: [(0, '7.578')]
[2023-04-30 12:55:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1736704. Throughput: 0: 750.7. Samples: 430940. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:55:13,044][682983] Avg episode reward: [(0, '8.023')]
[2023-04-30 12:55:14,336][683074] Saving new best policy, reward=8.023!
[2023-04-30 12:55:14,338][683137] Updated weights for policy 0, policy_version 425 (0.0821)
[2023-04-30 12:55:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1748992. Throughput: 0: 762.8. Samples: 433516. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:55:18,044][682983] Avg episode reward: [(0, '8.136')]
[2023-04-30 12:55:19,826][683074] Saving new best policy, reward=8.136!
[2023-04-30 12:55:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1765376. Throughput: 0: 743.1. Samples: 437708. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:55:23,044][682983] Avg episode reward: [(0, '8.116')]
[2023-04-30 12:55:27,989][683137] Updated weights for policy 0, policy_version 435 (0.0813)
[2023-04-30 12:55:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1781760. Throughput: 0: 739.4. Samples: 442200. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:55:28,044][682983] Avg episode reward: [(0, '8.541')]
[2023-04-30 12:55:29,363][683074] Saving new best policy, reward=8.541!
[2023-04-30 12:55:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1794048. Throughput: 0: 738.5. Samples: 444232. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:55:33,044][682983] Avg episode reward: [(0, '8.531')]
[2023-04-30 12:55:34,902][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000440_1802240.pth...
[2023-04-30 12:55:34,926][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000264_1081344.pth
[2023-04-30 12:55:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1810432. Throughput: 0: 734.3. Samples: 448336. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:55:38,044][682983] Avg episode reward: [(0, '8.741')]
[2023-04-30 12:55:38,965][683074] Saving new best policy, reward=8.741!
[2023-04-30 12:55:41,878][683137] Updated weights for policy 0, policy_version 445 (0.0410)
[2023-04-30 12:55:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 1822720. Throughput: 0: 745.9. Samples: 453268. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:55:43,044][682983] Avg episode reward: [(0, '9.066')]
[2023-04-30 12:55:44,418][683074] Saving new best policy, reward=9.066!
[2023-04-30 12:55:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1839104. Throughput: 0: 761.9. Samples: 456052. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:55:48,044][682983] Avg episode reward: [(0, '8.074')]
[2023-04-30 12:55:53,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1855488. Throughput: 0: 753.9. Samples: 460180. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:55:53,044][682983] Avg episode reward: [(0, '8.291')]
[2023-04-30 12:55:55,516][683137] Updated weights for policy 0, policy_version 455 (0.1209)
[2023-04-30 12:55:56,165][683074] Signal inference workers to stop experience collection... (450 times)
[2023-04-30 12:55:56,185][683137] InferenceWorker_p0-w0: stopping experience collection (450 times)
[2023-04-30 12:55:56,699][683074] Signal inference workers to resume experience collection... (450 times)
[2023-04-30 12:55:56,700][683137] InferenceWorker_p0-w0: resuming experience collection (450 times)
[2023-04-30 12:55:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 1867776. Throughput: 0: 750.2. Samples: 464700. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:55:58,044][682983] Avg episode reward: [(0, '8.285')]
[2023-04-30 12:56:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1884160. Throughput: 0: 738.3. Samples: 466740. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:56:03,044][682983] Avg episode reward: [(0, '8.085')]
[2023-04-30 12:56:08,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1900544. Throughput: 0: 736.5. Samples: 470852. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:56:08,044][682983] Avg episode reward: [(0, '8.204')]
[2023-04-30 12:56:09,097][683137] Updated weights for policy 0, policy_version 465 (0.0821)
[2023-04-30 12:56:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 1912832. Throughput: 0: 747.8. Samples: 475852. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:56:13,044][682983] Avg episode reward: [(0, '8.138')]
[2023-04-30 12:56:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1929216. Throughput: 0: 762.1. Samples: 478528. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:56:18,044][682983] Avg episode reward: [(0, '8.551')]
[2023-04-30 12:56:22,620][683137] Updated weights for policy 0, policy_version 475 (0.0607)
[2023-04-30 12:56:23,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1945600. Throughput: 0: 763.7. Samples: 482704. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:56:23,044][682983] Avg episode reward: [(0, '9.012')]
[2023-04-30 12:56:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 1961984. Throughput: 0: 754.6. Samples: 487224. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:56:28,045][682983] Avg episode reward: [(0, '8.989')]
[2023-04-30 12:56:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1974272. Throughput: 0: 738.4. Samples: 489280. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:56:33,044][682983] Avg episode reward: [(0, '9.311')]
[2023-04-30 12:56:34,913][683074] Saving new best policy, reward=9.311!
[2023-04-30 12:56:36,299][683137] Updated weights for policy 0, policy_version 485 (0.0218)
[2023-04-30 12:56:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 1990656. Throughput: 0: 738.8. Samples: 493424. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:56:38,044][682983] Avg episode reward: [(0, '9.671')]
[2023-04-30 12:56:40,396][683074] Saving new best policy, reward=9.671!
[2023-04-30 12:56:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2002944. Throughput: 0: 740.4. Samples: 498020. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:56:43,044][682983] Avg episode reward: [(0, '9.790')]
[2023-04-30 12:56:44,571][683074] Saving new best policy, reward=9.790!
[2023-04-30 12:56:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2019328. Throughput: 0: 763.2. Samples: 501084. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:56:48,045][682983] Avg episode reward: [(0, '9.728')]
[2023-04-30 12:56:50,079][683137] Updated weights for policy 0, policy_version 495 (0.0616)
[2023-04-30 12:56:53,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2035712. Throughput: 0: 762.8. Samples: 505180. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:56:53,044][682983] Avg episode reward: [(0, '9.638')]
[2023-04-30 12:56:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2048000. Throughput: 0: 755.7. Samples: 509860. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:56:58,044][682983] Avg episode reward: [(0, '9.757')]
[2023-04-30 12:57:03,044][682983] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2064384. Throughput: 0: 741.5. Samples: 511896. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:57:03,045][682983] Avg episode reward: [(0, '10.167')]
[2023-04-30 12:57:03,703][683137] Updated weights for policy 0, policy_version 505 (0.0016)
[2023-04-30 12:57:04,333][683074] Signal inference workers to stop experience collection... (500 times)
[2023-04-30 12:57:04,354][683137] InferenceWorker_p0-w0: stopping experience collection (500 times)
[2023-04-30 12:57:05,066][683074] Signal inference workers to resume experience collection... (500 times)
[2023-04-30 12:57:05,066][683074] Saving new best policy, reward=10.167!
[2023-04-30 12:57:05,066][683137] InferenceWorker_p0-w0: resuming experience collection (500 times)
[2023-04-30 12:57:08,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2080768. Throughput: 0: 739.4. Samples: 515976. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:57:08,044][682983] Avg episode reward: [(0, '10.532')]
[2023-04-30 12:57:09,183][683074] Saving new best policy, reward=10.532!
[2023-04-30 12:57:13,044][682983] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2093056. Throughput: 0: 745.6. Samples: 520776. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:57:13,044][682983] Avg episode reward: [(0, '11.026')]
[2023-04-30 12:57:14,636][683074] Saving new best policy, reward=11.026!
[2023-04-30 12:57:17,352][683137] Updated weights for policy 0, policy_version 515 (0.0614)
[2023-04-30 12:57:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2109440. Throughput: 0: 759.0. Samples: 523436. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:57:18,045][682983] Avg episode reward: [(0, '11.371')]
[2023-04-30 12:57:20,086][683074] Saving new best policy, reward=11.371!
[2023-04-30 12:57:23,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2125824. Throughput: 0: 762.8. Samples: 527752. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:57:23,044][682983] Avg episode reward: [(0, '11.179')]
[2023-04-30 12:57:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 2138112. Throughput: 0: 758.1. Samples: 532136. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:57:28,044][682983] Avg episode reward: [(0, '10.791')]
[2023-04-30 12:57:31,020][683137] Updated weights for policy 0, policy_version 525 (0.0611)
[2023-04-30 12:57:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2154496. Throughput: 0: 739.1. Samples: 534344. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:57:33,044][682983] Avg episode reward: [(0, '11.104')]
[2023-04-30 12:57:35,116][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000528_2162688.pth...
[2023-04-30 12:57:35,138][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000352_1441792.pth
[2023-04-30 12:57:38,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2170880. Throughput: 0: 739.2. Samples: 538444. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:57:38,045][682983] Avg episode reward: [(0, '11.005')]
[2023-04-30 12:57:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2183168. Throughput: 0: 740.6. Samples: 543188. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:57:43,044][682983] Avg episode reward: [(0, '11.569')]
[2023-04-30 12:57:44,619][683074] Saving new best policy, reward=11.569!
[2023-04-30 12:57:44,621][683137] Updated weights for policy 0, policy_version 535 (0.0408)
[2023-04-30 12:57:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2199552. Throughput: 0: 754.7. Samples: 545856. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:57:48,044][682983] Avg episode reward: [(0, '12.888')]
[2023-04-30 12:57:48,756][683074] Saving new best policy, reward=12.888!
[2023-04-30 12:57:53,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2215936. Throughput: 0: 763.0. Samples: 550312. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:57:53,045][682983] Avg episode reward: [(0, '12.593')]
[2023-04-30 12:57:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2228224. Throughput: 0: 757.0. Samples: 554840. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 12:57:58,044][682983] Avg episode reward: [(0, '12.292')]
[2023-04-30 12:57:58,376][683137] Updated weights for policy 0, policy_version 545 (0.0821)
[2023-04-30 12:58:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2244608. Throughput: 0: 743.2. Samples: 556880. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:58:03,044][682983] Avg episode reward: [(0, '11.857')]
[2023-04-30 12:58:08,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2260992. Throughput: 0: 739.6. Samples: 561032. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:58:08,044][682983] Avg episode reward: [(0, '11.286')]
[2023-04-30 12:58:11,949][683137] Updated weights for policy 0, policy_version 555 (0.0800)
[2023-04-30 12:58:12,642][683074] Signal inference workers to stop experience collection... (550 times)
[2023-04-30 12:58:12,664][683137] InferenceWorker_p0-w0: stopping experience collection (550 times)
[2023-04-30 12:58:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 2273280. Throughput: 0: 748.3. Samples: 565808. Policy #0 lag: (min: 1.0, avg: 2.3, max: 3.0)
[2023-04-30 12:58:13,044][682983] Avg episode reward: [(0, '11.360')]
[2023-04-30 12:58:13,322][683074] Signal inference workers to resume experience collection... (550 times)
[2023-04-30 12:58:13,322][683137] InferenceWorker_p0-w0: resuming experience collection (550 times)
[2023-04-30 12:58:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2289664. Throughput: 0: 749.2. Samples: 568056. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:58:18,045][682983] Avg episode reward: [(0, '11.548')]
[2023-04-30 12:58:23,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2306048. Throughput: 0: 764.5. Samples: 572848. Policy #0 lag: (min: 1.0, avg: 2.3, max: 4.0)
[2023-04-30 12:58:23,045][682983] Avg episode reward: [(0, '11.677')]
[2023-04-30 12:58:25,579][683137] Updated weights for policy 0, policy_version 565 (0.1000)
[2023-04-30 12:58:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 2318336. Throughput: 0: 753.6. Samples: 577100. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:58:28,044][682983] Avg episode reward: [(0, '11.566')]
[2023-04-30 12:58:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2334720. Throughput: 0: 747.5. Samples: 579492. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:58:33,044][682983] Avg episode reward: [(0, '13.022')]
[2023-04-30 12:58:35,207][683074] Saving new best policy, reward=13.022!
[2023-04-30 12:58:38,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2351104. Throughput: 0: 739.3. Samples: 583580. Policy #0 lag: (min: 1.0, avg: 2.3, max: 4.0)
[2023-04-30 12:58:38,044][682983] Avg episode reward: [(0, '13.044')]
[2023-04-30 12:58:39,308][683074] Saving new best policy, reward=13.044!
[2023-04-30 12:58:39,310][683137] Updated weights for policy 0, policy_version 575 (0.0609)
[2023-04-30 12:58:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2363392. Throughput: 0: 737.1. Samples: 588008. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:58:43,044][682983] Avg episode reward: [(0, '13.431')]
[2023-04-30 12:58:44,839][683074] Saving new best policy, reward=13.431!
[2023-04-30 12:58:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2379776. Throughput: 0: 750.4. Samples: 590648. Policy #0 lag: (min: 1.0, avg: 2.3, max: 4.0)
[2023-04-30 12:58:48,044][682983] Avg episode reward: [(0, '13.832')]
[2023-04-30 12:58:48,913][683074] Saving new best policy, reward=13.832!
[2023-04-30 12:58:52,991][683137] Updated weights for policy 0, policy_version 585 (0.0615)
[2023-04-30 12:58:53,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2396160. Throughput: 0: 762.6. Samples: 595348. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:58:53,044][682983] Avg episode reward: [(0, '14.697')]
[2023-04-30 12:58:54,362][683074] Saving new best policy, reward=14.697!
[2023-04-30 12:58:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 2408448. Throughput: 0: 748.2. Samples: 599476. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:58:58,044][682983] Avg episode reward: [(0, '14.173')]
[2023-04-30 12:59:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2424832. Throughput: 0: 751.2. Samples: 601860. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:59:03,044][682983] Avg episode reward: [(0, '13.818')]
[2023-04-30 12:59:06,870][683137] Updated weights for policy 0, policy_version 595 (0.0827)
[2023-04-30 12:59:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 2437120. Throughput: 0: 738.8. Samples: 606096. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:59:08,045][682983] Avg episode reward: [(0, '13.007')]
[2023-04-30 12:59:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2453504. Throughput: 0: 737.0. Samples: 610264. Policy #0 lag: (min: 1.0, avg: 2.3, max: 4.0)
[2023-04-30 12:59:13,044][682983] Avg episode reward: [(0, '13.464')]
[2023-04-30 12:59:18,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2469888. Throughput: 0: 741.8. Samples: 612872. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:59:18,044][682983] Avg episode reward: [(0, '13.153')]
[2023-04-30 12:59:20,409][683137] Updated weights for policy 0, policy_version 605 (0.0814)
[2023-04-30 12:59:21,031][683074] Signal inference workers to stop experience collection... (600 times)
[2023-04-30 12:59:21,059][683137] InferenceWorker_p0-w0: stopping experience collection (600 times)
[2023-04-30 12:59:21,783][683074] Signal inference workers to resume experience collection... (600 times)
[2023-04-30 12:59:21,783][683137] InferenceWorker_p0-w0: resuming experience collection (600 times)
[2023-04-30 12:59:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 2482176. Throughput: 0: 760.2. Samples: 617788. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:59:23,044][682983] Avg episode reward: [(0, '13.263')]
[2023-04-30 12:59:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2498560. Throughput: 0: 754.0. Samples: 621940. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:59:28,044][682983] Avg episode reward: [(0, '13.268')]
[2023-04-30 12:59:33,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2514944. Throughput: 0: 752.7. Samples: 624520. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:59:33,045][682983] Avg episode reward: [(0, '14.427')]
[2023-04-30 12:59:34,004][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000615_2519040.pth...
[2023-04-30 12:59:34,006][683137] Updated weights for policy 0, policy_version 615 (0.0612)
[2023-04-30 12:59:34,028][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000440_1802240.pth
[2023-04-30 12:59:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 2527232. Throughput: 0: 739.6. Samples: 628632. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:59:38,045][682983] Avg episode reward: [(0, '14.446')]
[2023-04-30 12:59:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2543616. Throughput: 0: 741.2. Samples: 632832. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:59:43,044][682983] Avg episode reward: [(0, '13.970')]
[2023-04-30 12:59:47,882][683137] Updated weights for policy 0, policy_version 625 (0.0820)
[2023-04-30 12:59:48,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2560000. Throughput: 0: 739.3. Samples: 635128. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 12:59:48,044][682983] Avg episode reward: [(0, '14.162')]
[2023-04-30 12:59:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 2572288. Throughput: 0: 758.7. Samples: 640236. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 12:59:53,044][682983] Avg episode reward: [(0, '14.640')]
[2023-04-30 12:59:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2588672. Throughput: 0: 759.6. Samples: 644448. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 12:59:58,044][682983] Avg episode reward: [(0, '14.552')]
[2023-04-30 13:00:01,358][683137] Updated weights for policy 0, policy_version 635 (0.0613)
[2023-04-30 13:00:03,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2605056. Throughput: 0: 756.4. Samples: 646912. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:00:03,044][682983] Avg episode reward: [(0, '14.921')]
[2023-04-30 13:00:04,140][683074] Saving new best policy, reward=14.921!
[2023-04-30 13:00:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 2617344. Throughput: 0: 744.6. Samples: 651296. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 13:00:08,044][682983] Avg episode reward: [(0, '15.287')]
[2023-04-30 13:00:09,541][683074] Saving new best policy, reward=15.287!
[2023-04-30 13:00:13,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2633728. Throughput: 0: 743.8. Samples: 655412. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:00:13,044][682983] Avg episode reward: [(0, '14.729')]
[2023-04-30 13:00:15,055][683137] Updated weights for policy 0, policy_version 645 (0.0411)
[2023-04-30 13:00:18,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2650112. Throughput: 0: 740.9. Samples: 657860. Policy #0 lag: (min: 1.0, avg: 2.3, max: 4.0)
[2023-04-30 13:00:18,044][682983] Avg episode reward: [(0, '14.097')]
[2023-04-30 13:00:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 2662400. Throughput: 0: 754.8. Samples: 662596. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:00:23,044][682983] Avg episode reward: [(0, '14.728')]
[2023-04-30 13:00:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2678784. Throughput: 0: 758.5. Samples: 666964. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:00:28,044][682983] Avg episode reward: [(0, '13.782')]
[2023-04-30 13:00:28,819][683137] Updated weights for policy 0, policy_version 655 (0.1023)
[2023-04-30 13:00:29,397][683074] Signal inference workers to stop experience collection... (650 times)
[2023-04-30 13:00:29,418][683137] InferenceWorker_p0-w0: stopping experience collection (650 times)
[2023-04-30 13:00:30,208][683074] Signal inference workers to resume experience collection... (650 times)
[2023-04-30 13:00:30,208][683137] InferenceWorker_p0-w0: resuming experience collection (650 times)
[2023-04-30 13:00:33,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2695168. Throughput: 0: 753.7. Samples: 669044. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:00:33,044][682983] Avg episode reward: [(0, '14.370')]
[2023-04-30 13:00:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2707456. Throughput: 0: 743.7. Samples: 673704. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:00:38,044][682983] Avg episode reward: [(0, '14.548')]
[2023-04-30 13:00:42,774][683137] Updated weights for policy 0, policy_version 665 (0.1226)
[2023-04-30 13:00:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2723840. Throughput: 0: 742.2. Samples: 677848. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:00:43,044][682983] Avg episode reward: [(0, '14.702')]
[2023-04-30 13:00:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 2736128. Throughput: 0: 732.7. Samples: 679884. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:00:48,044][682983] Avg episode reward: [(0, '15.510')]
[2023-04-30 13:00:49,457][683074] Saving new best policy, reward=15.510!
[2023-04-30 13:00:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2752512. Throughput: 0: 737.2. Samples: 684472. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:00:53,044][682983] Avg episode reward: [(0, '15.263')]
[2023-04-30 13:00:56,263][683137] Updated weights for policy 0, policy_version 675 (0.0828)
[2023-04-30 13:00:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2768896. Throughput: 0: 758.5. Samples: 689544. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:00:58,044][682983] Avg episode reward: [(0, '14.507')]
[2023-04-30 13:01:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 2781184. Throughput: 0: 749.7. Samples: 691596. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:01:03,044][682983] Avg episode reward: [(0, '14.790')]
[2023-04-30 13:01:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2797568. Throughput: 0: 748.9. Samples: 696296. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:01:08,044][682983] Avg episode reward: [(0, '14.394')]
[2023-04-30 13:01:09,921][683137] Updated weights for policy 0, policy_version 685 (0.0806)
[2023-04-30 13:01:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2813952. Throughput: 0: 742.1. Samples: 700360. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:01:13,044][682983] Avg episode reward: [(0, '14.092')]
[2023-04-30 13:01:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 2826240. Throughput: 0: 742.1. Samples: 702440. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:01:18,044][682983] Avg episode reward: [(0, '14.554')]
[2023-04-30 13:01:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 2842624. Throughput: 0: 735.1. Samples: 706784. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:01:23,044][682983] Avg episode reward: [(0, '14.575')]
[2023-04-30 13:01:23,656][683137] Updated weights for policy 0, policy_version 695 (0.0820)
[2023-04-30 13:01:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2859008. Throughput: 0: 760.0. Samples: 712048. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:01:28,044][682983] Avg episode reward: [(0, '15.110')]
[2023-04-30 13:01:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 2871296. Throughput: 0: 760.4. Samples: 714100. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:01:33,045][682983] Avg episode reward: [(0, '14.599')]
[2023-04-30 13:01:34,482][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000703_2879488.pth...
[2023-04-30 13:01:34,507][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000528_2162688.pth
[2023-04-30 13:01:37,211][683137] Updated weights for policy 0, policy_version 705 (0.1002)
[2023-04-30 13:01:37,869][683074] Signal inference workers to stop experience collection... (700 times)
[2023-04-30 13:01:37,890][683137] InferenceWorker_p0-w0: stopping experience collection (700 times)
[2023-04-30 13:01:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2887680. Throughput: 0: 762.8. Samples: 718800. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:01:38,044][682983] Avg episode reward: [(0, '15.883')]
[2023-04-30 13:01:38,612][683074] Signal inference workers to resume experience collection... (700 times)
[2023-04-30 13:01:38,613][683137] InferenceWorker_p0-w0: resuming experience collection (700 times)
[2023-04-30 13:01:39,946][683074] Saving new best policy, reward=15.883!
[2023-04-30 13:01:43,044][682983] Fps is (10 sec: 3276.9, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2904064. Throughput: 0: 740.4. Samples: 722860. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:01:43,044][682983] Avg episode reward: [(0, '16.496')]
[2023-04-30 13:01:44,027][683074] Saving new best policy, reward=16.496!
[2023-04-30 13:01:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 2916352. Throughput: 0: 739.5. Samples: 724872. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:01:48,044][682983] Avg episode reward: [(0, '16.137')]
[2023-04-30 13:01:50,854][683137] Updated weights for policy 0, policy_version 715 (0.0612)
[2023-04-30 13:01:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2932736. Throughput: 0: 745.3. Samples: 729836. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:01:53,044][682983] Avg episode reward: [(0, '15.545')]
[2023-04-30 13:01:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2949120. Throughput: 0: 759.7. Samples: 734548. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:01:58,044][682983] Avg episode reward: [(0, '15.810')]
[2023-04-30 13:02:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 2961408. Throughput: 0: 759.4. Samples: 736612. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:02:03,044][682983] Avg episode reward: [(0, '14.536')]
[2023-04-30 13:02:04,465][683137] Updated weights for policy 0, policy_version 725 (0.0413)
[2023-04-30 13:02:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2977792. Throughput: 0: 764.7. Samples: 741196. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:02:08,044][682983] Avg episode reward: [(0, '13.761')]
[2023-04-30 13:02:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 2994176. Throughput: 0: 740.9. Samples: 745388. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:02:13,044][682983] Avg episode reward: [(0, '14.195')]
[2023-04-30 13:02:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 3006464. Throughput: 0: 740.5. Samples: 747424. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:02:18,044][682983] Avg episode reward: [(0, '14.984')]
[2023-04-30 13:02:18,312][683137] Updated weights for policy 0, policy_version 735 (0.0815)
[2023-04-30 13:02:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3022848. Throughput: 0: 737.2. Samples: 751976. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:02:23,044][682983] Avg episode reward: [(0, '15.762')]
[2023-04-30 13:02:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3039232. Throughput: 0: 761.7. Samples: 757136. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:02:28,044][682983] Avg episode reward: [(0, '16.268')]
[2023-04-30 13:02:31,945][683137] Updated weights for policy 0, policy_version 745 (0.1199)
[2023-04-30 13:02:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 3051520. Throughput: 0: 762.2. Samples: 759172. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:02:33,044][682983] Avg episode reward: [(0, '16.758')]
[2023-04-30 13:02:34,443][683074] Saving new best policy, reward=16.758!
[2023-04-30 13:02:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3067904. Throughput: 0: 756.0. Samples: 763856. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:02:38,044][682983] Avg episode reward: [(0, '18.018')]
[2023-04-30 13:02:39,978][683074] Saving new best policy, reward=18.018!
[2023-04-30 13:02:43,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3084288. Throughput: 0: 742.8. Samples: 767976. Policy #0 lag: (min: 1.0, avg: 2.3, max: 3.0)
[2023-04-30 13:02:43,044][682983] Avg episode reward: [(0, '17.980')]
[2023-04-30 13:02:45,496][683137] Updated weights for policy 0, policy_version 755 (0.0422)
[2023-04-30 13:02:46,083][683074] Signal inference workers to stop experience collection... (750 times)
[2023-04-30 13:02:46,104][683137] InferenceWorker_p0-w0: stopping experience collection (750 times)
[2023-04-30 13:02:46,844][683074] Signal inference workers to resume experience collection... (750 times)
[2023-04-30 13:02:46,845][683137] InferenceWorker_p0-w0: resuming experience collection (750 times)
[2023-04-30 13:02:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 3096576. Throughput: 0: 743.1. Samples: 770052. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:02:48,044][682983] Avg episode reward: [(0, '16.947')]
[2023-04-30 13:02:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3112960. Throughput: 0: 736.5. Samples: 774340. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:02:53,045][682983] Avg episode reward: [(0, '16.887')]
[2023-04-30 13:02:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3129344. Throughput: 0: 760.3. Samples: 779600. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:02:58,044][682983] Avg episode reward: [(0, '16.813')]
[2023-04-30 13:02:59,125][683137] Updated weights for policy 0, policy_version 765 (0.1199)
[2023-04-30 13:03:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 3141632. Throughput: 0: 760.3. Samples: 781636. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:03:03,044][682983] Avg episode reward: [(0, '15.977')]
[2023-04-30 13:03:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3158016. Throughput: 0: 765.2. Samples: 786412. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:03:08,044][682983] Avg episode reward: [(0, '16.698')]
[2023-04-30 13:03:12,932][683137] Updated weights for policy 0, policy_version 775 (0.0816)
[2023-04-30 13:03:13,044][682983] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3174400. Throughput: 0: 741.2. Samples: 790492. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:03:13,045][682983] Avg episode reward: [(0, '17.640')]
[2023-04-30 13:03:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 3186688. Throughput: 0: 741.9. Samples: 792556. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:03:18,044][682983] Avg episode reward: [(0, '16.939')]
[2023-04-30 13:03:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3203072. Throughput: 0: 733.8. Samples: 796876. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:03:23,045][682983] Avg episode reward: [(0, '17.946')]
[2023-04-30 13:03:26,430][683137] Updated weights for policy 0, policy_version 785 (0.1016)
[2023-04-30 13:03:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3219456. Throughput: 0: 759.5. Samples: 802152. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:03:28,045][682983] Avg episode reward: [(0, '18.516')]
[2023-04-30 13:03:29,161][683074] Saving new best policy, reward=18.516!
[2023-04-30 13:03:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 3231744. Throughput: 0: 759.0. Samples: 804208. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:03:33,044][682983] Avg episode reward: [(0, '18.890')]
[2023-04-30 13:03:34,662][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000791_3239936.pth...
[2023-04-30 13:03:34,686][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000615_2519040.pth
[2023-04-30 13:03:34,689][683074] Saving new best policy, reward=18.890!
[2023-04-30 13:03:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3248128. Throughput: 0: 764.7. Samples: 808752. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:03:38,044][682983] Avg episode reward: [(0, '18.836')]
[2023-04-30 13:03:40,104][683137] Updated weights for policy 0, policy_version 795 (0.0212)
[2023-04-30 13:03:43,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3264512. Throughput: 0: 743.5. Samples: 813056. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:03:43,045][682983] Avg episode reward: [(0, '19.253')]
[2023-04-30 13:03:44,192][683074] Saving new best policy, reward=19.253!
[2023-04-30 13:03:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 3276800. Throughput: 0: 743.9. Samples: 815112. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:03:48,044][682983] Avg episode reward: [(0, '20.032')]
[2023-04-30 13:03:49,634][683074] Saving new best policy, reward=20.032!
[2023-04-30 13:03:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3293184. Throughput: 0: 731.0. Samples: 819308. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:03:53,044][682983] Avg episode reward: [(0, '20.225')]
[2023-04-30 13:03:53,716][683137] Updated weights for policy 0, policy_version 805 (0.0798)
[2023-04-30 13:03:54,275][683074] Signal inference workers to stop experience collection... (800 times)
[2023-04-30 13:03:54,296][683137] InferenceWorker_p0-w0: stopping experience collection (800 times)
[2023-04-30 13:03:55,067][683074] Signal inference workers to resume experience collection... (800 times)
[2023-04-30 13:03:55,068][683074] Saving new best policy, reward=20.225!
[2023-04-30 13:03:55,068][683137] InferenceWorker_p0-w0: resuming experience collection (800 times)
[2023-04-30 13:03:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3309568. Throughput: 0: 759.3. Samples: 824660. Policy #0 lag: (min: 1.0, avg: 2.3, max: 3.0)
[2023-04-30 13:03:58,044][682983] Avg episode reward: [(0, '20.326')]
[2023-04-30 13:03:59,155][683074] Saving new best policy, reward=20.326!
[2023-04-30 13:04:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3321856. Throughput: 0: 759.3. Samples: 826724. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:04:03,044][682983] Avg episode reward: [(0, '20.112')]
[2023-04-30 13:04:07,458][683137] Updated weights for policy 0, policy_version 815 (0.1039)
[2023-04-30 13:04:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3338240. Throughput: 0: 756.4. Samples: 830916. Policy #0 lag: (min: 1.0, avg: 2.3, max: 4.0)
[2023-04-30 13:04:08,044][682983] Avg episode reward: [(0, '19.533')]
[2023-04-30 13:04:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3354624. Throughput: 0: 743.8. Samples: 835624. Policy #0 lag: (min: 1.0, avg: 2.3, max: 4.0)
[2023-04-30 13:04:13,044][682983] Avg episode reward: [(0, '20.020')]
[2023-04-30 13:04:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3366912. Throughput: 0: 743.4. Samples: 837660. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:04:18,044][682983] Avg episode reward: [(0, '18.374')]
[2023-04-30 13:04:21,109][683137] Updated weights for policy 0, policy_version 825 (0.0998)
[2023-04-30 13:04:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3383296. Throughput: 0: 739.2. Samples: 842016. Policy #0 lag: (min: 1.0, avg: 2.3, max: 3.0)
[2023-04-30 13:04:23,044][682983] Avg episode reward: [(0, '18.362')]
[2023-04-30 13:04:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3399680. Throughput: 0: 751.0. Samples: 846852. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 13:04:28,044][682983] Avg episode reward: [(0, '18.226')]
[2023-04-30 13:04:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3411968. Throughput: 0: 759.4. Samples: 849284. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:04:33,044][682983] Avg episode reward: [(0, '19.551')]
[2023-04-30 13:04:34,720][683137] Updated weights for policy 0, policy_version 835 (0.1216)
[2023-04-30 13:04:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3428352. Throughput: 0: 757.3. Samples: 853388. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:04:38,044][682983] Avg episode reward: [(0, '20.090')]
[2023-04-30 13:04:43,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3444736. Throughput: 0: 742.8. Samples: 858084. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:04:43,045][682983] Avg episode reward: [(0, '19.302')]
[2023-04-30 13:04:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3457024. Throughput: 0: 742.1. Samples: 860120. Policy #0 lag: (min: 1.0, avg: 2.2, max: 3.0)
[2023-04-30 13:04:48,044][682983] Avg episode reward: [(0, '20.120')]
[2023-04-30 13:04:48,281][683137] Updated weights for policy 0, policy_version 845 (0.0995)
[2023-04-30 13:04:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3473408. Throughput: 0: 749.9. Samples: 864660. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 13:04:53,044][682983] Avg episode reward: [(0, '20.576')]
[2023-04-30 13:04:55,093][683074] Saving new best policy, reward=20.576!
[2023-04-30 13:04:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3489792. Throughput: 0: 758.1. Samples: 869740. Policy #0 lag: (min: 1.0, avg: 2.2, max: 4.0)
[2023-04-30 13:04:58,044][682983] Avg episode reward: [(0, '20.160')]
[2023-04-30 13:05:02,072][683137] Updated weights for policy 0, policy_version 855 (0.1027)
[2023-04-30 13:05:02,733][683074] Signal inference workers to stop experience collection... (850 times)
[2023-04-30 13:05:02,753][683137] InferenceWorker_p0-w0: stopping experience collection (850 times)
[2023-04-30 13:05:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3502080. Throughput: 0: 758.0. Samples: 871772. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:05:03,044][682983] Avg episode reward: [(0, '19.109')]
[2023-04-30 13:05:03,253][683074] Signal inference workers to resume experience collection... (850 times)
[2023-04-30 13:05:03,254][683137] InferenceWorker_p0-w0: resuming experience collection (850 times)
[2023-04-30 13:05:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3518464. Throughput: 0: 755.6. Samples: 876020. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 13:05:08,044][682983] Avg episode reward: [(0, '19.191')]
[2023-04-30 13:05:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3534848. Throughput: 0: 745.9. Samples: 880416. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:05:13,045][682983] Avg episode reward: [(0, '19.888')]
[2023-04-30 13:05:15,467][683137] Updated weights for policy 0, policy_version 865 (0.0811)
[2023-04-30 13:05:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3547136. Throughput: 0: 737.7. Samples: 882480. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 13:05:18,044][682983] Avg episode reward: [(0, '20.366')]
[2023-04-30 13:05:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3563520. Throughput: 0: 751.9. Samples: 887224. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 13:05:23,045][682983] Avg episode reward: [(0, '18.907')]
[2023-04-30 13:05:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3579904. Throughput: 0: 757.3. Samples: 892164. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:05:28,044][682983] Avg episode reward: [(0, '18.653')]
[2023-04-30 13:05:29,298][683137] Updated weights for policy 0, policy_version 875 (0.0815)
[2023-04-30 13:05:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3592192. Throughput: 0: 757.8. Samples: 894220. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:05:33,044][682983] Avg episode reward: [(0, '19.605')]
[2023-04-30 13:05:34,608][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000879_3600384.pth...
[2023-04-30 13:05:34,633][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000703_2879488.pth
[2023-04-30 13:05:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3608576. Throughput: 0: 758.6. Samples: 898796. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:05:38,044][682983] Avg episode reward: [(0, '18.191')]
[2023-04-30 13:05:42,970][683137] Updated weights for policy 0, policy_version 885 (0.0601)
[2023-04-30 13:05:43,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 3624960. Throughput: 0: 739.1. Samples: 903000. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:05:43,044][682983] Avg episode reward: [(0, '17.661')]
[2023-04-30 13:05:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3637248. Throughput: 0: 738.8. Samples: 905016. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:05:48,044][682983] Avg episode reward: [(0, '17.378')]
[2023-04-30 13:05:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3653632. Throughput: 0: 750.1. Samples: 909776. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:05:53,044][682983] Avg episode reward: [(0, '17.987')]
[2023-04-30 13:05:56,402][683137] Updated weights for policy 0, policy_version 895 (0.0829)
[2023-04-30 13:05:58,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 3670016. Throughput: 0: 762.1. Samples: 914712. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:05:58,044][682983] Avg episode reward: [(0, '18.096')]
[2023-04-30 13:06:03,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3682304. Throughput: 0: 762.1. Samples: 916776. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:06:03,045][682983] Avg episode reward: [(0, '17.302')]
[2023-04-30 13:06:08,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3698688. Throughput: 0: 750.6. Samples: 921000. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:06:08,044][682983] Avg episode reward: [(0, '18.105')]
[2023-04-30 13:06:10,027][683137] Updated weights for policy 0, policy_version 905 (0.0615)
[2023-04-30 13:06:10,627][683074] Signal inference workers to stop experience collection... (900 times)
[2023-04-30 13:06:10,649][683137] InferenceWorker_p0-w0: stopping experience collection (900 times)
[2023-04-30 13:06:11,391][683074] Signal inference workers to resume experience collection... (900 times)
[2023-04-30 13:06:11,392][683137] InferenceWorker_p0-w0: resuming experience collection (900 times)
[2023-04-30 13:06:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 3715072. Throughput: 0: 742.3. Samples: 925568. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:06:13,045][682983] Avg episode reward: [(0, '18.338')]
[2023-04-30 13:06:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3727360. Throughput: 0: 742.7. Samples: 927640. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:06:18,044][682983] Avg episode reward: [(0, '18.425')]
[2023-04-30 13:06:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3743744. Throughput: 0: 741.1. Samples: 932144. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:06:23,044][682983] Avg episode reward: [(0, '18.785')]
[2023-04-30 13:06:23,750][683137] Updated weights for policy 0, policy_version 915 (0.1016)
[2023-04-30 13:06:28,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 3760128. Throughput: 0: 755.0. Samples: 936976. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:06:28,044][682983] Avg episode reward: [(0, '18.571')]
[2023-04-30 13:06:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3772416. Throughput: 0: 762.0. Samples: 939304. Policy #0 lag: (min: 1.0, avg: 2.0, max: 3.0)
[2023-04-30 13:06:33,045][682983] Avg episode reward: [(0, '19.278')]
[2023-04-30 13:06:37,462][683137] Updated weights for policy 0, policy_version 925 (0.0820)
[2023-04-30 13:06:38,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3788800. Throughput: 0: 748.8. Samples: 943472. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:06:38,044][682983] Avg episode reward: [(0, '19.292')]
[2023-04-30 13:06:43,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 3805184. Throughput: 0: 742.5. Samples: 948124. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:06:43,044][682983] Avg episode reward: [(0, '19.691')]
[2023-04-30 13:06:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3817472. Throughput: 0: 742.7. Samples: 950196. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:06:48,044][682983] Avg episode reward: [(0, '19.590')]
[2023-04-30 13:06:51,378][683137] Updated weights for policy 0, policy_version 935 (0.0809)
[2023-04-30 13:06:53,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3833856. Throughput: 0: 741.9. Samples: 954384. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:06:53,045][682983] Avg episode reward: [(0, '20.647')]
[2023-04-30 13:06:55,307][683074] Saving new best policy, reward=20.647!
[2023-04-30 13:06:58,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 3846144. Throughput: 0: 756.2. Samples: 959596. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:06:58,044][682983] Avg episode reward: [(0, '20.474')]
[2023-04-30 13:07:03,044][682983] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3862528. Throughput: 0: 758.2. Samples: 961760. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:03,044][682983] Avg episode reward: [(0, '20.640')]
[2023-04-30 13:07:04,875][683137] Updated weights for policy 0, policy_version 945 (0.1224)
[2023-04-30 13:07:08,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3878912. Throughput: 0: 749.9. Samples: 965888. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:08,044][682983] Avg episode reward: [(0, '20.677')]
[2023-04-30 13:07:08,923][683074] Saving new best policy, reward=20.677!
[2023-04-30 13:07:13,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 3895296. Throughput: 0: 749.4. Samples: 970700. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:13,044][682983] Avg episode reward: [(0, '20.801')]
[2023-04-30 13:07:14,378][683074] Saving new best policy, reward=20.801!
[2023-04-30 13:07:18,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3907584. Throughput: 0: 743.6. Samples: 972764. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:18,044][682983] Avg episode reward: [(0, '20.694')]
[2023-04-30 13:07:18,475][683137] Updated weights for policy 0, policy_version 955 (0.0998)
[2023-04-30 13:07:19,050][683074] Signal inference workers to stop experience collection... (950 times)
[2023-04-30 13:07:19,071][683137] InferenceWorker_p0-w0: stopping experience collection (950 times)
[2023-04-30 13:07:19,863][683074] Signal inference workers to resume experience collection... (950 times)
[2023-04-30 13:07:19,863][683137] InferenceWorker_p0-w0: resuming experience collection (950 times)
[2023-04-30 13:07:23,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3923968. Throughput: 0: 744.0. Samples: 976952. Policy #0 lag: (min: 1.0, avg: 2.1, max: 4.0)
[2023-04-30 13:07:23,044][682983] Avg episode reward: [(0, '20.036')]
[2023-04-30 13:07:28,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 3936256. Throughput: 0: 748.4. Samples: 981800. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:28,044][682983] Avg episode reward: [(0, '19.883')]
[2023-04-30 13:07:32,132][683137] Updated weights for policy 0, policy_version 965 (0.0822)
[2023-04-30 13:07:33,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3952640. Throughput: 0: 758.1. Samples: 984312. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:33,044][682983] Avg episode reward: [(0, '18.899')]
[2023-04-30 13:07:34,898][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000967_3960832.pth...
[2023-04-30 13:07:34,925][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000791_3239936.pth
[2023-04-30 13:07:38,044][682983] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3969024. Throughput: 0: 755.7. Samples: 988392. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:38,044][682983] Avg episode reward: [(0, '18.993')]
[2023-04-30 13:07:43,044][682983] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 3981312. Throughput: 0: 736.7. Samples: 992748. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:43,044][682983] Avg episode reward: [(0, '18.584')]
[2023-04-30 13:07:46,267][683137] Updated weights for policy 0, policy_version 975 (0.0823)
[2023-04-30 13:07:48,044][682983] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 3997696. Throughput: 0: 745.8. Samples: 995320. Policy #0 lag: (min: 1.0, avg: 2.1, max: 3.0)
[2023-04-30 13:07:48,044][682983] Avg episode reward: [(0, '19.073')]
[2023-04-30 13:07:50,206][683074] Stopping Batcher_0...
[2023-04-30 13:07:50,207][683074] Loop batcher_evt_loop terminating...
[2023-04-30 13:07:50,214][682983] Component Batcher_0 stopped!
[2023-04-30 13:07:50,223][683139] Stopping RolloutWorker_w1...
[2023-04-30 13:07:50,223][682983] Component RolloutWorker_w1 stopped!
[2023-04-30 13:07:50,223][683139] Loop rollout_proc1_evt_loop terminating...
[2023-04-30 13:07:50,223][683149] Stopping RolloutWorker_w7...
[2023-04-30 13:07:50,223][683141] Stopping RolloutWorker_w3...
[2023-04-30 13:07:50,223][683145] Stopping RolloutWorker_w6...
[2023-04-30 13:07:50,223][683140] Stopping RolloutWorker_w2...
[2023-04-30 13:07:50,223][683149] Loop rollout_proc7_evt_loop terminating...
[2023-04-30 13:07:50,223][682983] Component RolloutWorker_w7 stopped!
[2023-04-30 13:07:50,224][682983] Component RolloutWorker_w3 stopped!
[2023-04-30 13:07:50,224][683145] Loop rollout_proc6_evt_loop terminating...
[2023-04-30 13:07:50,224][683141] Loop rollout_proc3_evt_loop terminating...
[2023-04-30 13:07:50,224][683140] Loop rollout_proc2_evt_loop terminating...
[2023-04-30 13:07:50,224][682983] Component RolloutWorker_w6 stopped!
[2023-04-30 13:07:50,224][683144] Stopping RolloutWorker_w5...
[2023-04-30 13:07:50,224][683142] Stopping RolloutWorker_w4...
[2023-04-30 13:07:50,224][682983] Component RolloutWorker_w2 stopped!
[2023-04-30 13:07:50,224][682983] Component RolloutWorker_w5 stopped!
[2023-04-30 13:07:50,224][683142] Loop rollout_proc4_evt_loop terminating...
[2023-04-30 13:07:50,224][683144] Loop rollout_proc5_evt_loop terminating...
[2023-04-30 13:07:50,225][682983] Component RolloutWorker_w4 stopped!
[2023-04-30 13:07:50,240][683138] Stopping RolloutWorker_w0...
[2023-04-30 13:07:50,240][682983] Component RolloutWorker_w0 stopped!
[2023-04-30 13:07:50,241][683138] Loop rollout_proc0_evt_loop terminating...
[2023-04-30 13:07:50,280][683137] Weights refcount: 2 0
[2023-04-30 13:07:50,281][683137] Stopping InferenceWorker_p0-w0...
[2023-04-30 13:07:50,282][683137] Loop inference_proc0-0_evt_loop terminating...
[2023-04-30 13:07:50,282][682983] Component InferenceWorker_p0-w0 stopped!
[2023-04-30 13:07:51,610][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000979_4009984.pth...
[2023-04-30 13:07:51,633][683074] Removing ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000879_3600384.pth
[2023-04-30 13:07:51,636][683074] Saving ./train_dir/doom_health_gathering_supreme/checkpoint_p0/checkpoint_000000979_4009984.pth...
[2023-04-30 13:07:51,667][683074] Stopping LearnerWorker_p0...
[2023-04-30 13:07:51,667][682983] Component LearnerWorker_p0 stopped!
[2023-04-30 13:07:51,667][683074] Loop learner_proc0_evt_loop terminating...
[2023-04-30 13:07:51,667][682983] Waiting for process learner_proc0 to stop...
[2023-04-30 13:07:51,842][682983] Waiting for process inference_proc0-0 to join...
[2023-04-30 13:07:51,843][682983] Waiting for process rollout_proc0 to join...
[2023-04-30 13:07:51,843][682983] Waiting for process rollout_proc1 to join...
[2023-04-30 13:07:51,843][682983] Waiting for process rollout_proc2 to join...
[2023-04-30 13:07:51,843][682983] Waiting for process rollout_proc3 to join...
[2023-04-30 13:07:51,843][682983] Waiting for process rollout_proc4 to join...
[2023-04-30 13:07:51,843][682983] Waiting for process rollout_proc5 to join...
[2023-04-30 13:07:51,844][682983] Waiting for process rollout_proc6 to join...
[2023-04-30 13:07:51,844][682983] Waiting for process rollout_proc7 to join...
[2023-04-30 13:07:51,844][682983] Batcher 0 profile tree view:
batching: 4.6847, releasing_batches: 0.1589
[2023-04-30 13:07:51,844][682983] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0051
  wait_policy_total: 6.7719
update_model: 74.6759
  weight_update: 0.1017
one_step: 0.0334
  handle_policy_step: 455.4509
    deserialize: 5.5774, stack: 0.4649, obs_to_device_normalize: 29.5796, forward: 403.7178, send_messages: 8.4459
    prepare_outputs: 4.5571
      to_cpu: 0.3871
[2023-04-30 13:07:51,844][682983] Learner 0 profile tree view:
misc: 0.0030, prepare_batch: 230.8644
train: 1097.8844
  epoch_init: 0.0034, minibatch_init: 0.0043, losses_postprocess: 0.0338, kl_divergence: 0.1467, after_optimizer: 0.7092
  calculate_losses: 382.0104
    losses_init: 0.0019, forward_head: 277.3595, bptt_initial: 0.9937, tail: 0.7954, advantages_returns: 0.0669, losses: 0.3979
    bptt: 102.2738
      bptt_forward_core: 102.0908
  update: 714.7093
    clip: 1.3180
[2023-04-30 13:07:51,844][682983] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.0646, enqueue_policy_requests: 3.8134, env_step: 90.4966, overhead: 7.0037, complete_rollouts: 0.1099
save_policy_outputs: 4.7685
  split_output_tensors: 2.2309
[2023-04-30 13:07:51,844][682983] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.0636, enqueue_policy_requests: 3.7639, env_step: 90.4639, overhead: 7.0318, complete_rollouts: 0.1070
save_policy_outputs: 4.7276
  split_output_tensors: 2.2120
[2023-04-30 13:07:51,845][682983] Loop Runner_EvtLoop terminating...
[2023-04-30 13:07:51,845][682983] Runner profile tree view:
main_loop: 1337.7066
[2023-04-30 13:07:51,845][682983] Collected {0: 4009984}, FPS: 2982.3