Hugging Face's logo

chqmatteo
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
rl_course_vizdoom_health_gathering_supreme
File size: 118,225 Bytes 
c45c0f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44ed953
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c45c0f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c81c30d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15ac740
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
[2023-02-24 07:55:59,139][784615] Saving configuration to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json...
[2023-02-24 07:55:59,305][784615] Rollout worker 0 uses device cpu
[2023-02-24 07:55:59,305][784615] Rollout worker 1 uses device cpu
[2023-02-24 07:55:59,306][784615] Rollout worker 2 uses device cpu
[2023-02-24 07:55:59,306][784615] Rollout worker 3 uses device cpu
[2023-02-24 07:55:59,306][784615] Rollout worker 4 uses device cpu
[2023-02-24 07:55:59,307][784615] Rollout worker 5 uses device cpu
[2023-02-24 07:55:59,307][784615] Rollout worker 6 uses device cpu
[2023-02-24 07:55:59,308][784615] Rollout worker 7 uses device cpu
[2023-02-24 07:55:59,357][784615] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 07:55:59,358][784615] InferenceWorker_p0-w0: min num requests: 2
[2023-02-24 07:55:59,378][784615] Starting all processes...
[2023-02-24 07:55:59,378][784615] Starting process learner_proc0
[2023-02-24 07:55:59,428][784615] Starting all processes...
[2023-02-24 07:55:59,438][784615] Starting process inference_proc0-0
[2023-02-24 07:55:59,439][784615] Starting process rollout_proc0
[2023-02-24 07:55:59,439][784615] Starting process rollout_proc1
[2023-02-24 07:55:59,439][784615] Starting process rollout_proc2
[2023-02-24 07:55:59,439][784615] Starting process rollout_proc3
[2023-02-24 07:55:59,439][784615] Starting process rollout_proc4
[2023-02-24 07:55:59,439][784615] Starting process rollout_proc5
[2023-02-24 07:55:59,440][784615] Starting process rollout_proc6
[2023-02-24 07:55:59,441][784615] Starting process rollout_proc7
[2023-02-24 07:56:00,842][794035] Worker 3 uses CPU cores [3]
[2023-02-24 07:56:00,862][794036] Worker 5 uses CPU cores [5]
[2023-02-24 07:56:00,978][794037] Worker 4 uses CPU cores [4]
[2023-02-24 07:56:00,998][794038] Worker 2 uses CPU cores [2]
[2023-02-24 07:56:00,999][794019] Low niceness requires sudo!
[2023-02-24 07:56:00,999][794019] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 07:56:01,000][794019] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for learning process 0
[2023-02-24 07:56:01,022][794032] Low niceness requires sudo!
[2023-02-24 07:56:01,022][794032] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 07:56:01,022][794032] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for inference process 0
[2023-02-24 07:56:01,025][794019] Num visible devices: 1
[2023-02-24 07:56:01,040][794032] Num visible devices: 1
[2023-02-24 07:56:01,050][794019] Starting seed is not provided
[2023-02-24 07:56:01,050][794019] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 07:56:01,050][794019] Initializing actor-critic model on device cuda:0
[2023-02-24 07:56:01,051][794019] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 07:56:01,051][794019] RunningMeanStd input shape: (1,)
[2023-02-24 07:56:01,058][794040] Worker 7 uses CPU cores [7]
[2023-02-24 07:56:01,065][794019] ConvEncoder: input_channels=3
[2023-02-24 07:56:01,154][794034] Worker 1 uses CPU cores [1]
[2023-02-24 07:56:01,186][794039] Worker 6 uses CPU cores [6]
[2023-02-24 07:56:01,194][794033] Worker 0 uses CPU cores [0]
[2023-02-24 07:56:01,198][794019] Conv encoder output size: 512
[2023-02-24 07:56:01,198][794019] Policy head output size: 512
[2023-02-24 07:56:01,216][794019] Created Actor Critic model with architecture:
[2023-02-24 07:56:01,216][794019] 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 07:56:04,122][794019] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-24 07:56:04,122][794019] No checkpoints found
[2023-02-24 07:56:04,122][794019] Did not load from checkpoint, starting from scratch!
[2023-02-24 07:56:04,122][794019] Initialized policy 0 weights for model version 0
[2023-02-24 07:56:04,124][794019] LearnerWorker_p0 finished initialization!
[2023-02-24 07:56:04,124][794019] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 07:56:05,229][794032] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 07:56:05,229][794032] RunningMeanStd input shape: (1,)
[2023-02-24 07:56:05,237][794032] ConvEncoder: input_channels=3
[2023-02-24 07:56:05,307][794032] Conv encoder output size: 512
[2023-02-24 07:56:05,307][794032] Policy head output size: 512
[2023-02-24 07:56:06,350][784615] Inference worker 0-0 is ready!
[2023-02-24 07:56:06,350][784615] All inference workers are ready! Signal rollout workers to start!
[2023-02-24 07:56:06,367][794036] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:56:06,368][794039] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:56:06,368][794034] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:56:06,368][794035] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:56:06,369][794038] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:56:06,374][794040] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:56:06,390][794037] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:56:06,393][794033] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:56:06,669][794035] Decorrelating experience for 0 frames...
[2023-02-24 07:56:06,672][794039] Decorrelating experience for 0 frames...
[2023-02-24 07:56:06,678][794036] Decorrelating experience for 0 frames...
[2023-02-24 07:56:06,681][794037] Decorrelating experience for 0 frames...
[2023-02-24 07:56:06,683][794040] Decorrelating experience for 0 frames...
[2023-02-24 07:56:06,929][794035] Decorrelating experience for 32 frames...
[2023-02-24 07:56:06,946][794040] Decorrelating experience for 32 frames...
[2023-02-24 07:56:06,958][794036] Decorrelating experience for 32 frames...
[2023-02-24 07:56:06,977][794037] Decorrelating experience for 32 frames...
[2023-02-24 07:56:06,986][794038] Decorrelating experience for 0 frames...
[2023-02-24 07:56:06,997][794039] Decorrelating experience for 32 frames...
[2023-02-24 07:56:07,033][794033] Decorrelating experience for 0 frames...
[2023-02-24 07:56:07,227][794038] Decorrelating experience for 32 frames...
[2023-02-24 07:56:07,268][794034] Decorrelating experience for 0 frames...
[2023-02-24 07:56:07,269][794036] Decorrelating experience for 64 frames...
[2023-02-24 07:56:07,278][794037] Decorrelating experience for 64 frames...
[2023-02-24 07:56:07,293][794033] Decorrelating experience for 32 frames...
[2023-02-24 07:56:07,502][794038] Decorrelating experience for 64 frames...
[2023-02-24 07:56:07,545][794039] Decorrelating experience for 64 frames...
[2023-02-24 07:56:07,584][794036] Decorrelating experience for 96 frames...
[2023-02-24 07:56:07,591][794033] Decorrelating experience for 64 frames...
[2023-02-24 07:56:07,594][794040] Decorrelating experience for 64 frames...
[2023-02-24 07:56:07,600][794037] Decorrelating experience for 96 frames...
[2023-02-24 07:56:07,628][794034] Decorrelating experience for 32 frames...
[2023-02-24 07:56:07,822][794033] Decorrelating experience for 96 frames...
[2023-02-24 07:56:07,846][794039] Decorrelating experience for 96 frames...
[2023-02-24 07:56:07,890][794038] Decorrelating experience for 96 frames...
[2023-02-24 07:56:07,895][794040] Decorrelating experience for 96 frames...
[2023-02-24 07:56:08,065][794035] Decorrelating experience for 64 frames...
[2023-02-24 07:56:08,153][784615] 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 07:56:08,319][794034] Decorrelating experience for 64 frames...
[2023-02-24 07:56:08,572][794035] Decorrelating experience for 96 frames...
[2023-02-24 07:56:08,577][794034] Decorrelating experience for 96 frames...
[2023-02-24 07:56:10,130][794019] Signal inference workers to stop experience collection...
[2023-02-24 07:56:10,137][794032] InferenceWorker_p0-w0: stopping experience collection
[2023-02-24 07:56:12,636][794019] Signal inference workers to resume experience collection...
[2023-02-24 07:56:12,637][794032] InferenceWorker_p0-w0: resuming experience collection
[2023-02-24 07:56:13,153][784615] Fps is (10 sec: 819.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 4096. Throughput: 0: 494.8. Samples: 2474. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-02-24 07:56:13,154][784615] Avg episode reward: [(0, '2.494')]
[2023-02-24 07:56:15,144][794032] Updated weights for policy 0, policy_version 10 (0.0249)
[2023-02-24 07:56:17,664][794032] Updated weights for policy 0, policy_version 20 (0.0006)
[2023-02-24 07:56:18,153][784615] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8601.6). Total num frames: 86016. Throughput: 0: 1166.6. Samples: 11666. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 07:56:18,154][784615] Avg episode reward: [(0, '4.437')]
[2023-02-24 07:56:19,351][784615] Heartbeat connected on Batcher_0
[2023-02-24 07:56:19,354][784615] Heartbeat connected on LearnerWorker_p0
[2023-02-24 07:56:19,362][784615] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-24 07:56:19,364][784615] Heartbeat connected on RolloutWorker_w0
[2023-02-24 07:56:19,365][784615] Heartbeat connected on RolloutWorker_w1
[2023-02-24 07:56:19,368][784615] Heartbeat connected on RolloutWorker_w3
[2023-02-24 07:56:19,373][784615] Heartbeat connected on RolloutWorker_w4
[2023-02-24 07:56:19,374][784615] Heartbeat connected on RolloutWorker_w5
[2023-02-24 07:56:19,375][784615] Heartbeat connected on RolloutWorker_w2
[2023-02-24 07:56:19,377][784615] Heartbeat connected on RolloutWorker_w7
[2023-02-24 07:56:19,378][784615] Heartbeat connected on RolloutWorker_w6
[2023-02-24 07:56:20,182][794032] Updated weights for policy 0, policy_version 30 (0.0006)
[2023-02-24 07:56:22,465][794032] Updated weights for policy 0, policy_version 40 (0.0007)
[2023-02-24 07:56:23,153][784615] Fps is (10 sec: 16793.7, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 172032. Throughput: 0: 2462.0. Samples: 36930. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 07:56:23,154][784615] Avg episode reward: [(0, '4.501')]
[2023-02-24 07:56:23,155][794019] Saving new best policy, reward=4.501!
[2023-02-24 07:56:25,053][794032] Updated weights for policy 0, policy_version 50 (0.0007)
[2023-02-24 07:56:27,490][794032] Updated weights for policy 0, policy_version 60 (0.0007)
[2023-02-24 07:56:28,153][784615] Fps is (10 sec: 16793.6, 60 sec: 12697.6, 300 sec: 12697.6). Total num frames: 253952. Throughput: 0: 3086.0. Samples: 61720. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 07:56:28,154][784615] Avg episode reward: [(0, '4.402')]
[2023-02-24 07:56:30,062][794032] Updated weights for policy 0, policy_version 70 (0.0007)
[2023-02-24 07:56:32,640][794032] Updated weights for policy 0, policy_version 80 (0.0007)
[2023-02-24 07:56:33,153][784615] Fps is (10 sec: 15974.4, 60 sec: 13271.1, 300 sec: 13271.1). Total num frames: 331776. Throughput: 0: 2951.7. Samples: 73792. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 07:56:33,154][784615] Avg episode reward: [(0, '4.289')]
[2023-02-24 07:56:35,246][794032] Updated weights for policy 0, policy_version 90 (0.0007)
[2023-02-24 07:56:37,855][794032] Updated weights for policy 0, policy_version 100 (0.0008)
[2023-02-24 07:56:38,153][784615] Fps is (10 sec: 15974.5, 60 sec: 13789.9, 300 sec: 13789.9). Total num frames: 413696. Throughput: 0: 3249.9. Samples: 97496. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 07:56:38,154][784615] Avg episode reward: [(0, '4.457')]
[2023-02-24 07:56:40,454][794032] Updated weights for policy 0, policy_version 110 (0.0007)
[2023-02-24 07:56:43,061][794032] Updated weights for policy 0, policy_version 120 (0.0006)
[2023-02-24 07:56:43,153][784615] Fps is (10 sec: 15973.9, 60 sec: 14043.3, 300 sec: 14043.3). Total num frames: 491520. Throughput: 0: 3461.9. Samples: 121166. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 07:56:43,154][784615] Avg episode reward: [(0, '4.401')]
[2023-02-24 07:56:45,699][794032] Updated weights for policy 0, policy_version 130 (0.0007)
[2023-02-24 07:56:48,153][784615] Fps is (10 sec: 15564.7, 60 sec: 14233.6, 300 sec: 14233.6). Total num frames: 569344. Throughput: 0: 3324.0. Samples: 132960. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 07:56:48,154][784615] Avg episode reward: [(0, '4.667')]
[2023-02-24 07:56:48,157][794019] Saving new best policy, reward=4.667!
[2023-02-24 07:56:48,334][794032] Updated weights for policy 0, policy_version 140 (0.0007)
[2023-02-24 07:56:50,891][794032] Updated weights for policy 0, policy_version 150 (0.0006)
[2023-02-24 07:56:53,153][784615] Fps is (10 sec: 15565.3, 60 sec: 14381.5, 300 sec: 14381.5). Total num frames: 647168. Throughput: 0: 3474.6. Samples: 156358. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 07:56:53,154][784615] Avg episode reward: [(0, '4.622')]
[2023-02-24 07:56:53,523][794032] Updated weights for policy 0, policy_version 160 (0.0008)
[2023-02-24 07:56:56,158][794032] Updated weights for policy 0, policy_version 170 (0.0007)
[2023-02-24 07:56:58,153][784615] Fps is (10 sec: 15565.0, 60 sec: 14499.9, 300 sec: 14499.9). Total num frames: 724992. Throughput: 0: 3940.0. Samples: 179774. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 07:56:58,153][784615] Avg episode reward: [(0, '4.603')]
[2023-02-24 07:56:58,738][794032] Updated weights for policy 0, policy_version 180 (0.0008)
[2023-02-24 07:57:01,298][794032] Updated weights for policy 0, policy_version 190 (0.0007)
[2023-02-24 07:57:03,153][784615] Fps is (10 sec: 15974.3, 60 sec: 14671.1, 300 sec: 14671.1). Total num frames: 806912. Throughput: 0: 3998.0. Samples: 191576. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 07:57:03,154][784615] Avg episode reward: [(0, '4.850')]
[2023-02-24 07:57:03,155][794019] Saving new best policy, reward=4.850!
[2023-02-24 07:57:03,931][794032] Updated weights for policy 0, policy_version 200 (0.0007)
[2023-02-24 07:57:06,517][794032] Updated weights for policy 0, policy_version 210 (0.0007)
[2023-02-24 07:57:08,153][784615] Fps is (10 sec: 15974.2, 60 sec: 14745.6, 300 sec: 14745.6). Total num frames: 884736. Throughput: 0: 3958.6. Samples: 215068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 07:57:08,154][784615] Avg episode reward: [(0, '5.203')]
[2023-02-24 07:57:08,156][794019] Saving new best policy, reward=5.203!
[2023-02-24 07:57:09,207][794032] Updated weights for policy 0, policy_version 220 (0.0006)
[2023-02-24 07:57:11,788][794032] Updated weights for policy 0, policy_version 230 (0.0006)
[2023-02-24 07:57:13,153][784615] Fps is (10 sec: 15564.9, 60 sec: 15974.4, 300 sec: 14808.6). Total num frames: 962560. Throughput: 0: 3932.8. Samples: 238698. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 07:57:13,154][784615] Avg episode reward: [(0, '4.831')]
[2023-02-24 07:57:14,400][794032] Updated weights for policy 0, policy_version 240 (0.0006)
[2023-02-24 07:57:17,007][794032] Updated weights for policy 0, policy_version 250 (0.0008)
[2023-02-24 07:57:18,153][784615] Fps is (10 sec: 15564.8, 60 sec: 15906.1, 300 sec: 14862.6). Total num frames: 1040384. Throughput: 0: 3928.0. Samples: 250550. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 07:57:18,154][784615] Avg episode reward: [(0, '6.010')]
[2023-02-24 07:57:18,157][794019] Saving new best policy, reward=6.010!
[2023-02-24 07:57:19,591][794032] Updated weights for policy 0, policy_version 260 (0.0006)
[2023-02-24 07:57:21,628][784615] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 784615], exiting...
[2023-02-24 07:57:21,629][794019] Stopping Batcher_0...
[2023-02-24 07:57:21,629][794019] Loop batcher_evt_loop terminating...
[2023-02-24 07:57:21,628][784615] Runner profile tree view:
main_loop: 82.2510
[2023-02-24 07:57:21,630][784615] Collected {0: 1093632}, FPS: 13296.3
[2023-02-24 07:57:21,638][794039] Stopping RolloutWorker_w6...
[2023-02-24 07:57:21,638][794035] Stopping RolloutWorker_w3...
[2023-02-24 07:57:21,638][794035] Loop rollout_proc3_evt_loop terminating...
[2023-02-24 07:57:21,638][794034] Stopping RolloutWorker_w1...
[2023-02-24 07:57:21,639][794039] Loop rollout_proc6_evt_loop terminating...
[2023-02-24 07:57:21,639][794034] Loop rollout_proc1_evt_loop terminating...
[2023-02-24 07:57:21,645][794033] Stopping RolloutWorker_w0...
[2023-02-24 07:57:21,646][794033] Loop rollout_proc0_evt_loop terminating...
[2023-02-24 07:57:21,646][794037] Stopping RolloutWorker_w4...
[2023-02-24 07:57:21,647][794037] Loop rollout_proc4_evt_loop terminating...
[2023-02-24 07:57:21,647][794038] Stopping RolloutWorker_w2...
[2023-02-24 07:57:21,648][794038] Loop rollout_proc2_evt_loop terminating...
[2023-02-24 07:57:21,651][794036] Stopping RolloutWorker_w5...
[2023-02-24 07:57:21,651][794036] Loop rollout_proc5_evt_loop terminating...
[2023-02-24 07:57:21,652][794040] Stopping RolloutWorker_w7...
[2023-02-24 07:57:21,653][794040] Loop rollout_proc7_evt_loop terminating...
[2023-02-24 07:57:21,667][794019] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000268_1097728.pth...
[2023-02-24 07:57:21,688][794032] Weights refcount: 2 0
[2023-02-24 07:57:21,695][794032] Stopping InferenceWorker_p0-w0...
[2023-02-24 07:57:21,696][794032] Loop inference_proc0-0_evt_loop terminating...
[2023-02-24 07:57:21,825][794019] Stopping LearnerWorker_p0...
[2023-02-24 07:57:21,826][794019] Loop learner_proc0_evt_loop terminating...
[2023-02-24 07:57:37,644][784615] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
[2023-02-24 07:57:37,644][784615] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-24 07:57:37,645][784615] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-24 07:57:37,645][784615] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-24 07:57:37,645][784615] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 07:57:37,646][784615] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-24 07:57:37,646][784615] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2023-02-24 07:57:37,646][784615] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-24 07:57:37,647][784615] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-24 07:57:37,647][784615] Adding new argument 'hf_repository'='chqmatteo/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-24 07:57:37,647][784615] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-24 07:57:37,648][784615] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-24 07:57:37,648][784615] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-24 07:57:37,648][784615] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-24 07:57:37,649][784615] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-24 07:57:37,655][784615] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 07:57:37,656][784615] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 07:57:37,657][784615] RunningMeanStd input shape: (1,)
[2023-02-24 07:57:37,665][784615] ConvEncoder: input_channels=3
[2023-02-24 07:57:37,755][784615] Conv encoder output size: 512
[2023-02-24 07:57:37,755][784615] Policy head output size: 512
[2023-02-24 07:57:40,369][784615] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000268_1097728.pth...
[2023-02-24 07:57:42,531][784615] Num frames 100...
[2023-02-24 07:57:42,595][784615] Num frames 200...
[2023-02-24 07:57:42,663][784615] Num frames 300...
[2023-02-24 07:57:42,732][784615] Num frames 400...
[2023-02-24 07:57:42,832][784615] Avg episode rewards: #0: 6.800, true rewards: #0: 4.800
[2023-02-24 07:57:42,833][784615] Avg episode reward: 6.800, avg true_objective: 4.800
[2023-02-24 07:57:42,848][784615] Num frames 500...
[2023-02-24 07:57:42,911][784615] Num frames 600...
[2023-02-24 07:57:42,969][784615] Num frames 700...
[2023-02-24 07:57:43,043][784615] Num frames 800...
[2023-02-24 07:57:43,113][784615] Avg episode rewards: #0: 5.630, true rewards: #0: 4.130
[2023-02-24 07:57:43,113][784615] Avg episode reward: 5.630, avg true_objective: 4.130
[2023-02-24 07:57:43,175][784615] Num frames 900...
[2023-02-24 07:57:43,244][784615] Num frames 1000...
[2023-02-24 07:57:43,309][784615] Num frames 1100...
[2023-02-24 07:57:43,371][784615] Num frames 1200...
[2023-02-24 07:57:43,470][784615] Avg episode rewards: #0: 5.580, true rewards: #0: 4.247
[2023-02-24 07:57:43,471][784615] Avg episode reward: 5.580, avg true_objective: 4.247
[2023-02-24 07:57:43,487][784615] Num frames 1300...
[2023-02-24 07:57:43,564][784615] Num frames 1400...
[2023-02-24 07:57:43,628][784615] Num frames 1500...
[2023-02-24 07:57:43,689][784615] Num frames 1600...
[2023-02-24 07:57:43,781][784615] Avg episode rewards: #0: 5.145, true rewards: #0: 4.145
[2023-02-24 07:57:43,781][784615] Avg episode reward: 5.145, avg true_objective: 4.145
[2023-02-24 07:57:43,817][784615] Num frames 1700...
[2023-02-24 07:57:43,887][784615] Num frames 1800...
[2023-02-24 07:57:43,956][784615] Num frames 1900...
[2023-02-24 07:57:44,024][784615] Num frames 2000...
[2023-02-24 07:57:44,089][784615] Num frames 2100...
[2023-02-24 07:57:44,147][784615] Avg episode rewards: #0: 5.612, true rewards: #0: 4.212
[2023-02-24 07:57:44,148][784615] Avg episode reward: 5.612, avg true_objective: 4.212
[2023-02-24 07:57:44,208][784615] Num frames 2200...
[2023-02-24 07:57:44,288][784615] Num frames 2300...
[2023-02-24 07:57:44,350][784615] Num frames 2400...
[2023-02-24 07:57:44,463][784615] Avg episode rewards: #0: 5.317, true rewards: #0: 4.150
[2023-02-24 07:57:44,463][784615] Avg episode reward: 5.317, avg true_objective: 4.150
[2023-02-24 07:57:44,471][784615] Num frames 2500...
[2023-02-24 07:57:44,540][784615] Num frames 2600...
[2023-02-24 07:57:44,607][784615] Num frames 2700...
[2023-02-24 07:57:44,671][784615] Num frames 2800...
[2023-02-24 07:57:44,738][784615] Num frames 2900...
[2023-02-24 07:57:44,810][784615] Num frames 3000...
[2023-02-24 07:57:44,865][784615] Avg episode rewards: #0: 5.717, true rewards: #0: 4.289
[2023-02-24 07:57:44,866][784615] Avg episode reward: 5.717, avg true_objective: 4.289
[2023-02-24 07:57:44,925][784615] Num frames 3100...
[2023-02-24 07:57:44,988][784615] Num frames 3200...
[2023-02-24 07:57:45,057][784615] Num frames 3300...
[2023-02-24 07:57:45,126][784615] Num frames 3400...
[2023-02-24 07:57:45,200][784615] Num frames 3500...
[2023-02-24 07:57:45,287][784615] Avg episode rewards: #0: 5.933, true rewards: #0: 4.432
[2023-02-24 07:57:45,287][784615] Avg episode reward: 5.933, avg true_objective: 4.432
[2023-02-24 07:57:45,332][784615] Num frames 3600...
[2023-02-24 07:57:45,410][784615] Num frames 3700...
[2023-02-24 07:57:45,468][784615] Num frames 3800...
[2023-02-24 07:57:45,570][784615] Num frames 3900...
[2023-02-24 07:57:45,634][784615] Num frames 4000...
[2023-02-24 07:57:45,698][784615] Num frames 4100...
[2023-02-24 07:57:45,762][784615] Num frames 4200...
[2023-02-24 07:57:45,873][784615] Avg episode rewards: #0: 6.869, true rewards: #0: 4.758
[2023-02-24 07:57:45,874][784615] Avg episode reward: 6.869, avg true_objective: 4.758
[2023-02-24 07:57:45,886][784615] Num frames 4300...
[2023-02-24 07:57:45,952][784615] Num frames 4400...
[2023-02-24 07:57:46,014][784615] Num frames 4500...
[2023-02-24 07:57:46,087][784615] Num frames 4600...
[2023-02-24 07:57:46,149][784615] Num frames 4700...
[2023-02-24 07:57:46,224][784615] Avg episode rewards: #0: 6.730, true rewards: #0: 4.730
[2023-02-24 07:57:46,225][784615] Avg episode reward: 6.730, avg true_objective: 4.730
[2023-02-24 07:57:48,353][784615] Replay video saved to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!
[2023-02-24 07:58:39,896][784615] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
[2023-02-24 07:58:39,896][784615] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-24 07:58:39,897][784615] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-24 07:58:39,897][784615] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-24 07:58:39,898][784615] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 07:58:39,898][784615] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-24 07:58:39,899][784615] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2023-02-24 07:58:39,899][784615] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-24 07:58:39,900][784615] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-24 07:58:39,900][784615] Adding new argument 'hf_repository'='chqmatteo/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-24 07:58:39,900][784615] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-24 07:58:39,901][784615] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-24 07:58:39,901][784615] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-24 07:58:39,902][784615] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-24 07:58:39,902][784615] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-24 07:58:39,911][784615] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 07:58:39,912][784615] RunningMeanStd input shape: (1,)
[2023-02-24 07:58:39,919][784615] ConvEncoder: input_channels=3
[2023-02-24 07:58:39,943][784615] Conv encoder output size: 512
[2023-02-24 07:58:39,944][784615] Policy head output size: 512
[2023-02-24 07:58:39,980][784615] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000268_1097728.pth...
[2023-02-24 07:58:40,400][784615] Num frames 100...
[2023-02-24 07:58:40,470][784615] Num frames 200...
[2023-02-24 07:58:40,530][784615] Num frames 300...
[2023-02-24 07:58:40,596][784615] Num frames 400...
[2023-02-24 07:58:40,684][784615] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
[2023-02-24 07:58:40,685][784615] Avg episode reward: 5.480, avg true_objective: 4.480
[2023-02-24 07:58:40,719][784615] Num frames 500...
[2023-02-24 07:58:40,787][784615] Num frames 600...
[2023-02-24 07:58:40,850][784615] Num frames 700...
[2023-02-24 07:58:40,918][784615] Num frames 800...
[2023-02-24 07:58:41,005][784615] Num frames 900...
[2023-02-24 07:58:41,078][784615] Avg episode rewards: #0: 6.640, true rewards: #0: 4.640
[2023-02-24 07:58:41,079][784615] Avg episode reward: 6.640, avg true_objective: 4.640
[2023-02-24 07:58:41,129][784615] Num frames 1000...
[2023-02-24 07:58:41,202][784615] Num frames 1100...
[2023-02-24 07:58:41,276][784615] Num frames 1200...
[2023-02-24 07:58:41,360][784615] Num frames 1300...
[2023-02-24 07:58:41,429][784615] Num frames 1400...
[2023-02-24 07:58:41,493][784615] Num frames 1500...
[2023-02-24 07:58:41,554][784615] Num frames 1600...
[2023-02-24 07:58:41,667][784615] Avg episode rewards: #0: 8.653, true rewards: #0: 5.653
[2023-02-24 07:58:41,668][784615] Avg episode reward: 8.653, avg true_objective: 5.653
[2023-02-24 07:58:41,673][784615] Num frames 1700...
[2023-02-24 07:58:41,734][784615] Num frames 1800...
[2023-02-24 07:58:41,791][784615] Num frames 1900...
[2023-02-24 07:58:41,848][784615] Num frames 2000...
[2023-02-24 07:58:41,905][784615] Num frames 2100...
[2023-02-24 07:58:41,961][784615] Num frames 2200...
[2023-02-24 07:58:42,055][784615] Avg episode rewards: #0: 8.680, true rewards: #0: 5.680
[2023-02-24 07:58:42,056][784615] Avg episode reward: 8.680, avg true_objective: 5.680
[2023-02-24 07:58:42,077][784615] Num frames 2300...
[2023-02-24 07:58:42,141][784615] Num frames 2400...
[2023-02-24 07:58:42,203][784615] Num frames 2500...
[2023-02-24 07:58:42,260][784615] Num frames 2600...
[2023-02-24 07:58:42,346][784615] Avg episode rewards: #0: 7.712, true rewards: #0: 5.312
[2023-02-24 07:58:42,348][784615] Avg episode reward: 7.712, avg true_objective: 5.312
[2023-02-24 07:58:42,385][784615] Num frames 2700...
[2023-02-24 07:58:42,449][784615] Num frames 2800...
[2023-02-24 07:58:42,506][784615] Num frames 2900...
[2023-02-24 07:58:42,563][784615] Num frames 3000...
[2023-02-24 07:58:42,621][784615] Num frames 3100...
[2023-02-24 07:58:42,688][784615] Num frames 3200...
[2023-02-24 07:58:42,788][784615] Avg episode rewards: #0: 7.940, true rewards: #0: 5.440
[2023-02-24 07:58:42,788][784615] Avg episode reward: 7.940, avg true_objective: 5.440
[2023-02-24 07:58:42,817][784615] Num frames 3300...
[2023-02-24 07:58:42,890][784615] Num frames 3400...
[2023-02-24 07:58:42,964][784615] Num frames 3500...
[2023-02-24 07:58:43,040][784615] Num frames 3600...
[2023-02-24 07:58:43,128][784615] Avg episode rewards: #0: 7.354, true rewards: #0: 5.211
[2023-02-24 07:58:43,130][784615] Avg episode reward: 7.354, avg true_objective: 5.211
[2023-02-24 07:58:43,174][784615] Num frames 3700...
[2023-02-24 07:58:43,248][784615] Num frames 3800...
[2023-02-24 07:58:43,316][784615] Num frames 3900...
[2023-02-24 07:58:43,383][784615] Num frames 4000...
[2023-02-24 07:58:43,475][784615] Avg episode rewards: #0: 7.205, true rewards: #0: 5.080
[2023-02-24 07:58:43,476][784615] Avg episode reward: 7.205, avg true_objective: 5.080
[2023-02-24 07:58:43,498][784615] Num frames 4100...
[2023-02-24 07:58:43,556][784615] Num frames 4200...
[2023-02-24 07:58:43,614][784615] Num frames 4300...
[2023-02-24 07:58:43,670][784615] Num frames 4400...
[2023-02-24 07:58:43,727][784615] Num frames 4500...
[2023-02-24 07:58:43,790][784615] Num frames 4600...
[2023-02-24 07:58:43,891][784615] Avg episode rewards: #0: 7.413, true rewards: #0: 5.191
[2023-02-24 07:58:43,891][784615] Avg episode reward: 7.413, avg true_objective: 5.191
[2023-02-24 07:58:43,912][784615] Num frames 4700...
[2023-02-24 07:58:43,982][784615] Num frames 4800...
[2023-02-24 07:58:44,049][784615] Num frames 4900...
[2023-02-24 07:58:44,117][784615] Num frames 5000...
[2023-02-24 07:58:44,184][784615] Num frames 5100...
[2023-02-24 07:58:44,250][784615] Avg episode rewards: #0: 7.220, true rewards: #0: 5.120
[2023-02-24 07:58:44,250][784615] Avg episode reward: 7.220, avg true_objective: 5.120
[2023-02-24 07:58:46,584][784615] Replay video saved to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!
[2023-02-24 07:59:12,402][784615] The model has been pushed to https://huggingface.co/chqmatteo/rl_course_vizdoom_health_gathering_supreme
[2023-02-24 08:02:31,136][784615] Environment doom_basic already registered, overwriting...
[2023-02-24 08:02:31,137][784615] Environment doom_two_colors_easy already registered, overwriting...
[2023-02-24 08:02:31,137][784615] Environment doom_two_colors_hard already registered, overwriting...
[2023-02-24 08:02:31,138][784615] Environment doom_dm already registered, overwriting...
[2023-02-24 08:02:31,138][784615] Environment doom_dwango5 already registered, overwriting...
[2023-02-24 08:02:31,139][784615] Environment doom_my_way_home_flat_actions already registered, overwriting...
[2023-02-24 08:02:31,139][784615] Environment doom_defend_the_center_flat_actions already registered, overwriting...
[2023-02-24 08:02:31,139][784615] Environment doom_my_way_home already registered, overwriting...
[2023-02-24 08:02:31,140][784615] Environment doom_deadly_corridor already registered, overwriting...
[2023-02-24 08:02:31,140][784615] Environment doom_defend_the_center already registered, overwriting...
[2023-02-24 08:02:31,140][784615] Environment doom_defend_the_line already registered, overwriting...
[2023-02-24 08:02:31,141][784615] Environment doom_health_gathering already registered, overwriting...
[2023-02-24 08:02:31,141][784615] Environment doom_health_gathering_supreme already registered, overwriting...
[2023-02-24 08:02:31,142][784615] Environment doom_battle already registered, overwriting...
[2023-02-24 08:02:31,142][784615] Environment doom_battle2 already registered, overwriting...
[2023-02-24 08:02:31,142][784615] Environment doom_duel_bots already registered, overwriting...
[2023-02-24 08:02:31,142][784615] Environment doom_deathmatch_bots already registered, overwriting...
[2023-02-24 08:02:31,143][784615] Environment doom_duel already registered, overwriting...
[2023-02-24 08:02:31,143][784615] Environment doom_deathmatch_full already registered, overwriting...
[2023-02-24 08:02:31,143][784615] Environment doom_benchmark already registered, overwriting...
[2023-02-24 08:02:31,144][784615] register_encoder_factory: <function make_vizdoom_encoder at 0x7f9fbe7ae680>
[2023-02-24 08:02:31,153][784615] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
[2023-02-24 08:02:31,154][784615] Overriding arg 'train_for_env_steps' with value 40000000 passed from command line
[2023-02-24 08:02:31,157][784615] Experiment dir /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment already exists!
[2023-02-24 08:02:31,158][784615] Resuming existing experiment from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment...
[2023-02-24 08:02:31,158][784615] Weights and Biases integration disabled
[2023-02-24 08:02:31,159][784615] Environment var CUDA_VISIBLE_DEVICES is 1
[2023-02-24 08:03:09,472][784615] Environment doom_basic already registered, overwriting...
[2023-02-24 08:03:09,474][784615] Environment doom_two_colors_easy already registered, overwriting...
[2023-02-24 08:03:09,475][784615] Environment doom_two_colors_hard already registered, overwriting...
[2023-02-24 08:03:09,476][784615] Environment doom_dm already registered, overwriting...
[2023-02-24 08:03:09,477][784615] Environment doom_dwango5 already registered, overwriting...
[2023-02-24 08:03:09,477][784615] Environment doom_my_way_home_flat_actions already registered, overwriting...
[2023-02-24 08:03:09,478][784615] Environment doom_defend_the_center_flat_actions already registered, overwriting...
[2023-02-24 08:03:09,478][784615] Environment doom_my_way_home already registered, overwriting...
[2023-02-24 08:03:09,479][784615] Environment doom_deadly_corridor already registered, overwriting...
[2023-02-24 08:03:09,479][784615] Environment doom_defend_the_center already registered, overwriting...
[2023-02-24 08:03:09,480][784615] Environment doom_defend_the_line already registered, overwriting...
[2023-02-24 08:03:09,480][784615] Environment doom_health_gathering already registered, overwriting...
[2023-02-24 08:03:09,481][784615] Environment doom_health_gathering_supreme already registered, overwriting...
[2023-02-24 08:03:09,481][784615] Environment doom_battle already registered, overwriting...
[2023-02-24 08:03:09,482][784615] Environment doom_battle2 already registered, overwriting...
[2023-02-24 08:03:09,482][784615] Environment doom_duel_bots already registered, overwriting...
[2023-02-24 08:03:09,483][784615] Environment doom_deathmatch_bots already registered, overwriting...
[2023-02-24 08:03:09,483][784615] Environment doom_duel already registered, overwriting...
[2023-02-24 08:03:09,483][784615] Environment doom_deathmatch_full already registered, overwriting...
[2023-02-24 08:03:09,484][784615] Environment doom_benchmark already registered, overwriting...
[2023-02-24 08:03:09,484][784615] register_encoder_factory: <function make_vizdoom_encoder at 0x7f9fbe7ae680>
[2023-02-24 08:03:09,494][784615] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
[2023-02-24 08:03:09,495][784615] Overriding arg 'train_for_env_steps' with value 40000000 passed from command line
[2023-02-24 08:03:09,498][784615] Experiment dir /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment already exists!
[2023-02-24 08:03:09,499][784615] Resuming existing experiment from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment...
[2023-02-24 08:03:09,499][784615] Weights and Biases integration disabled
[2023-02-24 08:03:09,500][784615] Environment var CUDA_VISIBLE_DEVICES is 1
[2023-02-24 08:06:20,559][795538] Saving configuration to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json...
[2023-02-24 08:06:20,725][795538] Rollout worker 0 uses device cpu
[2023-02-24 08:06:20,726][795538] Rollout worker 1 uses device cpu
[2023-02-24 08:06:20,726][795538] Rollout worker 2 uses device cpu
[2023-02-24 08:06:20,727][795538] Rollout worker 3 uses device cpu
[2023-02-24 08:06:20,727][795538] Rollout worker 4 uses device cpu
[2023-02-24 08:06:20,727][795538] Rollout worker 5 uses device cpu
[2023-02-24 08:06:20,728][795538] Rollout worker 6 uses device cpu
[2023-02-24 08:06:20,728][795538] Rollout worker 7 uses device cpu
[2023-02-24 08:06:20,767][795538] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:06:20,768][795538] InferenceWorker_p0-w0: min num requests: 2
[2023-02-24 08:06:20,819][795538] Starting all processes...
[2023-02-24 08:06:20,820][795538] Starting process learner_proc0
[2023-02-24 08:06:20,869][795538] Starting all processes...
[2023-02-24 08:06:20,872][795538] Starting process inference_proc0-0
[2023-02-24 08:06:20,873][795538] Starting process rollout_proc0
[2023-02-24 08:06:20,873][795538] Starting process rollout_proc1
[2023-02-24 08:06:20,873][795538] Starting process rollout_proc2
[2023-02-24 08:06:20,873][795538] Starting process rollout_proc3
[2023-02-24 08:06:20,874][795538] Starting process rollout_proc4
[2023-02-24 08:06:20,874][795538] Starting process rollout_proc5
[2023-02-24 08:06:20,874][795538] Starting process rollout_proc6
[2023-02-24 08:06:20,875][795538] Starting process rollout_proc7
[2023-02-24 08:06:22,179][795628] Worker 1 uses CPU cores [1]
[2023-02-24 08:06:22,214][795634] Worker 6 uses CPU cores [6]
[2023-02-24 08:06:22,319][795626] Low niceness requires sudo!
[2023-02-24 08:06:22,319][795626] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:06:22,319][795626] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for inference process 0
[2023-02-24 08:06:22,336][795626] Num visible devices: 1
[2023-02-24 08:06:22,343][795613] Low niceness requires sudo!
[2023-02-24 08:06:22,343][795613] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:06:22,344][795613] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for learning process 0
[2023-02-24 08:06:22,361][795613] Num visible devices: 1
[2023-02-24 08:06:22,366][795632] Worker 5 uses CPU cores [5]
[2023-02-24 08:06:22,394][795613] Starting seed is not provided
[2023-02-24 08:06:22,394][795613] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:06:22,394][795613] Initializing actor-critic model on device cuda:0
[2023-02-24 08:06:22,395][795613] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 08:06:22,395][795613] RunningMeanStd input shape: (1,)
[2023-02-24 08:06:22,409][795613] ConvEncoder: input_channels=3
[2023-02-24 08:06:22,497][795613] Conv encoder output size: 512
[2023-02-24 08:06:22,497][795613] Policy head output size: 512
[2023-02-24 08:06:22,506][795613] Created Actor Critic model with architecture:
[2023-02-24 08:06:22,507][795613] 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 08:06:22,514][795631] Worker 4 uses CPU cores [4]
[2023-02-24 08:06:22,542][795633] Worker 7 uses CPU cores [7]
[2023-02-24 08:06:22,548][795630] Worker 3 uses CPU cores [3]
[2023-02-24 08:06:22,590][795629] Worker 2 uses CPU cores [2]
[2023-02-24 08:06:22,604][795627] Worker 0 uses CPU cores [0]
[2023-02-24 08:06:25,136][795613] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-24 08:06:25,137][795613] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000268_1097728.pth...
[2023-02-24 08:06:25,196][795613] Loading model from checkpoint
[2023-02-24 08:06:25,198][795613] Loaded experiment state at self.train_step=268, self.env_steps=1097728
[2023-02-24 08:06:25,198][795613] Initialized policy 0 weights for model version 268
[2023-02-24 08:06:25,199][795613] LearnerWorker_p0 finished initialization!
[2023-02-24 08:06:25,199][795613] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:06:26,272][795626] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 08:06:26,272][795626] RunningMeanStd input shape: (1,)
[2023-02-24 08:06:26,280][795626] ConvEncoder: input_channels=3
[2023-02-24 08:06:26,341][795626] Conv encoder output size: 512
[2023-02-24 08:06:26,342][795626] Policy head output size: 512
[2023-02-24 08:06:27,341][795538] Inference worker 0-0 is ready!
[2023-02-24 08:06:27,341][795538] All inference workers are ready! Signal rollout workers to start!
[2023-02-24 08:06:27,358][795628] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:06:27,358][795631] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:06:27,358][795627] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:06:27,359][795629] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:06:27,364][795634] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:06:27,381][795632] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:06:27,380][795630] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:06:27,394][795633] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:06:27,569][795627] Decorrelating experience for 0 frames...
[2023-02-24 08:06:27,619][795634] Decorrelating experience for 0 frames...
[2023-02-24 08:06:27,650][795629] Decorrelating experience for 0 frames...
[2023-02-24 08:06:27,665][795630] Decorrelating experience for 0 frames...
[2023-02-24 08:06:27,805][795634] Decorrelating experience for 32 frames...
[2023-02-24 08:06:27,881][795630] Decorrelating experience for 32 frames...
[2023-02-24 08:06:27,882][795627] Decorrelating experience for 32 frames...
[2023-02-24 08:06:27,882][795632] Decorrelating experience for 0 frames...
[2023-02-24 08:06:28,090][795630] Decorrelating experience for 64 frames...
[2023-02-24 08:06:28,092][795632] Decorrelating experience for 32 frames...
[2023-02-24 08:06:28,106][795627] Decorrelating experience for 64 frames...
[2023-02-24 08:06:28,308][795632] Decorrelating experience for 64 frames...
[2023-02-24 08:06:28,376][795628] Decorrelating experience for 0 frames...
[2023-02-24 08:06:28,383][795630] Decorrelating experience for 96 frames...
[2023-02-24 08:06:28,383][795629] Decorrelating experience for 32 frames...
[2023-02-24 08:06:28,395][795627] Decorrelating experience for 96 frames...
[2023-02-24 08:06:28,625][795628] Decorrelating experience for 32 frames...
[2023-02-24 08:06:28,660][795633] Decorrelating experience for 0 frames...
[2023-02-24 08:06:28,720][795632] Decorrelating experience for 96 frames...
[2023-02-24 08:06:28,729][795631] Decorrelating experience for 0 frames...
[2023-02-24 08:06:28,907][795633] Decorrelating experience for 32 frames...
[2023-02-24 08:06:28,955][795628] Decorrelating experience for 64 frames...
[2023-02-24 08:06:28,975][795634] Decorrelating experience for 64 frames...
[2023-02-24 08:06:29,141][795633] Decorrelating experience for 64 frames...
[2023-02-24 08:06:29,169][795631] Decorrelating experience for 32 frames...
[2023-02-24 08:06:29,237][795628] Decorrelating experience for 96 frames...
[2023-02-24 08:06:29,253][795629] Decorrelating experience for 64 frames...
[2023-02-24 08:06:29,425][795631] Decorrelating experience for 64 frames...
[2023-02-24 08:06:29,531][795629] Decorrelating experience for 96 frames...
[2023-02-24 08:06:29,537][795634] Decorrelating experience for 96 frames...
[2023-02-24 08:06:29,541][795633] Decorrelating experience for 96 frames...
[2023-02-24 08:06:29,684][795631] Decorrelating experience for 96 frames...
[2023-02-24 08:06:29,698][795538] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 1097728. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-24 08:06:30,658][795613] Signal inference workers to stop experience collection...
[2023-02-24 08:06:30,662][795626] InferenceWorker_p0-w0: stopping experience collection
[2023-02-24 08:06:32,942][795613] Signal inference workers to resume experience collection...
[2023-02-24 08:06:32,942][795626] InferenceWorker_p0-w0: resuming experience collection
[2023-02-24 08:06:34,697][795538] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 1126400. Throughput: 0: 628.8. Samples: 3144. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-02-24 08:06:34,699][795538] Avg episode reward: [(0, '5.223')]
[2023-02-24 08:06:35,433][795626] Updated weights for policy 0, policy_version 278 (0.0234)
[2023-02-24 08:06:38,065][795626] Updated weights for policy 0, policy_version 288 (0.0006)
[2023-02-24 08:06:39,698][795538] Fps is (10 sec: 10649.4, 60 sec: 10649.4, 300 sec: 10649.4). Total num frames: 1204224. Throughput: 0: 2626.3. Samples: 26264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 08:06:39,699][795538] Avg episode reward: [(0, '6.797')]
[2023-02-24 08:06:39,702][795613] Saving new best policy, reward=6.797!
[2023-02-24 08:06:40,702][795626] Updated weights for policy 0, policy_version 298 (0.0006)
[2023-02-24 08:06:40,762][795538] Heartbeat connected on Batcher_0
[2023-02-24 08:06:40,764][795538] Heartbeat connected on LearnerWorker_p0
[2023-02-24 08:06:40,771][795538] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-24 08:06:40,775][795538] Heartbeat connected on RolloutWorker_w0
[2023-02-24 08:06:40,777][795538] Heartbeat connected on RolloutWorker_w2
[2023-02-24 08:06:40,778][795538] Heartbeat connected on RolloutWorker_w1
[2023-02-24 08:06:40,779][795538] Heartbeat connected on RolloutWorker_w3
[2023-02-24 08:06:40,783][795538] Heartbeat connected on RolloutWorker_w4
[2023-02-24 08:06:40,784][795538] Heartbeat connected on RolloutWorker_w5
[2023-02-24 08:06:40,819][795538] Heartbeat connected on RolloutWorker_w7
[2023-02-24 08:06:40,825][795538] Heartbeat connected on RolloutWorker_w6
[2023-02-24 08:06:43,242][795626] Updated weights for policy 0, policy_version 308 (0.0007)
[2023-02-24 08:06:44,698][795538] Fps is (10 sec: 15564.8, 60 sec: 12288.0, 300 sec: 12288.0). Total num frames: 1282048. Throughput: 0: 2536.4. Samples: 38046. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-24 08:06:44,698][795538] Avg episode reward: [(0, '7.215')]
[2023-02-24 08:06:44,700][795613] Saving new best policy, reward=7.215!
[2023-02-24 08:06:45,889][795626] Updated weights for policy 0, policy_version 318 (0.0007)
[2023-02-24 08:06:48,495][795626] Updated weights for policy 0, policy_version 328 (0.0007)
[2023-02-24 08:06:49,698][795538] Fps is (10 sec: 15565.1, 60 sec: 13107.2, 300 sec: 13107.2). Total num frames: 1359872. Throughput: 0: 3079.6. Samples: 61592. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 08:06:49,699][795538] Avg episode reward: [(0, '8.493')]
[2023-02-24 08:06:49,702][795613] Saving new best policy, reward=8.493!
[2023-02-24 08:06:51,107][795626] Updated weights for policy 0, policy_version 338 (0.0007)
[2023-02-24 08:06:53,724][795626] Updated weights for policy 0, policy_version 348 (0.0007)
[2023-02-24 08:06:54,698][795538] Fps is (10 sec: 15564.7, 60 sec: 13598.7, 300 sec: 13598.7). Total num frames: 1437696. Throughput: 0: 3404.3. Samples: 85108. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:06:54,699][795538] Avg episode reward: [(0, '10.669')]
[2023-02-24 08:06:54,700][795613] Saving new best policy, reward=10.669!
[2023-02-24 08:06:56,371][795626] Updated weights for policy 0, policy_version 358 (0.0007)
[2023-02-24 08:06:58,972][795626] Updated weights for policy 0, policy_version 368 (0.0007)
[2023-02-24 08:06:59,697][795538] Fps is (10 sec: 15564.8, 60 sec: 13926.4, 300 sec: 13926.4). Total num frames: 1515520. Throughput: 0: 3226.5. Samples: 96796. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:06:59,698][795538] Avg episode reward: [(0, '13.259')]
[2023-02-24 08:06:59,701][795613] Saving new best policy, reward=13.259!
[2023-02-24 08:07:01,613][795626] Updated weights for policy 0, policy_version 378 (0.0007)
[2023-02-24 08:07:04,206][795626] Updated weights for policy 0, policy_version 388 (0.0007)
[2023-02-24 08:07:04,698][795538] Fps is (10 sec: 15564.9, 60 sec: 14160.5, 300 sec: 14160.5). Total num frames: 1593344. Throughput: 0: 3437.5. Samples: 120312. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:07:04,698][795538] Avg episode reward: [(0, '13.989')]
[2023-02-24 08:07:04,699][795613] Saving new best policy, reward=13.989!
[2023-02-24 08:07:06,831][795626] Updated weights for policy 0, policy_version 398 (0.0007)
[2023-02-24 08:07:08,206][795538] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 795538], exiting...
[2023-02-24 08:07:08,207][795538] Runner profile tree view:
main_loop: 47.3880
[2023-02-24 08:07:08,208][795613] Stopping Batcher_0...
[2023-02-24 08:07:08,208][795613] Loop batcher_evt_loop terminating...
[2023-02-24 08:07:08,208][795538] Collected {0: 1650688}, FPS: 11668.8
[2023-02-24 08:07:08,209][795613] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000403_1650688.pth...
[2023-02-24 08:07:08,216][795632] Stopping RolloutWorker_w5...
[2023-02-24 08:07:08,216][795632] Loop rollout_proc5_evt_loop terminating...
[2023-02-24 08:07:08,218][795630] Stopping RolloutWorker_w3...
[2023-02-24 08:07:08,218][795630] Loop rollout_proc3_evt_loop terminating...
[2023-02-24 08:07:08,218][795628] Stopping RolloutWorker_w1...
[2023-02-24 08:07:08,218][795633] Stopping RolloutWorker_w7...
[2023-02-24 08:07:08,219][795628] Loop rollout_proc1_evt_loop terminating...
[2023-02-24 08:07:08,219][795633] Loop rollout_proc7_evt_loop terminating...
[2023-02-24 08:07:08,221][795631] Stopping RolloutWorker_w4...
[2023-02-24 08:07:08,221][795631] Loop rollout_proc4_evt_loop terminating...
[2023-02-24 08:07:08,228][795629] Stopping RolloutWorker_w2...
[2023-02-24 08:07:08,228][795629] Loop rollout_proc2_evt_loop terminating...
[2023-02-24 08:07:08,230][795627] Stopping RolloutWorker_w0...
[2023-02-24 08:07:08,230][795634] Stopping RolloutWorker_w6...
[2023-02-24 08:07:08,230][795634] Loop rollout_proc6_evt_loop terminating...
[2023-02-24 08:07:08,230][795627] Loop rollout_proc0_evt_loop terminating...
[2023-02-24 08:07:08,252][795626] Weights refcount: 2 0
[2023-02-24 08:07:08,256][795626] Stopping InferenceWorker_p0-w0...
[2023-02-24 08:07:08,260][795626] Loop inference_proc0-0_evt_loop terminating...
[2023-02-24 08:07:08,376][795613] Stopping LearnerWorker_p0...
[2023-02-24 08:07:08,377][795613] Loop learner_proc0_evt_loop terminating...
[2023-02-24 08:07:38,064][795538] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
[2023-02-24 08:07:38,065][795538] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-24 08:07:38,065][795538] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-24 08:07:38,065][795538] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-24 08:07:38,066][795538] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 08:07:38,066][795538] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-24 08:07:38,066][795538] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2023-02-24 08:07:38,067][795538] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-24 08:07:38,067][795538] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-24 08:07:38,068][795538] Adding new argument 'hf_repository'='chqmatteo/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-24 08:07:38,068][795538] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-24 08:07:38,068][795538] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-24 08:07:38,068][795538] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-24 08:07:38,069][795538] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-24 08:07:38,069][795538] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-24 08:07:38,076][795538] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:07:38,077][795538] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 08:07:38,078][795538] RunningMeanStd input shape: (1,)
[2023-02-24 08:07:38,086][795538] ConvEncoder: input_channels=3
[2023-02-24 08:07:38,169][795538] Conv encoder output size: 512
[2023-02-24 08:07:38,170][795538] Policy head output size: 512
[2023-02-24 08:07:40,757][795538] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000403_1650688.pth...
[2023-02-24 08:07:42,930][795538] Num frames 100...
[2023-02-24 08:07:43,007][795538] Num frames 200...
[2023-02-24 08:07:43,075][795538] Num frames 300...
[2023-02-24 08:07:43,138][795538] Num frames 400...
[2023-02-24 08:07:43,207][795538] Num frames 500...
[2023-02-24 08:07:43,275][795538] Num frames 600...
[2023-02-24 08:07:43,349][795538] Num frames 700...
[2023-02-24 08:07:43,409][795538] Avg episode rewards: #0: 16.090, true rewards: #0: 7.090
[2023-02-24 08:07:43,410][795538] Avg episode reward: 16.090, avg true_objective: 7.090
[2023-02-24 08:07:43,472][795538] Num frames 800...
[2023-02-24 08:07:43,536][795538] Num frames 900...
[2023-02-24 08:07:43,605][795538] Num frames 1000...
[2023-02-24 08:07:43,689][795538] Num frames 1100...
[2023-02-24 08:07:43,790][795538] Avg episode rewards: #0: 10.785, true rewards: #0: 5.785
[2023-02-24 08:07:43,791][795538] Avg episode reward: 10.785, avg true_objective: 5.785
[2023-02-24 08:07:43,819][795538] Num frames 1200...
[2023-02-24 08:07:43,885][795538] Num frames 1300...
[2023-02-24 08:07:43,956][795538] Num frames 1400...
[2023-02-24 08:07:44,024][795538] Num frames 1500...
[2023-02-24 08:07:44,102][795538] Num frames 1600...
[2023-02-24 08:07:44,182][795538] Num frames 1700...
[2023-02-24 08:07:44,280][795538] Avg episode rewards: #0: 10.217, true rewards: #0: 5.883
[2023-02-24 08:07:44,280][795538] Avg episode reward: 10.217, avg true_objective: 5.883
[2023-02-24 08:07:44,305][795538] Num frames 1800...
[2023-02-24 08:07:44,373][795538] Num frames 1900...
[2023-02-24 08:07:44,443][795538] Num frames 2000...
[2023-02-24 08:07:44,519][795538] Num frames 2100...
[2023-02-24 08:07:44,607][795538] Num frames 2200...
[2023-02-24 08:07:44,678][795538] Num frames 2300...
[2023-02-24 08:07:44,753][795538] Num frames 2400...
[2023-02-24 08:07:44,838][795538] Num frames 2500...
[2023-02-24 08:07:44,919][795538] Num frames 2600...
[2023-02-24 08:07:45,012][795538] Avg episode rewards: #0: 12.653, true rewards: #0: 6.652
[2023-02-24 08:07:45,013][795538] Avg episode reward: 12.653, avg true_objective: 6.652
[2023-02-24 08:07:45,040][795538] Num frames 2700...
[2023-02-24 08:07:45,115][795538] Num frames 2800...
[2023-02-24 08:07:45,187][795538] Num frames 2900...
[2023-02-24 08:07:45,261][795538] Num frames 3000...
[2023-02-24 08:07:45,381][795538] Num frames 3100...
[2023-02-24 08:07:45,448][795538] Num frames 3200...
[2023-02-24 08:07:45,513][795538] Num frames 3300...
[2023-02-24 08:07:45,581][795538] Num frames 3400...
[2023-02-24 08:07:45,652][795538] Num frames 3500...
[2023-02-24 08:07:45,717][795538] Num frames 3600...
[2023-02-24 08:07:45,790][795538] Num frames 3700...
[2023-02-24 08:07:45,860][795538] Num frames 3800...
[2023-02-24 08:07:45,935][795538] Num frames 3900...
[2023-02-24 08:07:46,006][795538] Num frames 4000...
[2023-02-24 08:07:46,078][795538] Num frames 4100...
[2023-02-24 08:07:46,213][795538] Avg episode rewards: #0: 17.194, true rewards: #0: 8.394
[2023-02-24 08:07:46,214][795538] Avg episode reward: 17.194, avg true_objective: 8.394
[2023-02-24 08:07:46,216][795538] Num frames 4200...
[2023-02-24 08:07:46,291][795538] Num frames 4300...
[2023-02-24 08:07:46,369][795538] Num frames 4400...
[2023-02-24 08:07:46,449][795538] Num frames 4500...
[2023-02-24 08:07:46,522][795538] Num frames 4600...
[2023-02-24 08:07:46,591][795538] Num frames 4700...
[2023-02-24 08:07:46,662][795538] Num frames 4800...
[2023-02-24 08:07:46,732][795538] Num frames 4900...
[2023-02-24 08:07:46,831][795538] Avg episode rewards: #0: 16.942, true rewards: #0: 8.275
[2023-02-24 08:07:46,831][795538] Avg episode reward: 16.942, avg true_objective: 8.275
[2023-02-24 08:07:46,855][795538] Num frames 5000...
[2023-02-24 08:07:46,919][795538] Num frames 5100...
[2023-02-24 08:07:46,986][795538] Num frames 5200...
[2023-02-24 08:07:47,056][795538] Num frames 5300...
[2023-02-24 08:07:47,141][795538] Num frames 5400...
[2023-02-24 08:07:47,210][795538] Num frames 5500...
[2023-02-24 08:07:47,278][795538] Num frames 5600...
[2023-02-24 08:07:47,382][795538] Avg episode rewards: #0: 16.394, true rewards: #0: 8.109
[2023-02-24 08:07:47,383][795538] Avg episode reward: 16.394, avg true_objective: 8.109
[2023-02-24 08:07:47,406][795538] Num frames 5700...
[2023-02-24 08:07:47,483][795538] Num frames 5800...
[2023-02-24 08:07:47,567][795538] Num frames 5900...
[2023-02-24 08:07:47,636][795538] Num frames 6000...
[2023-02-24 08:07:47,706][795538] Num frames 6100...
[2023-02-24 08:07:47,783][795538] Num frames 6200...
[2023-02-24 08:07:47,861][795538] Num frames 6300...
[2023-02-24 08:07:47,935][795538] Num frames 6400...
[2023-02-24 08:07:48,009][795538] Num frames 6500...
[2023-02-24 08:07:48,093][795538] Num frames 6600...
[2023-02-24 08:07:48,166][795538] Num frames 6700...
[2023-02-24 08:07:48,237][795538] Num frames 6800...
[2023-02-24 08:07:48,313][795538] Num frames 6900...
[2023-02-24 08:07:48,383][795538] Num frames 7000...
[2023-02-24 08:07:48,450][795538] Num frames 7100...
[2023-02-24 08:07:48,516][795538] Num frames 7200...
[2023-02-24 08:07:48,594][795538] Num frames 7300...
[2023-02-24 08:07:48,669][795538] Num frames 7400...
[2023-02-24 08:07:48,742][795538] Num frames 7500...
[2023-02-24 08:07:48,814][795538] Num frames 7600...
[2023-02-24 08:07:48,895][795538] Num frames 7700...
[2023-02-24 08:07:48,996][795538] Avg episode rewards: #0: 21.345, true rewards: #0: 9.720
[2023-02-24 08:07:48,997][795538] Avg episode reward: 21.345, avg true_objective: 9.720
[2023-02-24 08:07:49,018][795538] Num frames 7800...
[2023-02-24 08:07:49,092][795538] Num frames 7900...
[2023-02-24 08:07:49,171][795538] Num frames 8000...
[2023-02-24 08:07:49,241][795538] Num frames 8100...
[2023-02-24 08:07:49,311][795538] Num frames 8200...
[2023-02-24 08:07:49,424][795538] Avg episode rewards: #0: 20.098, true rewards: #0: 9.209
[2023-02-24 08:07:49,425][795538] Avg episode reward: 20.098, avg true_objective: 9.209
[2023-02-24 08:07:49,434][795538] Num frames 8300...
[2023-02-24 08:07:49,502][795538] Num frames 8400...
[2023-02-24 08:07:49,568][795538] Num frames 8500...
[2023-02-24 08:07:49,643][795538] Num frames 8600...
[2023-02-24 08:07:49,707][795538] Num frames 8700...
[2023-02-24 08:07:49,763][795538] Avg episode rewards: #0: 18.704, true rewards: #0: 8.704
[2023-02-24 08:07:49,764][795538] Avg episode reward: 18.704, avg true_objective: 8.704
[2023-02-24 08:07:53,791][795538] Replay video saved to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!
[2023-02-24 08:08:19,273][795538] The model has been pushed to https://huggingface.co/chqmatteo/rl_course_vizdoom_health_gathering_supreme
[2023-02-24 08:08:42,140][795538] Environment doom_basic already registered, overwriting...
[2023-02-24 08:08:42,141][795538] Environment doom_two_colors_easy already registered, overwriting...
[2023-02-24 08:08:42,142][795538] Environment doom_two_colors_hard already registered, overwriting...
[2023-02-24 08:08:42,142][795538] Environment doom_dm already registered, overwriting...
[2023-02-24 08:08:42,142][795538] Environment doom_dwango5 already registered, overwriting...
[2023-02-24 08:08:42,143][795538] Environment doom_my_way_home_flat_actions already registered, overwriting...
[2023-02-24 08:08:42,143][795538] Environment doom_defend_the_center_flat_actions already registered, overwriting...
[2023-02-24 08:08:42,143][795538] Environment doom_my_way_home already registered, overwriting...
[2023-02-24 08:08:42,144][795538] Environment doom_deadly_corridor already registered, overwriting...
[2023-02-24 08:08:42,144][795538] Environment doom_defend_the_center already registered, overwriting...
[2023-02-24 08:08:42,144][795538] Environment doom_defend_the_line already registered, overwriting...
[2023-02-24 08:08:42,145][795538] Environment doom_health_gathering already registered, overwriting...
[2023-02-24 08:08:42,145][795538] Environment doom_health_gathering_supreme already registered, overwriting...
[2023-02-24 08:08:42,145][795538] Environment doom_battle already registered, overwriting...
[2023-02-24 08:08:42,146][795538] Environment doom_battle2 already registered, overwriting...
[2023-02-24 08:08:42,146][795538] Environment doom_duel_bots already registered, overwriting...
[2023-02-24 08:08:42,146][795538] Environment doom_deathmatch_bots already registered, overwriting...
[2023-02-24 08:08:42,147][795538] Environment doom_duel already registered, overwriting...
[2023-02-24 08:08:42,147][795538] Environment doom_deathmatch_full already registered, overwriting...
[2023-02-24 08:08:42,148][795538] Environment doom_benchmark already registered, overwriting...
[2023-02-24 08:08:42,148][795538] register_encoder_factory: <function make_vizdoom_encoder at 0x7efd09ae12d0>
[2023-02-24 08:08:42,156][795538] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
[2023-02-24 08:08:42,157][795538] Experiment dir /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment already exists!
[2023-02-24 08:08:42,158][795538] Resuming existing experiment from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment...
[2023-02-24 08:08:42,158][795538] Weights and Biases integration disabled
[2023-02-24 08:08:42,159][795538] Environment var CUDA_VISIBLE_DEVICES is 1
[2023-02-24 08:08:43,053][795538] Starting experiment with the following configuration:
help=False
algo=APPO
env=doom_health_gathering_supreme
experiment=default_experiment
train_dir=/mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir
restart_behavior=resume
device=gpu
seed=None
num_policies=1
async_rl=True
serial_mode=False
batched_sampling=False
num_batches_to_accumulate=2
worker_num_splits=2
policy_workers_per_policy=1
max_policy_lag=1000
num_workers=8
num_envs_per_worker=4
batch_size=1024
num_batches_per_epoch=1
num_epochs=1
rollout=32
recurrence=32
shuffle_minibatches=False
gamma=0.99
reward_scale=1.0
reward_clip=1000.0
value_bootstrap=False
normalize_returns=True
exploration_loss_coeff=0.001
value_loss_coeff=0.5
kl_loss_coeff=0.0
exploration_loss=symmetric_kl
gae_lambda=0.95
ppo_clip_ratio=0.1
ppo_clip_value=0.2
with_vtrace=False
vtrace_rho=1.0
vtrace_c=1.0
optimizer=adam
adam_eps=1e-06
adam_beta1=0.9
adam_beta2=0.999
max_grad_norm=4.0
learning_rate=0.0001
lr_schedule=constant
lr_schedule_kl_threshold=0.008
lr_adaptive_min=1e-06
lr_adaptive_max=0.01
obs_subtract_mean=0.0
obs_scale=255.0
normalize_input=True
normalize_input_keys=None
decorrelate_experience_max_seconds=0
decorrelate_envs_on_one_worker=True
actor_worker_gpus=[]
set_workers_cpu_affinity=True
force_envs_single_thread=False
default_niceness=0
log_to_file=True
experiment_summaries_interval=10
flush_summaries_interval=30
stats_avg=100
summaries_use_frameskip=True
heartbeat_interval=20
heartbeat_reporting_interval=600
train_for_env_steps=40000000
train_for_seconds=10000000000
save_every_sec=120
keep_checkpoints=2
load_checkpoint_kind=latest
save_milestones_sec=-1
save_best_every_sec=5
save_best_metric=reward
save_best_after=100000
benchmark=False
encoder_mlp_layers=[512, 512]
encoder_conv_architecture=convnet_simple
encoder_conv_mlp_layers=[512]
use_rnn=True
rnn_size=512
rnn_type=gru
rnn_num_layers=1
decoder_mlp_layers=[]
nonlinearity=elu
policy_initialization=orthogonal
policy_init_gain=1.0
actor_critic_share_weights=True
adaptive_stddev=True
continuous_tanh_scale=0.0
initial_stddev=1.0
use_env_info_cache=False
env_gpu_actions=False
env_gpu_observations=True
env_frameskip=4
env_framestack=1
pixel_format=CHW
use_record_episode_statistics=False
with_wandb=False
wandb_user=None
wandb_project=sample_factory
wandb_group=None
wandb_job_type=SF
wandb_tags=[]
with_pbt=False
pbt_mix_policies_in_one_env=True
pbt_period_env_steps=5000000
pbt_start_mutation=20000000
pbt_replace_fraction=0.3
pbt_mutation_rate=0.15
pbt_replace_reward_gap=0.1
pbt_replace_reward_gap_absolute=1e-06
pbt_optimize_gamma=False
pbt_target_objective=true_objective
pbt_perturb_min=1.1
pbt_perturb_max=1.5
num_agents=-1
num_humans=0
num_bots=-1
start_bot_difficulty=None
timelimit=None
res_w=128
res_h=72
wide_aspect_ratio=False
eval_env_frameskip=1
fps=35
command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
git_hash=1a2374cbd09490752b14aee6fdecfe64db411550
git_repo_name=https://github.com/huggingface/deep-rl-class.git
[2023-02-24 08:08:43,053][795538] Saving configuration to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json...
[2023-02-24 08:08:43,222][795538] Rollout worker 0 uses device cpu
[2023-02-24 08:08:43,223][795538] Rollout worker 1 uses device cpu
[2023-02-24 08:08:43,223][795538] Rollout worker 2 uses device cpu
[2023-02-24 08:08:43,223][795538] Rollout worker 3 uses device cpu
[2023-02-24 08:08:43,224][795538] Rollout worker 4 uses device cpu
[2023-02-24 08:08:43,224][795538] Rollout worker 5 uses device cpu
[2023-02-24 08:08:43,225][795538] Rollout worker 6 uses device cpu
[2023-02-24 08:08:43,225][795538] Rollout worker 7 uses device cpu
[2023-02-24 08:08:43,257][795538] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:08:43,258][795538] InferenceWorker_p0-w0: min num requests: 2
[2023-02-24 08:08:43,278][795538] Starting all processes...
[2023-02-24 08:08:43,278][795538] Starting process learner_proc0
[2023-02-24 08:08:43,328][795538] Starting all processes...
[2023-02-24 08:08:43,329][795538] Starting process inference_proc0-0
[2023-02-24 08:08:43,330][795538] Starting process rollout_proc0
[2023-02-24 08:08:43,330][795538] Starting process rollout_proc1
[2023-02-24 08:08:43,330][795538] Starting process rollout_proc2
[2023-02-24 08:08:43,331][795538] Starting process rollout_proc3
[2023-02-24 08:08:43,331][795538] Starting process rollout_proc4
[2023-02-24 08:08:43,331][795538] Starting process rollout_proc5
[2023-02-24 08:08:43,331][795538] Starting process rollout_proc6
[2023-02-24 08:08:43,331][795538] Starting process rollout_proc7
[2023-02-24 08:08:44,462][796098] Low niceness requires sudo!
[2023-02-24 08:08:44,463][796098] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:08:44,463][796098] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for learning process 0
[2023-02-24 08:08:44,484][796098] Num visible devices: 1
[2023-02-24 08:08:44,522][796098] Starting seed is not provided
[2023-02-24 08:08:44,522][796098] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:08:44,523][796098] Initializing actor-critic model on device cuda:0
[2023-02-24 08:08:44,523][796098] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 08:08:44,524][796098] RunningMeanStd input shape: (1,)
[2023-02-24 08:08:44,549][796098] ConvEncoder: input_channels=3
[2023-02-24 08:08:44,706][796112] Low niceness requires sudo!
[2023-02-24 08:08:44,707][796112] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:08:44,707][796112] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for inference process 0
[2023-02-24 08:08:44,724][796112] Num visible devices: 1
[2023-02-24 08:08:44,767][796113] Worker 2 uses CPU cores [2]
[2023-02-24 08:08:44,802][796098] Conv encoder output size: 512
[2023-02-24 08:08:44,810][796098] Policy head output size: 512
[2023-02-24 08:08:44,842][796098] Created Actor Critic model with architecture:
[2023-02-24 08:08:44,843][796098] 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 08:08:44,946][796119] Worker 6 uses CPU cores [6]
[2023-02-24 08:08:44,948][796117] Worker 5 uses CPU cores [5]
[2023-02-24 08:08:45,059][796114] Worker 1 uses CPU cores [1]
[2023-02-24 08:08:45,108][796115] Worker 3 uses CPU cores [3]
[2023-02-24 08:08:45,108][796111] Worker 0 uses CPU cores [0]
[2023-02-24 08:08:45,114][796118] Worker 4 uses CPU cores [4]
[2023-02-24 08:08:45,164][796116] Worker 7 uses CPU cores [7]
[2023-02-24 08:08:46,945][796098] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-24 08:08:46,945][796098] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000403_1650688.pth...
[2023-02-24 08:08:47,005][796098] Loading model from checkpoint
[2023-02-24 08:08:47,007][796098] Loaded experiment state at self.train_step=403, self.env_steps=1650688
[2023-02-24 08:08:47,007][796098] Initialized policy 0 weights for model version 403
[2023-02-24 08:08:47,008][796098] LearnerWorker_p0 finished initialization!
[2023-02-24 08:08:47,008][796098] Using GPUs [0] for process 0 (actually maps to GPUs [1])
[2023-02-24 08:08:47,160][795538] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 1650688. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-24 08:08:48,101][796112] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 08:08:48,101][796112] RunningMeanStd input shape: (1,)
[2023-02-24 08:08:48,108][796112] ConvEncoder: input_channels=3
[2023-02-24 08:08:48,178][796112] Conv encoder output size: 512
[2023-02-24 08:08:48,178][796112] Policy head output size: 512
[2023-02-24 08:08:49,152][795538] Inference worker 0-0 is ready!
[2023-02-24 08:08:49,152][795538] All inference workers are ready! Signal rollout workers to start!
[2023-02-24 08:08:49,171][796116] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:08:49,171][796118] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:08:49,170][796115] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:08:49,171][796119] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:08:49,175][796111] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:08:49,176][796117] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:08:49,204][796113] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:08:49,205][796114] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 08:08:49,421][796115] Decorrelating experience for 0 frames...
[2023-02-24 08:08:49,457][796116] Decorrelating experience for 0 frames...
[2023-02-24 08:08:49,467][796114] Decorrelating experience for 0 frames...
[2023-02-24 08:08:49,471][796118] Decorrelating experience for 0 frames...
[2023-02-24 08:08:49,475][796117] Decorrelating experience for 0 frames...
[2023-02-24 08:08:49,653][796115] Decorrelating experience for 32 frames...
[2023-02-24 08:08:49,732][796116] Decorrelating experience for 32 frames...
[2023-02-24 08:08:49,752][796118] Decorrelating experience for 32 frames...
[2023-02-24 08:08:49,758][796117] Decorrelating experience for 32 frames...
[2023-02-24 08:08:49,795][796119] Decorrelating experience for 0 frames...
[2023-02-24 08:08:49,932][796114] Decorrelating experience for 32 frames...
[2023-02-24 08:08:50,017][796111] Decorrelating experience for 0 frames...
[2023-02-24 08:08:50,033][796116] Decorrelating experience for 64 frames...
[2023-02-24 08:08:50,071][796119] Decorrelating experience for 32 frames...
[2023-02-24 08:08:50,078][796115] Decorrelating experience for 64 frames...
[2023-02-24 08:08:50,109][796113] Decorrelating experience for 0 frames...
[2023-02-24 08:08:50,145][796118] Decorrelating experience for 64 frames...
[2023-02-24 08:08:50,241][796111] Decorrelating experience for 32 frames...
[2023-02-24 08:08:50,325][796116] Decorrelating experience for 96 frames...
[2023-02-24 08:08:50,338][796115] Decorrelating experience for 96 frames...
[2023-02-24 08:08:50,377][796117] Decorrelating experience for 64 frames...
[2023-02-24 08:08:50,445][796118] Decorrelating experience for 96 frames...
[2023-02-24 08:08:50,502][796111] Decorrelating experience for 64 frames...
[2023-02-24 08:08:50,527][796119] Decorrelating experience for 64 frames...
[2023-02-24 08:08:50,669][796117] Decorrelating experience for 96 frames...
[2023-02-24 08:08:50,704][796113] Decorrelating experience for 32 frames...
[2023-02-24 08:08:50,716][796114] Decorrelating experience for 64 frames...
[2023-02-24 08:08:50,804][796111] Decorrelating experience for 96 frames...
[2023-02-24 08:08:50,833][796119] Decorrelating experience for 96 frames...
[2023-02-24 08:08:50,958][796113] Decorrelating experience for 64 frames...
[2023-02-24 08:08:50,977][796114] Decorrelating experience for 96 frames...
[2023-02-24 08:08:51,210][796113] Decorrelating experience for 96 frames...
[2023-02-24 08:08:52,160][795538] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 1650688. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-24 08:08:52,161][795538] Avg episode reward: [(0, '0.903')]
[2023-02-24 08:08:52,586][796098] Signal inference workers to stop experience collection...
[2023-02-24 08:08:52,593][796112] InferenceWorker_p0-w0: stopping experience collection
[2023-02-24 08:08:54,537][796098] Signal inference workers to resume experience collection...
[2023-02-24 08:08:54,538][796112] InferenceWorker_p0-w0: resuming experience collection
[2023-02-24 08:08:57,090][796112] Updated weights for policy 0, policy_version 413 (0.0247)
[2023-02-24 08:08:57,160][795538] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 1691648. Throughput: 0: 332.8. Samples: 3328. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 08:08:57,161][795538] Avg episode reward: [(0, '8.033')]
[2023-02-24 08:08:59,657][796112] Updated weights for policy 0, policy_version 423 (0.0013)
[2023-02-24 08:09:02,160][795538] Fps is (10 sec: 11878.4, 60 sec: 7918.9, 300 sec: 7918.9). Total num frames: 1769472. Throughput: 0: 1818.4. Samples: 27276. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:09:02,161][795538] Avg episode reward: [(0, '21.201')]
[2023-02-24 08:09:02,163][796098] Saving new best policy, reward=21.201!
[2023-02-24 08:09:02,326][796112] Updated weights for policy 0, policy_version 433 (0.0009)
[2023-02-24 08:09:03,254][795538] Heartbeat connected on LearnerWorker_p0
[2023-02-24 08:09:03,262][795538] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-24 08:09:03,263][795538] Heartbeat connected on Batcher_0
[2023-02-24 08:09:03,264][795538] Heartbeat connected on RolloutWorker_w1
[2023-02-24 08:09:03,266][795538] Heartbeat connected on RolloutWorker_w2
[2023-02-24 08:09:03,269][795538] Heartbeat connected on RolloutWorker_w3
[2023-02-24 08:09:03,271][795538] Heartbeat connected on RolloutWorker_w0
[2023-02-24 08:09:03,275][795538] Heartbeat connected on RolloutWorker_w5
[2023-02-24 08:09:03,276][795538] Heartbeat connected on RolloutWorker_w4
[2023-02-24 08:09:03,280][795538] Heartbeat connected on RolloutWorker_w7
[2023-02-24 08:09:03,282][795538] Heartbeat connected on RolloutWorker_w6
[2023-02-24 08:09:04,840][796112] Updated weights for policy 0, policy_version 443 (0.0007)
[2023-02-24 08:09:07,160][795538] Fps is (10 sec: 15974.5, 60 sec: 10035.2, 300 sec: 10035.2). Total num frames: 1851392. Throughput: 0: 2569.2. Samples: 51384. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:09:07,161][795538] Avg episode reward: [(0, '18.568')]
[2023-02-24 08:09:07,343][796112] Updated weights for policy 0, policy_version 453 (0.0007)
[2023-02-24 08:09:09,849][796112] Updated weights for policy 0, policy_version 463 (0.0006)
[2023-02-24 08:09:12,160][795538] Fps is (10 sec: 16384.0, 60 sec: 11304.9, 300 sec: 11304.9). Total num frames: 1933312. Throughput: 0: 2543.8. Samples: 63594. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:09:12,161][795538] Avg episode reward: [(0, '20.173')]
[2023-02-24 08:09:12,344][796112] Updated weights for policy 0, policy_version 473 (0.0006)
[2023-02-24 08:09:14,882][796112] Updated weights for policy 0, policy_version 483 (0.0007)
[2023-02-24 08:09:17,160][795538] Fps is (10 sec: 16384.0, 60 sec: 12151.5, 300 sec: 12151.5). Total num frames: 2015232. Throughput: 0: 2934.7. Samples: 88042. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:09:17,161][795538] Avg episode reward: [(0, '21.495')]
[2023-02-24 08:09:17,162][796098] Saving new best policy, reward=21.495!
[2023-02-24 08:09:17,416][796112] Updated weights for policy 0, policy_version 493 (0.0009)
[2023-02-24 08:09:19,892][796112] Updated weights for policy 0, policy_version 503 (0.0006)
[2023-02-24 08:09:22,160][795538] Fps is (10 sec: 16384.0, 60 sec: 12756.1, 300 sec: 12756.1). Total num frames: 2097152. Throughput: 0: 3214.6. Samples: 112512. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 08:09:22,161][795538] Avg episode reward: [(0, '18.695')]
[2023-02-24 08:09:22,364][796112] Updated weights for policy 0, policy_version 513 (0.0010)
[2023-02-24 08:09:24,860][796112] Updated weights for policy 0, policy_version 523 (0.0007)
[2023-02-24 08:09:27,160][795538] Fps is (10 sec: 16384.1, 60 sec: 13209.6, 300 sec: 13209.6). Total num frames: 2179072. Throughput: 0: 3120.8. Samples: 124832. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 08:09:27,161][795538] Avg episode reward: [(0, '21.156')]
[2023-02-24 08:09:27,388][796112] Updated weights for policy 0, policy_version 533 (0.0006)
[2023-02-24 08:09:29,933][796112] Updated weights for policy 0, policy_version 543 (0.0011)
[2023-02-24 08:09:32,160][795538] Fps is (10 sec: 15974.5, 60 sec: 13471.3, 300 sec: 13471.3). Total num frames: 2256896. Throughput: 0: 3315.7. Samples: 149206. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:09:32,164][795538] Avg episode reward: [(0, '19.110')]
[2023-02-24 08:09:32,491][796112] Updated weights for policy 0, policy_version 553 (0.0008)
[2023-02-24 08:09:34,962][796112] Updated weights for policy 0, policy_version 563 (0.0006)
[2023-02-24 08:09:37,160][795538] Fps is (10 sec: 15974.4, 60 sec: 13762.6, 300 sec: 13762.6). Total num frames: 2338816. Throughput: 0: 3865.1. Samples: 173928. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:09:37,160][795538] Avg episode reward: [(0, '20.430')]
[2023-02-24 08:09:37,443][796112] Updated weights for policy 0, policy_version 573 (0.0006)
[2023-02-24 08:09:40,104][796112] Updated weights for policy 0, policy_version 583 (0.0007)
[2023-02-24 08:09:42,160][795538] Fps is (10 sec: 15974.4, 60 sec: 13926.4, 300 sec: 13926.4). Total num frames: 2416640. Throughput: 0: 4050.8. Samples: 185616. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:09:42,160][795538] Avg episode reward: [(0, '22.387')]
[2023-02-24 08:09:42,172][796098] Saving new best policy, reward=22.387!
[2023-02-24 08:09:42,735][796112] Updated weights for policy 0, policy_version 593 (0.0008)
[2023-02-24 08:09:45,371][796112] Updated weights for policy 0, policy_version 603 (0.0006)
[2023-02-24 08:09:47,160][795538] Fps is (10 sec: 15974.3, 60 sec: 14131.2, 300 sec: 14131.2). Total num frames: 2498560. Throughput: 0: 4036.7. Samples: 208926. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:09:47,162][795538] Avg episode reward: [(0, '23.294')]
[2023-02-24 08:09:47,163][796098] Saving new best policy, reward=23.294!
[2023-02-24 08:09:47,936][796112] Updated weights for policy 0, policy_version 613 (0.0009)
[2023-02-24 08:09:50,471][796112] Updated weights for policy 0, policy_version 623 (0.0006)
[2023-02-24 08:09:52,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15428.3, 300 sec: 14241.5). Total num frames: 2576384. Throughput: 0: 4030.0. Samples: 232734. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-24 08:09:52,161][795538] Avg episode reward: [(0, '23.526')]
[2023-02-24 08:09:52,164][796098] Saving new best policy, reward=23.526!
[2023-02-24 08:09:53,087][796112] Updated weights for policy 0, policy_version 633 (0.0006)
[2023-02-24 08:09:55,707][796112] Updated weights for policy 0, policy_version 643 (0.0007)
[2023-02-24 08:09:57,160][795538] Fps is (10 sec: 15564.8, 60 sec: 16042.7, 300 sec: 14336.0). Total num frames: 2654208. Throughput: 0: 4017.6. Samples: 244384. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:09:57,161][795538] Avg episode reward: [(0, '23.324')]
[2023-02-24 08:09:58,316][796112] Updated weights for policy 0, policy_version 653 (0.0008)
[2023-02-24 08:10:00,905][796112] Updated weights for policy 0, policy_version 663 (0.0006)
[2023-02-24 08:10:02,160][795538] Fps is (10 sec: 15564.8, 60 sec: 16042.7, 300 sec: 14417.9). Total num frames: 2732032. Throughput: 0: 4002.8. Samples: 268166. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:10:02,161][795538] Avg episode reward: [(0, '23.305')]
[2023-02-24 08:10:03,498][796112] Updated weights for policy 0, policy_version 673 (0.0006)
[2023-02-24 08:10:06,102][796112] Updated weights for policy 0, policy_version 683 (0.0006)
[2023-02-24 08:10:07,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15974.4, 300 sec: 14489.6). Total num frames: 2809856. Throughput: 0: 3723.8. Samples: 280082. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:10:07,162][795538] Avg episode reward: [(0, '24.939')]
[2023-02-24 08:10:07,168][796098] Saving new best policy, reward=24.939!
[2023-02-24 08:10:08,749][796112] Updated weights for policy 0, policy_version 693 (0.0006)
[2023-02-24 08:10:11,316][796112] Updated weights for policy 0, policy_version 703 (0.0007)
[2023-02-24 08:10:12,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15974.4, 300 sec: 14601.0). Total num frames: 2891776. Throughput: 0: 3972.7. Samples: 303606. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:10:12,161][795538] Avg episode reward: [(0, '27.390')]
[2023-02-24 08:10:12,165][796098] Saving new best policy, reward=27.390!
[2023-02-24 08:10:13,931][796112] Updated weights for policy 0, policy_version 713 (0.0006)
[2023-02-24 08:10:16,517][796112] Updated weights for policy 0, policy_version 723 (0.0007)
[2023-02-24 08:10:17,160][795538] Fps is (10 sec: 15974.5, 60 sec: 15906.1, 300 sec: 14654.6). Total num frames: 2969600. Throughput: 0: 3957.6. Samples: 327298. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:10:17,160][795538] Avg episode reward: [(0, '23.654')]
[2023-02-24 08:10:19,064][796112] Updated weights for policy 0, policy_version 733 (0.0006)
[2023-02-24 08:10:21,654][796112] Updated weights for policy 0, policy_version 743 (0.0007)
[2023-02-24 08:10:22,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15837.9, 300 sec: 14702.5). Total num frames: 3047424. Throughput: 0: 3672.8. Samples: 339206. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:10:22,161][795538] Avg episode reward: [(0, '23.892')]
[2023-02-24 08:10:24,239][796112] Updated weights for policy 0, policy_version 753 (0.0007)
[2023-02-24 08:10:26,790][796112] Updated weights for policy 0, policy_version 763 (0.0007)
[2023-02-24 08:10:27,160][795538] Fps is (10 sec: 15974.3, 60 sec: 15837.8, 300 sec: 14786.6). Total num frames: 3129344. Throughput: 0: 3942.0. Samples: 363004. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:10:27,161][795538] Avg episode reward: [(0, '24.204')]
[2023-02-24 08:10:29,329][796112] Updated weights for policy 0, policy_version 773 (0.0007)
[2023-02-24 08:10:31,939][796112] Updated weights for policy 0, policy_version 783 (0.0006)
[2023-02-24 08:10:32,160][795538] Fps is (10 sec: 15974.3, 60 sec: 15837.9, 300 sec: 14823.6). Total num frames: 3207168. Throughput: 0: 3952.3. Samples: 386780. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 08:10:32,161][795538] Avg episode reward: [(0, '26.121')]
[2023-02-24 08:10:34,527][796112] Updated weights for policy 0, policy_version 793 (0.0006)
[2023-02-24 08:10:37,160][796112] Updated weights for policy 0, policy_version 803 (0.0006)
[2023-02-24 08:10:37,160][795538] Fps is (10 sec: 15974.5, 60 sec: 15837.9, 300 sec: 14894.6). Total num frames: 3289088. Throughput: 0: 3950.8. Samples: 410518. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:10:37,161][795538] Avg episode reward: [(0, '24.946')]
[2023-02-24 08:10:39,753][796112] Updated weights for policy 0, policy_version 813 (0.0007)
[2023-02-24 08:10:42,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 14923.7). Total num frames: 3366912. Throughput: 0: 3957.0. Samples: 422448. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:10:42,160][795538] Avg episode reward: [(0, '24.684')]
[2023-02-24 08:10:42,164][796098] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000822_3366912.pth...
[2023-02-24 08:10:42,260][796098] Removing /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000268_1097728.pth
[2023-02-24 08:10:42,367][796112] Updated weights for policy 0, policy_version 823 (0.0006)
[2023-02-24 08:10:44,973][796112] Updated weights for policy 0, policy_version 833 (0.0006)
[2023-02-24 08:10:47,160][795538] Fps is (10 sec: 15564.7, 60 sec: 15769.6, 300 sec: 14950.4). Total num frames: 3444736. Throughput: 0: 3949.0. Samples: 445872. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:10:47,160][795538] Avg episode reward: [(0, '26.184')]
[2023-02-24 08:10:47,617][796112] Updated weights for policy 0, policy_version 843 (0.0006)
[2023-02-24 08:10:50,205][796112] Updated weights for policy 0, policy_version 853 (0.0007)
[2023-02-24 08:10:52,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15769.6, 300 sec: 14975.0). Total num frames: 3522560. Throughput: 0: 4210.3. Samples: 469546. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:10:52,161][795538] Avg episode reward: [(0, '26.862')]
[2023-02-24 08:10:52,756][796112] Updated weights for policy 0, policy_version 863 (0.0008)
[2023-02-24 08:10:55,295][796112] Updated weights for policy 0, policy_version 873 (0.0006)
[2023-02-24 08:10:57,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15029.2). Total num frames: 3604480. Throughput: 0: 3953.6. Samples: 481518. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-24 08:10:57,161][795538] Avg episode reward: [(0, '25.390')]
[2023-02-24 08:10:57,895][796112] Updated weights for policy 0, policy_version 883 (0.0007)
[2023-02-24 08:11:00,550][796112] Updated weights for policy 0, policy_version 893 (0.0009)
[2023-02-24 08:11:02,160][795538] Fps is (10 sec: 15974.2, 60 sec: 15837.8, 300 sec: 15049.0). Total num frames: 3682304. Throughput: 0: 3949.9. Samples: 505042. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:11:02,161][795538] Avg episode reward: [(0, '25.427')]
[2023-02-24 08:11:03,150][796112] Updated weights for policy 0, policy_version 903 (0.0008)
[2023-02-24 08:11:05,738][796112] Updated weights for policy 0, policy_version 913 (0.0008)
[2023-02-24 08:11:07,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15837.9, 300 sec: 15067.4). Total num frames: 3760128. Throughput: 0: 4217.3. Samples: 528986. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:11:07,161][795538] Avg episode reward: [(0, '25.526')]
[2023-02-24 08:11:08,213][796112] Updated weights for policy 0, policy_version 923 (0.0006)
[2023-02-24 08:11:10,734][796112] Updated weights for policy 0, policy_version 933 (0.0007)
[2023-02-24 08:11:12,160][795538] Fps is (10 sec: 15974.6, 60 sec: 15837.9, 300 sec: 15112.8). Total num frames: 3842048. Throughput: 0: 3965.5. Samples: 541452. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:11:12,160][795538] Avg episode reward: [(0, '26.175')]
[2023-02-24 08:11:13,377][796112] Updated weights for policy 0, policy_version 943 (0.0007)
[2023-02-24 08:11:15,931][796112] Updated weights for policy 0, policy_version 953 (0.0007)
[2023-02-24 08:11:17,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15127.9). Total num frames: 3919872. Throughput: 0: 3960.2. Samples: 564990. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:11:17,161][795538] Avg episode reward: [(0, '26.638')]
[2023-02-24 08:11:18,529][796112] Updated weights for policy 0, policy_version 963 (0.0008)
[2023-02-24 08:11:21,078][796112] Updated weights for policy 0, policy_version 973 (0.0007)
[2023-02-24 08:11:22,160][795538] Fps is (10 sec: 15974.3, 60 sec: 15906.1, 300 sec: 15168.4). Total num frames: 4001792. Throughput: 0: 3964.5. Samples: 588920. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:11:22,161][795538] Avg episode reward: [(0, '26.420')]
[2023-02-24 08:11:23,650][796112] Updated weights for policy 0, policy_version 983 (0.0006)
[2023-02-24 08:11:26,246][796112] Updated weights for policy 0, policy_version 993 (0.0006)
[2023-02-24 08:11:27,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15180.8). Total num frames: 4079616. Throughput: 0: 3963.6. Samples: 600810. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:11:27,161][795538] Avg episode reward: [(0, '23.763')]
[2023-02-24 08:11:28,856][796112] Updated weights for policy 0, policy_version 1003 (0.0006)
[2023-02-24 08:11:31,443][796112] Updated weights for policy 0, policy_version 1013 (0.0006)
[2023-02-24 08:11:32,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15837.9, 300 sec: 15192.4). Total num frames: 4157440. Throughput: 0: 3970.3. Samples: 624536. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:11:32,161][795538] Avg episode reward: [(0, '29.275')]
[2023-02-24 08:11:32,165][796098] Saving new best policy, reward=29.275!
[2023-02-24 08:11:34,059][796112] Updated weights for policy 0, policy_version 1023 (0.0007)
[2023-02-24 08:11:36,631][796112] Updated weights for policy 0, policy_version 1033 (0.0006)
[2023-02-24 08:11:37,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15227.5). Total num frames: 4239360. Throughput: 0: 3966.3. Samples: 648028. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
[2023-02-24 08:11:37,161][795538] Avg episode reward: [(0, '30.081')]
[2023-02-24 08:11:37,162][796098] Saving new best policy, reward=30.081!
[2023-02-24 08:11:39,264][796112] Updated weights for policy 0, policy_version 1043 (0.0006)
[2023-02-24 08:11:41,882][796112] Updated weights for policy 0, policy_version 1053 (0.0008)
[2023-02-24 08:11:42,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15237.1). Total num frames: 4317184. Throughput: 0: 3961.7. Samples: 659794. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:11:42,162][795538] Avg episode reward: [(0, '28.237')]
[2023-02-24 08:11:44,465][796112] Updated weights for policy 0, policy_version 1063 (0.0007)
[2023-02-24 08:11:47,078][796112] Updated weights for policy 0, policy_version 1073 (0.0007)
[2023-02-24 08:11:47,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15837.9, 300 sec: 15246.2). Total num frames: 4395008. Throughput: 0: 3964.2. Samples: 683430. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:11:47,160][795538] Avg episode reward: [(0, '27.334')]
[2023-02-24 08:11:49,667][796112] Updated weights for policy 0, policy_version 1083 (0.0007)
[2023-02-24 08:11:52,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15837.9, 300 sec: 15254.8). Total num frames: 4472832. Throughput: 0: 3957.7. Samples: 707084. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:11:52,161][795538] Avg episode reward: [(0, '27.060')]
[2023-02-24 08:11:52,282][796112] Updated weights for policy 0, policy_version 1093 (0.0006)
[2023-02-24 08:11:54,877][796112] Updated weights for policy 0, policy_version 1103 (0.0006)
[2023-02-24 08:11:57,160][795538] Fps is (10 sec: 15564.7, 60 sec: 15769.6, 300 sec: 15263.0). Total num frames: 4550656. Throughput: 0: 3941.8. Samples: 718832. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:11:57,161][795538] Avg episode reward: [(0, '26.759')]
[2023-02-24 08:11:57,461][796112] Updated weights for policy 0, policy_version 1113 (0.0006)
[2023-02-24 08:12:00,051][796112] Updated weights for policy 0, policy_version 1123 (0.0006)
[2023-02-24 08:12:02,160][795538] Fps is (10 sec: 15974.5, 60 sec: 15837.9, 300 sec: 15291.7). Total num frames: 4632576. Throughput: 0: 3946.0. Samples: 742562. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:12:02,161][795538] Avg episode reward: [(0, '31.137')]
[2023-02-24 08:12:02,164][796098] Saving new best policy, reward=31.137!
[2023-02-24 08:12:02,698][796112] Updated weights for policy 0, policy_version 1133 (0.0008)
[2023-02-24 08:12:05,265][796112] Updated weights for policy 0, policy_version 1143 (0.0007)
[2023-02-24 08:12:07,160][795538] Fps is (10 sec: 15974.4, 60 sec: 15837.9, 300 sec: 15298.6). Total num frames: 4710400. Throughput: 0: 3936.4. Samples: 766056. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:12:07,161][795538] Avg episode reward: [(0, '29.446')]
[2023-02-24 08:12:07,854][796112] Updated weights for policy 0, policy_version 1153 (0.0009)
[2023-02-24 08:12:10,527][796112] Updated weights for policy 0, policy_version 1163 (0.0008)
[2023-02-24 08:12:12,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15769.6, 300 sec: 15305.1). Total num frames: 4788224. Throughput: 0: 3933.4. Samples: 777814. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:12:12,161][795538] Avg episode reward: [(0, '25.534')]
[2023-02-24 08:12:13,157][796112] Updated weights for policy 0, policy_version 1173 (0.0008)
[2023-02-24 08:12:15,767][796112] Updated weights for policy 0, policy_version 1183 (0.0007)
[2023-02-24 08:12:17,160][795538] Fps is (10 sec: 15564.5, 60 sec: 15769.6, 300 sec: 15311.2). Total num frames: 4866048. Throughput: 0: 3927.5. Samples: 801272. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:12:17,161][795538] Avg episode reward: [(0, '28.476')]
[2023-02-24 08:12:18,390][796112] Updated weights for policy 0, policy_version 1193 (0.0006)
[2023-02-24 08:12:21,010][796112] Updated weights for policy 0, policy_version 1203 (0.0008)
[2023-02-24 08:12:22,161][795538] Fps is (10 sec: 15563.3, 60 sec: 15701.1, 300 sec: 15317.1). Total num frames: 4943872. Throughput: 0: 3926.3. Samples: 824714. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:12:22,162][795538] Avg episode reward: [(0, '29.026')]
[2023-02-24 08:12:23,640][796112] Updated weights for policy 0, policy_version 1213 (0.0007)
[2023-02-24 08:12:26,277][796112] Updated weights for policy 0, policy_version 1223 (0.0006)
[2023-02-24 08:12:27,160][795538] Fps is (10 sec: 15565.1, 60 sec: 15701.3, 300 sec: 15322.8). Total num frames: 5021696. Throughput: 0: 3925.6. Samples: 836444. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:12:27,161][795538] Avg episode reward: [(0, '28.968')]
[2023-02-24 08:12:28,839][796112] Updated weights for policy 0, policy_version 1233 (0.0008)
[2023-02-24 08:12:31,424][796112] Updated weights for policy 0, policy_version 1243 (0.0009)
[2023-02-24 08:12:32,160][795538] Fps is (10 sec: 15566.2, 60 sec: 15701.3, 300 sec: 15328.1). Total num frames: 5099520. Throughput: 0: 3926.8. Samples: 860134. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:12:32,161][795538] Avg episode reward: [(0, '30.627')]
[2023-02-24 08:12:34,002][796112] Updated weights for policy 0, policy_version 1253 (0.0006)
[2023-02-24 08:12:36,598][796112] Updated weights for policy 0, policy_version 1263 (0.0007)
[2023-02-24 08:12:37,160][795538] Fps is (10 sec: 15974.5, 60 sec: 15701.3, 300 sec: 15351.1). Total num frames: 5181440. Throughput: 0: 3927.4. Samples: 883818. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
[2023-02-24 08:12:37,160][795538] Avg episode reward: [(0, '30.119')]
[2023-02-24 08:12:39,183][796112] Updated weights for policy 0, policy_version 1273 (0.0006)
[2023-02-24 08:12:41,827][796112] Updated weights for policy 0, policy_version 1283 (0.0006)
[2023-02-24 08:12:42,160][795538] Fps is (10 sec: 15974.3, 60 sec: 15701.3, 300 sec: 15355.6). Total num frames: 5259264. Throughput: 0: 3932.7. Samples: 895804. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:12:42,161][795538] Avg episode reward: [(0, '28.016')]
[2023-02-24 08:12:42,165][796098] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001284_5259264.pth...
[2023-02-24 08:12:42,261][796098] Removing /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000403_1650688.pth
[2023-02-24 08:12:44,477][796112] Updated weights for policy 0, policy_version 1293 (0.0006)
[2023-02-24 08:12:47,112][796112] Updated weights for policy 0, policy_version 1303 (0.0007)
[2023-02-24 08:12:47,160][795538] Fps is (10 sec: 15564.7, 60 sec: 15701.3, 300 sec: 15360.0). Total num frames: 5337088. Throughput: 0: 3918.7. Samples: 918904. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
[2023-02-24 08:12:47,161][795538] Avg episode reward: [(0, '29.296')]
[2023-02-24 08:12:49,686][796112] Updated weights for policy 0, policy_version 1313 (0.0006)
[2023-02-24 08:12:52,160][795538] Fps is (10 sec: 15564.8, 60 sec: 15701.3, 300 sec: 15364.2). Total num frames: 5414912. Throughput: 0: 3658.7. Samples: 930696. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 08:12:52,161][795538] Avg episode reward: [(0, '29.969')]
[2023-02-24 08:12:52,236][796112] Updated weights for policy 0, policy_version 1323 (0.0007)
[2023-02-24 08:12:54,849][796112] Updated weights for policy 0, policy_version 1333 (0.0006)
[2023-02-24 08:12:57,160][795538] Fps is (10 sec: 15564.9, 60 sec: 15701.3, 300 sec: 15368.2). Total num frames: 5492736. Throughput: 0: 3924.4. Samples: 954414. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 08:12:57,160][795538] Avg episode reward: [(0, '26.997')]
[2023-02-24 08:12:57,451][796112] Updated weights for policy 0, policy_version 1343 (0.0007)
[2023-02-24 08:13:00,062][796112] Updated weights for policy 0, policy_version 1353 (0.0007)
[2023-02-24 08:13:02,127][795538] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 795538], exiting...
[2023-02-24 08:13:02,128][796098] Stopping Batcher_0...
[2023-02-24 08:13:02,129][796098] Loop batcher_evt_loop terminating...
[2023-02-24 08:13:02,130][796098] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001361_5574656.pth...
[2023-02-24 08:13:02,130][795538] Runner profile tree view:
main_loop: 258.8521
[2023-02-24 08:13:02,130][795538] Collected {0: 5574656}, FPS: 15159.1
[2023-02-24 08:13:02,136][796113] Stopping RolloutWorker_w2...
[2023-02-24 08:13:02,137][796113] Loop rollout_proc2_evt_loop terminating...
[2023-02-24 08:13:02,139][796118] Stopping RolloutWorker_w4...
[2023-02-24 08:13:02,139][796118] Loop rollout_proc4_evt_loop terminating...
[2023-02-24 08:13:02,139][796117] Stopping RolloutWorker_w5...
[2023-02-24 08:13:02,140][796117] Loop rollout_proc5_evt_loop terminating...
[2023-02-24 08:13:02,142][796115] Stopping RolloutWorker_w3...
[2023-02-24 08:13:02,143][796115] Loop rollout_proc3_evt_loop terminating...
[2023-02-24 08:13:02,143][796111] Stopping RolloutWorker_w0...
[2023-02-24 08:13:02,144][796119] Stopping RolloutWorker_w6...
[2023-02-24 08:13:02,144][796111] Loop rollout_proc0_evt_loop terminating...
[2023-02-24 08:13:02,144][796119] Loop rollout_proc6_evt_loop terminating...
[2023-02-24 08:13:02,148][796114] Stopping RolloutWorker_w1...
[2023-02-24 08:13:02,148][796114] Loop rollout_proc1_evt_loop terminating...
[2023-02-24 08:13:02,151][796116] Stopping RolloutWorker_w7...
[2023-02-24 08:13:02,152][796116] Loop rollout_proc7_evt_loop terminating...
[2023-02-24 08:13:02,163][796112] Weights refcount: 2 0
[2023-02-24 08:13:02,171][796112] Stopping InferenceWorker_p0-w0...
[2023-02-24 08:13:02,172][796112] Loop inference_proc0-0_evt_loop terminating...
[2023-02-24 08:13:02,301][796098] Removing /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000822_3366912.pth
[2023-02-24 08:13:02,305][796098] Stopping LearnerWorker_p0...
[2023-02-24 08:13:02,314][796098] Loop learner_proc0_evt_loop terminating...
[2023-02-24 08:13:11,768][795538] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
[2023-02-24 08:13:11,769][795538] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-24 08:13:11,770][795538] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-24 08:13:11,770][795538] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-24 08:13:11,770][795538] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 08:13:11,771][795538] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-24 08:13:11,771][795538] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2023-02-24 08:13:11,772][795538] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-24 08:13:11,772][795538] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-24 08:13:11,773][795538] Adding new argument 'hf_repository'='chqmatteo/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-24 08:13:11,773][795538] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-24 08:13:11,773][795538] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-24 08:13:11,774][795538] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-24 08:13:11,774][795538] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-24 08:13:11,775][795538] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-24 08:13:11,779][795538] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 08:13:11,780][795538] RunningMeanStd input shape: (1,)
[2023-02-24 08:13:11,787][795538] ConvEncoder: input_channels=3
[2023-02-24 08:13:11,812][795538] Conv encoder output size: 512
[2023-02-24 08:13:11,813][795538] Policy head output size: 512
[2023-02-24 08:13:11,845][795538] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001361_5574656.pth...
[2023-02-24 08:13:12,294][795538] Num frames 100...
[2023-02-24 08:13:12,360][795538] Num frames 200...
[2023-02-24 08:13:12,438][795538] Num frames 300...
[2023-02-24 08:13:12,502][795538] Num frames 400...
[2023-02-24 08:13:12,568][795538] Num frames 500...
[2023-02-24 08:13:12,635][795538] Num frames 600...
[2023-02-24 08:13:12,701][795538] Num frames 700...
[2023-02-24 08:13:12,763][795538] Num frames 800...
[2023-02-24 08:13:12,833][795538] Num frames 900...
[2023-02-24 08:13:12,896][795538] Num frames 1000...
[2023-02-24 08:13:12,971][795538] Num frames 1100...
[2023-02-24 08:13:13,037][795538] Num frames 1200...
[2023-02-24 08:13:13,102][795538] Avg episode rewards: #0: 29.160, true rewards: #0: 12.160
[2023-02-24 08:13:13,102][795538] Avg episode reward: 29.160, avg true_objective: 12.160
[2023-02-24 08:13:13,165][795538] Num frames 1300...
[2023-02-24 08:13:13,228][795538] Num frames 1400...
[2023-02-24 08:13:13,291][795538] Num frames 1500...
[2023-02-24 08:13:13,362][795538] Num frames 1600...
[2023-02-24 08:13:13,429][795538] Num frames 1700...
[2023-02-24 08:13:13,494][795538] Num frames 1800...
[2023-02-24 08:13:13,563][795538] Num frames 1900...
[2023-02-24 08:13:13,627][795538] Num frames 2000...
[2023-02-24 08:13:13,697][795538] Num frames 2100...
[2023-02-24 08:13:13,770][795538] Num frames 2200...
[2023-02-24 08:13:13,838][795538] Num frames 2300...
[2023-02-24 08:13:13,919][795538] Num frames 2400...
[2023-02-24 08:13:13,989][795538] Num frames 2500...
[2023-02-24 08:13:14,053][795538] Num frames 2600...
[2023-02-24 08:13:14,132][795538] Num frames 2700...
[2023-02-24 08:13:14,205][795538] Num frames 2800...
[2023-02-24 08:13:14,265][795538] Avg episode rewards: #0: 35.535, true rewards: #0: 14.035
[2023-02-24 08:13:14,266][795538] Avg episode reward: 35.535, avg true_objective: 14.035
[2023-02-24 08:13:14,332][795538] Num frames 2900...
[2023-02-24 08:13:14,399][795538] Num frames 3000...
[2023-02-24 08:13:14,464][795538] Num frames 3100...
[2023-02-24 08:13:14,537][795538] Num frames 3200...
[2023-02-24 08:13:14,627][795538] Num frames 3300...
[2023-02-24 08:13:14,696][795538] Num frames 3400...
[2023-02-24 08:13:14,807][795538] Avg episode rewards: #0: 28.950, true rewards: #0: 11.617
[2023-02-24 08:13:14,808][795538] Avg episode reward: 28.950, avg true_objective: 11.617
[2023-02-24 08:13:14,818][795538] Num frames 3500...
[2023-02-24 08:13:14,882][795538] Num frames 3600...
[2023-02-24 08:13:14,943][795538] Num frames 3700...
[2023-02-24 08:13:15,002][795538] Num frames 3800...
[2023-02-24 08:13:15,069][795538] Num frames 3900...
[2023-02-24 08:13:15,133][795538] Num frames 4000...
[2023-02-24 08:13:15,196][795538] Num frames 4100...
[2023-02-24 08:13:15,259][795538] Num frames 4200...
[2023-02-24 08:13:15,327][795538] Num frames 4300...
[2023-02-24 08:13:15,403][795538] Num frames 4400...
[2023-02-24 08:13:15,470][795538] Num frames 4500...
[2023-02-24 08:13:15,534][795538] Num frames 4600...
[2023-02-24 08:13:15,596][795538] Num frames 4700...
[2023-02-24 08:13:15,660][795538] Num frames 4800...
[2023-02-24 08:13:15,736][795538] Num frames 4900...
[2023-02-24 08:13:15,804][795538] Num frames 5000...
[2023-02-24 08:13:15,870][795538] Num frames 5100...
[2023-02-24 08:13:15,944][795538] Num frames 5200...
[2023-02-24 08:13:16,023][795538] Num frames 5300...
[2023-02-24 08:13:16,098][795538] Num frames 5400...
[2023-02-24 08:13:16,186][795538] Num frames 5500...
[2023-02-24 08:13:16,306][795538] Avg episode rewards: #0: 35.962, true rewards: #0: 13.962
[2023-02-24 08:13:16,307][795538] Avg episode reward: 35.962, avg true_objective: 13.962
[2023-02-24 08:13:16,320][795538] Num frames 5600...
[2023-02-24 08:13:16,393][795538] Num frames 5700...
[2023-02-24 08:13:16,460][795538] Num frames 5800...
[2023-02-24 08:13:16,524][795538] Num frames 5900...
[2023-02-24 08:13:16,601][795538] Avg episode rewards: #0: 30.080, true rewards: #0: 11.880
[2023-02-24 08:13:16,602][795538] Avg episode reward: 30.080, avg true_objective: 11.880
[2023-02-24 08:13:16,640][795538] Num frames 6000...
[2023-02-24 08:13:16,708][795538] Num frames 6100...
[2023-02-24 08:13:16,794][795538] Num frames 6200...
[2023-02-24 08:13:16,854][795538] Num frames 6300...
[2023-02-24 08:13:16,920][795538] Num frames 6400...
[2023-02-24 08:13:16,995][795538] Num frames 6500...
[2023-02-24 08:13:17,060][795538] Num frames 6600...
[2023-02-24 08:13:17,136][795538] Num frames 6700...
[2023-02-24 08:13:17,202][795538] Num frames 6800...
[2023-02-24 08:13:17,265][795538] Num frames 6900...
[2023-02-24 08:13:17,334][795538] Num frames 7000...
[2023-02-24 08:13:17,402][795538] Num frames 7100...
[2023-02-24 08:13:17,467][795538] Num frames 7200...
[2023-02-24 08:13:17,541][795538] Num frames 7300...
[2023-02-24 08:13:17,614][795538] Num frames 7400...
[2023-02-24 08:13:17,693][795538] Num frames 7500...
[2023-02-24 08:13:17,761][795538] Num frames 7600...
[2023-02-24 08:13:17,852][795538] Avg episode rewards: #0: 32.753, true rewards: #0: 12.753
[2023-02-24 08:13:17,853][795538] Avg episode reward: 32.753, avg true_objective: 12.753
[2023-02-24 08:13:17,891][795538] Num frames 7700...
[2023-02-24 08:13:17,954][795538] Num frames 7800...
[2023-02-24 08:13:18,026][795538] Num frames 7900...
[2023-02-24 08:13:18,113][795538] Num frames 8000...
[2023-02-24 08:13:18,178][795538] Num frames 8100...
[2023-02-24 08:13:18,244][795538] Num frames 8200...
[2023-02-24 08:13:18,314][795538] Num frames 8300...
[2023-02-24 08:13:18,380][795538] Num frames 8400...
[2023-02-24 08:13:18,452][795538] Num frames 8500...
[2023-02-24 08:13:18,528][795538] Num frames 8600...
[2023-02-24 08:13:18,601][795538] Num frames 8700...
[2023-02-24 08:13:18,664][795538] Num frames 8800...
[2023-02-24 08:13:18,732][795538] Num frames 8900...
[2023-02-24 08:13:18,799][795538] Num frames 9000...
[2023-02-24 08:13:18,876][795538] Num frames 9100...
[2023-02-24 08:13:18,945][795538] Num frames 9200...
[2023-02-24 08:13:19,017][795538] Num frames 9300...
[2023-02-24 08:13:19,083][795538] Num frames 9400...
[2023-02-24 08:13:19,162][795538] Num frames 9500...
[2023-02-24 08:13:19,240][795538] Num frames 9600...
[2023-02-24 08:13:19,308][795538] Num frames 9700...
[2023-02-24 08:13:19,398][795538] Avg episode rewards: #0: 36.788, true rewards: #0: 13.931
[2023-02-24 08:13:19,398][795538] Avg episode reward: 36.788, avg true_objective: 13.931
[2023-02-24 08:13:19,431][795538] Num frames 9800...
[2023-02-24 08:13:19,505][795538] Num frames 9900...
[2023-02-24 08:13:19,570][795538] Num frames 10000...
[2023-02-24 08:13:19,642][795538] Num frames 10100...
[2023-02-24 08:13:19,704][795538] Num frames 10200...
[2023-02-24 08:13:19,778][795538] Avg episode rewards: #0: 33.665, true rewards: #0: 12.790
[2023-02-24 08:13:19,779][795538] Avg episode reward: 33.665, avg true_objective: 12.790
[2023-02-24 08:13:19,831][795538] Num frames 10300...
[2023-02-24 08:13:19,906][795538] Num frames 10400...
[2023-02-24 08:13:20,011][795538] Num frames 10500...
[2023-02-24 08:13:20,081][795538] Num frames 10600...
[2023-02-24 08:13:20,144][795538] Num frames 10700...
[2023-02-24 08:13:20,220][795538] Num frames 10800...
[2023-02-24 08:13:20,322][795538] Avg episode rewards: #0: 31.302, true rewards: #0: 12.080
[2023-02-24 08:13:20,322][795538] Avg episode reward: 31.302, avg true_objective: 12.080
[2023-02-24 08:13:20,348][795538] Num frames 10900...
[2023-02-24 08:13:20,415][795538] Num frames 11000...
[2023-02-24 08:13:20,477][795538] Num frames 11100...
[2023-02-24 08:13:20,537][795538] Num frames 11200...
[2023-02-24 08:13:20,596][795538] Num frames 11300...
[2023-02-24 08:13:20,656][795538] Num frames 11400...
[2023-02-24 08:13:20,717][795538] Num frames 11500...
[2023-02-24 08:13:20,774][795538] Num frames 11600...
[2023-02-24 08:13:20,836][795538] Num frames 11700...
[2023-02-24 08:13:20,897][795538] Num frames 11800...
[2023-02-24 08:13:20,958][795538] Num frames 11900...
[2023-02-24 08:13:21,028][795538] Num frames 12000...
[2023-02-24 08:13:21,097][795538] Num frames 12100...
[2023-02-24 08:13:21,160][795538] Num frames 12200...
[2023-02-24 08:13:21,224][795538] Num frames 12300...
[2023-02-24 08:13:21,292][795538] Num frames 12400...
[2023-02-24 08:13:21,394][795538] Avg episode rewards: #0: 32.272, true rewards: #0: 12.472
[2023-02-24 08:13:21,395][795538] Avg episode reward: 32.272, avg true_objective: 12.472
[2023-02-24 08:13:27,245][795538] Replay video saved to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!