Hugging Face's logo

eldraco
/
rl_course_vizdoom_deathmatch_v1

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
rl_course_vizdoom_deathmatch_v1
File size: 182,220 Bytes 
dd7baaa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8cf5943
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dd7baaa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0042ca4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b17365e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
 
[2023-02-24 17:11:14,766][2343622] Saving configuration to /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/config.json...
[2023-02-24 17:11:14,767][2343622] Rollout worker 0 uses device cpu
[2023-02-24 17:11:14,767][2343622] Rollout worker 1 uses device cpu
[2023-02-24 17:11:14,767][2343622] Rollout worker 2 uses device cpu
[2023-02-24 17:11:14,767][2343622] Rollout worker 3 uses device cpu
[2023-02-24 17:11:14,767][2343622] Rollout worker 4 uses device cpu
[2023-02-24 17:11:14,767][2343622] Rollout worker 5 uses device cpu
[2023-02-24 17:11:14,768][2343622] Rollout worker 6 uses device cpu
[2023-02-24 17:11:14,768][2343622] Rollout worker 7 uses device cpu
[2023-02-24 17:11:14,797][2343622] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:11:14,797][2343622] InferenceWorker_p0-w0: min num requests: 2
[2023-02-24 17:11:14,815][2343622] Starting all processes...
[2023-02-24 17:11:14,815][2343622] Starting process learner_proc0
[2023-02-24 17:11:15,520][2343622] Starting all processes...
[2023-02-24 17:11:15,523][2343622] Starting process inference_proc0-0
[2023-02-24 17:11:15,523][2343622] Starting process rollout_proc0
[2023-02-24 17:11:15,525][2343698] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:11:15,525][2343698] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2023-02-24 17:11:15,524][2343622] Starting process rollout_proc1
[2023-02-24 17:11:15,527][2343622] Starting process rollout_proc2
[2023-02-24 17:11:15,530][2343622] Starting process rollout_proc3
[2023-02-24 17:11:15,530][2343622] Starting process rollout_proc4
[2023-02-24 17:11:15,532][2343622] Starting process rollout_proc5
[2023-02-24 17:11:15,533][2343622] Starting process rollout_proc6
[2023-02-24 17:11:15,533][2343622] Starting process rollout_proc7
[2023-02-24 17:11:15,542][2343698] Num visible devices: 1
[2023-02-24 17:11:15,559][2343698] Starting seed is not provided
[2023-02-24 17:11:15,559][2343698] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:11:15,559][2343698] Initializing actor-critic model on device cuda:0
[2023-02-24 17:11:15,559][2343698] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 17:11:15,560][2343698] RunningMeanStd input shape: (1,)
[2023-02-24 17:11:15,571][2343698] ConvEncoder: input_channels=3
[2023-02-24 17:11:15,751][2343698] Conv encoder output size: 512
[2023-02-24 17:11:15,751][2343698] Policy head output size: 512
[2023-02-24 17:11:15,766][2343698] Created Actor Critic model with architecture:
[2023-02-24 17:11:15,766][2343698] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2023-02-24 17:11:16,608][2343747] Worker 7 uses CPU cores [14, 15]
[2023-02-24 17:11:16,626][2343746] Worker 4 uses CPU cores [8, 9]
[2023-02-24 17:11:16,638][2343750] Worker 3 uses CPU cores [6, 7]
[2023-02-24 17:11:16,640][2343744] Worker 1 uses CPU cores [2, 3]
[2023-02-24 17:11:16,669][2343745] Worker 2 uses CPU cores [4, 5]
[2023-02-24 17:11:16,708][2343749] Worker 5 uses CPU cores [10, 11]
[2023-02-24 17:11:16,715][2343726] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:11:16,715][2343726] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2023-02-24 17:11:16,730][2343726] Num visible devices: 1
[2023-02-24 17:11:16,758][2343748] Worker 6 uses CPU cores [12, 13]
[2023-02-24 17:11:16,825][2343743] Worker 0 uses CPU cores [0, 1]
[2023-02-24 17:11:17,546][2343698] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-24 17:11:17,547][2343698] No checkpoints found
[2023-02-24 17:11:17,547][2343698] Did not load from checkpoint, starting from scratch!
[2023-02-24 17:11:17,547][2343698] Initialized policy 0 weights for model version 0
[2023-02-24 17:11:17,548][2343698] LearnerWorker_p0 finished initialization!
[2023-02-24 17:11:17,548][2343698] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:11:17,640][2343726] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 17:11:17,641][2343726] RunningMeanStd input shape: (1,)
[2023-02-24 17:11:17,648][2343726] ConvEncoder: input_channels=3
[2023-02-24 17:11:17,708][2343726] Conv encoder output size: 512
[2023-02-24 17:11:17,708][2343726] Policy head output size: 512
[2023-02-24 17:11:18,236][2343622] 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)
[2023-02-24 17:11:18,948][2343622] Inference worker 0-0 is ready!
[2023-02-24 17:11:18,948][2343622] All inference workers are ready! Signal rollout workers to start!
[2023-02-24 17:11:18,961][2343745] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:11:18,961][2343746] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:11:18,961][2343743] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:11:18,961][2343749] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:11:18,966][2343748] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:11:18,966][2343744] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:11:18,975][2343747] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:11:18,977][2343750] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:11:19,171][2343744] Decorrelating experience for 0 frames...
[2023-02-24 17:11:19,174][2343746] Decorrelating experience for 0 frames...
[2023-02-24 17:11:19,174][2343743] Decorrelating experience for 0 frames...
[2023-02-24 17:11:19,243][2343745] Decorrelating experience for 0 frames...
[2023-02-24 17:11:19,245][2343748] Decorrelating experience for 0 frames...
[2023-02-24 17:11:19,356][2343746] Decorrelating experience for 32 frames...
[2023-02-24 17:11:19,359][2343744] Decorrelating experience for 32 frames...
[2023-02-24 17:11:19,427][2343748] Decorrelating experience for 32 frames...
[2023-02-24 17:11:19,496][2343749] Decorrelating experience for 0 frames...
[2023-02-24 17:11:19,561][2343743] Decorrelating experience for 32 frames...
[2023-02-24 17:11:19,635][2343748] Decorrelating experience for 64 frames...
[2023-02-24 17:11:19,702][2343744] Decorrelating experience for 64 frames...
[2023-02-24 17:11:19,725][2343750] Decorrelating experience for 0 frames...
[2023-02-24 17:11:19,763][2343749] Decorrelating experience for 32 frames...
[2023-02-24 17:11:19,803][2343746] Decorrelating experience for 64 frames...
[2023-02-24 17:11:19,804][2343743] Decorrelating experience for 64 frames...
[2023-02-24 17:11:19,893][2343748] Decorrelating experience for 96 frames...
[2023-02-24 17:11:19,916][2343750] Decorrelating experience for 32 frames...
[2023-02-24 17:11:19,952][2343744] Decorrelating experience for 96 frames...
[2023-02-24 17:11:20,019][2343746] Decorrelating experience for 96 frames...
[2023-02-24 17:11:20,028][2343749] Decorrelating experience for 64 frames...
[2023-02-24 17:11:20,101][2343747] Decorrelating experience for 0 frames...
[2023-02-24 17:11:20,240][2343749] Decorrelating experience for 96 frames...
[2023-02-24 17:11:20,241][2343745] Decorrelating experience for 32 frames...
[2023-02-24 17:11:20,296][2343750] Decorrelating experience for 64 frames...
[2023-02-24 17:11:20,325][2343743] Decorrelating experience for 96 frames...
[2023-02-24 17:11:20,369][2343747] Decorrelating experience for 32 frames...
[2023-02-24 17:11:20,471][2343745] Decorrelating experience for 64 frames...
[2023-02-24 17:11:20,530][2343750] Decorrelating experience for 96 frames...
[2023-02-24 17:11:20,679][2343747] Decorrelating experience for 64 frames...
[2023-02-24 17:11:20,777][2343745] Decorrelating experience for 96 frames...
[2023-02-24 17:11:20,815][2343698] Signal inference workers to stop experience collection...
[2023-02-24 17:11:20,819][2343726] InferenceWorker_p0-w0: stopping experience collection
[2023-02-24 17:11:20,912][2343747] Decorrelating experience for 96 frames...
[2023-02-24 17:11:21,610][2343698] Signal inference workers to resume experience collection...
[2023-02-24 17:11:21,610][2343726] InferenceWorker_p0-w0: resuming experience collection
[2023-02-24 17:11:23,236][2343622] Fps is (10 sec: 7372.6, 60 sec: 7372.6, 300 sec: 7372.6). Total num frames: 36864. Throughput: 0: 626.0. Samples: 3130. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-02-24 17:11:23,242][2343622] Avg episode reward: [(0, '4.086')]
[2023-02-24 17:11:23,269][2343726] Updated weights for policy 0, policy_version 10 (0.0231)
[2023-02-24 17:11:24,717][2343726] Updated weights for policy 0, policy_version 20 (0.0007)
[2023-02-24 17:11:26,117][2343726] Updated weights for policy 0, policy_version 30 (0.0007)
[2023-02-24 17:11:27,512][2343726] Updated weights for policy 0, policy_version 40 (0.0007)
[2023-02-24 17:11:28,236][2343622] Fps is (10 sec: 18431.9, 60 sec: 18431.9, 300 sec: 18431.9). Total num frames: 184320. Throughput: 0: 4463.4. Samples: 44634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 17:11:28,242][2343622] Avg episode reward: [(0, '4.252')]
[2023-02-24 17:11:28,243][2343698] Saving new best policy, reward=4.252!
[2023-02-24 17:11:28,928][2343726] Updated weights for policy 0, policy_version 50 (0.0007)
[2023-02-24 17:11:30,360][2343726] Updated weights for policy 0, policy_version 60 (0.0006)
[2023-02-24 17:11:31,782][2343726] Updated weights for policy 0, policy_version 70 (0.0007)
[2023-02-24 17:11:33,190][2343726] Updated weights for policy 0, policy_version 80 (0.0007)
[2023-02-24 17:11:33,236][2343622] Fps is (10 sec: 29081.8, 60 sec: 21845.2, 300 sec: 21845.2). Total num frames: 327680. Throughput: 0: 4426.8. Samples: 66402. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 17:11:33,244][2343622] Avg episode reward: [(0, '4.526')]
[2023-02-24 17:11:33,247][2343698] Saving new best policy, reward=4.526!
[2023-02-24 17:11:34,623][2343726] Updated weights for policy 0, policy_version 90 (0.0007)
[2023-02-24 17:11:34,792][2343622] Heartbeat connected on Batcher_0
[2023-02-24 17:11:34,794][2343622] Heartbeat connected on LearnerWorker_p0
[2023-02-24 17:11:34,800][2343622] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-24 17:11:34,801][2343622] Heartbeat connected on RolloutWorker_w0
[2023-02-24 17:11:34,802][2343622] Heartbeat connected on RolloutWorker_w1
[2023-02-24 17:11:34,807][2343622] Heartbeat connected on RolloutWorker_w3
[2023-02-24 17:11:34,808][2343622] Heartbeat connected on RolloutWorker_w2
[2023-02-24 17:11:34,809][2343622] Heartbeat connected on RolloutWorker_w4
[2023-02-24 17:11:34,810][2343622] Heartbeat connected on RolloutWorker_w5
[2023-02-24 17:11:34,813][2343622] Heartbeat connected on RolloutWorker_w6
[2023-02-24 17:11:34,816][2343622] Heartbeat connected on RolloutWorker_w7
[2023-02-24 17:11:36,090][2343726] Updated weights for policy 0, policy_version 100 (0.0007)
[2023-02-24 17:11:37,537][2343726] Updated weights for policy 0, policy_version 110 (0.0007)
[2023-02-24 17:11:38,236][2343622] Fps is (10 sec: 28262.5, 60 sec: 23347.2, 300 sec: 23347.2). Total num frames: 466944. Throughput: 0: 5462.9. Samples: 109258. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:11:38,246][2343622] Avg episode reward: [(0, '4.374')]
[2023-02-24 17:11:38,984][2343726] Updated weights for policy 0, policy_version 120 (0.0007)
[2023-02-24 17:11:40,452][2343726] Updated weights for policy 0, policy_version 130 (0.0007)
[2023-02-24 17:11:41,886][2343726] Updated weights for policy 0, policy_version 140 (0.0007)
[2023-02-24 17:11:43,236][2343622] Fps is (10 sec: 28262.5, 60 sec: 24412.1, 300 sec: 24412.1). Total num frames: 610304. Throughput: 0: 6064.6. Samples: 151616. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:11:43,248][2343622] Avg episode reward: [(0, '4.299')]
[2023-02-24 17:11:43,339][2343726] Updated weights for policy 0, policy_version 150 (0.0007)
[2023-02-24 17:11:44,774][2343726] Updated weights for policy 0, policy_version 160 (0.0007)
[2023-02-24 17:11:46,247][2343726] Updated weights for policy 0, policy_version 170 (0.0007)
[2023-02-24 17:11:47,693][2343726] Updated weights for policy 0, policy_version 180 (0.0007)
[2023-02-24 17:11:48,236][2343622] Fps is (10 sec: 28262.2, 60 sec: 24985.5, 300 sec: 24985.5). Total num frames: 749568. Throughput: 0: 5760.8. Samples: 172826. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 17:11:48,236][2343622] Avg episode reward: [(0, '4.570')]
[2023-02-24 17:11:48,259][2343698] Saving new best policy, reward=4.570!
[2023-02-24 17:11:49,140][2343726] Updated weights for policy 0, policy_version 190 (0.0008)
[2023-02-24 17:11:50,563][2343726] Updated weights for policy 0, policy_version 200 (0.0007)
[2023-02-24 17:11:52,015][2343726] Updated weights for policy 0, policy_version 210 (0.0007)
[2023-02-24 17:11:53,236][2343622] Fps is (10 sec: 28262.4, 60 sec: 25512.2, 300 sec: 25512.2). Total num frames: 892928. Throughput: 0: 6152.8. Samples: 215350. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 17:11:53,238][2343622] Avg episode reward: [(0, '4.848')]
[2023-02-24 17:11:53,242][2343698] Saving new best policy, reward=4.848!
[2023-02-24 17:11:53,484][2343726] Updated weights for policy 0, policy_version 220 (0.0007)
[2023-02-24 17:11:54,907][2343726] Updated weights for policy 0, policy_version 230 (0.0007)
[2023-02-24 17:11:56,319][2343726] Updated weights for policy 0, policy_version 240 (0.0007)
[2023-02-24 17:11:57,782][2343726] Updated weights for policy 0, policy_version 250 (0.0006)
[2023-02-24 17:11:58,236][2343622] Fps is (10 sec: 28672.2, 60 sec: 25907.2, 300 sec: 25907.2). Total num frames: 1036288. Throughput: 0: 6446.3. Samples: 257854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 17:11:58,236][2343622] Avg episode reward: [(0, '4.846')]
[2023-02-24 17:11:59,235][2343726] Updated weights for policy 0, policy_version 260 (0.0007)
[2023-02-24 17:12:00,862][2343726] Updated weights for policy 0, policy_version 270 (0.0008)
[2023-02-24 17:12:02,356][2343726] Updated weights for policy 0, policy_version 280 (0.0007)
[2023-02-24 17:12:03,236][2343622] Fps is (10 sec: 27853.0, 60 sec: 26032.4, 300 sec: 26032.4). Total num frames: 1171456. Throughput: 0: 6174.2. Samples: 277840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 17:12:03,236][2343622] Avg episode reward: [(0, '4.947')]
[2023-02-24 17:12:03,239][2343698] Saving new best policy, reward=4.947!
[2023-02-24 17:12:03,847][2343726] Updated weights for policy 0, policy_version 290 (0.0008)
[2023-02-24 17:12:05,268][2343726] Updated weights for policy 0, policy_version 300 (0.0007)
[2023-02-24 17:12:06,687][2343726] Updated weights for policy 0, policy_version 310 (0.0006)
[2023-02-24 17:12:08,150][2343726] Updated weights for policy 0, policy_version 320 (0.0007)
[2023-02-24 17:12:08,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 26214.4, 300 sec: 26214.4). Total num frames: 1310720. Throughput: 0: 7043.1. Samples: 320070. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:12:08,236][2343622] Avg episode reward: [(0, '6.912')]
[2023-02-24 17:12:08,236][2343698] Saving new best policy, reward=6.912!
[2023-02-24 17:12:09,606][2343726] Updated weights for policy 0, policy_version 330 (0.0008)
[2023-02-24 17:12:11,175][2343726] Updated weights for policy 0, policy_version 340 (0.0007)
[2023-02-24 17:12:12,639][2343726] Updated weights for policy 0, policy_version 350 (0.0007)
[2023-02-24 17:12:13,236][2343622] Fps is (10 sec: 27443.0, 60 sec: 26288.8, 300 sec: 26288.8). Total num frames: 1445888. Throughput: 0: 7036.6. Samples: 361282. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 17:12:13,236][2343622] Avg episode reward: [(0, '8.564')]
[2023-02-24 17:12:13,242][2343698] Saving new best policy, reward=8.564!
[2023-02-24 17:12:14,109][2343726] Updated weights for policy 0, policy_version 360 (0.0007)
[2023-02-24 17:12:15,599][2343726] Updated weights for policy 0, policy_version 370 (0.0007)
[2023-02-24 17:12:17,098][2343726] Updated weights for policy 0, policy_version 380 (0.0007)
[2023-02-24 17:12:18,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 26419.2, 300 sec: 26419.2). Total num frames: 1585152. Throughput: 0: 7014.2. Samples: 382040. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 17:12:18,236][2343622] Avg episode reward: [(0, '8.241')]
[2023-02-24 17:12:18,592][2343726] Updated weights for policy 0, policy_version 390 (0.0008)
[2023-02-24 17:12:20,082][2343726] Updated weights for policy 0, policy_version 400 (0.0007)
[2023-02-24 17:12:21,524][2343726] Updated weights for policy 0, policy_version 410 (0.0007)
[2023-02-24 17:12:22,983][2343726] Updated weights for policy 0, policy_version 420 (0.0007)
[2023-02-24 17:12:23,236][2343622] Fps is (10 sec: 27852.9, 60 sec: 28125.9, 300 sec: 26529.5). Total num frames: 1724416. Throughput: 0: 6984.0. Samples: 423538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 17:12:23,236][2343622] Avg episode reward: [(0, '10.228')]
[2023-02-24 17:12:23,263][2343698] Saving new best policy, reward=10.228!
[2023-02-24 17:12:24,436][2343726] Updated weights for policy 0, policy_version 430 (0.0007)
[2023-02-24 17:12:25,914][2343726] Updated weights for policy 0, policy_version 440 (0.0007)
[2023-02-24 17:12:27,379][2343726] Updated weights for policy 0, policy_version 450 (0.0007)
[2023-02-24 17:12:28,236][2343622] Fps is (10 sec: 27852.7, 60 sec: 27989.3, 300 sec: 26624.0). Total num frames: 1863680. Throughput: 0: 6975.6. Samples: 465520. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 17:12:28,236][2343622] Avg episode reward: [(0, '12.021')]
[2023-02-24 17:12:28,264][2343698] Saving new best policy, reward=12.021!
[2023-02-24 17:12:28,842][2343726] Updated weights for policy 0, policy_version 460 (0.0007)
[2023-02-24 17:12:30,319][2343726] Updated weights for policy 0, policy_version 470 (0.0007)
[2023-02-24 17:12:31,757][2343726] Updated weights for policy 0, policy_version 480 (0.0007)
[2023-02-24 17:12:33,211][2343726] Updated weights for policy 0, policy_version 490 (0.0007)
[2023-02-24 17:12:33,236][2343622] Fps is (10 sec: 28262.3, 60 sec: 27989.3, 300 sec: 26760.5). Total num frames: 2007040. Throughput: 0: 6972.7. Samples: 486596. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:12:33,236][2343622] Avg episode reward: [(0, '14.858')]
[2023-02-24 17:12:33,239][2343698] Saving new best policy, reward=14.858!
[2023-02-24 17:12:34,673][2343726] Updated weights for policy 0, policy_version 500 (0.0007)
[2023-02-24 17:12:36,167][2343726] Updated weights for policy 0, policy_version 510 (0.0007)
[2023-02-24 17:12:37,680][2343726] Updated weights for policy 0, policy_version 520 (0.0007)
[2023-02-24 17:12:38,236][2343622] Fps is (10 sec: 27852.8, 60 sec: 27921.0, 300 sec: 26777.6). Total num frames: 2142208. Throughput: 0: 6958.1. Samples: 528464. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 17:12:38,236][2343622] Avg episode reward: [(0, '13.124')]
[2023-02-24 17:12:39,147][2343726] Updated weights for policy 0, policy_version 530 (0.0007)
[2023-02-24 17:12:40,649][2343726] Updated weights for policy 0, policy_version 540 (0.0008)
[2023-02-24 17:12:42,118][2343726] Updated weights for policy 0, policy_version 550 (0.0007)
[2023-02-24 17:12:43,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 27852.8, 300 sec: 26840.8). Total num frames: 2281472. Throughput: 0: 6928.3. Samples: 569626. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:12:43,236][2343622] Avg episode reward: [(0, '14.789')]
[2023-02-24 17:12:43,605][2343726] Updated weights for policy 0, policy_version 560 (0.0007)
[2023-02-24 17:12:45,110][2343726] Updated weights for policy 0, policy_version 570 (0.0006)
[2023-02-24 17:12:46,567][2343726] Updated weights for policy 0, policy_version 580 (0.0007)
[2023-02-24 17:12:48,043][2343726] Updated weights for policy 0, policy_version 590 (0.0007)
[2023-02-24 17:12:48,236][2343622] Fps is (10 sec: 27853.0, 60 sec: 27852.8, 300 sec: 26897.1). Total num frames: 2420736. Throughput: 0: 6946.0. Samples: 590410. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 17:12:48,236][2343622] Avg episode reward: [(0, '19.318')]
[2023-02-24 17:12:48,236][2343698] Saving new best policy, reward=19.318!
[2023-02-24 17:12:49,544][2343726] Updated weights for policy 0, policy_version 600 (0.0006)
[2023-02-24 17:12:50,998][2343726] Updated weights for policy 0, policy_version 610 (0.0007)
[2023-02-24 17:12:52,482][2343726] Updated weights for policy 0, policy_version 620 (0.0006)
[2023-02-24 17:12:53,236][2343622] Fps is (10 sec: 27852.8, 60 sec: 27784.5, 300 sec: 26947.4). Total num frames: 2560000. Throughput: 0: 6928.7. Samples: 631860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 17:12:53,236][2343622] Avg episode reward: [(0, '16.987')]
[2023-02-24 17:12:53,955][2343726] Updated weights for policy 0, policy_version 630 (0.0007)
[2023-02-24 17:12:55,438][2343726] Updated weights for policy 0, policy_version 640 (0.0007)
[2023-02-24 17:12:56,905][2343726] Updated weights for policy 0, policy_version 650 (0.0007)
[2023-02-24 17:12:58,236][2343622] Fps is (10 sec: 27852.8, 60 sec: 27716.3, 300 sec: 26992.6). Total num frames: 2699264. Throughput: 0: 6940.9. Samples: 673620. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:12:58,236][2343622] Avg episode reward: [(0, '17.090')]
[2023-02-24 17:12:58,372][2343726] Updated weights for policy 0, policy_version 660 (0.0007)
[2023-02-24 17:12:59,889][2343726] Updated weights for policy 0, policy_version 670 (0.0008)
[2023-02-24 17:13:01,368][2343726] Updated weights for policy 0, policy_version 680 (0.0007)
[2023-02-24 17:13:02,828][2343726] Updated weights for policy 0, policy_version 690 (0.0007)
[2023-02-24 17:13:03,236][2343622] Fps is (10 sec: 27443.1, 60 sec: 27716.2, 300 sec: 26994.6). Total num frames: 2834432. Throughput: 0: 6933.1. Samples: 694028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 17:13:03,236][2343622] Avg episode reward: [(0, '22.089')]
[2023-02-24 17:13:03,240][2343698] Saving new best policy, reward=22.089!
[2023-02-24 17:13:04,318][2343726] Updated weights for policy 0, policy_version 700 (0.0008)
[2023-02-24 17:13:05,824][2343726] Updated weights for policy 0, policy_version 710 (0.0008)
[2023-02-24 17:13:07,331][2343726] Updated weights for policy 0, policy_version 720 (0.0008)
[2023-02-24 17:13:08,236][2343622] Fps is (10 sec: 27443.1, 60 sec: 27716.3, 300 sec: 27033.6). Total num frames: 2973696. Throughput: 0: 6930.7. Samples: 735420. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:13:08,236][2343622] Avg episode reward: [(0, '19.494')]
[2023-02-24 17:13:08,793][2343726] Updated weights for policy 0, policy_version 730 (0.0007)
[2023-02-24 17:13:10,279][2343726] Updated weights for policy 0, policy_version 740 (0.0007)
[2023-02-24 17:13:11,813][2343726] Updated weights for policy 0, policy_version 750 (0.0007)
[2023-02-24 17:13:13,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 27716.3, 300 sec: 27033.6). Total num frames: 3108864. Throughput: 0: 6916.3. Samples: 776754. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:13:13,236][2343622] Avg episode reward: [(0, '20.543')]
[2023-02-24 17:13:13,240][2343698] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000759_3108864.pth...
[2023-02-24 17:13:13,329][2343726] Updated weights for policy 0, policy_version 760 (0.0008)
[2023-02-24 17:13:14,774][2343726] Updated weights for policy 0, policy_version 770 (0.0006)
[2023-02-24 17:13:16,248][2343726] Updated weights for policy 0, policy_version 780 (0.0008)
[2023-02-24 17:13:17,761][2343726] Updated weights for policy 0, policy_version 790 (0.0007)
[2023-02-24 17:13:18,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 27716.3, 300 sec: 27067.7). Total num frames: 3248128. Throughput: 0: 6906.6. Samples: 797394. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 17:13:18,236][2343622] Avg episode reward: [(0, '21.927')]
[2023-02-24 17:13:19,279][2343726] Updated weights for policy 0, policy_version 800 (0.0007)
[2023-02-24 17:13:20,759][2343726] Updated weights for policy 0, policy_version 810 (0.0007)
[2023-02-24 17:13:22,276][2343726] Updated weights for policy 0, policy_version 820 (0.0007)
[2023-02-24 17:13:23,236][2343622] Fps is (10 sec: 27443.3, 60 sec: 27648.0, 300 sec: 27066.4). Total num frames: 3383296. Throughput: 0: 6885.7. Samples: 838322. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 17:13:23,236][2343622] Avg episode reward: [(0, '22.487')]
[2023-02-24 17:13:23,239][2343698] Saving new best policy, reward=22.487!
[2023-02-24 17:13:23,768][2343726] Updated weights for policy 0, policy_version 830 (0.0007)
[2023-02-24 17:13:25,246][2343726] Updated weights for policy 0, policy_version 840 (0.0007)
[2023-02-24 17:13:26,742][2343726] Updated weights for policy 0, policy_version 850 (0.0007)
[2023-02-24 17:13:28,236][2343622] Fps is (10 sec: 27034.0, 60 sec: 27579.8, 300 sec: 27065.1). Total num frames: 3518464. Throughput: 0: 6883.4. Samples: 879380. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 17:13:28,236][2343622] Avg episode reward: [(0, '22.399')]
[2023-02-24 17:13:28,237][2343726] Updated weights for policy 0, policy_version 860 (0.0007)
[2023-02-24 17:13:29,767][2343726] Updated weights for policy 0, policy_version 870 (0.0007)
[2023-02-24 17:13:31,283][2343726] Updated weights for policy 0, policy_version 880 (0.0007)
[2023-02-24 17:13:32,771][2343726] Updated weights for policy 0, policy_version 890 (0.0007)
[2023-02-24 17:13:33,236][2343622] Fps is (10 sec: 27443.3, 60 sec: 27511.5, 300 sec: 27094.3). Total num frames: 3657728. Throughput: 0: 6874.0. Samples: 899738. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:13:33,236][2343622] Avg episode reward: [(0, '24.897')]
[2023-02-24 17:13:33,239][2343698] Saving new best policy, reward=24.897!
[2023-02-24 17:13:34,270][2343726] Updated weights for policy 0, policy_version 900 (0.0007)
[2023-02-24 17:13:35,771][2343726] Updated weights for policy 0, policy_version 910 (0.0007)
[2023-02-24 17:13:37,284][2343726] Updated weights for policy 0, policy_version 920 (0.0007)
[2023-02-24 17:13:38,236][2343622] Fps is (10 sec: 27442.9, 60 sec: 27511.5, 300 sec: 27092.1). Total num frames: 3792896. Throughput: 0: 6862.1. Samples: 940656. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 17:13:38,236][2343622] Avg episode reward: [(0, '22.457')]
[2023-02-24 17:13:38,783][2343726] Updated weights for policy 0, policy_version 930 (0.0007)
[2023-02-24 17:13:40,263][2343726] Updated weights for policy 0, policy_version 940 (0.0007)
[2023-02-24 17:13:41,748][2343726] Updated weights for policy 0, policy_version 950 (0.0007)
[2023-02-24 17:13:43,236][2343622] Fps is (10 sec: 27033.6, 60 sec: 27443.2, 300 sec: 27090.1). Total num frames: 3928064. Throughput: 0: 6847.8. Samples: 981770. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 17:13:43,236][2343622] Avg episode reward: [(0, '21.833')]
[2023-02-24 17:13:43,244][2343726] Updated weights for policy 0, policy_version 960 (0.0008)
[2023-02-24 17:13:44,723][2343726] Updated weights for policy 0, policy_version 970 (0.0007)
[2023-02-24 17:13:45,940][2343698] Stopping Batcher_0...
[2023-02-24 17:13:45,941][2343698] Loop batcher_evt_loop terminating...
[2023-02-24 17:13:45,941][2343698] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-24 17:13:45,945][2343622] Component Batcher_0 stopped!
[2023-02-24 17:13:45,949][2343744] Stopping RolloutWorker_w1...
[2023-02-24 17:13:45,949][2343745] Stopping RolloutWorker_w2...
[2023-02-24 17:13:45,949][2343622] Component RolloutWorker_w2 stopped!
[2023-02-24 17:13:45,949][2343622] Component RolloutWorker_w1 stopped!
[2023-02-24 17:13:45,949][2343744] Loop rollout_proc1_evt_loop terminating...
[2023-02-24 17:13:45,949][2343746] Stopping RolloutWorker_w4...
[2023-02-24 17:13:45,949][2343750] Stopping RolloutWorker_w3...
[2023-02-24 17:13:45,949][2343745] Loop rollout_proc2_evt_loop terminating...
[2023-02-24 17:13:45,949][2343749] Stopping RolloutWorker_w5...
[2023-02-24 17:13:45,950][2343622] Component RolloutWorker_w4 stopped!
[2023-02-24 17:13:45,950][2343746] Loop rollout_proc4_evt_loop terminating...
[2023-02-24 17:13:45,950][2343622] Component RolloutWorker_w3 stopped!
[2023-02-24 17:13:45,950][2343749] Loop rollout_proc5_evt_loop terminating...
[2023-02-24 17:13:45,950][2343750] Loop rollout_proc3_evt_loop terminating...
[2023-02-24 17:13:45,950][2343622] Component RolloutWorker_w5 stopped!
[2023-02-24 17:13:45,950][2343743] Stopping RolloutWorker_w0...
[2023-02-24 17:13:45,950][2343622] Component RolloutWorker_w0 stopped!
[2023-02-24 17:13:45,950][2343743] Loop rollout_proc0_evt_loop terminating...
[2023-02-24 17:13:45,953][2343622] Component RolloutWorker_w7 stopped!
[2023-02-24 17:13:45,953][2343747] Stopping RolloutWorker_w7...
[2023-02-24 17:13:45,953][2343747] Loop rollout_proc7_evt_loop terminating...
[2023-02-24 17:13:45,955][2343726] Weights refcount: 2 0
[2023-02-24 17:13:45,955][2343726] Stopping InferenceWorker_p0-w0...
[2023-02-24 17:13:45,956][2343622] Component InferenceWorker_p0-w0 stopped!
[2023-02-24 17:13:45,956][2343726] Loop inference_proc0-0_evt_loop terminating...
[2023-02-24 17:13:46,004][2343748] Stopping RolloutWorker_w6...
[2023-02-24 17:13:46,005][2343622] Component RolloutWorker_w6 stopped!
[2023-02-24 17:13:46,005][2343748] Loop rollout_proc6_evt_loop terminating...
[2023-02-24 17:13:46,008][2343698] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-24 17:13:46,105][2343698] Stopping LearnerWorker_p0...
[2023-02-24 17:13:46,105][2343622] Component LearnerWorker_p0 stopped!
[2023-02-24 17:13:46,106][2343698] Loop learner_proc0_evt_loop terminating...
[2023-02-24 17:13:46,106][2343622] Waiting for process learner_proc0 to stop...
[2023-02-24 17:13:46,712][2343622] Waiting for process inference_proc0-0 to join...
[2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc0 to join...
[2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc1 to join...
[2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc2 to join...
[2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc3 to join...
[2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc4 to join...
[2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc5 to join...
[2023-02-24 17:13:46,713][2343622] Waiting for process rollout_proc6 to join...
[2023-02-24 17:13:46,713][2343622] Waiting for process rollout_proc7 to join...
[2023-02-24 17:13:46,713][2343622] Batcher 0 profile tree view:
batching: 11.9572, releasing_batches: 0.0124
[2023-02-24 17:13:46,713][2343622] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0000
  wait_policy_total: 2.9043
update_model: 2.1825
  weight_update: 0.0007
one_step: 0.0019
  handle_policy_step: 133.4731
    deserialize: 6.2447, stack: 0.7828, obs_to_device_normalize: 34.7488, forward: 55.1577, send_messages: 9.6852
    prepare_outputs: 21.4301
      to_cpu: 14.6154
[2023-02-24 17:13:46,714][2343622] Learner 0 profile tree view:
misc: 0.0029, prepare_batch: 6.2234
train: 18.9230
  epoch_init: 0.0032, minibatch_init: 0.0035, losses_postprocess: 0.3250, kl_divergence: 0.1740, after_optimizer: 6.1827
  calculate_losses: 6.6723
    losses_init: 0.0020, forward_head: 0.5088, bptt_initial: 4.1259, tail: 0.3587, advantages_returns: 0.1020, losses: 0.7122
    bptt: 0.7553
      bptt_forward_core: 0.7253
  update: 5.3342
    clip: 0.8350
[2023-02-24 17:13:46,714][2343622] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.1049, enqueue_policy_requests: 5.6350, env_step: 81.8998, overhead: 6.8628, complete_rollouts: 0.1662
save_policy_outputs: 6.0304
  split_output_tensors: 2.8870
[2023-02-24 17:13:46,714][2343622] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.1033, enqueue_policy_requests: 5.6327, env_step: 82.5081, overhead: 7.0028, complete_rollouts: 0.1684
save_policy_outputs: 6.1360
  split_output_tensors: 2.9393
[2023-02-24 17:13:46,714][2343622] Loop Runner_EvtLoop terminating...
[2023-02-24 17:13:46,714][2343622] Runner profile tree view:
main_loop: 151.8999
[2023-02-24 17:13:46,715][2343622] Collected {0: 4005888}, FPS: 26371.9
[2023-02-24 17:32:32,877][2364708] Saving configuration to /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/config.json...
[2023-02-24 17:32:32,878][2364708] Rollout worker 0 uses device cpu
[2023-02-24 17:32:32,878][2364708] Rollout worker 1 uses device cpu
[2023-02-24 17:32:32,878][2364708] Rollout worker 2 uses device cpu
[2023-02-24 17:32:32,878][2364708] Rollout worker 3 uses device cpu
[2023-02-24 17:32:32,878][2364708] Rollout worker 4 uses device cpu
[2023-02-24 17:32:32,879][2364708] Rollout worker 5 uses device cpu
[2023-02-24 17:32:32,879][2364708] Rollout worker 6 uses device cpu
[2023-02-24 17:32:32,879][2364708] Rollout worker 7 uses device cpu
[2023-02-24 17:32:32,879][2364708] Rollout worker 8 uses device cpu
[2023-02-24 17:32:32,879][2364708] Rollout worker 9 uses device cpu
[2023-02-24 17:32:32,879][2364708] Rollout worker 10 uses device cpu
[2023-02-24 17:32:32,879][2364708] Rollout worker 11 uses device cpu
[2023-02-24 17:32:32,879][2364708] Rollout worker 12 uses device cpu
[2023-02-24 17:32:32,880][2364708] Rollout worker 13 uses device cpu
[2023-02-24 17:32:32,880][2364708] Rollout worker 14 uses device cpu
[2023-02-24 17:32:32,880][2364708] Rollout worker 15 uses device cpu
[2023-02-24 17:32:32,936][2364708] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:32:32,936][2364708] InferenceWorker_p0-w0: min num requests: 5
[2023-02-24 17:32:32,970][2364708] Starting all processes...
[2023-02-24 17:32:32,970][2364708] Starting process learner_proc0
[2023-02-24 17:32:33,717][2364708] Starting all processes...
[2023-02-24 17:32:33,721][2364708] Starting process inference_proc0-0
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc0
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc1
[2023-02-24 17:32:33,722][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:32:33,722][2364791] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc2
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc3
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc4
[2023-02-24 17:32:33,722][2364708] Starting process rollout_proc5
[2023-02-24 17:32:33,722][2364708] Starting process rollout_proc6
[2023-02-24 17:32:33,723][2364708] Starting process rollout_proc7
[2023-02-24 17:32:33,726][2364708] Starting process rollout_proc8
[2023-02-24 17:32:33,727][2364708] Starting process rollout_proc9
[2023-02-24 17:32:33,739][2364791] Num visible devices: 1
[2023-02-24 17:32:33,728][2364708] Starting process rollout_proc10
[2023-02-24 17:32:33,729][2364708] Starting process rollout_proc11
[2023-02-24 17:32:33,729][2364708] Starting process rollout_proc12
[2023-02-24 17:32:33,729][2364708] Starting process rollout_proc13
[2023-02-24 17:32:33,796][2364791] Starting seed is not provided
[2023-02-24 17:32:33,796][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:32:33,797][2364791] Initializing actor-critic model on device cuda:0
[2023-02-24 17:32:33,797][2364791] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 17:32:33,798][2364791] RunningMeanStd input shape: (1,)
[2023-02-24 17:32:33,730][2364708] Starting process rollout_proc14
[2023-02-24 17:32:33,813][2364791] ConvEncoder: input_channels=3
[2023-02-24 17:32:34,006][2364791] Conv encoder output size: 512
[2023-02-24 17:32:34,023][2364791] Policy head output size: 512
[2023-02-24 17:32:34,038][2364791] Created Actor Critic model with architecture:
[2023-02-24 17:32:34,050][2364791] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2023-02-24 17:32:35,405][2364708] Starting process rollout_proc15
[2023-02-24 17:32:35,416][2364834] Worker 2 uses CPU cores [2]
[2023-02-24 17:32:35,418][2364833] Worker 1 uses CPU cores [1]
[2023-02-24 17:32:35,490][2364839] Worker 7 uses CPU cores [7]
[2023-02-24 17:32:35,500][2364855] Worker 10 uses CPU cores [10]
[2023-02-24 17:32:35,502][2364832] Worker 0 uses CPU cores [0]
[2023-02-24 17:32:35,502][2364831] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:32:35,503][2364831] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2023-02-24 17:32:35,518][2364838] Worker 6 uses CPU cores [6]
[2023-02-24 17:32:35,519][2364831] Num visible devices: 1
[2023-02-24 17:32:35,530][2364862] Worker 14 uses CPU cores [14]
[2023-02-24 17:32:35,534][2364860] Worker 12 uses CPU cores [12]
[2023-02-24 17:32:35,554][2364835] Worker 4 uses CPU cores [4]
[2023-02-24 17:32:35,573][2364861] Worker 13 uses CPU cores [13]
[2023-02-24 17:32:35,598][2364859] Worker 8 uses CPU cores [8]
[2023-02-24 17:32:35,642][2364836] Worker 3 uses CPU cores [3]
[2023-02-24 17:32:35,643][2364837] Worker 5 uses CPU cores [5]
[2023-02-24 17:32:35,661][2364856] Worker 9 uses CPU cores [9]
[2023-02-24 17:32:35,712][2364857] Worker 11 uses CPU cores [11]
[2023-02-24 17:32:36,334][2365108] Worker 15 uses CPU cores [15]
[2023-02-24 17:32:36,424][2364791] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-24 17:32:36,424][2364791] Loading state from checkpoint /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-24 17:32:36,444][2364791] Loading model from checkpoint
[2023-02-24 17:32:36,447][2364791] Loaded experiment state at self.train_step=978, self.env_steps=4005888
[2023-02-24 17:32:36,447][2364791] Initialized policy 0 weights for model version 978
[2023-02-24 17:32:36,449][2364791] LearnerWorker_p0 finished initialization!
[2023-02-24 17:32:36,449][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 17:32:36,525][2364831] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 17:32:36,525][2364831] RunningMeanStd input shape: (1,)
[2023-02-24 17:32:36,532][2364831] ConvEncoder: input_channels=3
[2023-02-24 17:32:36,595][2364831] Conv encoder output size: 512
[2023-02-24 17:32:36,595][2364831] Policy head output size: 512
[2023-02-24 17:32:37,849][2364708] Inference worker 0-0 is ready!
[2023-02-24 17:32:37,849][2364708] All inference workers are ready! Signal rollout workers to start!
[2023-02-24 17:32:37,887][2364862] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,887][2364836] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,888][2364833] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,888][2364835] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,888][2364832] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,888][2364859] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,887][2364857] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,889][2364856] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,889][2364837] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,889][2365108] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,889][2364839] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,889][2364860] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,887][2364855] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,888][2364861] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,888][2364834] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:37,892][2364838] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:32:38,292][2364855] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,293][2364833] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,294][2364857] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,294][2364836] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,295][2364834] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,295][2364856] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,296][2364859] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,296][2364832] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,484][2364856] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,511][2364862] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,516][2364861] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,517][2364835] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,517][2364839] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,585][2364834] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,617][2364857] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,617][2364836] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,628][2364855] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,697][2364856] Decorrelating experience for 64 frames...
[2023-02-24 17:32:38,700][2364862] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,719][2364832] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,821][2364857] Decorrelating experience for 64 frames...
[2023-02-24 17:32:38,827][2364835] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,834][2364860] Decorrelating experience for 0 frames...
[2023-02-24 17:32:38,844][2364834] Decorrelating experience for 64 frames...
[2023-02-24 17:32:38,858][2364861] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,877][2364859] Decorrelating experience for 32 frames...
[2023-02-24 17:32:38,926][2364856] Decorrelating experience for 96 frames...
[2023-02-24 17:32:39,022][2364860] Decorrelating experience for 32 frames...
[2023-02-24 17:32:39,026][2364837] Decorrelating experience for 0 frames...
[2023-02-24 17:32:39,041][2364832] Decorrelating experience for 64 frames...
[2023-02-24 17:32:39,129][2365108] Decorrelating experience for 0 frames...
[2023-02-24 17:32:39,155][2364839] Decorrelating experience for 32 frames...
[2023-02-24 17:32:39,180][2364861] Decorrelating experience for 64 frames...
[2023-02-24 17:32:39,263][2364832] Decorrelating experience for 96 frames...
[2023-02-24 17:32:39,298][2364837] Decorrelating experience for 32 frames...
[2023-02-24 17:32:39,332][2364835] Decorrelating experience for 64 frames...
[2023-02-24 17:32:39,336][2364836] Decorrelating experience for 64 frames...
[2023-02-24 17:32:39,359][2364857] Decorrelating experience for 96 frames...
[2023-02-24 17:32:39,365][2364838] Decorrelating experience for 0 frames...
[2023-02-24 17:32:39,378][2364834] Decorrelating experience for 96 frames...
[2023-02-24 17:32:39,523][2365108] Decorrelating experience for 32 frames...
[2023-02-24 17:32:39,535][2364833] Decorrelating experience for 32 frames...
[2023-02-24 17:32:39,552][2364862] Decorrelating experience for 64 frames...
[2023-02-24 17:32:39,593][2364857] Decorrelating experience for 128 frames...
[2023-02-24 17:32:39,623][2364861] Decorrelating experience for 96 frames...
[2023-02-24 17:32:39,682][2364835] Decorrelating experience for 96 frames...
[2023-02-24 17:32:39,695][2364860] Decorrelating experience for 64 frames...
[2023-02-24 17:32:39,708][2364837] Decorrelating experience for 64 frames...
[2023-02-24 17:32:39,748][2364856] Decorrelating experience for 128 frames...
[2023-02-24 17:32:39,783][2364862] Decorrelating experience for 96 frames...
[2023-02-24 17:32:39,789][2364832] Decorrelating experience for 128 frames...
[2023-02-24 17:32:39,875][2364857] Decorrelating experience for 160 frames...
[2023-02-24 17:32:39,884][2364855] Decorrelating experience for 64 frames...
[2023-02-24 17:32:39,898][2364861] Decorrelating experience for 128 frames...
[2023-02-24 17:32:39,924][2364859] Decorrelating experience for 64 frames...
[2023-02-24 17:32:40,010][2364838] Decorrelating experience for 32 frames...
[2023-02-24 17:32:40,043][2365108] Decorrelating experience for 64 frames...
[2023-02-24 17:32:40,047][2364856] Decorrelating experience for 160 frames...
[2023-02-24 17:32:40,051][2364860] Decorrelating experience for 96 frames...
[2023-02-24 17:32:40,070][2364839] Decorrelating experience for 64 frames...
[2023-02-24 17:32:40,088][2364835] Decorrelating experience for 128 frames...
[2023-02-24 17:32:40,123][2364834] Decorrelating experience for 128 frames...
[2023-02-24 17:32:40,183][2364833] Decorrelating experience for 64 frames...
[2023-02-24 17:32:40,213][2364859] Decorrelating experience for 96 frames...
[2023-02-24 17:32:40,319][2364838] Decorrelating experience for 64 frames...
[2023-02-24 17:32:40,333][2364835] Decorrelating experience for 160 frames...
[2023-02-24 17:32:40,337][2364832] Decorrelating experience for 160 frames...
[2023-02-24 17:32:40,372][2364862] Decorrelating experience for 128 frames...
[2023-02-24 17:32:40,404][2364861] Decorrelating experience for 160 frames...
[2023-02-24 17:32:40,429][2364837] Decorrelating experience for 96 frames...
[2023-02-24 17:32:40,514][2365108] Decorrelating experience for 96 frames...
[2023-02-24 17:32:40,535][2364839] Decorrelating experience for 96 frames...
[2023-02-24 17:32:40,595][2364834] Decorrelating experience for 160 frames...
[2023-02-24 17:32:40,629][2364860] Decorrelating experience for 128 frames...
[2023-02-24 17:32:40,640][2364833] Decorrelating experience for 96 frames...
[2023-02-24 17:32:40,643][2364859] Decorrelating experience for 128 frames...
[2023-02-24 17:32:40,748][2364838] Decorrelating experience for 96 frames...
[2023-02-24 17:32:40,777][2365108] Decorrelating experience for 128 frames...
[2023-02-24 17:32:40,793][2364836] Decorrelating experience for 96 frames...
[2023-02-24 17:32:40,912][2364837] Decorrelating experience for 128 frames...
[2023-02-24 17:32:40,918][2364791] Signal inference workers to stop experience collection...
[2023-02-24 17:32:40,922][2364831] InferenceWorker_p0-w0: stopping experience collection
[2023-02-24 17:32:40,955][2364860] Decorrelating experience for 160 frames...
[2023-02-24 17:32:40,971][2364859] Decorrelating experience for 160 frames...
[2023-02-24 17:32:41,025][2364833] Decorrelating experience for 128 frames...
[2023-02-24 17:32:41,056][2364836] Decorrelating experience for 128 frames...
[2023-02-24 17:32:41,076][2364838] Decorrelating experience for 128 frames...
[2023-02-24 17:32:41,132][2365108] Decorrelating experience for 160 frames...
[2023-02-24 17:32:41,199][2364837] Decorrelating experience for 160 frames...
[2023-02-24 17:32:41,202][2364862] Decorrelating experience for 160 frames...
[2023-02-24 17:32:41,266][2364708] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 2304. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-24 17:32:41,266][2364708] Avg episode reward: [(0, '1.871')]
[2023-02-24 17:32:41,343][2364839] Decorrelating experience for 128 frames...
[2023-02-24 17:32:41,343][2364836] Decorrelating experience for 160 frames...
[2023-02-24 17:32:41,392][2364838] Decorrelating experience for 160 frames...
[2023-02-24 17:32:41,443][2364855] Decorrelating experience for 96 frames...
[2023-02-24 17:32:41,569][2364833] Decorrelating experience for 160 frames...
[2023-02-24 17:32:41,656][2364855] Decorrelating experience for 128 frames...
[2023-02-24 17:32:41,671][2364839] Decorrelating experience for 160 frames...
[2023-02-24 17:32:41,801][2364791] Signal inference workers to resume experience collection...
[2023-02-24 17:32:41,801][2364831] InferenceWorker_p0-w0: resuming experience collection
[2023-02-24 17:32:41,877][2364855] Decorrelating experience for 160 frames...
[2023-02-24 17:32:43,213][2364831] Updated weights for policy 0, policy_version 988 (0.0223)
[2023-02-24 17:32:44,160][2364831] Updated weights for policy 0, policy_version 998 (0.0009)
[2023-02-24 17:32:45,129][2364831] Updated weights for policy 0, policy_version 1008 (0.0011)
[2023-02-24 17:32:46,071][2364831] Updated weights for policy 0, policy_version 1018 (0.0009)
[2023-02-24 17:32:46,266][2364708] Fps is (10 sec: 33586.6, 60 sec: 33586.6, 300 sec: 33586.6). Total num frames: 4173824. Throughput: 0: 3350.3. Samples: 19056. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:32:46,266][2364708] Avg episode reward: [(0, '18.870')]
[2023-02-24 17:32:47,062][2364831] Updated weights for policy 0, policy_version 1028 (0.0009)
[2023-02-24 17:32:48,070][2364831] Updated weights for policy 0, policy_version 1038 (0.0012)
[2023-02-24 17:32:49,031][2364831] Updated weights for policy 0, policy_version 1048 (0.0009)
[2023-02-24 17:32:50,044][2364831] Updated weights for policy 0, policy_version 1058 (0.0016)
[2023-02-24 17:32:50,993][2364831] Updated weights for policy 0, policy_version 1068 (0.0013)
[2023-02-24 17:32:51,266][2364708] Fps is (10 sec: 37683.0, 60 sec: 37683.0, 300 sec: 37683.0). Total num frames: 4382720. Throughput: 0: 7973.1. Samples: 82035. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:32:51,266][2364708] Avg episode reward: [(0, '24.692')]
[2023-02-24 17:32:51,978][2364831] Updated weights for policy 0, policy_version 1078 (0.0010)
[2023-02-24 17:32:52,932][2364708] Heartbeat connected on Batcher_0
[2023-02-24 17:32:52,934][2364708] Heartbeat connected on LearnerWorker_p0
[2023-02-24 17:32:52,941][2364708] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-24 17:32:52,944][2364708] Heartbeat connected on RolloutWorker_w2
[2023-02-24 17:32:52,945][2364708] Heartbeat connected on RolloutWorker_w3
[2023-02-24 17:32:52,949][2364708] Heartbeat connected on RolloutWorker_w4
[2023-02-24 17:32:52,949][2364708] Heartbeat connected on RolloutWorker_w5
[2023-02-24 17:32:52,953][2364708] Heartbeat connected on RolloutWorker_w6
[2023-02-24 17:32:52,953][2364708] Heartbeat connected on RolloutWorker_w7
[2023-02-24 17:32:52,955][2364708] Heartbeat connected on RolloutWorker_w0
[2023-02-24 17:32:52,955][2364708] Heartbeat connected on RolloutWorker_w1
[2023-02-24 17:32:52,957][2364708] Heartbeat connected on RolloutWorker_w8
[2023-02-24 17:32:52,958][2364708] Heartbeat connected on RolloutWorker_w9
[2023-02-24 17:32:52,962][2364708] Heartbeat connected on RolloutWorker_w10
[2023-02-24 17:32:52,963][2364708] Heartbeat connected on RolloutWorker_w11
[2023-02-24 17:32:52,966][2364708] Heartbeat connected on RolloutWorker_w13
[2023-02-24 17:32:52,967][2364708] Heartbeat connected on RolloutWorker_w12
[2023-02-24 17:32:52,968][2364708] Heartbeat connected on RolloutWorker_w14
[2023-02-24 17:32:52,981][2364708] Heartbeat connected on RolloutWorker_w15
[2023-02-24 17:32:52,981][2364831] Updated weights for policy 0, policy_version 1088 (0.0012)
[2023-02-24 17:32:53,959][2364831] Updated weights for policy 0, policy_version 1098 (0.0010)
[2023-02-24 17:32:54,954][2364831] Updated weights for policy 0, policy_version 1108 (0.0009)
[2023-02-24 17:32:55,930][2364831] Updated weights for policy 0, policy_version 1118 (0.0011)
[2023-02-24 17:32:56,266][2364708] Fps is (10 sec: 41779.4, 60 sec: 39048.4, 300 sec: 39048.4). Total num frames: 4591616. Throughput: 0: 9485.2. Samples: 144582. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:32:56,266][2364708] Avg episode reward: [(0, '25.204')]
[2023-02-24 17:32:56,266][2364791] Saving new best policy, reward=25.204!
[2023-02-24 17:32:56,911][2364831] Updated weights for policy 0, policy_version 1128 (0.0014)
[2023-02-24 17:32:57,948][2364831] Updated weights for policy 0, policy_version 1138 (0.0011)
[2023-02-24 17:32:58,912][2364831] Updated weights for policy 0, policy_version 1148 (0.0011)
[2023-02-24 17:32:59,887][2364831] Updated weights for policy 0, policy_version 1158 (0.0012)
[2023-02-24 17:33:00,871][2364831] Updated weights for policy 0, policy_version 1168 (0.0016)
[2023-02-24 17:33:01,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 39526.2, 300 sec: 39526.2). Total num frames: 4796416. Throughput: 0: 8660.6. Samples: 175518. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:33:01,266][2364708] Avg episode reward: [(0, '24.312')]
[2023-02-24 17:33:01,888][2364831] Updated weights for policy 0, policy_version 1178 (0.0009)
[2023-02-24 17:33:02,860][2364831] Updated weights for policy 0, policy_version 1188 (0.0009)
[2023-02-24 17:33:03,875][2364831] Updated weights for policy 0, policy_version 1198 (0.0014)
[2023-02-24 17:33:04,853][2364831] Updated weights for policy 0, policy_version 1208 (0.0009)
[2023-02-24 17:33:05,857][2364831] Updated weights for policy 0, policy_version 1218 (0.0012)
[2023-02-24 17:33:06,266][2364708] Fps is (10 sec: 41368.6, 60 sec: 39976.5, 300 sec: 39976.5). Total num frames: 5005312. Throughput: 0: 9410.3. Samples: 237564. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:33:06,266][2364708] Avg episode reward: [(0, '24.517')]
[2023-02-24 17:33:06,796][2364831] Updated weights for policy 0, policy_version 1228 (0.0011)
[2023-02-24 17:33:07,774][2364831] Updated weights for policy 0, policy_version 1238 (0.0011)
[2023-02-24 17:33:08,779][2364831] Updated weights for policy 0, policy_version 1248 (0.0012)
[2023-02-24 17:33:09,772][2364831] Updated weights for policy 0, policy_version 1258 (0.0010)
[2023-02-24 17:33:10,736][2364831] Updated weights for policy 0, policy_version 1268 (0.0014)
[2023-02-24 17:33:11,266][2364708] Fps is (10 sec: 41779.2, 60 sec: 40277.2, 300 sec: 40277.2). Total num frames: 5214208. Throughput: 0: 9920.8. Samples: 299928. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:33:11,266][2364708] Avg episode reward: [(0, '30.044')]
[2023-02-24 17:33:11,269][2364791] Saving new best policy, reward=30.044!
[2023-02-24 17:33:11,776][2364831] Updated weights for policy 0, policy_version 1278 (0.0009)
[2023-02-24 17:33:12,732][2364831] Updated weights for policy 0, policy_version 1288 (0.0009)
[2023-02-24 17:33:13,718][2364831] Updated weights for policy 0, policy_version 1298 (0.0014)
[2023-02-24 17:33:14,743][2364831] Updated weights for policy 0, policy_version 1308 (0.0011)
[2023-02-24 17:33:15,710][2364831] Updated weights for policy 0, policy_version 1318 (0.0012)
[2023-02-24 17:33:16,266][2364708] Fps is (10 sec: 41370.3, 60 sec: 40374.7, 300 sec: 40374.7). Total num frames: 5419008. Throughput: 0: 9385.3. Samples: 330789. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:33:16,266][2364708] Avg episode reward: [(0, '26.183')]
[2023-02-24 17:33:16,724][2364831] Updated weights for policy 0, policy_version 1328 (0.0008)
[2023-02-24 17:33:17,710][2364831] Updated weights for policy 0, policy_version 1338 (0.0014)
[2023-02-24 17:33:18,666][2364831] Updated weights for policy 0, policy_version 1348 (0.0009)
[2023-02-24 17:33:19,683][2364831] Updated weights for policy 0, policy_version 1358 (0.0009)
[2023-02-24 17:33:20,617][2364831] Updated weights for policy 0, policy_version 1368 (0.0010)
[2023-02-24 17:33:21,266][2364708] Fps is (10 sec: 41370.0, 60 sec: 40550.4, 300 sec: 40550.4). Total num frames: 5627904. Throughput: 0: 9770.6. Samples: 393129. Policy #0 lag: (min: 1.0, avg: 2.0, max: 4.0)
[2023-02-24 17:33:21,266][2364708] Avg episode reward: [(0, '25.398')]
[2023-02-24 17:33:21,637][2364831] Updated weights for policy 0, policy_version 1378 (0.0009)
[2023-02-24 17:33:22,601][2364831] Updated weights for policy 0, policy_version 1388 (0.0012)
[2023-02-24 17:33:23,610][2364831] Updated weights for policy 0, policy_version 1398 (0.0009)
[2023-02-24 17:33:24,587][2364831] Updated weights for policy 0, policy_version 1408 (0.0012)
[2023-02-24 17:33:25,585][2364831] Updated weights for policy 0, policy_version 1418 (0.0010)
[2023-02-24 17:33:26,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 40595.8, 300 sec: 40595.8). Total num frames: 5832704. Throughput: 0: 10069.7. Samples: 455439. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:33:26,266][2364708] Avg episode reward: [(0, '24.553')]
[2023-02-24 17:33:26,570][2364831] Updated weights for policy 0, policy_version 1428 (0.0009)
[2023-02-24 17:33:27,565][2364831] Updated weights for policy 0, policy_version 1438 (0.0009)
[2023-02-24 17:33:28,519][2364831] Updated weights for policy 0, policy_version 1448 (0.0012)
[2023-02-24 17:33:29,541][2364831] Updated weights for policy 0, policy_version 1458 (0.0011)
[2023-02-24 17:33:30,518][2364831] Updated weights for policy 0, policy_version 1468 (0.0012)
[2023-02-24 17:33:31,266][2364708] Fps is (10 sec: 41369.0, 60 sec: 40714.1, 300 sec: 40714.1). Total num frames: 6041600. Throughput: 0: 10387.5. Samples: 486495. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0)
[2023-02-24 17:33:31,266][2364708] Avg episode reward: [(0, '27.755')]
[2023-02-24 17:33:31,537][2364831] Updated weights for policy 0, policy_version 1478 (0.0009)
[2023-02-24 17:33:32,488][2364831] Updated weights for policy 0, policy_version 1488 (0.0009)
[2023-02-24 17:33:33,488][2364831] Updated weights for policy 0, policy_version 1498 (0.0010)
[2023-02-24 17:33:34,494][2364831] Updated weights for policy 0, policy_version 1508 (0.0009)
[2023-02-24 17:33:35,471][2364831] Updated weights for policy 0, policy_version 1518 (0.0012)
[2023-02-24 17:33:36,266][2364708] Fps is (10 sec: 41368.5, 60 sec: 40736.3, 300 sec: 40736.3). Total num frames: 6246400. Throughput: 0: 10367.1. Samples: 548559. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:33:36,267][2364708] Avg episode reward: [(0, '29.595')]
[2023-02-24 17:33:36,445][2364831] Updated weights for policy 0, policy_version 1528 (0.0015)
[2023-02-24 17:33:37,457][2364831] Updated weights for policy 0, policy_version 1538 (0.0010)
[2023-02-24 17:33:38,386][2364831] Updated weights for policy 0, policy_version 1548 (0.0010)
[2023-02-24 17:33:39,394][2364831] Updated weights for policy 0, policy_version 1558 (0.0009)
[2023-02-24 17:33:40,414][2364831] Updated weights for policy 0, policy_version 1568 (0.0013)
[2023-02-24 17:33:41,266][2364708] Fps is (10 sec: 41779.5, 60 sec: 40891.7, 300 sec: 40891.7). Total num frames: 6459392. Throughput: 0: 10363.3. Samples: 610929. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:33:41,266][2364708] Avg episode reward: [(0, '27.467')]
[2023-02-24 17:33:41,392][2364831] Updated weights for policy 0, policy_version 1578 (0.0011)
[2023-02-24 17:33:42,409][2364831] Updated weights for policy 0, policy_version 1588 (0.0015)
[2023-02-24 17:33:43,364][2364831] Updated weights for policy 0, policy_version 1598 (0.0016)
[2023-02-24 17:33:44,391][2364831] Updated weights for policy 0, policy_version 1608 (0.0009)
[2023-02-24 17:33:45,344][2364831] Updated weights for policy 0, policy_version 1618 (0.0009)
[2023-02-24 17:33:46,266][2364708] Fps is (10 sec: 41371.0, 60 sec: 41437.9, 300 sec: 40834.0). Total num frames: 6660096. Throughput: 0: 10362.0. Samples: 641805. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:33:46,266][2364708] Avg episode reward: [(0, '26.443')]
[2023-02-24 17:33:46,345][2364831] Updated weights for policy 0, policy_version 1628 (0.0009)
[2023-02-24 17:33:47,361][2364831] Updated weights for policy 0, policy_version 1638 (0.0012)
[2023-02-24 17:33:48,358][2364831] Updated weights for policy 0, policy_version 1648 (0.0015)
[2023-02-24 17:33:49,372][2364831] Updated weights for policy 0, policy_version 1658 (0.0010)
[2023-02-24 17:33:50,384][2364831] Updated weights for policy 0, policy_version 1668 (0.0009)
[2023-02-24 17:33:51,266][2364708] Fps is (10 sec: 40550.3, 60 sec: 41369.5, 300 sec: 40842.9). Total num frames: 6864896. Throughput: 0: 10346.7. Samples: 703164. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0)
[2023-02-24 17:33:51,266][2364708] Avg episode reward: [(0, '29.470')]
[2023-02-24 17:33:51,339][2364831] Updated weights for policy 0, policy_version 1678 (0.0009)
[2023-02-24 17:33:52,333][2364831] Updated weights for policy 0, policy_version 1688 (0.0013)
[2023-02-24 17:33:53,373][2364831] Updated weights for policy 0, policy_version 1698 (0.0010)
[2023-02-24 17:33:54,326][2364831] Updated weights for policy 0, policy_version 1708 (0.0011)
[2023-02-24 17:33:55,317][2364831] Updated weights for policy 0, policy_version 1718 (0.0015)
[2023-02-24 17:33:56,266][2364708] Fps is (10 sec: 41369.2, 60 sec: 41369.5, 300 sec: 40905.3). Total num frames: 7073792. Throughput: 0: 10341.1. Samples: 765279. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
[2023-02-24 17:33:56,266][2364708] Avg episode reward: [(0, '29.662')]
[2023-02-24 17:33:56,319][2364831] Updated weights for policy 0, policy_version 1728 (0.0009)
[2023-02-24 17:33:57,289][2364831] Updated weights for policy 0, policy_version 1738 (0.0014)
[2023-02-24 17:33:58,346][2364831] Updated weights for policy 0, policy_version 1748 (0.0009)
[2023-02-24 17:33:59,308][2364831] Updated weights for policy 0, policy_version 1758 (0.0009)
[2023-02-24 17:34:00,266][2364831] Updated weights for policy 0, policy_version 1768 (0.0009)
[2023-02-24 17:34:01,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41369.6, 300 sec: 40908.7). Total num frames: 7278592. Throughput: 0: 10343.3. Samples: 796236. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
[2023-02-24 17:34:01,266][2364708] Avg episode reward: [(0, '28.381')]
[2023-02-24 17:34:01,272][2364831] Updated weights for policy 0, policy_version 1778 (0.0014)
[2023-02-24 17:34:02,285][2364831] Updated weights for policy 0, policy_version 1788 (0.0012)
[2023-02-24 17:34:03,229][2364831] Updated weights for policy 0, policy_version 1798 (0.0014)
[2023-02-24 17:34:04,225][2364831] Updated weights for policy 0, policy_version 1808 (0.0011)
[2023-02-24 17:34:05,252][2364831] Updated weights for policy 0, policy_version 1818 (0.0011)
[2023-02-24 17:34:06,217][2364831] Updated weights for policy 0, policy_version 1828 (0.0014)
[2023-02-24 17:34:06,266][2364708] Fps is (10 sec: 41370.1, 60 sec: 41369.8, 300 sec: 40960.0). Total num frames: 7487488. Throughput: 0: 10333.9. Samples: 858156. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:34:06,266][2364708] Avg episode reward: [(0, '28.723')]
[2023-02-24 17:34:07,238][2364831] Updated weights for policy 0, policy_version 1838 (0.0012)
[2023-02-24 17:34:08,199][2364831] Updated weights for policy 0, policy_version 1848 (0.0009)
[2023-02-24 17:34:09,209][2364831] Updated weights for policy 0, policy_version 1858 (0.0015)
[2023-02-24 17:34:10,200][2364831] Updated weights for policy 0, policy_version 1868 (0.0013)
[2023-02-24 17:34:11,160][2364831] Updated weights for policy 0, policy_version 1878 (0.0012)
[2023-02-24 17:34:11,266][2364708] Fps is (10 sec: 41370.0, 60 sec: 41301.4, 300 sec: 40960.0). Total num frames: 7692288. Throughput: 0: 10328.4. Samples: 920217. Policy #0 lag: (min: 0.0, avg: 1.6, max: 3.0)
[2023-02-24 17:34:11,266][2364708] Avg episode reward: [(0, '27.028')]
[2023-02-24 17:34:12,189][2364831] Updated weights for policy 0, policy_version 1888 (0.0013)
[2023-02-24 17:34:13,157][2364831] Updated weights for policy 0, policy_version 1898 (0.0009)
[2023-02-24 17:34:14,140][2364831] Updated weights for policy 0, policy_version 1908 (0.0009)
[2023-02-24 17:34:15,142][2364831] Updated weights for policy 0, policy_version 1918 (0.0009)
[2023-02-24 17:34:16,149][2364831] Updated weights for policy 0, policy_version 1928 (0.0008)
[2023-02-24 17:34:16,266][2364708] Fps is (10 sec: 41368.9, 60 sec: 41369.6, 300 sec: 41003.1). Total num frames: 7901184. Throughput: 0: 10329.2. Samples: 951309. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:34:16,266][2364708] Avg episode reward: [(0, '31.603')]
[2023-02-24 17:34:16,267][2364791] Saving new best policy, reward=31.603!
[2023-02-24 17:34:17,141][2364831] Updated weights for policy 0, policy_version 1938 (0.0011)
[2023-02-24 17:34:18,125][2364831] Updated weights for policy 0, policy_version 1948 (0.0010)
[2023-02-24 17:34:19,131][2364831] Updated weights for policy 0, policy_version 1958 (0.0012)
[2023-02-24 17:34:20,142][2364831] Updated weights for policy 0, policy_version 1968 (0.0009)
[2023-02-24 17:34:21,131][2364831] Updated weights for policy 0, policy_version 1978 (0.0014)
[2023-02-24 17:34:21,266][2364708] Fps is (10 sec: 41369.1, 60 sec: 41301.3, 300 sec: 41000.9). Total num frames: 8105984. Throughput: 0: 10320.3. Samples: 1012971. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:34:21,266][2364708] Avg episode reward: [(0, '28.359')]
[2023-02-24 17:34:22,137][2364831] Updated weights for policy 0, policy_version 1988 (0.0009)
[2023-02-24 17:34:23,105][2364831] Updated weights for policy 0, policy_version 1998 (0.0009)
[2023-02-24 17:34:24,115][2364831] Updated weights for policy 0, policy_version 2008 (0.0012)
[2023-02-24 17:34:25,058][2364831] Updated weights for policy 0, policy_version 2018 (0.0010)
[2023-02-24 17:34:26,094][2364831] Updated weights for policy 0, policy_version 2028 (0.0010)
[2023-02-24 17:34:26,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41369.6, 300 sec: 41038.0). Total num frames: 8314880. Throughput: 0: 10310.5. Samples: 1074903. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:34:26,266][2364708] Avg episode reward: [(0, '28.710')]
[2023-02-24 17:34:27,060][2364831] Updated weights for policy 0, policy_version 2038 (0.0011)
[2023-02-24 17:34:28,047][2364831] Updated weights for policy 0, policy_version 2048 (0.0013)
[2023-02-24 17:34:29,023][2364831] Updated weights for policy 0, policy_version 2058 (0.0009)
[2023-02-24 17:34:30,021][2364831] Updated weights for policy 0, policy_version 2068 (0.0012)
[2023-02-24 17:34:31,055][2364831] Updated weights for policy 0, policy_version 2078 (0.0009)
[2023-02-24 17:34:31,266][2364708] Fps is (10 sec: 41369.6, 60 sec: 41301.4, 300 sec: 41034.4). Total num frames: 8519680. Throughput: 0: 10314.6. Samples: 1105962. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:34:31,266][2364708] Avg episode reward: [(0, '32.526')]
[2023-02-24 17:34:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000002080_8519680.pth...
[2023-02-24 17:34:31,337][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000759_3108864.pth
[2023-02-24 17:34:31,343][2364791] Saving new best policy, reward=32.526!
[2023-02-24 17:34:32,027][2364831] Updated weights for policy 0, policy_version 2088 (0.0014)
[2023-02-24 17:34:33,002][2364831] Updated weights for policy 0, policy_version 2098 (0.0011)
[2023-02-24 17:34:34,028][2364831] Updated weights for policy 0, policy_version 2108 (0.0010)
[2023-02-24 17:34:34,994][2364831] Updated weights for policy 0, policy_version 2118 (0.0009)
[2023-02-24 17:34:36,021][2364831] Updated weights for policy 0, policy_version 2128 (0.0011)
[2023-02-24 17:34:36,266][2364708] Fps is (10 sec: 40960.1, 60 sec: 41301.5, 300 sec: 41031.2). Total num frames: 8724480. Throughput: 0: 10328.4. Samples: 1167942. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:34:36,266][2364708] Avg episode reward: [(0, '29.338')]
[2023-02-24 17:34:37,019][2364831] Updated weights for policy 0, policy_version 2138 (0.0012)
[2023-02-24 17:34:38,029][2364831] Updated weights for policy 0, policy_version 2148 (0.0010)
[2023-02-24 17:34:38,999][2364831] Updated weights for policy 0, policy_version 2158 (0.0009)
[2023-02-24 17:34:40,008][2364831] Updated weights for policy 0, policy_version 2168 (0.0009)
[2023-02-24 17:34:40,960][2364831] Updated weights for policy 0, policy_version 2178 (0.0013)
[2023-02-24 17:34:41,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41164.8, 300 sec: 41028.2). Total num frames: 8929280. Throughput: 0: 10315.9. Samples: 1229496. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:34:41,266][2364708] Avg episode reward: [(0, '28.569')]
[2023-02-24 17:34:41,985][2364831] Updated weights for policy 0, policy_version 2188 (0.0012)
[2023-02-24 17:34:42,962][2364831] Updated weights for policy 0, policy_version 2198 (0.0009)
[2023-02-24 17:34:43,968][2364831] Updated weights for policy 0, policy_version 2208 (0.0009)
[2023-02-24 17:34:44,995][2364831] Updated weights for policy 0, policy_version 2218 (0.0010)
[2023-02-24 17:34:45,933][2364831] Updated weights for policy 0, policy_version 2228 (0.0010)
[2023-02-24 17:34:46,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41301.2, 300 sec: 41058.3). Total num frames: 9138176. Throughput: 0: 10313.9. Samples: 1260363. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:34:46,266][2364708] Avg episode reward: [(0, '29.705')]
[2023-02-24 17:34:46,949][2364831] Updated weights for policy 0, policy_version 2238 (0.0011)
[2023-02-24 17:34:47,940][2364831] Updated weights for policy 0, policy_version 2248 (0.0012)
[2023-02-24 17:34:48,931][2364831] Updated weights for policy 0, policy_version 2258 (0.0016)
[2023-02-24 17:34:49,903][2364831] Updated weights for policy 0, policy_version 2268 (0.0015)
[2023-02-24 17:34:50,883][2364831] Updated weights for policy 0, policy_version 2278 (0.0009)
[2023-02-24 17:34:51,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41301.4, 300 sec: 41054.5). Total num frames: 9342976. Throughput: 0: 10311.3. Samples: 1322166. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0)
[2023-02-24 17:34:51,266][2364708] Avg episode reward: [(0, '30.602')]
[2023-02-24 17:34:51,902][2364831] Updated weights for policy 0, policy_version 2288 (0.0010)
[2023-02-24 17:34:52,909][2364831] Updated weights for policy 0, policy_version 2298 (0.0010)
[2023-02-24 17:34:53,904][2364831] Updated weights for policy 0, policy_version 2308 (0.0010)
[2023-02-24 17:34:54,860][2364831] Updated weights for policy 0, policy_version 2318 (0.0010)
[2023-02-24 17:34:55,858][2364831] Updated weights for policy 0, policy_version 2328 (0.0009)
[2023-02-24 17:34:56,266][2364708] Fps is (10 sec: 40960.2, 60 sec: 41233.1, 300 sec: 41051.0). Total num frames: 9547776. Throughput: 0: 10311.1. Samples: 1384218. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:34:56,266][2364708] Avg episode reward: [(0, '29.322')]
[2023-02-24 17:34:56,865][2364831] Updated weights for policy 0, policy_version 2338 (0.0009)
[2023-02-24 17:34:57,857][2364831] Updated weights for policy 0, policy_version 2348 (0.0009)
[2023-02-24 17:34:58,810][2364831] Updated weights for policy 0, policy_version 2358 (0.0016)
[2023-02-24 17:34:59,854][2364831] Updated weights for policy 0, policy_version 2368 (0.0012)
[2023-02-24 17:35:00,835][2364831] Updated weights for policy 0, policy_version 2378 (0.0009)
[2023-02-24 17:35:01,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41301.3, 300 sec: 41077.0). Total num frames: 9756672. Throughput: 0: 10308.8. Samples: 1415205. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
[2023-02-24 17:35:01,266][2364708] Avg episode reward: [(0, '30.241')]
[2023-02-24 17:35:01,804][2364831] Updated weights for policy 0, policy_version 2388 (0.0012)
[2023-02-24 17:35:02,822][2364831] Updated weights for policy 0, policy_version 2398 (0.0010)
[2023-02-24 17:35:03,814][2364831] Updated weights for policy 0, policy_version 2408 (0.0010)
[2023-02-24 17:35:04,799][2364831] Updated weights for policy 0, policy_version 2418 (0.0011)
[2023-02-24 17:35:05,796][2364831] Updated weights for policy 0, policy_version 2428 (0.0009)
[2023-02-24 17:35:06,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41233.0, 300 sec: 41073.0). Total num frames: 9961472. Throughput: 0: 10314.6. Samples: 1477128. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0)
[2023-02-24 17:35:06,266][2364708] Avg episode reward: [(0, '26.511')]
[2023-02-24 17:35:06,791][2364831] Updated weights for policy 0, policy_version 2438 (0.0012)
[2023-02-24 17:35:07,790][2364831] Updated weights for policy 0, policy_version 2448 (0.0009)
[2023-02-24 17:35:08,780][2364831] Updated weights for policy 0, policy_version 2458 (0.0014)
[2023-02-24 17:35:09,752][2364831] Updated weights for policy 0, policy_version 2468 (0.0010)
[2023-02-24 17:35:10,772][2364831] Updated weights for policy 0, policy_version 2478 (0.0010)
[2023-02-24 17:35:11,266][2364708] Fps is (10 sec: 40958.9, 60 sec: 41232.8, 300 sec: 41069.1). Total num frames: 10166272. Throughput: 0: 10309.2. Samples: 1538820. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:35:11,267][2364708] Avg episode reward: [(0, '31.927')]
[2023-02-24 17:35:11,766][2364831] Updated weights for policy 0, policy_version 2488 (0.0012)
[2023-02-24 17:35:12,753][2364831] Updated weights for policy 0, policy_version 2498 (0.0011)
[2023-02-24 17:35:13,754][2364831] Updated weights for policy 0, policy_version 2508 (0.0014)
[2023-02-24 17:35:14,735][2364831] Updated weights for policy 0, policy_version 2518 (0.0013)
[2023-02-24 17:35:15,703][2364831] Updated weights for policy 0, policy_version 2528 (0.0011)
[2023-02-24 17:35:16,266][2364708] Fps is (10 sec: 41370.2, 60 sec: 41233.2, 300 sec: 41092.1). Total num frames: 10375168. Throughput: 0: 10308.7. Samples: 1569852. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:35:16,266][2364708] Avg episode reward: [(0, '29.333')]
[2023-02-24 17:35:16,713][2364831] Updated weights for policy 0, policy_version 2538 (0.0012)
[2023-02-24 17:35:17,728][2364831] Updated weights for policy 0, policy_version 2548 (0.0009)
[2023-02-24 17:35:18,681][2364831] Updated weights for policy 0, policy_version 2558 (0.0012)
[2023-02-24 17:35:19,719][2364831] Updated weights for policy 0, policy_version 2568 (0.0008)
[2023-02-24 17:35:20,725][2364831] Updated weights for policy 0, policy_version 2578 (0.0010)
[2023-02-24 17:35:21,266][2364708] Fps is (10 sec: 41370.6, 60 sec: 41233.1, 300 sec: 41088.0). Total num frames: 10579968. Throughput: 0: 10308.5. Samples: 1631826. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0)
[2023-02-24 17:35:21,266][2364708] Avg episode reward: [(0, '29.221')]
[2023-02-24 17:35:21,646][2364831] Updated weights for policy 0, policy_version 2588 (0.0013)
[2023-02-24 17:35:22,678][2364831] Updated weights for policy 0, policy_version 2598 (0.0011)
[2023-02-24 17:35:23,706][2364831] Updated weights for policy 0, policy_version 2608 (0.0010)
[2023-02-24 17:35:24,640][2364831] Updated weights for policy 0, policy_version 2618 (0.0014)
[2023-02-24 17:35:25,686][2364831] Updated weights for policy 0, policy_version 2628 (0.0014)
[2023-02-24 17:35:26,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41233.2, 300 sec: 41108.9). Total num frames: 10788864. Throughput: 0: 10318.8. Samples: 1693842. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
[2023-02-24 17:35:26,266][2364708] Avg episode reward: [(0, '32.770')]
[2023-02-24 17:35:26,267][2364791] Saving new best policy, reward=32.770!
[2023-02-24 17:35:26,645][2364831] Updated weights for policy 0, policy_version 2638 (0.0019)
[2023-02-24 17:35:27,596][2364831] Updated weights for policy 0, policy_version 2648 (0.0012)
[2023-02-24 17:35:28,675][2364831] Updated weights for policy 0, policy_version 2658 (0.0012)
[2023-02-24 17:35:29,615][2364831] Updated weights for policy 0, policy_version 2668 (0.0009)
[2023-02-24 17:35:30,625][2364831] Updated weights for policy 0, policy_version 2678 (0.0012)
[2023-02-24 17:35:31,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41233.0, 300 sec: 41104.5). Total num frames: 10993664. Throughput: 0: 10317.5. Samples: 1724652. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:35:31,266][2364708] Avg episode reward: [(0, '33.019')]
[2023-02-24 17:35:31,271][2364791] Saving new best policy, reward=33.019!
[2023-02-24 17:35:31,627][2364831] Updated weights for policy 0, policy_version 2688 (0.0013)
[2023-02-24 17:35:32,607][2364831] Updated weights for policy 0, policy_version 2698 (0.0012)
[2023-02-24 17:35:33,625][2364831] Updated weights for policy 0, policy_version 2708 (0.0009)
[2023-02-24 17:35:34,595][2364831] Updated weights for policy 0, policy_version 2718 (0.0010)
[2023-02-24 17:35:35,612][2364831] Updated weights for policy 0, policy_version 2728 (0.0010)
[2023-02-24 17:35:36,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41233.1, 300 sec: 41100.4). Total num frames: 11198464. Throughput: 0: 10313.8. Samples: 1786287. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
[2023-02-24 17:35:36,266][2364708] Avg episode reward: [(0, '30.687')]
[2023-02-24 17:35:36,597][2364831] Updated weights for policy 0, policy_version 2738 (0.0012)
[2023-02-24 17:35:37,588][2364831] Updated weights for policy 0, policy_version 2748 (0.0012)
[2023-02-24 17:35:38,625][2364831] Updated weights for policy 0, policy_version 2758 (0.0016)
[2023-02-24 17:35:39,609][2364831] Updated weights for policy 0, policy_version 2768 (0.0009)
[2023-02-24 17:35:40,592][2364831] Updated weights for policy 0, policy_version 2778 (0.0009)
[2023-02-24 17:35:41,266][2364708] Fps is (10 sec: 40960.2, 60 sec: 41233.0, 300 sec: 41096.5). Total num frames: 11403264. Throughput: 0: 10304.3. Samples: 1847913. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:35:41,266][2364708] Avg episode reward: [(0, '30.382')]
[2023-02-24 17:35:41,573][2364831] Updated weights for policy 0, policy_version 2788 (0.0012)
[2023-02-24 17:35:42,590][2364831] Updated weights for policy 0, policy_version 2798 (0.0010)
[2023-02-24 17:35:43,575][2364831] Updated weights for policy 0, policy_version 2808 (0.0010)
[2023-02-24 17:35:44,572][2364831] Updated weights for policy 0, policy_version 2818 (0.0011)
[2023-02-24 17:35:45,597][2364831] Updated weights for policy 0, policy_version 2828 (0.0008)
[2023-02-24 17:35:46,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 41233.1, 300 sec: 41115.0). Total num frames: 11612160. Throughput: 0: 10300.4. Samples: 1878723. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0)
[2023-02-24 17:35:46,266][2364708] Avg episode reward: [(0, '30.394')]
[2023-02-24 17:35:46,560][2364831] Updated weights for policy 0, policy_version 2838 (0.0010)
[2023-02-24 17:35:47,531][2364831] Updated weights for policy 0, policy_version 2848 (0.0010)
[2023-02-24 17:35:48,545][2364831] Updated weights for policy 0, policy_version 2858 (0.0012)
[2023-02-24 17:35:49,500][2364831] Updated weights for policy 0, policy_version 2868 (0.0010)
[2023-02-24 17:35:50,524][2364831] Updated weights for policy 0, policy_version 2878 (0.0012)
[2023-02-24 17:35:51,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41233.0, 300 sec: 41110.9). Total num frames: 11816960. Throughput: 0: 10303.3. Samples: 1940775. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:35:51,266][2364708] Avg episode reward: [(0, '27.697')]
[2023-02-24 17:35:51,481][2364831] Updated weights for policy 0, policy_version 2888 (0.0011)
[2023-02-24 17:35:52,493][2364831] Updated weights for policy 0, policy_version 2898 (0.0012)
[2023-02-24 17:35:53,490][2364831] Updated weights for policy 0, policy_version 2908 (0.0009)
[2023-02-24 17:35:54,455][2364831] Updated weights for policy 0, policy_version 2918 (0.0012)
[2023-02-24 17:35:55,469][2364831] Updated weights for policy 0, policy_version 2928 (0.0012)
[2023-02-24 17:35:56,266][2364708] Fps is (10 sec: 40960.4, 60 sec: 41233.1, 300 sec: 41107.0). Total num frames: 12021760. Throughput: 0: 10309.2. Samples: 2002731. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:35:56,266][2364708] Avg episode reward: [(0, '32.058')]
[2023-02-24 17:35:56,472][2364831] Updated weights for policy 0, policy_version 2938 (0.0009)
[2023-02-24 17:35:57,467][2364831] Updated weights for policy 0, policy_version 2948 (0.0011)
[2023-02-24 17:35:58,438][2364831] Updated weights for policy 0, policy_version 2958 (0.0013)
[2023-02-24 17:35:59,455][2364831] Updated weights for policy 0, policy_version 2968 (0.0009)
[2023-02-24 17:36:00,457][2364831] Updated weights for policy 0, policy_version 2978 (0.0009)
[2023-02-24 17:36:01,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41233.0, 300 sec: 41123.8). Total num frames: 12230656. Throughput: 0: 10305.4. Samples: 2033598. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:36:01,266][2364708] Avg episode reward: [(0, '29.736')]
[2023-02-24 17:36:01,465][2364831] Updated weights for policy 0, policy_version 2988 (0.0009)
[2023-02-24 17:36:02,473][2364831] Updated weights for policy 0, policy_version 2998 (0.0009)
[2023-02-24 17:36:03,476][2364831] Updated weights for policy 0, policy_version 3008 (0.0010)
[2023-02-24 17:36:04,459][2364831] Updated weights for policy 0, policy_version 3018 (0.0009)
[2023-02-24 17:36:05,480][2364831] Updated weights for policy 0, policy_version 3028 (0.0011)
[2023-02-24 17:36:06,266][2364708] Fps is (10 sec: 41369.1, 60 sec: 41233.0, 300 sec: 41119.8). Total num frames: 12435456. Throughput: 0: 10293.7. Samples: 2095044. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:36:06,266][2364708] Avg episode reward: [(0, '30.393')]
[2023-02-24 17:36:06,445][2364831] Updated weights for policy 0, policy_version 3038 (0.0012)
[2023-02-24 17:36:07,421][2364831] Updated weights for policy 0, policy_version 3048 (0.0009)
[2023-02-24 17:36:08,415][2364831] Updated weights for policy 0, policy_version 3058 (0.0011)
[2023-02-24 17:36:09,436][2364831] Updated weights for policy 0, policy_version 3068 (0.0010)
[2023-02-24 17:36:10,457][2364831] Updated weights for policy 0, policy_version 3078 (0.0009)
[2023-02-24 17:36:11,266][2364708] Fps is (10 sec: 40960.7, 60 sec: 41233.3, 300 sec: 41116.0). Total num frames: 12640256. Throughput: 0: 10281.7. Samples: 2156517. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:36:11,266][2364708] Avg episode reward: [(0, '30.391')]
[2023-02-24 17:36:11,465][2364831] Updated weights for policy 0, policy_version 3088 (0.0009)
[2023-02-24 17:36:12,457][2364831] Updated weights for policy 0, policy_version 3098 (0.0011)
[2023-02-24 17:36:13,406][2364831] Updated weights for policy 0, policy_version 3108 (0.0013)
[2023-02-24 17:36:14,404][2364831] Updated weights for policy 0, policy_version 3118 (0.0012)
[2023-02-24 17:36:15,425][2364831] Updated weights for policy 0, policy_version 3128 (0.0011)
[2023-02-24 17:36:16,266][2364708] Fps is (10 sec: 40960.3, 60 sec: 41164.7, 300 sec: 41112.4). Total num frames: 12845056. Throughput: 0: 10287.8. Samples: 2187600. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:36:16,266][2364708] Avg episode reward: [(0, '27.913')]
[2023-02-24 17:36:16,372][2364831] Updated weights for policy 0, policy_version 3138 (0.0014)
[2023-02-24 17:36:17,447][2364831] Updated weights for policy 0, policy_version 3148 (0.0009)
[2023-02-24 17:36:18,429][2364831] Updated weights for policy 0, policy_version 3158 (0.0009)
[2023-02-24 17:36:19,407][2364831] Updated weights for policy 0, policy_version 3168 (0.0013)
[2023-02-24 17:36:20,357][2364831] Updated weights for policy 0, policy_version 3178 (0.0009)
[2023-02-24 17:36:21,266][2364708] Fps is (10 sec: 40959.6, 60 sec: 41164.8, 300 sec: 41108.9). Total num frames: 13049856. Throughput: 0: 10288.8. Samples: 2249286. Policy #0 lag: (min: 0.0, avg: 1.9, max: 3.0)
[2023-02-24 17:36:21,266][2364708] Avg episode reward: [(0, '32.921')]
[2023-02-24 17:36:21,375][2364831] Updated weights for policy 0, policy_version 3188 (0.0012)
[2023-02-24 17:36:22,374][2364831] Updated weights for policy 0, policy_version 3198 (0.0015)
[2023-02-24 17:36:23,132][2364791] Signal inference workers to stop experience collection... (50 times)
[2023-02-24 17:36:23,134][2364791] Signal inference workers to resume experience collection... (50 times)
[2023-02-24 17:36:23,142][2364831] InferenceWorker_p0-w0: stopping experience collection (50 times)
[2023-02-24 17:36:23,145][2364831] InferenceWorker_p0-w0: resuming experience collection (50 times)
[2023-02-24 17:36:23,415][2364831] Updated weights for policy 0, policy_version 3208 (0.0010)
[2023-02-24 17:36:24,357][2364831] Updated weights for policy 0, policy_version 3218 (0.0009)
[2023-02-24 17:36:25,363][2364831] Updated weights for policy 0, policy_version 3228 (0.0014)
[2023-02-24 17:36:26,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41164.7, 300 sec: 41123.8). Total num frames: 13258752. Throughput: 0: 10290.0. Samples: 2310963. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:36:26,266][2364708] Avg episode reward: [(0, '34.018')]
[2023-02-24 17:36:26,267][2364791] Saving new best policy, reward=34.018!
[2023-02-24 17:36:26,376][2364831] Updated weights for policy 0, policy_version 3238 (0.0009)
[2023-02-24 17:36:27,385][2364831] Updated weights for policy 0, policy_version 3248 (0.0012)
[2023-02-24 17:36:28,374][2364831] Updated weights for policy 0, policy_version 3258 (0.0008)
[2023-02-24 17:36:29,381][2364831] Updated weights for policy 0, policy_version 3268 (0.0009)
[2023-02-24 17:36:30,372][2364831] Updated weights for policy 0, policy_version 3278 (0.0009)
[2023-02-24 17:36:31,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41164.8, 300 sec: 41120.3). Total num frames: 13463552. Throughput: 0: 10287.8. Samples: 2341674. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:36:31,266][2364708] Avg episode reward: [(0, '31.155')]
[2023-02-24 17:36:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000003287_13463552.pth...
[2023-02-24 17:36:31,331][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
[2023-02-24 17:36:31,376][2364831] Updated weights for policy 0, policy_version 3288 (0.0010)
[2023-02-24 17:36:32,389][2364831] Updated weights for policy 0, policy_version 3298 (0.0012)
[2023-02-24 17:36:33,398][2364831] Updated weights for policy 0, policy_version 3308 (0.0013)
[2023-02-24 17:36:34,328][2364831] Updated weights for policy 0, policy_version 3318 (0.0009)
[2023-02-24 17:36:35,370][2364831] Updated weights for policy 0, policy_version 3328 (0.0009)
[2023-02-24 17:36:36,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41164.8, 300 sec: 41116.9). Total num frames: 13668352. Throughput: 0: 10277.8. Samples: 2403273. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:36:36,266][2364708] Avg episode reward: [(0, '32.249')]
[2023-02-24 17:36:36,352][2364831] Updated weights for policy 0, policy_version 3338 (0.0008)
[2023-02-24 17:36:37,358][2364831] Updated weights for policy 0, policy_version 3348 (0.0012)
[2023-02-24 17:36:38,366][2364831] Updated weights for policy 0, policy_version 3358 (0.0013)
[2023-02-24 17:36:39,348][2364831] Updated weights for policy 0, policy_version 3368 (0.0010)
[2023-02-24 17:36:40,325][2364831] Updated weights for policy 0, policy_version 3378 (0.0009)
[2023-02-24 17:36:41,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41164.9, 300 sec: 41113.6). Total num frames: 13873152. Throughput: 0: 10271.1. Samples: 2464929. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:36:41,266][2364708] Avg episode reward: [(0, '30.922')]
[2023-02-24 17:36:41,354][2364831] Updated weights for policy 0, policy_version 3388 (0.0013)
[2023-02-24 17:36:42,336][2364831] Updated weights for policy 0, policy_version 3398 (0.0011)
[2023-02-24 17:36:43,307][2364831] Updated weights for policy 0, policy_version 3408 (0.0010)
[2023-02-24 17:36:44,352][2364831] Updated weights for policy 0, policy_version 3418 (0.0017)
[2023-02-24 17:36:45,308][2364831] Updated weights for policy 0, policy_version 3428 (0.0011)
[2023-02-24 17:36:46,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.6, 300 sec: 41110.5). Total num frames: 14077952. Throughput: 0: 10271.3. Samples: 2495805. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:36:46,266][2364708] Avg episode reward: [(0, '35.645')]
[2023-02-24 17:36:46,267][2364791] Saving new best policy, reward=35.645!
[2023-02-24 17:36:46,360][2364831] Updated weights for policy 0, policy_version 3438 (0.0011)
[2023-02-24 17:36:47,341][2364831] Updated weights for policy 0, policy_version 3448 (0.0010)
[2023-02-24 17:36:48,315][2364831] Updated weights for policy 0, policy_version 3458 (0.0012)
[2023-02-24 17:36:49,289][2364831] Updated weights for policy 0, policy_version 3468 (0.0008)
[2023-02-24 17:36:50,307][2364831] Updated weights for policy 0, policy_version 3478 (0.0009)
[2023-02-24 17:36:51,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.6, 300 sec: 41107.5). Total num frames: 14282752. Throughput: 0: 10276.8. Samples: 2557500. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:36:51,266][2364708] Avg episode reward: [(0, '34.180')]
[2023-02-24 17:36:51,296][2364831] Updated weights for policy 0, policy_version 3488 (0.0009)
[2023-02-24 17:36:52,295][2364831] Updated weights for policy 0, policy_version 3498 (0.0014)
[2023-02-24 17:36:53,320][2364831] Updated weights for policy 0, policy_version 3508 (0.0010)
[2023-02-24 17:36:54,312][2364831] Updated weights for policy 0, policy_version 3518 (0.0013)
[2023-02-24 17:36:55,310][2364831] Updated weights for policy 0, policy_version 3528 (0.0012)
[2023-02-24 17:36:56,260][2364831] Updated weights for policy 0, policy_version 3538 (0.0011)
[2023-02-24 17:36:56,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41164.9, 300 sec: 41120.6). Total num frames: 14491648. Throughput: 0: 10279.0. Samples: 2619072. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0)
[2023-02-24 17:36:56,266][2364708] Avg episode reward: [(0, '35.711')]
[2023-02-24 17:36:56,267][2364791] Saving new best policy, reward=35.711!
[2023-02-24 17:36:57,297][2364831] Updated weights for policy 0, policy_version 3548 (0.0014)
[2023-02-24 17:36:58,305][2364831] Updated weights for policy 0, policy_version 3558 (0.0009)
[2023-02-24 17:36:59,282][2364831] Updated weights for policy 0, policy_version 3568 (0.0009)
[2023-02-24 17:37:00,281][2364831] Updated weights for policy 0, policy_version 3578 (0.0018)
[2023-02-24 17:37:01,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.4, 300 sec: 41101.8). Total num frames: 14692352. Throughput: 0: 10270.1. Samples: 2649753. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:37:01,266][2364708] Avg episode reward: [(0, '32.713')]
[2023-02-24 17:37:01,290][2364831] Updated weights for policy 0, policy_version 3588 (0.0011)
[2023-02-24 17:37:02,293][2364831] Updated weights for policy 0, policy_version 3598 (0.0012)
[2023-02-24 17:37:03,300][2364831] Updated weights for policy 0, policy_version 3608 (0.0010)
[2023-02-24 17:37:04,288][2364831] Updated weights for policy 0, policy_version 3618 (0.0012)
[2023-02-24 17:37:05,307][2364831] Updated weights for policy 0, policy_version 3628 (0.0012)
[2023-02-24 17:37:06,256][2364831] Updated weights for policy 0, policy_version 3638 (0.0011)
[2023-02-24 17:37:06,266][2364708] Fps is (10 sec: 40959.4, 60 sec: 41096.6, 300 sec: 41114.5). Total num frames: 14901248. Throughput: 0: 10265.3. Samples: 2711226. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:37:06,266][2364708] Avg episode reward: [(0, '33.770')]
[2023-02-24 17:37:07,256][2364831] Updated weights for policy 0, policy_version 3648 (0.0010)
[2023-02-24 17:37:08,283][2364831] Updated weights for policy 0, policy_version 3658 (0.0010)
[2023-02-24 17:37:09,271][2364831] Updated weights for policy 0, policy_version 3668 (0.0010)
[2023-02-24 17:37:10,247][2364831] Updated weights for policy 0, policy_version 3678 (0.0011)
[2023-02-24 17:37:11,255][2364831] Updated weights for policy 0, policy_version 3688 (0.0009)
[2023-02-24 17:37:11,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41096.5, 300 sec: 41111.7). Total num frames: 15106048. Throughput: 0: 10267.2. Samples: 2772984. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0)
[2023-02-24 17:37:11,266][2364708] Avg episode reward: [(0, '35.557')]
[2023-02-24 17:37:12,240][2364831] Updated weights for policy 0, policy_version 3698 (0.0010)
[2023-02-24 17:37:13,251][2364831] Updated weights for policy 0, policy_version 3708 (0.0010)
[2023-02-24 17:37:14,229][2364831] Updated weights for policy 0, policy_version 3718 (0.0009)
[2023-02-24 17:37:15,279][2364831] Updated weights for policy 0, policy_version 3728 (0.0015)
[2023-02-24 17:37:16,243][2364831] Updated weights for policy 0, policy_version 3738 (0.0011)
[2023-02-24 17:37:16,266][2364708] Fps is (10 sec: 40960.5, 60 sec: 41096.6, 300 sec: 41108.9). Total num frames: 15310848. Throughput: 0: 10269.1. Samples: 2803782. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0)
[2023-02-24 17:37:16,266][2364708] Avg episode reward: [(0, '34.978')]
[2023-02-24 17:37:17,232][2364831] Updated weights for policy 0, policy_version 3748 (0.0011)
[2023-02-24 17:37:18,232][2364831] Updated weights for policy 0, policy_version 3758 (0.0012)
[2023-02-24 17:37:19,246][2364831] Updated weights for policy 0, policy_version 3768 (0.0011)
[2023-02-24 17:37:20,215][2364831] Updated weights for policy 0, policy_version 3778 (0.0016)
[2023-02-24 17:37:21,224][2364831] Updated weights for policy 0, policy_version 3788 (0.0009)
[2023-02-24 17:37:21,266][2364708] Fps is (10 sec: 40959.6, 60 sec: 41096.5, 300 sec: 41106.3). Total num frames: 15515648. Throughput: 0: 10267.2. Samples: 2865300. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:37:21,266][2364708] Avg episode reward: [(0, '32.422')]
[2023-02-24 17:37:22,190][2364831] Updated weights for policy 0, policy_version 3798 (0.0009)
[2023-02-24 17:37:23,210][2364831] Updated weights for policy 0, policy_version 3808 (0.0010)
[2023-02-24 17:37:24,201][2364831] Updated weights for policy 0, policy_version 3818 (0.0009)
[2023-02-24 17:37:25,224][2364831] Updated weights for policy 0, policy_version 3828 (0.0012)
[2023-02-24 17:37:26,251][2364831] Updated weights for policy 0, policy_version 3838 (0.0012)
[2023-02-24 17:37:26,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.4, 300 sec: 41103.7). Total num frames: 15720448. Throughput: 0: 10264.2. Samples: 2926818. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:37:26,266][2364708] Avg episode reward: [(0, '30.861')]
[2023-02-24 17:37:27,226][2364831] Updated weights for policy 0, policy_version 3848 (0.0014)
[2023-02-24 17:37:28,214][2364831] Updated weights for policy 0, policy_version 3858 (0.0010)
[2023-02-24 17:37:29,243][2364831] Updated weights for policy 0, policy_version 3868 (0.0013)
[2023-02-24 17:37:30,235][2364831] Updated weights for policy 0, policy_version 3878 (0.0009)
[2023-02-24 17:37:31,194][2364831] Updated weights for policy 0, policy_version 3888 (0.0010)
[2023-02-24 17:37:31,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41028.3, 300 sec: 41101.2). Total num frames: 15925248. Throughput: 0: 10260.7. Samples: 2957538. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:37:31,266][2364708] Avg episode reward: [(0, '33.478')]
[2023-02-24 17:37:32,210][2364831] Updated weights for policy 0, policy_version 3898 (0.0011)
[2023-02-24 17:37:33,187][2364831] Updated weights for policy 0, policy_version 3908 (0.0013)
[2023-02-24 17:37:34,160][2364831] Updated weights for policy 0, policy_version 3918 (0.0012)
[2023-02-24 17:37:35,197][2364831] Updated weights for policy 0, policy_version 3928 (0.0012)
[2023-02-24 17:37:36,189][2364831] Updated weights for policy 0, policy_version 3938 (0.0012)
[2023-02-24 17:37:36,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.3, 300 sec: 41098.8). Total num frames: 16130048. Throughput: 0: 10267.2. Samples: 3019524. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
[2023-02-24 17:37:36,266][2364708] Avg episode reward: [(0, '34.030')]
[2023-02-24 17:37:37,168][2364831] Updated weights for policy 0, policy_version 3948 (0.0010)
[2023-02-24 17:37:38,212][2364831] Updated weights for policy 0, policy_version 3958 (0.0010)
[2023-02-24 17:37:39,181][2364831] Updated weights for policy 0, policy_version 3968 (0.0009)
[2023-02-24 17:37:40,158][2364831] Updated weights for policy 0, policy_version 3978 (0.0012)
[2023-02-24 17:37:41,178][2364831] Updated weights for policy 0, policy_version 3988 (0.0011)
[2023-02-24 17:37:41,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41028.3, 300 sec: 41223.8). Total num frames: 16334848. Throughput: 0: 10262.3. Samples: 3080874. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:37:41,266][2364708] Avg episode reward: [(0, '30.119')]
[2023-02-24 17:37:42,173][2364831] Updated weights for policy 0, policy_version 3998 (0.0009)
[2023-02-24 17:37:43,173][2364831] Updated weights for policy 0, policy_version 4008 (0.0012)
[2023-02-24 17:37:44,204][2364831] Updated weights for policy 0, policy_version 4018 (0.0013)
[2023-02-24 17:37:45,182][2364831] Updated weights for policy 0, policy_version 4028 (0.0015)
[2023-02-24 17:37:46,192][2364831] Updated weights for policy 0, policy_version 4038 (0.0010)
[2023-02-24 17:37:46,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41028.2, 300 sec: 41209.9). Total num frames: 16539648. Throughput: 0: 10264.2. Samples: 3111642. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:37:46,266][2364708] Avg episode reward: [(0, '34.674')]
[2023-02-24 17:37:47,165][2364831] Updated weights for policy 0, policy_version 4048 (0.0009)
[2023-02-24 17:37:48,150][2364831] Updated weights for policy 0, policy_version 4058 (0.0009)
[2023-02-24 17:37:49,155][2364831] Updated weights for policy 0, policy_version 4068 (0.0010)
[2023-02-24 17:37:50,176][2364831] Updated weights for policy 0, policy_version 4078 (0.0011)
[2023-02-24 17:37:51,128][2364831] Updated weights for policy 0, policy_version 4088 (0.0013)
[2023-02-24 17:37:51,266][2364708] Fps is (10 sec: 41369.0, 60 sec: 41096.4, 300 sec: 41209.9). Total num frames: 16748544. Throughput: 0: 10268.4. Samples: 3173304. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:37:51,267][2364708] Avg episode reward: [(0, '33.236')]
[2023-02-24 17:37:52,111][2364831] Updated weights for policy 0, policy_version 4098 (0.0009)
[2023-02-24 17:37:53,146][2364831] Updated weights for policy 0, policy_version 4108 (0.0014)
[2023-02-24 17:37:54,142][2364831] Updated weights for policy 0, policy_version 4118 (0.0012)
[2023-02-24 17:37:55,117][2364831] Updated weights for policy 0, policy_version 4128 (0.0010)
[2023-02-24 17:37:56,172][2364831] Updated weights for policy 0, policy_version 4138 (0.0011)
[2023-02-24 17:37:56,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41028.2, 300 sec: 41209.9). Total num frames: 16953344. Throughput: 0: 10265.4. Samples: 3234927. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:37:56,266][2364708] Avg episode reward: [(0, '33.288')]
[2023-02-24 17:37:57,176][2364831] Updated weights for policy 0, policy_version 4148 (0.0009)
[2023-02-24 17:37:58,108][2364831] Updated weights for policy 0, policy_version 4158 (0.0010)
[2023-02-24 17:37:59,170][2364831] Updated weights for policy 0, policy_version 4168 (0.0016)
[2023-02-24 17:38:00,167][2364831] Updated weights for policy 0, policy_version 4178 (0.0016)
[2023-02-24 17:38:01,108][2364831] Updated weights for policy 0, policy_version 4188 (0.0011)
[2023-02-24 17:38:01,266][2364708] Fps is (10 sec: 40550.7, 60 sec: 41028.2, 300 sec: 41182.2). Total num frames: 17154048. Throughput: 0: 10261.8. Samples: 3265563. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0)
[2023-02-24 17:38:01,266][2364708] Avg episode reward: [(0, '35.841')]
[2023-02-24 17:38:01,270][2364791] Saving new best policy, reward=35.841!
[2023-02-24 17:38:02,155][2364831] Updated weights for policy 0, policy_version 4198 (0.0012)
[2023-02-24 17:38:03,132][2364831] Updated weights for policy 0, policy_version 4208 (0.0009)
[2023-02-24 17:38:04,177][2364831] Updated weights for policy 0, policy_version 4218 (0.0012)
[2023-02-24 17:38:05,155][2364831] Updated weights for policy 0, policy_version 4228 (0.0013)
[2023-02-24 17:38:06,137][2364831] Updated weights for policy 0, policy_version 4238 (0.0010)
[2023-02-24 17:38:06,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.3, 300 sec: 41182.2). Total num frames: 17362944. Throughput: 0: 10260.6. Samples: 3327027. Policy #0 lag: (min: 1.0, avg: 2.0, max: 4.0)
[2023-02-24 17:38:06,266][2364708] Avg episode reward: [(0, '34.701')]
[2023-02-24 17:38:07,128][2364831] Updated weights for policy 0, policy_version 4248 (0.0010)
[2023-02-24 17:38:08,120][2364831] Updated weights for policy 0, policy_version 4258 (0.0009)
[2023-02-24 17:38:09,120][2364831] Updated weights for policy 0, policy_version 4268 (0.0010)
[2023-02-24 17:38:10,112][2364831] Updated weights for policy 0, policy_version 4278 (0.0009)
[2023-02-24 17:38:11,084][2364831] Updated weights for policy 0, policy_version 4288 (0.0009)
[2023-02-24 17:38:11,266][2364708] Fps is (10 sec: 41368.9, 60 sec: 41028.1, 300 sec: 41182.1). Total num frames: 17567744. Throughput: 0: 10268.7. Samples: 3388911. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:38:11,267][2364708] Avg episode reward: [(0, '32.559')]
[2023-02-24 17:38:12,108][2364831] Updated weights for policy 0, policy_version 4298 (0.0009)
[2023-02-24 17:38:13,088][2364831] Updated weights for policy 0, policy_version 4308 (0.0011)
[2023-02-24 17:38:14,094][2364831] Updated weights for policy 0, policy_version 4318 (0.0009)
[2023-02-24 17:38:15,081][2364831] Updated weights for policy 0, policy_version 4328 (0.0009)
[2023-02-24 17:38:16,054][2364831] Updated weights for policy 0, policy_version 4338 (0.0010)
[2023-02-24 17:38:16,266][2364708] Fps is (10 sec: 40959.2, 60 sec: 41028.1, 300 sec: 41168.2). Total num frames: 17772544. Throughput: 0: 10274.2. Samples: 3419880. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:38:16,267][2364708] Avg episode reward: [(0, '32.783')]
[2023-02-24 17:38:17,103][2364831] Updated weights for policy 0, policy_version 4348 (0.0012)
[2023-02-24 17:38:18,095][2364831] Updated weights for policy 0, policy_version 4358 (0.0009)
[2023-02-24 17:38:19,078][2364831] Updated weights for policy 0, policy_version 4368 (0.0011)
[2023-02-24 17:38:20,078][2364831] Updated weights for policy 0, policy_version 4378 (0.0012)
[2023-02-24 17:38:21,065][2364831] Updated weights for policy 0, policy_version 4388 (0.0016)
[2023-02-24 17:38:21,266][2364708] Fps is (10 sec: 41370.7, 60 sec: 41096.6, 300 sec: 41182.2). Total num frames: 17981440. Throughput: 0: 10262.9. Samples: 3481353. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:38:21,266][2364708] Avg episode reward: [(0, '35.299')]
[2023-02-24 17:38:22,058][2364831] Updated weights for policy 0, policy_version 4398 (0.0012)
[2023-02-24 17:38:23,045][2364831] Updated weights for policy 0, policy_version 4408 (0.0010)
[2023-02-24 17:38:24,107][2364831] Updated weights for policy 0, policy_version 4418 (0.0011)
[2023-02-24 17:38:25,058][2364831] Updated weights for policy 0, policy_version 4428 (0.0009)
[2023-02-24 17:38:26,042][2364831] Updated weights for policy 0, policy_version 4438 (0.0012)
[2023-02-24 17:38:26,266][2364708] Fps is (10 sec: 40960.7, 60 sec: 41028.2, 300 sec: 41154.4). Total num frames: 18182144. Throughput: 0: 10268.6. Samples: 3542961. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:38:26,266][2364708] Avg episode reward: [(0, '33.602')]
[2023-02-24 17:38:27,045][2364831] Updated weights for policy 0, policy_version 4448 (0.0013)
[2023-02-24 17:38:28,079][2364831] Updated weights for policy 0, policy_version 4458 (0.0009)
[2023-02-24 17:38:29,077][2364831] Updated weights for policy 0, policy_version 4468 (0.0012)
[2023-02-24 17:38:30,014][2364831] Updated weights for policy 0, policy_version 4478 (0.0014)
[2023-02-24 17:38:31,056][2364831] Updated weights for policy 0, policy_version 4488 (0.0014)
[2023-02-24 17:38:31,266][2364708] Fps is (10 sec: 40959.3, 60 sec: 41096.5, 300 sec: 41168.3). Total num frames: 18391040. Throughput: 0: 10269.4. Samples: 3573768. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0)
[2023-02-24 17:38:31,266][2364708] Avg episode reward: [(0, '30.251')]
[2023-02-24 17:38:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004490_18391040.pth...
[2023-02-24 17:38:31,336][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000002080_8519680.pth
[2023-02-24 17:38:32,050][2364831] Updated weights for policy 0, policy_version 4498 (0.0012)
[2023-02-24 17:38:33,042][2364831] Updated weights for policy 0, policy_version 4508 (0.0009)
[2023-02-24 17:38:34,048][2364831] Updated weights for policy 0, policy_version 4518 (0.0010)
[2023-02-24 17:38:35,020][2364831] Updated weights for policy 0, policy_version 4528 (0.0010)
[2023-02-24 17:38:36,020][2364831] Updated weights for policy 0, policy_version 4538 (0.0010)
[2023-02-24 17:38:36,266][2364708] Fps is (10 sec: 41369.6, 60 sec: 41096.5, 300 sec: 41140.5). Total num frames: 18595840. Throughput: 0: 10268.5. Samples: 3635388. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0)
[2023-02-24 17:38:36,266][2364708] Avg episode reward: [(0, '34.728')]
[2023-02-24 17:38:37,018][2364831] Updated weights for policy 0, policy_version 4548 (0.0012)
[2023-02-24 17:38:37,996][2364831] Updated weights for policy 0, policy_version 4558 (0.0009)
[2023-02-24 17:38:39,029][2364831] Updated weights for policy 0, policy_version 4568 (0.0010)
[2023-02-24 17:38:40,017][2364831] Updated weights for policy 0, policy_version 4578 (0.0010)
[2023-02-24 17:38:40,985][2364831] Updated weights for policy 0, policy_version 4588 (0.0010)
[2023-02-24 17:38:41,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.4, 300 sec: 41154.4). Total num frames: 18800640. Throughput: 0: 10268.8. Samples: 3697023. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
[2023-02-24 17:38:41,267][2364708] Avg episode reward: [(0, '32.483')]
[2023-02-24 17:38:42,014][2364831] Updated weights for policy 0, policy_version 4598 (0.0014)
[2023-02-24 17:38:42,975][2364831] Updated weights for policy 0, policy_version 4608 (0.0009)
[2023-02-24 17:38:44,032][2364831] Updated weights for policy 0, policy_version 4618 (0.0009)
[2023-02-24 17:38:45,014][2364831] Updated weights for policy 0, policy_version 4628 (0.0011)
[2023-02-24 17:38:45,974][2364831] Updated weights for policy 0, policy_version 4638 (0.0012)
[2023-02-24 17:38:46,266][2364708] Fps is (10 sec: 41370.5, 60 sec: 41164.9, 300 sec: 41168.3). Total num frames: 19009536. Throughput: 0: 10273.0. Samples: 3727845. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
[2023-02-24 17:38:46,266][2364708] Avg episode reward: [(0, '34.188')]
[2023-02-24 17:38:47,022][2364831] Updated weights for policy 0, policy_version 4648 (0.0014)
[2023-02-24 17:38:48,027][2364831] Updated weights for policy 0, policy_version 4658 (0.0013)
[2023-02-24 17:38:49,020][2364831] Updated weights for policy 0, policy_version 4668 (0.0010)
[2023-02-24 17:38:50,024][2364831] Updated weights for policy 0, policy_version 4678 (0.0010)
[2023-02-24 17:38:51,024][2364831] Updated weights for policy 0, policy_version 4688 (0.0011)
[2023-02-24 17:38:51,266][2364708] Fps is (10 sec: 40960.4, 60 sec: 41028.3, 300 sec: 41140.5). Total num frames: 19210240. Throughput: 0: 10270.9. Samples: 3789216. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
[2023-02-24 17:38:51,266][2364708] Avg episode reward: [(0, '36.140')]
[2023-02-24 17:38:51,270][2364791] Saving new best policy, reward=36.140!
[2023-02-24 17:38:52,009][2364831] Updated weights for policy 0, policy_version 4698 (0.0012)
[2023-02-24 17:38:53,006][2364831] Updated weights for policy 0, policy_version 4708 (0.0011)
[2023-02-24 17:38:54,017][2364831] Updated weights for policy 0, policy_version 4718 (0.0012)
[2023-02-24 17:38:54,981][2364831] Updated weights for policy 0, policy_version 4728 (0.0011)
[2023-02-24 17:38:55,968][2364831] Updated weights for policy 0, policy_version 4738 (0.0012)
[2023-02-24 17:38:56,266][2364708] Fps is (10 sec: 40959.4, 60 sec: 41096.6, 300 sec: 41154.4). Total num frames: 19419136. Throughput: 0: 10265.0. Samples: 3850833. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
[2023-02-24 17:38:56,266][2364708] Avg episode reward: [(0, '32.669')]
[2023-02-24 17:38:56,994][2364831] Updated weights for policy 0, policy_version 4748 (0.0011)
[2023-02-24 17:38:57,985][2364831] Updated weights for policy 0, policy_version 4758 (0.0008)
[2023-02-24 17:38:58,970][2364831] Updated weights for policy 0, policy_version 4768 (0.0010)
[2023-02-24 17:38:59,953][2364831] Updated weights for policy 0, policy_version 4778 (0.0010)
[2023-02-24 17:39:00,969][2364831] Updated weights for policy 0, policy_version 4788 (0.0012)
[2023-02-24 17:39:01,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 41164.8, 300 sec: 41140.5). Total num frames: 19623936. Throughput: 0: 10264.2. Samples: 3881769. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:39:01,266][2364708] Avg episode reward: [(0, '33.503')]
[2023-02-24 17:39:01,956][2364831] Updated weights for policy 0, policy_version 4798 (0.0011)
[2023-02-24 17:39:02,959][2364831] Updated weights for policy 0, policy_version 4808 (0.0009)
[2023-02-24 17:39:03,937][2364831] Updated weights for policy 0, policy_version 4818 (0.0010)
[2023-02-24 17:39:04,994][2364831] Updated weights for policy 0, policy_version 4828 (0.0012)
[2023-02-24 17:39:05,948][2364831] Updated weights for policy 0, policy_version 4838 (0.0009)
[2023-02-24 17:39:06,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41096.5, 300 sec: 41140.5). Total num frames: 19828736. Throughput: 0: 10266.0. Samples: 3943326. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
[2023-02-24 17:39:06,266][2364708] Avg episode reward: [(0, '33.048')]
[2023-02-24 17:39:06,927][2364831] Updated weights for policy 0, policy_version 4848 (0.0009)
[2023-02-24 17:39:07,963][2364831] Updated weights for policy 0, policy_version 4858 (0.0010)
[2023-02-24 17:39:08,957][2364831] Updated weights for policy 0, policy_version 4868 (0.0013)
[2023-02-24 17:39:09,952][2364831] Updated weights for policy 0, policy_version 4878 (0.0009)
[2023-02-24 17:39:10,563][2364791] Stopping Batcher_0...
[2023-02-24 17:39:10,563][2364708] Component Batcher_0 stopped!
[2023-02-24 17:39:10,564][2364791] Loop batcher_evt_loop terminating...
[2023-02-24 17:39:10,566][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
[2023-02-24 17:39:10,580][2365108] Stopping RolloutWorker_w15...
[2023-02-24 17:39:10,580][2364708] Component RolloutWorker_w15 stopped!
[2023-02-24 17:39:10,580][2364862] Stopping RolloutWorker_w14...
[2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w14 stopped!
[2023-02-24 17:39:10,581][2364855] Stopping RolloutWorker_w10...
[2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w10 stopped!
[2023-02-24 17:39:10,581][2364855] Loop rollout_proc10_evt_loop terminating...
[2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w0 stopped!
[2023-02-24 17:39:10,581][2365108] Loop rollout_proc15_evt_loop terminating...
[2023-02-24 17:39:10,581][2364832] Stopping RolloutWorker_w0...
[2023-02-24 17:39:10,582][2364862] Loop rollout_proc14_evt_loop terminating...
[2023-02-24 17:39:10,582][2364708] Component RolloutWorker_w3 stopped!
[2023-02-24 17:39:10,582][2364836] Stopping RolloutWorker_w3...
[2023-02-24 17:39:10,582][2364857] Stopping RolloutWorker_w11...
[2023-02-24 17:39:10,582][2364832] Loop rollout_proc0_evt_loop terminating...
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w11 stopped!
[2023-02-24 17:39:10,583][2364836] Loop rollout_proc3_evt_loop terminating...
[2023-02-24 17:39:10,583][2364859] Stopping RolloutWorker_w8...
[2023-02-24 17:39:10,583][2364857] Loop rollout_proc11_evt_loop terminating...
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w8 stopped!
[2023-02-24 17:39:10,583][2364861] Stopping RolloutWorker_w13...
[2023-02-24 17:39:10,583][2364833] Stopping RolloutWorker_w1...
[2023-02-24 17:39:10,583][2364839] Stopping RolloutWorker_w7...
[2023-02-24 17:39:10,583][2364838] Stopping RolloutWorker_w6...
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w13 stopped!
[2023-02-24 17:39:10,583][2364861] Loop rollout_proc13_evt_loop terminating...
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w1 stopped!
[2023-02-24 17:39:10,583][2364833] Loop rollout_proc1_evt_loop terminating...
[2023-02-24 17:39:10,583][2364838] Loop rollout_proc6_evt_loop terminating...
[2023-02-24 17:39:10,583][2364839] Loop rollout_proc7_evt_loop terminating...
[2023-02-24 17:39:10,583][2364860] Stopping RolloutWorker_w12...
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w7 stopped!
[2023-02-24 17:39:10,584][2364708] Component RolloutWorker_w6 stopped!
[2023-02-24 17:39:10,584][2364860] Loop rollout_proc12_evt_loop terminating...
[2023-02-24 17:39:10,584][2364708] Component RolloutWorker_w12 stopped!
[2023-02-24 17:39:10,583][2364859] Loop rollout_proc8_evt_loop terminating...
[2023-02-24 17:39:10,585][2364708] Component RolloutWorker_w9 stopped!
[2023-02-24 17:39:10,585][2364856] Stopping RolloutWorker_w9...
[2023-02-24 17:39:10,585][2364856] Loop rollout_proc9_evt_loop terminating...
[2023-02-24 17:39:10,585][2364708] Component RolloutWorker_w4 stopped!
[2023-02-24 17:39:10,585][2364835] Stopping RolloutWorker_w4...
[2023-02-24 17:39:10,586][2364835] Loop rollout_proc4_evt_loop terminating...
[2023-02-24 17:39:10,591][2364831] Weights refcount: 2 0
[2023-02-24 17:39:10,596][2364831] Stopping InferenceWorker_p0-w0...
[2023-02-24 17:39:10,596][2364708] Component InferenceWorker_p0-w0 stopped!
[2023-02-24 17:39:10,596][2364831] Loop inference_proc0-0_evt_loop terminating...
[2023-02-24 17:39:10,664][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000003287_13463552.pth
[2023-02-24 17:39:10,667][2364837] Stopping RolloutWorker_w5...
[2023-02-24 17:39:10,667][2364708] Component RolloutWorker_w5 stopped!
[2023-02-24 17:39:10,667][2364837] Loop rollout_proc5_evt_loop terminating...
[2023-02-24 17:39:10,675][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
[2023-02-24 17:39:10,679][2364834] Stopping RolloutWorker_w2...
[2023-02-24 17:39:10,679][2364708] Component RolloutWorker_w2 stopped!
[2023-02-24 17:39:10,679][2364834] Loop rollout_proc2_evt_loop terminating...
[2023-02-24 17:39:10,810][2364791] Stopping LearnerWorker_p0...
[2023-02-24 17:39:10,810][2364708] Component LearnerWorker_p0 stopped!
[2023-02-24 17:39:10,811][2364791] Loop learner_proc0_evt_loop terminating...
[2023-02-24 17:39:10,811][2364708] Waiting for process learner_proc0 to stop...
[2023-02-24 17:39:11,642][2364708] Waiting for process inference_proc0-0 to join...
[2023-02-24 17:39:11,642][2364708] Waiting for process rollout_proc0 to join...
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc1 to join...
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc2 to join...
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc3 to join...
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc4 to join...
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc5 to join...
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc6 to join...
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc7 to join...
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc8 to join...
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc9 to join...
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc10 to join...
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc11 to join...
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc12 to join...
[2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc13 to join...
[2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc14 to join...
[2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc15 to join...
[2023-02-24 17:39:11,645][2364708] Batcher 0 profile tree view:
batching: 73.4519, releasing_batches: 0.1153
[2023-02-24 17:39:11,645][2364708] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0001
  wait_policy_total: 14.4354
update_model: 8.0668
  weight_update: 0.0009
one_step: 0.0083
  handle_policy_step: 352.4861
    deserialize: 37.8441, stack: 1.8339, obs_to_device_normalize: 110.8509, forward: 112.2633, send_messages: 30.0739
    prepare_outputs: 46.8292
      to_cpu: 31.2023
[2023-02-24 17:39:11,646][2364708] Learner 0 profile tree view:
misc: 0.0142, prepare_batch: 21.8985
train: 88.0533
  epoch_init: 0.0176, minibatch_init: 0.0202, losses_postprocess: 1.0969, kl_divergence: 0.8556, after_optimizer: 0.9595
  calculate_losses: 27.5889
    losses_init: 0.0102, forward_head: 2.8021, bptt_initial: 14.7305, tail: 1.9333, advantages_returns: 0.5209, losses: 3.3108
    bptt: 3.7098
      bptt_forward_core: 3.5507
  update: 56.2303
    clip: 3.0247
[2023-02-24 17:39:11,646][2364708] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.1784, enqueue_policy_requests: 13.5703, env_step: 193.6379, overhead: 19.5570, complete_rollouts: 0.3859
save_policy_outputs: 14.2004
  split_output_tensors: 6.7511
[2023-02-24 17:39:11,646][2364708] RolloutWorker_w15 profile tree view:
wait_for_trajectories: 0.1858, enqueue_policy_requests: 14.0534, env_step: 199.4115, overhead: 20.2979, complete_rollouts: 0.3205
save_policy_outputs: 14.6899
  split_output_tensors: 6.9819
[2023-02-24 17:39:11,646][2364708] Loop Runner_EvtLoop terminating...
[2023-02-24 17:39:11,646][2364708] Runner profile tree view:
main_loop: 398.6762
[2023-02-24 17:39:11,647][2364708] Collected {0: 20004864}, FPS: 40130.2
[2023-02-24 17:39:11,652][2364708] Loading existing experiment configuration from train_dir/default_experiment/config.json
[2023-02-24 17:39:11,652][2364708] Overriding arg 'train_dir' with value 'train_dir' passed from command line
[2023-02-24 17:39:11,652][2364708] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-24 17:39:11,652][2364708] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-24 17:39:11,652][2364708] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-24 17:39:11,652][2364708] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 17:39:11,652][2364708] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-24 17:39:11,652][2364708] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 17:39:11,653][2364708] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-24 17:39:11,653][2364708] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-24 17:39:11,653][2364708] Adding new argument 'hf_repository'='eldraco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-24 17:39:11,653][2364708] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-24 17:39:11,653][2364708] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-24 17:39:11,653][2364708] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-24 17:39:11,653][2364708] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-24 17:39:11,653][2364708] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-24 17:39:11,659][2364708] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 17:39:11,659][2364708] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 17:39:11,660][2364708] RunningMeanStd input shape: (1,)
[2023-02-24 17:39:11,667][2364708] ConvEncoder: input_channels=3
[2023-02-24 17:39:11,779][2364708] Conv encoder output size: 512
[2023-02-24 17:39:11,779][2364708] Policy head output size: 512
[2023-02-24 17:39:13,104][2364708] Loading state from checkpoint train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
[2023-02-24 17:39:13,883][2364708] Num frames 100...
[2023-02-24 17:39:13,953][2364708] Num frames 200...
[2023-02-24 17:39:14,021][2364708] Num frames 300...
[2023-02-24 17:39:14,089][2364708] Num frames 400...
[2023-02-24 17:39:14,160][2364708] Num frames 500...
[2023-02-24 17:39:14,229][2364708] Num frames 600...
[2023-02-24 17:39:14,297][2364708] Num frames 700...
[2023-02-24 17:39:14,365][2364708] Num frames 800...
[2023-02-24 17:39:14,435][2364708] Num frames 900...
[2023-02-24 17:39:14,505][2364708] Num frames 1000...
[2023-02-24 17:39:14,575][2364708] Num frames 1100...
[2023-02-24 17:39:14,645][2364708] Num frames 1200...
[2023-02-24 17:39:14,714][2364708] Num frames 1300...
[2023-02-24 17:39:14,784][2364708] Num frames 1400...
[2023-02-24 17:39:14,886][2364708] Avg episode rewards: #0: 34.720, true rewards: #0: 14.720
[2023-02-24 17:39:14,887][2364708] Avg episode reward: 34.720, avg true_objective: 14.720
[2023-02-24 17:39:14,917][2364708] Num frames 1500...
[2023-02-24 17:39:14,998][2364708] Num frames 1600...
[2023-02-24 17:39:15,067][2364708] Num frames 1700...
[2023-02-24 17:39:15,138][2364708] Num frames 1800...
[2023-02-24 17:39:15,208][2364708] Num frames 1900...
[2023-02-24 17:39:15,277][2364708] Num frames 2000...
[2023-02-24 17:39:15,347][2364708] Num frames 2100...
[2023-02-24 17:39:15,415][2364708] Num frames 2200...
[2023-02-24 17:39:15,485][2364708] Num frames 2300...
[2023-02-24 17:39:15,554][2364708] Num frames 2400...
[2023-02-24 17:39:15,621][2364708] Num frames 2500...
[2023-02-24 17:39:15,714][2364708] Avg episode rewards: #0: 31.300, true rewards: #0: 12.800
[2023-02-24 17:39:15,715][2364708] Avg episode reward: 31.300, avg true_objective: 12.800
[2023-02-24 17:39:15,758][2364708] Num frames 2600...
[2023-02-24 17:39:15,831][2364708] Num frames 2700...
[2023-02-24 17:39:15,900][2364708] Num frames 2800...
[2023-02-24 17:39:15,969][2364708] Num frames 2900...
[2023-02-24 17:39:16,037][2364708] Num frames 3000...
[2023-02-24 17:39:16,106][2364708] Num frames 3100...
[2023-02-24 17:39:16,177][2364708] Num frames 3200...
[2023-02-24 17:39:16,247][2364708] Num frames 3300...
[2023-02-24 17:39:16,316][2364708] Num frames 3400...
[2023-02-24 17:39:16,386][2364708] Num frames 3500...
[2023-02-24 17:39:16,455][2364708] Num frames 3600...
[2023-02-24 17:39:16,526][2364708] Num frames 3700...
[2023-02-24 17:39:16,596][2364708] Num frames 3800...
[2023-02-24 17:39:16,665][2364708] Num frames 3900...
[2023-02-24 17:39:16,734][2364708] Num frames 4000...
[2023-02-24 17:39:16,802][2364708] Num frames 4100...
[2023-02-24 17:39:16,871][2364708] Num frames 4200...
[2023-02-24 17:39:16,941][2364708] Num frames 4300...
[2023-02-24 17:39:17,010][2364708] Num frames 4400...
[2023-02-24 17:39:17,078][2364708] Num frames 4500...
[2023-02-24 17:39:17,148][2364708] Num frames 4600...
[2023-02-24 17:39:17,244][2364708] Avg episode rewards: #0: 41.533, true rewards: #0: 15.533
[2023-02-24 17:39:17,244][2364708] Avg episode reward: 41.533, avg true_objective: 15.533
[2023-02-24 17:39:17,288][2364708] Num frames 4700...
[2023-02-24 17:39:17,360][2364708] Num frames 4800...
[2023-02-24 17:39:17,430][2364708] Num frames 4900...
[2023-02-24 17:39:17,499][2364708] Num frames 5000...
[2023-02-24 17:39:17,569][2364708] Num frames 5100...
[2023-02-24 17:39:17,640][2364708] Num frames 5200...
[2023-02-24 17:39:17,720][2364708] Avg episode rewards: #0: 34.100, true rewards: #0: 13.100
[2023-02-24 17:39:17,720][2364708] Avg episode reward: 34.100, avg true_objective: 13.100
[2023-02-24 17:39:17,789][2364708] Num frames 5300...
[2023-02-24 17:39:17,857][2364708] Num frames 5400...
[2023-02-24 17:39:17,926][2364708] Num frames 5500...
[2023-02-24 17:39:17,995][2364708] Num frames 5600...
[2023-02-24 17:39:18,063][2364708] Num frames 5700...
[2023-02-24 17:39:18,132][2364708] Num frames 5800...
[2023-02-24 17:39:18,195][2364708] Avg episode rewards: #0: 29.232, true rewards: #0: 11.632
[2023-02-24 17:39:18,195][2364708] Avg episode reward: 29.232, avg true_objective: 11.632
[2023-02-24 17:39:18,273][2364708] Num frames 5900...
[2023-02-24 17:39:18,342][2364708] Num frames 6000...
[2023-02-24 17:39:18,409][2364708] Num frames 6100...
[2023-02-24 17:39:18,482][2364708] Num frames 6200...
[2023-02-24 17:39:18,552][2364708] Num frames 6300...
[2023-02-24 17:39:18,646][2364708] Avg episode rewards: #0: 25.600, true rewards: #0: 10.600
[2023-02-24 17:39:18,646][2364708] Avg episode reward: 25.600, avg true_objective: 10.600
[2023-02-24 17:39:18,691][2364708] Num frames 6400...
[2023-02-24 17:39:18,767][2364708] Num frames 6500...
[2023-02-24 17:39:18,835][2364708] Num frames 6600...
[2023-02-24 17:39:18,904][2364708] Num frames 6700...
[2023-02-24 17:39:18,972][2364708] Num frames 6800...
[2023-02-24 17:39:19,041][2364708] Num frames 6900...
[2023-02-24 17:39:19,110][2364708] Num frames 7000...
[2023-02-24 17:39:19,179][2364708] Num frames 7100...
[2023-02-24 17:39:19,249][2364708] Num frames 7200...
[2023-02-24 17:39:19,318][2364708] Num frames 7300...
[2023-02-24 17:39:19,388][2364708] Num frames 7400...
[2023-02-24 17:39:19,458][2364708] Num frames 7500...
[2023-02-24 17:39:19,528][2364708] Num frames 7600...
[2023-02-24 17:39:19,598][2364708] Num frames 7700...
[2023-02-24 17:39:19,667][2364708] Num frames 7800...
[2023-02-24 17:39:19,736][2364708] Num frames 7900...
[2023-02-24 17:39:19,808][2364708] Avg episode rewards: #0: 28.040, true rewards: #0: 11.326
[2023-02-24 17:39:19,808][2364708] Avg episode reward: 28.040, avg true_objective: 11.326
[2023-02-24 17:39:19,879][2364708] Num frames 8000...
[2023-02-24 17:39:19,948][2364708] Num frames 8100...
[2023-02-24 17:39:20,017][2364708] Num frames 8200...
[2023-02-24 17:39:20,086][2364708] Num frames 8300...
[2023-02-24 17:39:20,155][2364708] Num frames 8400...
[2023-02-24 17:39:20,225][2364708] Num frames 8500...
[2023-02-24 17:39:20,294][2364708] Num frames 8600...
[2023-02-24 17:39:20,363][2364708] Num frames 8700...
[2023-02-24 17:39:20,432][2364708] Num frames 8800...
[2023-02-24 17:39:20,501][2364708] Num frames 8900...
[2023-02-24 17:39:20,571][2364708] Num frames 9000...
[2023-02-24 17:39:20,640][2364708] Num frames 9100...
[2023-02-24 17:39:20,711][2364708] Num frames 9200...
[2023-02-24 17:39:20,781][2364708] Num frames 9300...
[2023-02-24 17:39:20,850][2364708] Num frames 9400...
[2023-02-24 17:39:20,919][2364708] Num frames 9500...
[2023-02-24 17:39:20,990][2364708] Num frames 9600...
[2023-02-24 17:39:21,060][2364708] Num frames 9700...
[2023-02-24 17:39:21,130][2364708] Num frames 9800...
[2023-02-24 17:39:21,198][2364708] Num frames 9900...
[2023-02-24 17:39:21,269][2364708] Num frames 10000...
[2023-02-24 17:39:21,341][2364708] Avg episode rewards: #0: 32.035, true rewards: #0: 12.535
[2023-02-24 17:39:21,341][2364708] Avg episode reward: 32.035, avg true_objective: 12.535
[2023-02-24 17:39:21,412][2364708] Num frames 10100...
[2023-02-24 17:39:21,481][2364708] Num frames 10200...
[2023-02-24 17:39:21,551][2364708] Num frames 10300...
[2023-02-24 17:39:21,621][2364708] Num frames 10400...
[2023-02-24 17:39:21,691][2364708] Num frames 10500...
[2023-02-24 17:39:21,759][2364708] Num frames 10600...
[2023-02-24 17:39:21,828][2364708] Num frames 10700...
[2023-02-24 17:39:21,897][2364708] Num frames 10800...
[2023-02-24 17:39:21,966][2364708] Num frames 10900...
[2023-02-24 17:39:22,035][2364708] Num frames 11000...
[2023-02-24 17:39:22,117][2364708] Avg episode rewards: #0: 31.603, true rewards: #0: 12.270
[2023-02-24 17:39:22,118][2364708] Avg episode reward: 31.603, avg true_objective: 12.270
[2023-02-24 17:39:22,180][2364708] Num frames 11100...
[2023-02-24 17:39:22,251][2364708] Num frames 11200...
[2023-02-24 17:39:22,320][2364708] Num frames 11300...
[2023-02-24 17:39:22,389][2364708] Num frames 11400...
[2023-02-24 17:39:22,458][2364708] Num frames 11500...
[2023-02-24 17:39:22,527][2364708] Num frames 11600...
[2023-02-24 17:39:22,596][2364708] Num frames 11700...
[2023-02-24 17:39:22,666][2364708] Num frames 11800...
[2023-02-24 17:39:22,735][2364708] Num frames 11900...
[2023-02-24 17:39:22,804][2364708] Num frames 12000...
[2023-02-24 17:39:22,874][2364708] Num frames 12100...
[2023-02-24 17:39:22,944][2364708] Num frames 12200...
[2023-02-24 17:39:23,013][2364708] Num frames 12300...
[2023-02-24 17:39:23,082][2364708] Num frames 12400...
[2023-02-24 17:39:23,152][2364708] Num frames 12500...
[2023-02-24 17:39:23,220][2364708] Num frames 12600...
[2023-02-24 17:39:23,289][2364708] Num frames 12700...
[2023-02-24 17:39:23,360][2364708] Num frames 12800...
[2023-02-24 17:39:23,433][2364708] Avg episode rewards: #0: 33.229, true rewards: #0: 12.829
[2023-02-24 17:39:23,433][2364708] Avg episode reward: 33.229, avg true_objective: 12.829
[2023-02-24 17:39:39,087][2364708] Replay video saved to train_dir/default_experiment/replay.mp4!
[2023-02-24 17:39:45,076][2364708] The model has been pushed to https://huggingface.co/eldraco/rl_course_vizdoom_health_gathering_supreme
[2023-02-25 11:13:23,382][2391555] Saving configuration to /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/config.json...
[2023-02-25 11:13:23,382][2391555] Rollout worker 0 uses device cpu
[2023-02-25 11:13:23,382][2391555] Rollout worker 1 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 2 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 3 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 4 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 5 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 6 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 7 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 8 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 9 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 10 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 11 uses device cpu
[2023-02-25 11:13:23,383][2391555] Rollout worker 12 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 13 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 14 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 15 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 16 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 17 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 18 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 19 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 20 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 21 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 22 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 23 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 24 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 25 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 26 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 27 uses device cpu
[2023-02-25 11:13:23,384][2391555] Rollout worker 28 uses device cpu
[2023-02-25 11:13:23,385][2391555] Rollout worker 29 uses device cpu
[2023-02-25 11:13:23,385][2391555] Rollout worker 30 uses device cpu
[2023-02-25 11:13:23,385][2391555] Rollout worker 31 uses device cpu
[2023-02-25 11:13:23,820][2391555] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-25 11:13:23,821][2391555] InferenceWorker_p0-w0: min num requests: 10
[2023-02-25 11:13:23,889][2391555] Starting all processes...
[2023-02-25 11:13:23,889][2391555] Starting process learner_proc0
[2023-02-25 11:13:24,631][2391555] Starting all processes...
[2023-02-25 11:13:24,637][2391555] Starting process inference_proc0-0
[2023-02-25 11:13:24,638][2391646] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-25 11:13:24,638][2391646] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2023-02-25 11:13:24,639][2391555] Starting process rollout_proc0
[2023-02-25 11:13:24,639][2391555] Starting process rollout_proc1
[2023-02-25 11:13:24,639][2391555] Starting process rollout_proc2
[2023-02-25 11:13:24,640][2391555] Starting process rollout_proc3
[2023-02-25 11:13:24,641][2391555] Starting process rollout_proc4
[2023-02-25 11:13:24,642][2391555] Starting process rollout_proc5
[2023-02-25 11:13:24,643][2391555] Starting process rollout_proc6
[2023-02-25 11:13:24,645][2391555] Starting process rollout_proc7
[2023-02-25 11:13:24,648][2391555] Starting process rollout_proc8
[2023-02-25 11:13:24,654][2391646] Num visible devices: 1
[2023-02-25 11:13:24,649][2391555] Starting process rollout_proc9
[2023-02-25 11:13:24,687][2391646] Starting seed is not provided
[2023-02-25 11:13:24,687][2391646] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-25 11:13:24,688][2391646] Initializing actor-critic model on device cuda:0
[2023-02-25 11:13:24,688][2391646] RunningMeanStd input shape: (23,)
[2023-02-25 11:13:24,688][2391646] RunningMeanStd input shape: (3, 72, 128)
[2023-02-25 11:13:24,650][2391555] Starting process rollout_proc10
[2023-02-25 11:13:24,689][2391646] RunningMeanStd input shape: (1,)
[2023-02-25 11:13:24,650][2391555] Starting process rollout_proc11
[2023-02-25 11:13:24,650][2391555] Starting process rollout_proc12
[2023-02-25 11:13:24,651][2391555] Starting process rollout_proc13
[2023-02-25 11:13:24,653][2391555] Starting process rollout_proc14
[2023-02-25 11:13:24,704][2391646] ConvEncoder: input_channels=3
[2023-02-25 11:13:24,853][2391646] Conv encoder output size: 512
[2023-02-25 11:13:24,854][2391646] Policy head output size: 512
[2023-02-25 11:13:24,870][2391646] Created Actor Critic model with architecture:
[2023-02-25 11:13:24,870][2391646] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (measurements): RunningMeanStdInPlace()
        (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=39, bias=True)
  )
)
[2023-02-25 11:13:26,317][2391555] Starting process rollout_proc15
[2023-02-25 11:13:26,327][2391692] Worker 0 uses CPU cores [0]
[2023-02-25 11:13:26,341][2391555] Starting process rollout_proc16
[2023-02-25 11:13:26,352][2391691] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-25 11:13:26,353][2391691] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2023-02-25 11:13:26,370][2391555] Starting process rollout_proc17
[2023-02-25 11:13:26,376][2391691] Num visible devices: 1
[2023-02-25 11:13:26,377][2391696] Worker 5 uses CPU cores [5]
[2023-02-25 11:13:26,413][2391555] Starting process rollout_proc18
[2023-02-25 11:13:26,422][2391694] Worker 3 uses CPU cores [3]
[2023-02-25 11:13:26,423][2391555] Starting process rollout_proc19
[2023-02-25 11:13:26,434][2391695] Worker 1 uses CPU cores [1]
[2023-02-25 11:13:26,437][2391555] Starting process rollout_proc20
[2023-02-25 11:13:26,457][2391722] Worker 12 uses CPU cores [12]
[2023-02-25 11:13:26,457][2391555] Starting process rollout_proc21
[2023-02-25 11:13:26,459][2391555] Starting process rollout_proc22
[2023-02-25 11:13:26,466][2391555] Starting process rollout_proc23
[2023-02-25 11:13:26,469][2391721] Worker 14 uses CPU cores [14]
[2023-02-25 11:13:26,474][2391712] Worker 4 uses CPU cores [4]
[2023-02-25 11:13:26,486][2391718] Worker 11 uses CPU cores [11]
[2023-02-25 11:13:26,491][2391555] Starting process rollout_proc24
[2023-02-25 11:13:26,502][2391720] Worker 13 uses CPU cores [13]
[2023-02-25 11:13:26,523][2391555] Starting process rollout_proc25
[2023-02-25 11:13:26,536][2391555] Starting process rollout_proc26
[2023-02-25 11:13:26,546][2391715] Worker 7 uses CPU cores [7]
[2023-02-25 11:13:26,550][2391719] Worker 8 uses CPU cores [8]
[2023-02-25 11:13:26,558][2391555] Starting process rollout_proc27
[2023-02-25 11:13:26,570][2391693] Worker 2 uses CPU cores [2]
[2023-02-25 11:13:26,583][2391555] Starting process rollout_proc28
[2023-02-25 11:13:26,602][2391717] Worker 10 uses CPU cores [10]
[2023-02-25 11:13:26,638][2391555] Starting process rollout_proc29
[2023-02-25 11:13:26,646][2391716] Worker 9 uses CPU cores [9]
[2023-02-25 11:13:26,655][2391555] Starting process rollout_proc30
[2023-02-25 11:13:26,670][2391713] Worker 6 uses CPU cores [6]
[2023-02-25 11:13:27,941][2391646] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-25 11:13:27,942][2391646] Loading state from checkpoint /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
[2023-02-25 11:13:27,976][2391646] Loading model from checkpoint
[2023-02-25 11:13:27,978][2391646] EvtLoop [learner_proc0_evt_loop, process=learner_proc0] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Runner_EvtLoop', signal_name='start'), args=()
Traceback (most recent call last):
  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
    slot_callable(*args)
  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/sample_factory/algo/learning/learner_worker.py", line 139, in init
    init_model_data = self.learner.init()
  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/sample_factory/algo/learning/learner.py", line 243, in init
    self.load_from_checkpoint(self.policy_id)
  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/sample_factory/algo/learning/learner.py", line 305, in load_from_checkpoint
    self._load_state(checkpoint_dict, load_progress=load_progress)
  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/sample_factory/algo/learning/learner.py", line 289, in _load_state
    self.actor_critic.load_state_dict(checkpoint_dict["model"])
  File "/home/sebas/miniconda3/envs/RL-vizdoom/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1671, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for ActorCriticSharedWeights:
	Missing key(s) in state_dict: "obs_normalizer.running_mean_std.running_mean_std.measurements.running_mean", "obs_normalizer.running_mean_std.running_mean_std.measurements.running_var", "obs_normalizer.running_mean_std.running_mean_std.measurements.count". 
	size mismatch for action_parameterization.distribution_linear.weight: copying a param with shape torch.Size([5, 512]) from checkpoint, the shape in current model is torch.Size([39, 512]).
	size mismatch for action_parameterization.distribution_linear.bias: copying a param with shape torch.Size([5]) from checkpoint, the shape in current model is torch.Size([39]).
[2023-02-25 11:13:27,980][2391646] Unhandled exception Error(s) in loading state_dict for ActorCriticSharedWeights:
	Missing key(s) in state_dict: "obs_normalizer.running_mean_std.running_mean_std.measurements.running_mean", "obs_normalizer.running_mean_std.running_mean_std.measurements.running_var", "obs_normalizer.running_mean_std.running_mean_std.measurements.count". 
	size mismatch for action_parameterization.distribution_linear.weight: copying a param with shape torch.Size([5, 512]) from checkpoint, the shape in current model is torch.Size([39, 512]).
	size mismatch for action_parameterization.distribution_linear.bias: copying a param with shape torch.Size([5]) from checkpoint, the shape in current model is torch.Size([39]). in evt loop learner_proc0_evt_loop
[2023-02-25 11:13:28,110][2391555] Starting process rollout_proc31
[2023-02-25 11:13:28,126][2391996] Worker 17 uses CPU cores [1]
[2023-02-25 11:13:28,242][2392076] Worker 23 uses CPU cores [7]
[2023-02-25 11:13:28,314][2392027] Worker 18 uses CPU cores [2]
[2023-02-25 11:13:28,330][2392044] Worker 20 uses CPU cores [4]
[2023-02-25 11:13:28,350][2391995] Worker 16 uses CPU cores [0]
[2023-02-25 11:13:28,378][2392028] Worker 19 uses CPU cores [3]
[2023-02-25 11:13:28,394][2392139] Worker 25 uses CPU cores [9]
[2023-02-25 11:13:28,394][2391979] Worker 15 uses CPU cores [15]
[2023-02-25 11:13:28,397][2392123] Worker 24 uses CPU cores [8]
[2023-02-25 11:13:28,407][2392171] Worker 27 uses CPU cores [11]
[2023-02-25 11:13:28,410][2392107] Worker 22 uses CPU cores [6]
[2023-02-25 11:13:28,446][2392140] Worker 26 uses CPU cores [10]
[2023-02-25 11:13:28,458][2392075] Worker 21 uses CPU cores [5]
[2023-02-25 11:13:28,490][2392203] Worker 29 uses CPU cores [13]
[2023-02-25 11:13:28,547][2392187] Worker 28 uses CPU cores [12]
[2023-02-25 11:13:28,562][2392219] Worker 30 uses CPU cores [14]
[2023-02-25 11:13:29,110][2392478] Worker 31 uses CPU cores [15]
[2023-02-25 11:13:43,817][2391555] Heartbeat connected on Batcher_0
[2023-02-25 11:13:43,822][2391555] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-25 11:13:43,824][2391555] Heartbeat connected on RolloutWorker_w0
[2023-02-25 11:13:43,826][2391555] Heartbeat connected on RolloutWorker_w1
[2023-02-25 11:13:43,829][2391555] Heartbeat connected on RolloutWorker_w2
[2023-02-25 11:13:43,831][2391555] Heartbeat connected on RolloutWorker_w3
[2023-02-25 11:13:43,833][2391555] Heartbeat connected on RolloutWorker_w4
[2023-02-25 11:13:43,835][2391555] Heartbeat connected on RolloutWorker_w5
[2023-02-25 11:13:43,837][2391555] Heartbeat connected on RolloutWorker_w6
[2023-02-25 11:13:43,839][2391555] Heartbeat connected on RolloutWorker_w7
[2023-02-25 11:13:43,841][2391555] Heartbeat connected on RolloutWorker_w8
[2023-02-25 11:13:43,843][2391555] Heartbeat connected on RolloutWorker_w9
[2023-02-25 11:13:43,845][2391555] Heartbeat connected on RolloutWorker_w10
[2023-02-25 11:13:43,847][2391555] Heartbeat connected on RolloutWorker_w11
[2023-02-25 11:13:43,849][2391555] Heartbeat connected on RolloutWorker_w12
[2023-02-25 11:13:43,852][2391555] Heartbeat connected on RolloutWorker_w13
[2023-02-25 11:13:43,854][2391555] Heartbeat connected on RolloutWorker_w14
[2023-02-25 11:13:43,856][2391555] Heartbeat connected on RolloutWorker_w15
[2023-02-25 11:13:43,858][2391555] Heartbeat connected on RolloutWorker_w16
[2023-02-25 11:13:43,860][2391555] Heartbeat connected on RolloutWorker_w17
[2023-02-25 11:13:43,861][2391555] Heartbeat connected on RolloutWorker_w18
[2023-02-25 11:13:43,863][2391555] Heartbeat connected on RolloutWorker_w19
[2023-02-25 11:13:43,865][2391555] Heartbeat connected on RolloutWorker_w20
[2023-02-25 11:13:43,867][2391555] Heartbeat connected on RolloutWorker_w21
[2023-02-25 11:13:43,870][2391555] Heartbeat connected on RolloutWorker_w22
[2023-02-25 11:13:43,872][2391555] Heartbeat connected on RolloutWorker_w23
[2023-02-25 11:13:43,874][2391555] Heartbeat connected on RolloutWorker_w24
[2023-02-25 11:13:43,876][2391555] Heartbeat connected on RolloutWorker_w25
[2023-02-25 11:13:43,878][2391555] Heartbeat connected on RolloutWorker_w26
[2023-02-25 11:13:43,880][2391555] Heartbeat connected on RolloutWorker_w27
[2023-02-25 11:13:43,882][2391555] Heartbeat connected on RolloutWorker_w28
[2023-02-25 11:13:43,884][2391555] Heartbeat connected on RolloutWorker_w29
[2023-02-25 11:13:43,886][2391555] Heartbeat connected on RolloutWorker_w30
[2023-02-25 11:13:43,888][2391555] Heartbeat connected on RolloutWorker_w31
[2023-02-25 11:23:21,760][2391555] Components not started: LearnerWorker_p0, wait_time=600.0 seconds
[2023-02-25 11:33:21,760][2391555] Components not started: LearnerWorker_p0, wait_time=1200.0 seconds
[2023-02-25 11:43:21,761][2391555] Components not started: LearnerWorker_p0, wait_time=1800.0 seconds
[2023-02-25 11:43:21,762][2391555] Components take too long to start: LearnerWorker_p0. Aborting the experiment!



[2023-02-25 11:43:21,763][2391694] Stopping RolloutWorker_w3...
[2023-02-25 11:43:21,764][2391555] Component RolloutWorker_w3 stopped!
[2023-02-25 11:43:21,763][2391716] Stopping RolloutWorker_w9...
[2023-02-25 11:43:21,763][2392140] Stopping RolloutWorker_w26...
[2023-02-25 11:43:21,764][2391691] Stopping InferenceWorker_p0-w0...
[2023-02-25 11:43:21,764][2392187] Stopping RolloutWorker_w28...
[2023-02-25 11:43:21,764][2391712] Stopping RolloutWorker_w4...
[2023-02-25 11:43:21,764][2391721] Stopping RolloutWorker_w14...
[2023-02-25 11:43:21,764][2391646] Stopping Batcher_0...
[2023-02-25 11:43:21,764][2392027] Stopping RolloutWorker_w18...
[2023-02-25 11:43:21,764][2391719] Stopping RolloutWorker_w8...
[2023-02-25 11:43:21,764][2391720] Stopping RolloutWorker_w13...
[2023-02-25 11:43:21,764][2391715] Stopping RolloutWorker_w7...
[2023-02-25 11:43:21,764][2392028] Stopping RolloutWorker_w19...
[2023-02-25 11:43:21,764][2391695] Stopping RolloutWorker_w1...
[2023-02-25 11:43:21,764][2392187] Loop rollout_proc28_evt_loop terminating...
[2023-02-25 11:43:21,764][2391716] Loop rollout_proc9_evt_loop terminating...
[2023-02-25 11:43:21,764][2392140] Loop rollout_proc26_evt_loop terminating...
[2023-02-25 11:43:21,764][2391646] Loop batcher_evt_loop terminating...
[2023-02-25 11:43:21,764][2391721] Loop rollout_proc14_evt_loop terminating...
[2023-02-25 11:43:21,764][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w6', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w9', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w20', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w26', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,764][2392027] Loop rollout_proc18_evt_loop terminating...
[2023-02-25 11:43:21,764][2391719] Loop rollout_proc8_evt_loop terminating...
[2023-02-25 11:43:21,764][2391715] Loop rollout_proc7_evt_loop terminating...
[2023-02-25 11:43:21,764][2392028] Loop rollout_proc19_evt_loop terminating...
[2023-02-25 11:43:21,764][2391718] Stopping RolloutWorker_w11...
[2023-02-25 11:43:21,764][2391555] Component RolloutWorker_w26 stopped!
[2023-02-25 11:43:21,764][2392075] Stopping RolloutWorker_w21...
[2023-02-25 11:43:21,764][2391995] Stopping RolloutWorker_w16...
[2023-02-25 11:43:21,764][2392107] Stopping RolloutWorker_w22...
[2023-02-25 11:43:21,764][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w6', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w9', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w20', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,764][2391718] Loop rollout_proc11_evt_loop terminating...
[2023-02-25 11:43:21,765][2391995] Loop rollout_proc16_evt_loop terminating...
[2023-02-25 11:43:21,765][2391555] Component RolloutWorker_w9 stopped!
[2023-02-25 11:43:21,765][2392075] Loop rollout_proc21_evt_loop terminating...
[2023-02-25 11:43:21,763][2391713] Stopping RolloutWorker_w6...
[2023-02-25 11:43:21,763][2392044] Stopping RolloutWorker_w20...
[2023-02-25 11:43:21,765][2391713] Loop rollout_proc6_evt_loop terminating...
[2023-02-25 11:43:21,765][2391979] Stopping RolloutWorker_w15...
[2023-02-25 11:43:21,765][2392044] Loop rollout_proc20_evt_loop terminating...
[2023-02-25 11:43:21,766][2391979] Loop rollout_proc15_evt_loop terminating...
[2023-02-25 11:43:21,763][2391722] Stopping RolloutWorker_w12...
[2023-02-25 11:43:21,771][2392076] Stopping RolloutWorker_w23...
[2023-02-25 11:43:21,771][2391722] Loop rollout_proc12_evt_loop terminating...
[2023-02-25 11:43:21,771][2392478] Stopping RolloutWorker_w31...
[2023-02-25 11:43:21,771][2392076] Loop rollout_proc23_evt_loop terminating...
[2023-02-25 11:43:21,771][2392478] Loop rollout_proc31_evt_loop terminating...
[2023-02-25 11:43:21,763][2392219] Stopping RolloutWorker_w30...
[2023-02-25 11:43:21,775][2392219] Loop rollout_proc30_evt_loop terminating...
[2023-02-25 11:43:21,763][2391693] Stopping RolloutWorker_w2...
[2023-02-25 11:43:21,779][2391693] Loop rollout_proc2_evt_loop terminating...
[2023-02-25 11:43:21,763][2392123] Stopping RolloutWorker_w24...
[2023-02-25 11:43:21,783][2392123] Loop rollout_proc24_evt_loop terminating...
[2023-02-25 11:43:21,763][2392203] Stopping RolloutWorker_w29...
[2023-02-25 11:43:21,787][2392203] Loop rollout_proc29_evt_loop terminating...
[2023-02-25 11:43:21,763][2391694] Loop rollout_proc3_evt_loop terminating...
[2023-02-25 11:43:21,764][2391720] Loop rollout_proc13_evt_loop terminating...
[2023-02-25 11:43:21,763][2391996] Stopping RolloutWorker_w17...
[2023-02-25 11:43:21,791][2391996] Loop rollout_proc17_evt_loop terminating...
[2023-02-25 11:43:21,764][2391717] Stopping RolloutWorker_w10...
[2023-02-25 11:43:21,795][2391717] Loop rollout_proc10_evt_loop terminating...
[2023-02-25 11:43:21,764][2392139] Stopping RolloutWorker_w25...
[2023-02-25 11:43:21,799][2392139] Loop rollout_proc25_evt_loop terminating...
[2023-02-25 11:43:21,764][2392171] Stopping RolloutWorker_w27...
[2023-02-25 11:43:21,764][2391691] Loop inference_proc0-0_evt_loop terminating...
[2023-02-25 11:43:21,803][2392171] Loop rollout_proc27_evt_loop terminating...
[2023-02-25 11:43:21,764][2391712] Loop rollout_proc4_evt_loop terminating...
[2023-02-25 11:43:21,764][2391695] Loop rollout_proc1_evt_loop terminating...
[2023-02-25 11:43:21,765][2392107] Loop rollout_proc22_evt_loop terminating...
[2023-02-25 11:43:21,763][2391696] Stopping RolloutWorker_w5...
[2023-02-25 11:43:21,765][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w6', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w20', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,815][2391555] Component RolloutWorker_w20 stopped!
[2023-02-25 11:43:21,815][2391696] Loop rollout_proc5_evt_loop terminating...
[2023-02-25 11:43:21,815][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w6', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,816][2391555] Component RolloutWorker_w6 stopped!
[2023-02-25 11:43:21,816][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w12', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,816][2391555] Component RolloutWorker_w12 stopped!
[2023-02-25 11:43:21,816][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w30', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,816][2391555] Component RolloutWorker_w30 stopped!
[2023-02-25 11:43:21,816][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w2', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,817][2391555] Component RolloutWorker_w2 stopped!
[2023-02-25 11:43:21,817][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w5', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,817][2391555] Component RolloutWorker_w5 stopped!
[2023-02-25 11:43:21,817][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w29', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,817][2391555] Component RolloutWorker_w29 stopped!
[2023-02-25 11:43:21,817][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w24', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,818][2391555] Component RolloutWorker_w24 stopped!
[2023-02-25 11:43:21,818][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w11', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,818][2391555] Component RolloutWorker_w11 stopped!
[2023-02-25 11:43:21,818][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w17', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,818][2391555] Component RolloutWorker_w17 stopped!
[2023-02-25 11:43:21,771][2391692] Stopping RolloutWorker_w0...
[2023-02-25 11:43:21,818][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w10', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,819][2391555] Component RolloutWorker_w10 stopped!
[2023-02-25 11:43:21,819][2391692] Loop rollout_proc0_evt_loop terminating...
[2023-02-25 11:43:21,819][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w25', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,819][2391555] Component RolloutWorker_w25 stopped!
[2023-02-25 11:43:21,819][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'InferenceWorker_p0-w0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,819][2391555] Component InferenceWorker_p0-w0 stopped!
[2023-02-25 11:43:21,819][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w27', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,820][2391555] Component RolloutWorker_w27 stopped!
[2023-02-25 11:43:21,820][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w28', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,820][2391555] Component RolloutWorker_w28 stopped!
[2023-02-25 11:43:21,820][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w4', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,820][2391555] Component RolloutWorker_w4 stopped!
[2023-02-25 11:43:21,820][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w21', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,820][2391555] Component RolloutWorker_w21 stopped!
[2023-02-25 11:43:21,821][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w22', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,821][2391555] Component RolloutWorker_w22 stopped!
[2023-02-25 11:43:21,821][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w14', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,821][2391555] Component RolloutWorker_w14 stopped!
[2023-02-25 11:43:21,821][2391555] Waiting for ['Batcher_0', 'LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,821][2391555] Component Batcher_0 stopped!
[2023-02-25 11:43:21,821][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w18', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,821][2391555] Component RolloutWorker_w18 stopped!
[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w13', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,822][2391555] Component RolloutWorker_w13 stopped!
[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w8', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,822][2391555] Component RolloutWorker_w8 stopped!
[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w7', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,822][2391555] Component RolloutWorker_w7 stopped!
[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w19', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,822][2391555] Component RolloutWorker_w19 stopped!
[2023-02-25 11:43:21,822][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w1', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w1 stopped!
[2023-02-25 11:43:21,823][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w15', 'RolloutWorker_w16', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w16 stopped!
[2023-02-25 11:43:21,823][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w15', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w15 stopped!
[2023-02-25 11:43:21,823][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w23', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w23 stopped!
[2023-02-25 11:43:21,823][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w0', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,823][2391555] Component RolloutWorker_w0 stopped!
[2023-02-25 11:43:21,824][2391555] Waiting for ['LearnerWorker_p0', 'RolloutWorker_w31'] to stop...
[2023-02-25 11:43:21,824][2391555] Component RolloutWorker_w31 stopped!
[2023-02-25 11:43:21,824][2391555] Waiting for ['LearnerWorker_p0'] to stop...
[2023-02-25 12:10:30,585][2391555] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 2391555], exiting...
[2023-02-25 12:10:30,588][2391555] Runner profile tree view:
main_loop: 3426.6990
[2023-02-25 12:10:30,588][2391555] Collected {}, FPS: 0.0
[2023-02-25 12:10:30,595][2391555] Loading existing experiment configuration from train_dir/default_experiment/config.json
[2023-02-25 12:10:30,595][2391555] Overriding arg 'env' with value 'doom_health_gathering_supreme' passed from command line
[2023-02-25 12:10:30,596][2391555] Overriding arg 'train_dir' with value 'train_dir' passed from command line
[2023-02-25 12:10:30,596][2391555] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-25 12:10:30,596][2391555] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'hf_repository'='eldraco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-25 12:10:30,596][2391555] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-25 12:10:30,597][2391555] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-25 12:10:30,597][2391555] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-25 12:10:30,602][2391555] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-25 12:10:30,603][2391555] RunningMeanStd input shape: (3, 72, 128)
[2023-02-25 12:10:30,603][2391555] RunningMeanStd input shape: (1,)
[2023-02-25 12:10:30,610][2391555] ConvEncoder: input_channels=3
[2023-02-25 12:10:30,753][2391555] Conv encoder output size: 512
[2023-02-25 12:10:30,753][2391555] Policy head output size: 512
[2023-02-25 12:10:32,086][2391555] Loading state from checkpoint train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
[2023-02-25 12:10:32,762][2391555] Num frames 100...
[2023-02-25 12:10:32,829][2391555] Num frames 200...
[2023-02-25 12:10:32,896][2391555] Num frames 300...
[2023-02-25 12:10:32,964][2391555] Num frames 400...
[2023-02-25 12:10:33,034][2391555] Num frames 500...
[2023-02-25 12:10:33,121][2391555] Num frames 600...
[2023-02-25 12:10:33,191][2391555] Num frames 700...
[2023-02-25 12:10:33,261][2391555] Num frames 800...
[2023-02-25 12:10:33,330][2391555] Num frames 900...
[2023-02-25 12:10:33,398][2391555] Num frames 1000...
[2023-02-25 12:10:33,466][2391555] Num frames 1100...
[2023-02-25 12:10:33,536][2391555] Num frames 1200...
[2023-02-25 12:10:33,605][2391555] Num frames 1300...
[2023-02-25 12:10:33,673][2391555] Num frames 1400...
[2023-02-25 12:10:33,741][2391555] Num frames 1500...
[2023-02-25 12:10:33,796][2391555] Avg episode rewards: #0: 40.040, true rewards: #0: 15.040
[2023-02-25 12:10:33,796][2391555] Avg episode reward: 40.040, avg true_objective: 15.040
[2023-02-25 12:10:33,886][2391555] Num frames 1600...
[2023-02-25 12:10:33,955][2391555] Num frames 1700...
[2023-02-25 12:10:34,023][2391555] Num frames 1800...
[2023-02-25 12:10:34,091][2391555] Num frames 1900...
[2023-02-25 12:10:34,158][2391555] Num frames 2000...
[2023-02-25 12:10:34,226][2391555] Num frames 2100...
[2023-02-25 12:10:34,286][2391555] Avg episode rewards: #0: 25.560, true rewards: #0: 10.560
[2023-02-25 12:10:34,287][2391555] Avg episode reward: 25.560, avg true_objective: 10.560
[2023-02-25 12:10:34,371][2391555] Num frames 2200...
[2023-02-25 12:10:34,439][2391555] Num frames 2300...
[2023-02-25 12:10:34,506][2391555] Num frames 2400...
[2023-02-25 12:10:34,573][2391555] Num frames 2500...
[2023-02-25 12:10:34,642][2391555] Num frames 2600...
[2023-02-25 12:10:34,711][2391555] Num frames 2700...
[2023-02-25 12:10:34,780][2391555] Num frames 2800...
[2023-02-25 12:10:34,842][2391555] Avg episode rewards: #0: 22.043, true rewards: #0: 9.377
[2023-02-25 12:10:34,842][2391555] Avg episode reward: 22.043, avg true_objective: 9.377
[2023-02-25 12:10:34,928][2391555] Num frames 2900...
[2023-02-25 12:10:34,995][2391555] Num frames 3000...
[2023-02-25 12:10:35,062][2391555] Num frames 3100...
[2023-02-25 12:10:35,133][2391555] Num frames 3200...
[2023-02-25 12:10:35,203][2391555] Num frames 3300...
[2023-02-25 12:10:35,271][2391555] Num frames 3400...
[2023-02-25 12:10:35,339][2391555] Num frames 3500...
[2023-02-25 12:10:35,408][2391555] Num frames 3600...
[2023-02-25 12:10:35,475][2391555] Num frames 3700...
[2023-02-25 12:10:35,545][2391555] Num frames 3800...
[2023-02-25 12:10:35,613][2391555] Num frames 3900...
[2023-02-25 12:10:35,680][2391555] Num frames 4000...
[2023-02-25 12:10:35,749][2391555] Num frames 4100...
[2023-02-25 12:10:35,819][2391555] Num frames 4200...
[2023-02-25 12:10:35,889][2391555] Num frames 4300...
[2023-02-25 12:10:35,957][2391555] Num frames 4400...
[2023-02-25 12:10:36,024][2391555] Num frames 4500...
[2023-02-25 12:10:36,093][2391555] Num frames 4600...
[2023-02-25 12:10:36,163][2391555] Num frames 4700...
[2023-02-25 12:10:36,231][2391555] Num frames 4800...
[2023-02-25 12:10:36,299][2391555] Num frames 4900...
[2023-02-25 12:10:36,361][2391555] Avg episode rewards: #0: 31.282, true rewards: #0: 12.283
[2023-02-25 12:10:36,361][2391555] Avg episode reward: 31.282, avg true_objective: 12.283
[2023-02-25 12:10:36,443][2391555] Num frames 5000...
[2023-02-25 12:10:36,511][2391555] Num frames 5100...
[2023-02-25 12:10:36,580][2391555] Num frames 5200...
[2023-02-25 12:10:36,647][2391555] Num frames 5300...
[2023-02-25 12:10:36,716][2391555] Num frames 5400...
[2023-02-25 12:10:36,786][2391555] Num frames 5500...
[2023-02-25 12:10:36,854][2391555] Num frames 5600...
[2023-02-25 12:10:36,923][2391555] Num frames 5700...
[2023-02-25 12:10:36,991][2391555] Num frames 5800...
[2023-02-25 12:10:37,060][2391555] Num frames 5900...
[2023-02-25 12:10:37,128][2391555] Num frames 6000...
[2023-02-25 12:10:37,198][2391555] Num frames 6100...
[2023-02-25 12:10:37,280][2391555] Num frames 6200...
[2023-02-25 12:10:37,350][2391555] Num frames 6300...
[2023-02-25 12:10:37,418][2391555] Num frames 6400...
[2023-02-25 12:10:37,488][2391555] Num frames 6500...
[2023-02-25 12:10:37,557][2391555] Num frames 6600...
[2023-02-25 12:10:37,625][2391555] Num frames 6700...
[2023-02-25 12:10:37,696][2391555] Num frames 6800...
[2023-02-25 12:10:37,765][2391555] Num frames 6900...
[2023-02-25 12:10:37,834][2391555] Num frames 7000...
[2023-02-25 12:10:37,895][2391555] Avg episode rewards: #0: 36.425, true rewards: #0: 14.026
[2023-02-25 12:10:37,896][2391555] Avg episode reward: 36.425, avg true_objective: 14.026
[2023-02-25 12:10:37,979][2391555] Num frames 7100...
[2023-02-25 12:10:38,045][2391555] Num frames 7200...
[2023-02-25 12:10:38,113][2391555] Num frames 7300...
[2023-02-25 12:10:38,182][2391555] Num frames 7400...
[2023-02-25 12:10:38,251][2391555] Num frames 7500...
[2023-02-25 12:10:38,318][2391555] Num frames 7600...
[2023-02-25 12:10:38,386][2391555] Num frames 7700...
[2023-02-25 12:10:38,455][2391555] Num frames 7800...
[2023-02-25 12:10:38,522][2391555] Num frames 7900...
[2023-02-25 12:10:38,591][2391555] Num frames 8000...
[2023-02-25 12:10:38,659][2391555] Num frames 8100...
[2023-02-25 12:10:38,729][2391555] Num frames 8200...
[2023-02-25 12:10:38,798][2391555] Num frames 8300...
[2023-02-25 12:10:38,866][2391555] Num frames 8400...
[2023-02-25 12:10:38,936][2391555] Num frames 8500...
[2023-02-25 12:10:39,004][2391555] Num frames 8600...
[2023-02-25 12:10:39,072][2391555] Num frames 8700...
[2023-02-25 12:10:39,131][2391555] Avg episode rewards: #0: 38.514, true rewards: #0: 14.515
[2023-02-25 12:10:39,131][2391555] Avg episode reward: 38.514, avg true_objective: 14.515
[2023-02-25 12:10:39,218][2391555] Num frames 8800...
[2023-02-25 12:10:39,287][2391555] Num frames 8900...
[2023-02-25 12:10:39,364][2391555] Num frames 9000...
[2023-02-25 12:10:39,433][2391555] Num frames 9100...
[2023-02-25 12:10:39,502][2391555] Num frames 9200...
[2023-02-25 12:10:39,570][2391555] Num frames 9300...
[2023-02-25 12:10:39,638][2391555] Num frames 9400...
[2023-02-25 12:10:39,706][2391555] Num frames 9500...
[2023-02-25 12:10:39,774][2391555] Num frames 9600...
[2023-02-25 12:10:39,842][2391555] Num frames 9700...
[2023-02-25 12:10:39,934][2391555] Avg episode rewards: #0: 36.367, true rewards: #0: 13.939
[2023-02-25 12:10:39,935][2391555] Avg episode reward: 36.367, avg true_objective: 13.939
[2023-02-25 12:10:40,022][2391555] Num frames 9800...
[2023-02-25 12:10:40,090][2391555] Num frames 9900...
[2023-02-25 12:10:40,159][2391555] Num frames 10000...
[2023-02-25 12:10:40,227][2391555] Num frames 10100...
[2023-02-25 12:10:40,296][2391555] Num frames 10200...
[2023-02-25 12:10:40,365][2391555] Num frames 10300...
[2023-02-25 12:10:40,434][2391555] Num frames 10400...
[2023-02-25 12:10:40,503][2391555] Num frames 10500...
[2023-02-25 12:10:40,571][2391555] Num frames 10600...
[2023-02-25 12:10:40,641][2391555] Num frames 10700...
[2023-02-25 12:10:40,712][2391555] Num frames 10800...
[2023-02-25 12:10:40,783][2391555] Num frames 10900...
[2023-02-25 12:10:40,852][2391555] Num frames 11000...
[2023-02-25 12:10:40,922][2391555] Num frames 11100...
[2023-02-25 12:10:40,991][2391555] Num frames 11200...
[2023-02-25 12:10:41,048][2391555] Avg episode rewards: #0: 36.757, true rewards: #0: 14.007
[2023-02-25 12:10:41,048][2391555] Avg episode reward: 36.757, avg true_objective: 14.007
[2023-02-25 12:10:41,141][2391555] Num frames 11300...
[2023-02-25 12:10:41,209][2391555] Num frames 11400...
[2023-02-25 12:10:41,278][2391555] Num frames 11500...
[2023-02-25 12:10:41,347][2391555] Num frames 11600...
[2023-02-25 12:10:41,419][2391555] Num frames 11700...
[2023-02-25 12:10:41,489][2391555] Num frames 11800...
[2023-02-25 12:10:41,559][2391555] Num frames 11900...
[2023-02-25 12:10:41,626][2391555] Num frames 12000...
[2023-02-25 12:10:41,694][2391555] Num frames 12100...
[2023-02-25 12:10:41,793][2391555] Avg episode rewards: #0: 34.740, true rewards: #0: 13.518
[2023-02-25 12:10:41,793][2391555] Avg episode reward: 34.740, avg true_objective: 13.518
[2023-02-25 12:10:41,834][2391555] Num frames 12200...
[2023-02-25 12:10:41,911][2391555] Num frames 12300...
[2023-02-25 12:10:41,981][2391555] Num frames 12400...
[2023-02-25 12:10:42,050][2391555] Num frames 12500...
[2023-02-25 12:10:42,121][2391555] Num frames 12600...
[2023-02-25 12:10:42,192][2391555] Num frames 12700...
[2023-02-25 12:10:42,261][2391555] Num frames 12800...
[2023-02-25 12:10:42,330][2391555] Num frames 12900...
[2023-02-25 12:10:42,399][2391555] Num frames 13000...
[2023-02-25 12:10:42,468][2391555] Num frames 13100...
[2023-02-25 12:10:42,538][2391555] Num frames 13200...
[2023-02-25 12:10:42,607][2391555] Num frames 13300...
[2023-02-25 12:10:42,675][2391555] Num frames 13400...
[2023-02-25 12:10:42,748][2391555] Num frames 13500...
[2023-02-25 12:10:42,820][2391555] Num frames 13600...
[2023-02-25 12:10:42,891][2391555] Num frames 13700...
[2023-02-25 12:10:42,964][2391555] Num frames 13800...
[2023-02-25 12:10:43,037][2391555] Num frames 13900...
[2023-02-25 12:10:43,108][2391555] Num frames 14000...
[2023-02-25 12:10:43,178][2391555] Num frames 14100...
[2023-02-25 12:10:43,251][2391555] Num frames 14200...
[2023-02-25 12:10:43,351][2391555] Avg episode rewards: #0: 37.566, true rewards: #0: 14.266
[2023-02-25 12:10:43,351][2391555] Avg episode reward: 37.566, avg true_objective: 14.266
[2023-02-25 12:11:00,944][2391555] Replay video saved to train_dir/default_experiment/replay.mp4!