Hugging Face's logo

usamabuttar
/
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: 131,279 Bytes 
88a2333
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2637f1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
[2024-11-11 14:13:20,505][00562] Saving configuration to /content/train_dir/default_experiment/config.json...
[2024-11-11 14:13:20,509][00562] Rollout worker 0 uses device cpu
[2024-11-11 14:13:20,510][00562] Rollout worker 1 uses device cpu
[2024-11-11 14:13:20,511][00562] Rollout worker 2 uses device cpu
[2024-11-11 14:13:20,512][00562] Rollout worker 3 uses device cpu
[2024-11-11 14:13:20,513][00562] Rollout worker 4 uses device cpu
[2024-11-11 14:13:20,514][00562] Rollout worker 5 uses device cpu
[2024-11-11 14:13:20,515][00562] Rollout worker 6 uses device cpu
[2024-11-11 14:13:20,516][00562] Rollout worker 7 uses device cpu
[2024-11-11 14:13:20,669][00562] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-11-11 14:13:20,670][00562] InferenceWorker_p0-w0: min num requests: 2
[2024-11-11 14:13:20,702][00562] Starting all processes...
[2024-11-11 14:13:20,703][00562] Starting process learner_proc0
[2024-11-11 14:13:20,748][00562] Starting all processes...
[2024-11-11 14:13:20,754][00562] Starting process inference_proc0-0
[2024-11-11 14:13:20,755][00562] Starting process rollout_proc0
[2024-11-11 14:13:20,757][00562] Starting process rollout_proc1
[2024-11-11 14:13:20,757][00562] Starting process rollout_proc2
[2024-11-11 14:13:20,757][00562] Starting process rollout_proc3
[2024-11-11 14:13:20,757][00562] Starting process rollout_proc4
[2024-11-11 14:13:20,757][00562] Starting process rollout_proc5
[2024-11-11 14:13:20,757][00562] Starting process rollout_proc6
[2024-11-11 14:13:20,757][00562] Starting process rollout_proc7
[2024-11-11 14:13:38,740][03143] Worker 7 uses CPU cores [1]
[2024-11-11 14:13:38,851][03135] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-11-11 14:13:38,858][03135] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2024-11-11 14:13:38,892][03141] Worker 5 uses CPU cores [1]
[2024-11-11 14:13:38,946][03137] Worker 1 uses CPU cores [1]
[2024-11-11 14:13:38,955][03135] Num visible devices: 1
[2024-11-11 14:13:39,090][03142] Worker 6 uses CPU cores [0]
[2024-11-11 14:13:39,192][03138] Worker 2 uses CPU cores [0]
[2024-11-11 14:13:39,308][03122] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-11-11 14:13:39,309][03122] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2024-11-11 14:13:39,334][03122] Num visible devices: 1
[2024-11-11 14:13:39,359][03122] Starting seed is not provided
[2024-11-11 14:13:39,360][03122] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-11-11 14:13:39,360][03122] Initializing actor-critic model on device cuda:0
[2024-11-11 14:13:39,361][03122] RunningMeanStd input shape: (3, 72, 128)
[2024-11-11 14:13:39,364][03122] RunningMeanStd input shape: (1,)
[2024-11-11 14:13:39,401][03139] Worker 3 uses CPU cores [1]
[2024-11-11 14:13:39,400][03122] ConvEncoder: input_channels=3
[2024-11-11 14:13:39,420][03136] Worker 0 uses CPU cores [0]
[2024-11-11 14:13:39,425][03140] Worker 4 uses CPU cores [0]
[2024-11-11 14:13:40,071][03122] Conv encoder output size: 512
[2024-11-11 14:13:40,071][03122] Policy head output size: 512
[2024-11-11 14:13:40,151][03122] Created Actor Critic model with architecture:
[2024-11-11 14:13:40,152][03122] 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)
  )
)
[2024-11-11 14:13:40,593][03122] Using optimizer <class 'torch.optim.adam.Adam'>
[2024-11-11 14:13:40,671][00562] Heartbeat connected on InferenceWorker_p0-w0
[2024-11-11 14:13:40,677][00562] Heartbeat connected on RolloutWorker_w0
[2024-11-11 14:13:40,687][00562] Heartbeat connected on RolloutWorker_w1
[2024-11-11 14:13:40,693][00562] Heartbeat connected on RolloutWorker_w2
[2024-11-11 14:13:40,694][00562] Heartbeat connected on RolloutWorker_w3
[2024-11-11 14:13:40,699][00562] Heartbeat connected on RolloutWorker_w4
[2024-11-11 14:13:40,700][00562] Heartbeat connected on RolloutWorker_w5
[2024-11-11 14:13:40,701][00562] Heartbeat connected on RolloutWorker_w6
[2024-11-11 14:13:40,706][00562] Heartbeat connected on RolloutWorker_w7
[2024-11-11 14:13:40,741][00562] Heartbeat connected on Batcher_0
[2024-11-11 14:13:45,455][03122] No checkpoints found
[2024-11-11 14:13:45,456][03122] Did not load from checkpoint, starting from scratch!
[2024-11-11 14:13:45,457][03122] Initialized policy 0 weights for model version 0
[2024-11-11 14:13:45,464][03122] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-11-11 14:13:45,477][03122] LearnerWorker_p0 finished initialization!
[2024-11-11 14:13:45,477][00562] Heartbeat connected on LearnerWorker_p0
[2024-11-11 14:13:45,558][03135] RunningMeanStd input shape: (3, 72, 128)
[2024-11-11 14:13:45,560][03135] RunningMeanStd input shape: (1,)
[2024-11-11 14:13:45,571][03135] ConvEncoder: input_channels=3
[2024-11-11 14:13:45,674][03135] Conv encoder output size: 512
[2024-11-11 14:13:45,675][03135] Policy head output size: 512
[2024-11-11 14:13:45,728][00562] Inference worker 0-0 is ready!
[2024-11-11 14:13:45,729][00562] All inference workers are ready! Signal rollout workers to start!
[2024-11-11 14:13:45,932][03143] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:13:45,933][03139] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:13:45,929][03136] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:13:45,936][03137] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:13:45,934][03138] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:13:45,936][03141] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:13:45,933][03140] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:13:45,935][03142] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:13:46,615][03143] Decorrelating experience for 0 frames...
[2024-11-11 14:13:47,230][03136] Decorrelating experience for 0 frames...
[2024-11-11 14:13:47,233][03142] Decorrelating experience for 0 frames...
[2024-11-11 14:13:47,238][03140] Decorrelating experience for 0 frames...
[2024-11-11 14:13:47,235][03138] Decorrelating experience for 0 frames...
[2024-11-11 14:13:48,364][03136] Decorrelating experience for 32 frames...
[2024-11-11 14:13:48,380][03138] Decorrelating experience for 32 frames...
[2024-11-11 14:13:48,385][03140] Decorrelating experience for 32 frames...
[2024-11-11 14:13:48,436][03139] Decorrelating experience for 0 frames...
[2024-11-11 14:13:48,441][03137] Decorrelating experience for 0 frames...
[2024-11-11 14:13:48,444][03141] Decorrelating experience for 0 frames...
[2024-11-11 14:13:49,388][03142] Decorrelating experience for 32 frames...
[2024-11-11 14:13:49,536][00562] 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)
[2024-11-11 14:13:49,634][03136] Decorrelating experience for 64 frames...
[2024-11-11 14:13:50,015][03139] Decorrelating experience for 32 frames...
[2024-11-11 14:13:50,010][03137] Decorrelating experience for 32 frames...
[2024-11-11 14:13:50,012][03141] Decorrelating experience for 32 frames...
[2024-11-11 14:13:50,018][03143] Decorrelating experience for 32 frames...
[2024-11-11 14:13:50,794][03138] Decorrelating experience for 64 frames...
[2024-11-11 14:13:50,831][03136] Decorrelating experience for 96 frames...
[2024-11-11 14:13:50,911][03139] Decorrelating experience for 64 frames...
[2024-11-11 14:13:51,535][03142] Decorrelating experience for 64 frames...
[2024-11-11 14:13:51,539][03140] Decorrelating experience for 64 frames...
[2024-11-11 14:13:52,033][03143] Decorrelating experience for 64 frames...
[2024-11-11 14:13:52,175][03139] Decorrelating experience for 96 frames...
[2024-11-11 14:13:52,407][03138] Decorrelating experience for 96 frames...
[2024-11-11 14:13:52,976][03140] Decorrelating experience for 96 frames...
[2024-11-11 14:13:53,081][03137] Decorrelating experience for 64 frames...
[2024-11-11 14:13:53,881][03141] Decorrelating experience for 64 frames...
[2024-11-11 14:13:54,126][03143] Decorrelating experience for 96 frames...
[2024-11-11 14:13:54,496][03142] Decorrelating experience for 96 frames...
[2024-11-11 14:13:54,536][00562] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 3.2. Samples: 16. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-11-11 14:13:54,538][00562] Avg episode reward: [(0, '1.240')]
[2024-11-11 14:13:56,816][03137] Decorrelating experience for 96 frames...
[2024-11-11 14:13:58,646][03141] Decorrelating experience for 96 frames...
[2024-11-11 14:13:59,536][00562] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 195.2. Samples: 1952. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-11-11 14:13:59,539][00562] Avg episode reward: [(0, '2.538')]
[2024-11-11 14:14:00,594][03122] Signal inference workers to stop experience collection...
[2024-11-11 14:14:00,626][03135] InferenceWorker_p0-w0: stopping experience collection
[2024-11-11 14:14:02,988][03122] Signal inference workers to resume experience collection...
[2024-11-11 14:14:02,990][03135] InferenceWorker_p0-w0: resuming experience collection
[2024-11-11 14:14:04,536][00562] Fps is (10 sec: 1228.8, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 12288. Throughput: 0: 224.7. Samples: 3370. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2024-11-11 14:14:04,541][00562] Avg episode reward: [(0, '2.654')]
[2024-11-11 14:14:09,536][00562] Fps is (10 sec: 3276.8, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 32768. Throughput: 0: 330.9. Samples: 6618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:14:09,540][00562] Avg episode reward: [(0, '3.712')]
[2024-11-11 14:14:10,740][03135] Updated weights for policy 0, policy_version 10 (0.0158)
[2024-11-11 14:14:14,539][00562] Fps is (10 sec: 3685.4, 60 sec: 1965.9, 300 sec: 1965.9). Total num frames: 49152. Throughput: 0: 479.4. Samples: 11986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:14:14,541][00562] Avg episode reward: [(0, '4.213')]
[2024-11-11 14:14:19,536][00562] Fps is (10 sec: 2867.2, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 61440. Throughput: 0: 522.7. Samples: 15682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:14:19,540][00562] Avg episode reward: [(0, '4.425')]
[2024-11-11 14:14:23,894][03135] Updated weights for policy 0, policy_version 20 (0.0033)
[2024-11-11 14:14:24,536][00562] Fps is (10 sec: 3277.7, 60 sec: 2340.6, 300 sec: 2340.6). Total num frames: 81920. Throughput: 0: 536.7. Samples: 18784. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:14:24,542][00562] Avg episode reward: [(0, '4.474')]
[2024-11-11 14:14:29,537][00562] Fps is (10 sec: 4095.4, 60 sec: 2559.9, 300 sec: 2559.9). Total num frames: 102400. Throughput: 0: 631.5. Samples: 25262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:14:29,543][00562] Avg episode reward: [(0, '4.385')]
[2024-11-11 14:14:29,546][03122] Saving new best policy, reward=4.385!
[2024-11-11 14:14:34,540][00562] Fps is (10 sec: 3275.4, 60 sec: 2548.4, 300 sec: 2548.4). Total num frames: 114688. Throughput: 0: 649.9. Samples: 29246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:14:34,543][00562] Avg episode reward: [(0, '4.387')]
[2024-11-11 14:14:34,555][03122] Saving new best policy, reward=4.387!
[2024-11-11 14:14:36,570][03135] Updated weights for policy 0, policy_version 30 (0.0035)
[2024-11-11 14:14:39,536][00562] Fps is (10 sec: 2867.6, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 131072. Throughput: 0: 700.9. Samples: 31556. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:14:39,541][00562] Avg episode reward: [(0, '4.332')]
[2024-11-11 14:14:44,536][00562] Fps is (10 sec: 4097.7, 60 sec: 2830.0, 300 sec: 2830.0). Total num frames: 155648. Throughput: 0: 794.4. Samples: 37702. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:14:44,539][00562] Avg episode reward: [(0, '4.309')]
[2024-11-11 14:14:46,762][03135] Updated weights for policy 0, policy_version 40 (0.0032)
[2024-11-11 14:14:49,536][00562] Fps is (10 sec: 3686.4, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 877.4. Samples: 42854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:14:49,538][00562] Avg episode reward: [(0, '4.368')]
[2024-11-11 14:14:54,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 2898.7). Total num frames: 188416. Throughput: 0: 850.6. Samples: 44896. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:14:54,542][00562] Avg episode reward: [(0, '4.408')]
[2024-11-11 14:14:54,551][03122] Saving new best policy, reward=4.408!
[2024-11-11 14:14:58,442][03135] Updated weights for policy 0, policy_version 50 (0.0018)
[2024-11-11 14:14:59,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 2984.2). Total num frames: 208896. Throughput: 0: 866.1. Samples: 50956. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:14:59,541][00562] Avg episode reward: [(0, '4.312')]
[2024-11-11 14:15:04,537][00562] Fps is (10 sec: 3686.1, 60 sec: 3549.8, 300 sec: 3003.7). Total num frames: 225280. Throughput: 0: 920.3. Samples: 57098. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:15:04,543][00562] Avg episode reward: [(0, '4.295')]
[2024-11-11 14:15:09,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3020.8). Total num frames: 241664. Throughput: 0: 895.1. Samples: 59062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:15:09,540][00562] Avg episode reward: [(0, '4.409')]
[2024-11-11 14:15:09,542][03122] Saving new best policy, reward=4.409!
[2024-11-11 14:15:10,575][03135] Updated weights for policy 0, policy_version 60 (0.0042)
[2024-11-11 14:15:14,536][00562] Fps is (10 sec: 3686.7, 60 sec: 3550.0, 300 sec: 3084.0). Total num frames: 262144. Throughput: 0: 866.4. Samples: 64250. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:15:14,543][00562] Avg episode reward: [(0, '4.556')]
[2024-11-11 14:15:14,550][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth...
[2024-11-11 14:15:14,700][03122] Saving new best policy, reward=4.556!
[2024-11-11 14:15:19,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3140.3). Total num frames: 282624. Throughput: 0: 915.1. Samples: 70422. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:15:19,543][00562] Avg episode reward: [(0, '4.557')]
[2024-11-11 14:15:20,911][03135] Updated weights for policy 0, policy_version 70 (0.0019)
[2024-11-11 14:15:24,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3104.3). Total num frames: 294912. Throughput: 0: 916.0. Samples: 72776. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:15:24,542][00562] Avg episode reward: [(0, '4.631')]
[2024-11-11 14:15:24,551][03122] Saving new best policy, reward=4.631!
[2024-11-11 14:15:29,536][00562] Fps is (10 sec: 2867.2, 60 sec: 3481.7, 300 sec: 3113.0). Total num frames: 311296. Throughput: 0: 876.0. Samples: 77120. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:15:29,543][00562] Avg episode reward: [(0, '4.743')]
[2024-11-11 14:15:29,548][03122] Saving new best policy, reward=4.743!
[2024-11-11 14:15:33,030][03135] Updated weights for policy 0, policy_version 80 (0.0028)
[2024-11-11 14:15:34,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3618.4, 300 sec: 3159.8). Total num frames: 331776. Throughput: 0: 900.9. Samples: 83394. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:15:34,542][00562] Avg episode reward: [(0, '4.588')]
[2024-11-11 14:15:39,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3165.1). Total num frames: 348160. Throughput: 0: 926.0. Samples: 86564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:15:39,543][00562] Avg episode reward: [(0, '4.451')]
[2024-11-11 14:15:44,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3169.9). Total num frames: 364544. Throughput: 0: 878.4. Samples: 90484. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:15:44,539][00562] Avg episode reward: [(0, '4.660')]
[2024-11-11 14:15:45,430][03135] Updated weights for policy 0, policy_version 90 (0.0023)
[2024-11-11 14:15:49,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3208.5). Total num frames: 385024. Throughput: 0: 872.9. Samples: 96376. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:15:49,538][00562] Avg episode reward: [(0, '4.720')]
[2024-11-11 14:15:54,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3244.0). Total num frames: 405504. Throughput: 0: 903.6. Samples: 99722. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:15:54,541][00562] Avg episode reward: [(0, '4.603')]
[2024-11-11 14:15:55,158][03135] Updated weights for policy 0, policy_version 100 (0.0013)
[2024-11-11 14:15:59,541][00562] Fps is (10 sec: 3275.1, 60 sec: 3481.3, 300 sec: 3213.7). Total num frames: 417792. Throughput: 0: 896.5. Samples: 104598. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:15:59,544][00562] Avg episode reward: [(0, '4.750')]
[2024-11-11 14:15:59,550][03122] Saving new best policy, reward=4.750!
[2024-11-11 14:16:04,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3246.5). Total num frames: 438272. Throughput: 0: 874.9. Samples: 109794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:16:04,539][00562] Avg episode reward: [(0, '4.947')]
[2024-11-11 14:16:04,547][03122] Saving new best policy, reward=4.947!
[2024-11-11 14:16:07,043][03135] Updated weights for policy 0, policy_version 110 (0.0031)
[2024-11-11 14:16:09,536][00562] Fps is (10 sec: 4098.1, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 458752. Throughput: 0: 891.1. Samples: 112874. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:16:09,540][00562] Avg episode reward: [(0, '4.808')]
[2024-11-11 14:16:14,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 475136. Throughput: 0: 918.0. Samples: 118428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:16:14,541][00562] Avg episode reward: [(0, '4.764')]
[2024-11-11 14:16:19,536][00562] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3249.5). Total num frames: 487424. Throughput: 0: 871.7. Samples: 122620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:16:19,543][00562] Avg episode reward: [(0, '4.668')]
[2024-11-11 14:16:19,670][03135] Updated weights for policy 0, policy_version 120 (0.0034)
[2024-11-11 14:16:24,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3303.2). Total num frames: 512000. Throughput: 0: 870.3. Samples: 125726. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:16:24,538][00562] Avg episode reward: [(0, '4.833')]
[2024-11-11 14:16:29,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3302.4). Total num frames: 528384. Throughput: 0: 927.5. Samples: 132222. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:16:29,539][00562] Avg episode reward: [(0, '5.245')]
[2024-11-11 14:16:29,649][03135] Updated weights for policy 0, policy_version 130 (0.0021)
[2024-11-11 14:16:29,664][03122] Saving new best policy, reward=5.245!
[2024-11-11 14:16:34,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3301.6). Total num frames: 544768. Throughput: 0: 889.1. Samples: 136386. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:16:34,544][00562] Avg episode reward: [(0, '5.391')]
[2024-11-11 14:16:34,557][03122] Saving new best policy, reward=5.391!
[2024-11-11 14:16:39,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3325.0). Total num frames: 565248. Throughput: 0: 870.9. Samples: 138912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:16:39,541][00562] Avg episode reward: [(0, '5.441')]
[2024-11-11 14:16:39,546][03122] Saving new best policy, reward=5.441!
[2024-11-11 14:16:41,376][03135] Updated weights for policy 0, policy_version 140 (0.0024)
[2024-11-11 14:16:44,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3347.0). Total num frames: 585728. Throughput: 0: 905.1. Samples: 145322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:16:44,540][00562] Avg episode reward: [(0, '5.502')]
[2024-11-11 14:16:44,555][03122] Saving new best policy, reward=5.502!
[2024-11-11 14:16:49,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3322.3). Total num frames: 598016. Throughput: 0: 895.1. Samples: 150072. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:16:49,542][00562] Avg episode reward: [(0, '5.174')]
[2024-11-11 14:16:54,027][03135] Updated weights for policy 0, policy_version 150 (0.0026)
[2024-11-11 14:16:54,536][00562] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3321.1). Total num frames: 614400. Throughput: 0: 873.1. Samples: 152164. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:16:54,539][00562] Avg episode reward: [(0, '5.378')]
[2024-11-11 14:16:59,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3618.4, 300 sec: 3341.5). Total num frames: 634880. Throughput: 0: 884.6. Samples: 158236. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:16:59,545][00562] Avg episode reward: [(0, '5.539')]
[2024-11-11 14:16:59,620][03122] Saving new best policy, reward=5.539!
[2024-11-11 14:17:04,115][03135] Updated weights for policy 0, policy_version 160 (0.0030)
[2024-11-11 14:17:04,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3360.8). Total num frames: 655360. Throughput: 0: 921.9. Samples: 164106. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:17:04,540][00562] Avg episode reward: [(0, '5.798')]
[2024-11-11 14:17:04,552][03122] Saving new best policy, reward=5.798!
[2024-11-11 14:17:09,537][00562] Fps is (10 sec: 3276.5, 60 sec: 3481.6, 300 sec: 3338.2). Total num frames: 667648. Throughput: 0: 894.6. Samples: 165982. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:17:09,542][00562] Avg episode reward: [(0, '5.654')]
[2024-11-11 14:17:14,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3356.7). Total num frames: 688128. Throughput: 0: 870.3. Samples: 171386. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:17:14,542][00562] Avg episode reward: [(0, '5.711')]
[2024-11-11 14:17:14,552][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000168_688128.pth...
[2024-11-11 14:17:15,909][03135] Updated weights for policy 0, policy_version 170 (0.0018)
[2024-11-11 14:17:19,536][00562] Fps is (10 sec: 4096.3, 60 sec: 3686.4, 300 sec: 3374.3). Total num frames: 708608. Throughput: 0: 917.2. Samples: 177662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:17:19,538][00562] Avg episode reward: [(0, '5.479')]
[2024-11-11 14:17:24,541][00562] Fps is (10 sec: 3684.5, 60 sec: 3549.6, 300 sec: 3372.0). Total num frames: 724992. Throughput: 0: 911.6. Samples: 179940. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:17:24,546][00562] Avg episode reward: [(0, '5.572')]
[2024-11-11 14:17:28,184][03135] Updated weights for policy 0, policy_version 180 (0.0019)
[2024-11-11 14:17:29,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3369.9). Total num frames: 741376. Throughput: 0: 866.4. Samples: 184310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:17:29,541][00562] Avg episode reward: [(0, '5.582')]
[2024-11-11 14:17:34,536][00562] Fps is (10 sec: 3688.3, 60 sec: 3618.1, 300 sec: 3386.0). Total num frames: 761856. Throughput: 0: 903.1. Samples: 190712. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:17:34,540][00562] Avg episode reward: [(0, '5.400')]
[2024-11-11 14:17:38,535][03135] Updated weights for policy 0, policy_version 190 (0.0019)
[2024-11-11 14:17:39,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3383.7). Total num frames: 778240. Throughput: 0: 926.4. Samples: 193854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:17:39,539][00562] Avg episode reward: [(0, '5.618')]
[2024-11-11 14:17:44,536][00562] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3363.9). Total num frames: 790528. Throughput: 0: 880.0. Samples: 197836. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:17:44,541][00562] Avg episode reward: [(0, '5.695')]
[2024-11-11 14:17:49,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3396.3). Total num frames: 815104. Throughput: 0: 879.5. Samples: 203684. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:17:49,539][00562] Avg episode reward: [(0, '6.146')]
[2024-11-11 14:17:49,544][03122] Saving new best policy, reward=6.146!
[2024-11-11 14:17:50,420][03135] Updated weights for policy 0, policy_version 200 (0.0033)
[2024-11-11 14:17:54,541][00562] Fps is (10 sec: 4503.4, 60 sec: 3686.1, 300 sec: 3410.5). Total num frames: 835584. Throughput: 0: 908.1. Samples: 206850. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:17:54,544][00562] Avg episode reward: [(0, '6.938')]
[2024-11-11 14:17:54,556][03122] Saving new best policy, reward=6.938!
[2024-11-11 14:17:59,538][00562] Fps is (10 sec: 3276.1, 60 sec: 3549.7, 300 sec: 3391.5). Total num frames: 847872. Throughput: 0: 893.9. Samples: 211612. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:17:59,541][00562] Avg episode reward: [(0, '7.284')]
[2024-11-11 14:17:59,543][03122] Saving new best policy, reward=7.284!
[2024-11-11 14:18:02,770][03135] Updated weights for policy 0, policy_version 210 (0.0032)
[2024-11-11 14:18:04,537][00562] Fps is (10 sec: 2868.3, 60 sec: 3481.6, 300 sec: 3389.2). Total num frames: 864256. Throughput: 0: 866.4. Samples: 216650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:18:04,539][00562] Avg episode reward: [(0, '7.289')]
[2024-11-11 14:18:04,553][03122] Saving new best policy, reward=7.289!
[2024-11-11 14:18:09,536][00562] Fps is (10 sec: 3687.0, 60 sec: 3618.2, 300 sec: 3402.8). Total num frames: 884736. Throughput: 0: 884.5. Samples: 219738. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:18:09,541][00562] Avg episode reward: [(0, '6.772')]
[2024-11-11 14:18:13,268][03135] Updated weights for policy 0, policy_version 220 (0.0029)
[2024-11-11 14:18:14,537][00562] Fps is (10 sec: 3686.5, 60 sec: 3549.8, 300 sec: 3400.4). Total num frames: 901120. Throughput: 0: 914.7. Samples: 225474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:18:14,544][00562] Avg episode reward: [(0, '6.888')]
[2024-11-11 14:18:19,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3398.2). Total num frames: 917504. Throughput: 0: 869.5. Samples: 229838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:18:19,542][00562] Avg episode reward: [(0, '6.874')]
[2024-11-11 14:18:24,536][00562] Fps is (10 sec: 3686.6, 60 sec: 3550.2, 300 sec: 3410.9). Total num frames: 937984. Throughput: 0: 871.2. Samples: 233058. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:18:24,543][00562] Avg episode reward: [(0, '7.313')]
[2024-11-11 14:18:24,564][03122] Saving new best policy, reward=7.313!
[2024-11-11 14:18:24,562][03135] Updated weights for policy 0, policy_version 230 (0.0019)
[2024-11-11 14:18:29,538][00562] Fps is (10 sec: 4095.4, 60 sec: 3618.0, 300 sec: 3423.1). Total num frames: 958464. Throughput: 0: 925.4. Samples: 239480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:18:29,542][00562] Avg episode reward: [(0, '7.727')]
[2024-11-11 14:18:29,544][03122] Saving new best policy, reward=7.727!
[2024-11-11 14:18:34,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3406.1). Total num frames: 970752. Throughput: 0: 880.6. Samples: 243310. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:18:34,541][00562] Avg episode reward: [(0, '7.795')]
[2024-11-11 14:18:34,551][03122] Saving new best policy, reward=7.795!
[2024-11-11 14:18:37,011][03135] Updated weights for policy 0, policy_version 240 (0.0025)
[2024-11-11 14:18:39,536][00562] Fps is (10 sec: 3277.3, 60 sec: 3549.9, 300 sec: 3418.0). Total num frames: 991232. Throughput: 0: 873.4. Samples: 246148. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:18:39,541][00562] Avg episode reward: [(0, '8.393')]
[2024-11-11 14:18:39,544][03122] Saving new best policy, reward=8.393!
[2024-11-11 14:18:44,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3429.5). Total num frames: 1011712. Throughput: 0: 910.6. Samples: 252588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:18:44,539][00562] Avg episode reward: [(0, '8.526')]
[2024-11-11 14:18:44,549][03122] Saving new best policy, reward=8.526!
[2024-11-11 14:18:48,068][03135] Updated weights for policy 0, policy_version 250 (0.0015)
[2024-11-11 14:18:49,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1024000. Throughput: 0: 898.2. Samples: 257066. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:18:49,539][00562] Avg episode reward: [(0, '9.033')]
[2024-11-11 14:18:49,559][03122] Saving new best policy, reward=9.033!
[2024-11-11 14:18:54,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3481.9, 300 sec: 3540.6). Total num frames: 1044480. Throughput: 0: 874.0. Samples: 259066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:18:54,543][00562] Avg episode reward: [(0, '8.546')]
[2024-11-11 14:18:59,081][03135] Updated weights for policy 0, policy_version 260 (0.0025)
[2024-11-11 14:18:59,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3618.3, 300 sec: 3568.4). Total num frames: 1064960. Throughput: 0: 890.6. Samples: 265550. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:18:59,540][00562] Avg episode reward: [(0, '7.860')]
[2024-11-11 14:19:04,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3554.5). Total num frames: 1081344. Throughput: 0: 913.6. Samples: 270950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:19:04,546][00562] Avg episode reward: [(0, '7.881')]
[2024-11-11 14:19:09,536][00562] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1097728. Throughput: 0: 887.1. Samples: 272976. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:19:09,538][00562] Avg episode reward: [(0, '8.809')]
[2024-11-11 14:19:11,099][03135] Updated weights for policy 0, policy_version 270 (0.0031)
[2024-11-11 14:19:14,536][00562] Fps is (10 sec: 3686.3, 60 sec: 3618.2, 300 sec: 3582.3). Total num frames: 1118208. Throughput: 0: 878.3. Samples: 279000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:19:14,539][00562] Avg episode reward: [(0, '9.228')]
[2024-11-11 14:19:14,555][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000273_1118208.pth...
[2024-11-11 14:19:14,675][03122] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth
[2024-11-11 14:19:14,692][03122] Saving new best policy, reward=9.228!
[2024-11-11 14:19:19,536][00562] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1134592. Throughput: 0: 920.3. Samples: 284724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:19:19,540][00562] Avg episode reward: [(0, '9.538')]
[2024-11-11 14:19:19,604][03122] Saving new best policy, reward=9.538!
[2024-11-11 14:19:22,954][03135] Updated weights for policy 0, policy_version 280 (0.0018)
[2024-11-11 14:19:24,536][00562] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1150976. Throughput: 0: 898.6. Samples: 286586. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:19:24,540][00562] Avg episode reward: [(0, '9.325')]
[2024-11-11 14:19:29,536][00562] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 1171456. Throughput: 0: 873.1. Samples: 291876. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-11-11 14:19:29,538][00562] Avg episode reward: [(0, '9.553')]
[2024-11-11 14:19:29,542][03122] Saving new best policy, reward=9.553!
[2024-11-11 14:19:33,246][03135] Updated weights for policy 0, policy_version 290 (0.0019)
[2024-11-11 14:19:34,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 1191936. Throughput: 0: 910.7. Samples: 298046. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:19:34,541][00562] Avg episode reward: [(0, '10.099')]
[2024-11-11 14:19:34,551][03122] Saving new best policy, reward=10.099!
[2024-11-11 14:19:39,541][00562] Fps is (10 sec: 3275.2, 60 sec: 3549.6, 300 sec: 3554.4). Total num frames: 1204224. Throughput: 0: 915.3. Samples: 300258. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:19:39,544][00562] Avg episode reward: [(0, '9.851')]
[2024-11-11 14:19:44,542][00562] Fps is (10 sec: 3274.9, 60 sec: 3549.5, 300 sec: 3582.2). Total num frames: 1224704. Throughput: 0: 873.6. Samples: 304868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:19:44,544][00562] Avg episode reward: [(0, '9.566')]
[2024-11-11 14:19:45,424][03135] Updated weights for policy 0, policy_version 300 (0.0022)
[2024-11-11 14:19:49,536][00562] Fps is (10 sec: 4098.1, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 1245184. Throughput: 0: 899.8. Samples: 311440. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:19:49,544][00562] Avg episode reward: [(0, '9.843')]
[2024-11-11 14:19:54,536][00562] Fps is (10 sec: 3688.6, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1261568. Throughput: 0: 932.5. Samples: 314936. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:19:54,539][00562] Avg episode reward: [(0, '9.722')]
[2024-11-11 14:19:56,009][03135] Updated weights for policy 0, policy_version 310 (0.0016)
[2024-11-11 14:19:59,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1277952. Throughput: 0: 893.7. Samples: 319216. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:19:59,538][00562] Avg episode reward: [(0, '9.716')]
[2024-11-11 14:20:04,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 1302528. Throughput: 0: 914.5. Samples: 325876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:20:04,541][00562] Avg episode reward: [(0, '10.107')]
[2024-11-11 14:20:04,556][03122] Saving new best policy, reward=10.107!
[2024-11-11 14:20:05,974][03135] Updated weights for policy 0, policy_version 320 (0.0017)
[2024-11-11 14:20:09,539][00562] Fps is (10 sec: 4504.2, 60 sec: 3754.5, 300 sec: 3596.1). Total num frames: 1323008. Throughput: 0: 949.0. Samples: 329296. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:20:09,541][00562] Avg episode reward: [(0, '11.050')]
[2024-11-11 14:20:09,552][03122] Saving new best policy, reward=11.050!
[2024-11-11 14:20:14,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1335296. Throughput: 0: 941.1. Samples: 334226. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2024-11-11 14:20:14,539][00562] Avg episode reward: [(0, '11.349')]
[2024-11-11 14:20:14,558][03122] Saving new best policy, reward=11.349!
[2024-11-11 14:20:17,364][03135] Updated weights for policy 0, policy_version 330 (0.0037)
[2024-11-11 14:20:19,536][00562] Fps is (10 sec: 3687.5, 60 sec: 3754.7, 300 sec: 3610.0). Total num frames: 1359872. Throughput: 0: 932.2. Samples: 339996. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:20:19,538][00562] Avg episode reward: [(0, '11.071')]
[2024-11-11 14:20:24,536][00562] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3637.8). Total num frames: 1384448. Throughput: 0: 961.4. Samples: 343514. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:20:24,538][00562] Avg episode reward: [(0, '10.360')]
[2024-11-11 14:20:26,823][03135] Updated weights for policy 0, policy_version 340 (0.0031)
[2024-11-11 14:20:29,536][00562] Fps is (10 sec: 3686.3, 60 sec: 3754.7, 300 sec: 3610.0). Total num frames: 1396736. Throughput: 0: 988.7. Samples: 349354. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:20:29,546][00562] Avg episode reward: [(0, '10.946')]
[2024-11-11 14:20:34,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3623.9). Total num frames: 1417216. Throughput: 0: 961.4. Samples: 354702. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:20:34,538][00562] Avg episode reward: [(0, '11.230')]
[2024-11-11 14:20:37,353][03135] Updated weights for policy 0, policy_version 350 (0.0020)
[2024-11-11 14:20:39,536][00562] Fps is (10 sec: 4505.7, 60 sec: 3959.8, 300 sec: 3651.7). Total num frames: 1441792. Throughput: 0: 960.0. Samples: 358138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:20:39,538][00562] Avg episode reward: [(0, '13.045')]
[2024-11-11 14:20:39,542][03122] Saving new best policy, reward=13.045!
[2024-11-11 14:20:44,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3891.6, 300 sec: 3637.8). Total num frames: 1458176. Throughput: 0: 1009.6. Samples: 364648. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:20:44,538][00562] Avg episode reward: [(0, '14.305')]
[2024-11-11 14:20:44,555][03122] Saving new best policy, reward=14.305!
[2024-11-11 14:20:48,981][03135] Updated weights for policy 0, policy_version 360 (0.0027)
[2024-11-11 14:20:49,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3623.9). Total num frames: 1474560. Throughput: 0: 958.2. Samples: 368996. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:20:49,538][00562] Avg episode reward: [(0, '14.481')]
[2024-11-11 14:20:49,540][03122] Saving new best policy, reward=14.481!
[2024-11-11 14:20:54,536][00562] Fps is (10 sec: 4095.9, 60 sec: 3959.4, 300 sec: 3665.6). Total num frames: 1499136. Throughput: 0: 958.9. Samples: 372442. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:20:54,543][00562] Avg episode reward: [(0, '14.633')]
[2024-11-11 14:20:54,551][03122] Saving new best policy, reward=14.633!
[2024-11-11 14:20:57,890][03135] Updated weights for policy 0, policy_version 370 (0.0025)
[2024-11-11 14:20:59,536][00562] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3665.6). Total num frames: 1519616. Throughput: 0: 1002.1. Samples: 379322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:20:59,542][00562] Avg episode reward: [(0, '13.241')]
[2024-11-11 14:21:04,536][00562] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3637.8). Total num frames: 1531904. Throughput: 0: 974.9. Samples: 383868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:21:04,539][00562] Avg episode reward: [(0, '13.089')]
[2024-11-11 14:21:09,174][03135] Updated weights for policy 0, policy_version 380 (0.0021)
[2024-11-11 14:21:09,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.4, 300 sec: 3665.6). Total num frames: 1556480. Throughput: 0: 962.0. Samples: 386802. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:21:09,539][00562] Avg episode reward: [(0, '13.534')]
[2024-11-11 14:21:14,536][00562] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3707.2). Total num frames: 1581056. Throughput: 0: 989.8. Samples: 393894. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:21:14,538][00562] Avg episode reward: [(0, '14.577')]
[2024-11-11 14:21:14,546][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth...
[2024-11-11 14:21:14,667][03122] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000168_688128.pth
[2024-11-11 14:21:19,540][00562] Fps is (10 sec: 3684.8, 60 sec: 3890.9, 300 sec: 3665.5). Total num frames: 1593344. Throughput: 0: 988.3. Samples: 399180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:21:19,546][00562] Avg episode reward: [(0, '15.060')]
[2024-11-11 14:21:19,628][03135] Updated weights for policy 0, policy_version 390 (0.0020)
[2024-11-11 14:21:19,632][03122] Saving new best policy, reward=15.060!
[2024-11-11 14:21:24,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 1613824. Throughput: 0: 960.8. Samples: 401372. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:21:24,539][00562] Avg episode reward: [(0, '15.528')]
[2024-11-11 14:21:24,549][03122] Saving new best policy, reward=15.528!
[2024-11-11 14:21:29,315][03135] Updated weights for policy 0, policy_version 400 (0.0027)
[2024-11-11 14:21:29,536][00562] Fps is (10 sec: 4507.6, 60 sec: 4027.7, 300 sec: 3707.2). Total num frames: 1638400. Throughput: 0: 969.6. Samples: 408280. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:21:29,544][00562] Avg episode reward: [(0, '14.303')]
[2024-11-11 14:21:34,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3693.3). Total num frames: 1654784. Throughput: 0: 1011.9. Samples: 414530. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:21:34,542][00562] Avg episode reward: [(0, '12.693')]
[2024-11-11 14:21:39,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 1671168. Throughput: 0: 983.8. Samples: 416712. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:21:39,542][00562] Avg episode reward: [(0, '11.913')]
[2024-11-11 14:21:40,711][03135] Updated weights for policy 0, policy_version 410 (0.0020)
[2024-11-11 14:21:44,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3721.1). Total num frames: 1695744. Throughput: 0: 969.8. Samples: 422964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:21:44,539][00562] Avg episode reward: [(0, '12.488')]
[2024-11-11 14:21:49,537][00562] Fps is (10 sec: 4505.1, 60 sec: 4027.7, 300 sec: 3735.0). Total num frames: 1716224. Throughput: 0: 1025.6. Samples: 430020. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:21:49,540][00562] Avg episode reward: [(0, '13.037')]
[2024-11-11 14:21:49,650][03135] Updated weights for policy 0, policy_version 420 (0.0014)
[2024-11-11 14:21:54,542][00562] Fps is (10 sec: 3684.2, 60 sec: 3890.8, 300 sec: 3721.0). Total num frames: 1732608. Throughput: 0: 1008.1. Samples: 432174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:21:54,551][00562] Avg episode reward: [(0, '13.699')]
[2024-11-11 14:21:59,536][00562] Fps is (10 sec: 3686.8, 60 sec: 3891.2, 300 sec: 3721.1). Total num frames: 1753088. Throughput: 0: 967.2. Samples: 437418. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:21:59,539][00562] Avg episode reward: [(0, '15.479')]
[2024-11-11 14:22:01,010][03135] Updated weights for policy 0, policy_version 430 (0.0020)
[2024-11-11 14:22:04,537][00562] Fps is (10 sec: 4507.9, 60 sec: 4095.9, 300 sec: 3762.8). Total num frames: 1777664. Throughput: 0: 998.2. Samples: 444096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:22:04,544][00562] Avg episode reward: [(0, '15.164')]
[2024-11-11 14:22:09,537][00562] Fps is (10 sec: 3685.8, 60 sec: 3891.1, 300 sec: 3735.0). Total num frames: 1789952. Throughput: 0: 1012.5. Samples: 446936. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:22:09,543][00562] Avg episode reward: [(0, '15.847')]
[2024-11-11 14:22:09,548][03122] Saving new best policy, reward=15.847!
[2024-11-11 14:22:13,001][03135] Updated weights for policy 0, policy_version 440 (0.0038)
[2024-11-11 14:22:14,536][00562] Fps is (10 sec: 2867.5, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1806336. Throughput: 0: 948.5. Samples: 450962. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:22:14,539][00562] Avg episode reward: [(0, '15.502')]
[2024-11-11 14:22:19,536][00562] Fps is (10 sec: 4096.6, 60 sec: 3959.8, 300 sec: 3748.9). Total num frames: 1830912. Throughput: 0: 954.4. Samples: 457478. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:22:19,542][00562] Avg episode reward: [(0, '14.958')]
[2024-11-11 14:22:22,092][03135] Updated weights for policy 0, policy_version 450 (0.0028)
[2024-11-11 14:22:24,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 1847296. Throughput: 0: 982.1. Samples: 460906. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:22:24,540][00562] Avg episode reward: [(0, '15.776')]
[2024-11-11 14:22:29,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1863680. Throughput: 0: 939.7. Samples: 465250. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:22:29,538][00562] Avg episode reward: [(0, '16.064')]
[2024-11-11 14:22:29,540][03122] Saving new best policy, reward=16.064!
[2024-11-11 14:22:34,004][03135] Updated weights for policy 0, policy_version 460 (0.0025)
[2024-11-11 14:22:34,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1884160. Throughput: 0: 916.6. Samples: 471266. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:22:34,538][00562] Avg episode reward: [(0, '15.748')]
[2024-11-11 14:22:39,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 1904640. Throughput: 0: 943.1. Samples: 474608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:22:39,541][00562] Avg episode reward: [(0, '15.982')]
[2024-11-11 14:22:44,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1921024. Throughput: 0: 939.2. Samples: 479680. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:22:44,541][00562] Avg episode reward: [(0, '14.914')]
[2024-11-11 14:22:45,999][03135] Updated weights for policy 0, policy_version 470 (0.0026)
[2024-11-11 14:22:49,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3735.1). Total num frames: 1937408. Throughput: 0: 906.5. Samples: 484888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:22:49,539][00562] Avg episode reward: [(0, '14.322')]
[2024-11-11 14:22:54,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3823.3, 300 sec: 3776.7). Total num frames: 1961984. Throughput: 0: 916.4. Samples: 488174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:22:54,538][00562] Avg episode reward: [(0, '12.973')]
[2024-11-11 14:22:55,248][03135] Updated weights for policy 0, policy_version 480 (0.0021)
[2024-11-11 14:22:59,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 1978368. Throughput: 0: 959.3. Samples: 494130. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:22:59,539][00562] Avg episode reward: [(0, '13.627')]
[2024-11-11 14:23:04,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3762.8). Total num frames: 1994752. Throughput: 0: 918.2. Samples: 498798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:23:04,543][00562] Avg episode reward: [(0, '15.122')]
[2024-11-11 14:23:06,911][03135] Updated weights for policy 0, policy_version 490 (0.0036)
[2024-11-11 14:23:09,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 3776.7). Total num frames: 2015232. Throughput: 0: 917.5. Samples: 502194. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:23:09,542][00562] Avg episode reward: [(0, '16.168')]
[2024-11-11 14:23:09,550][03122] Saving new best policy, reward=16.168!
[2024-11-11 14:23:14,538][00562] Fps is (10 sec: 4095.1, 60 sec: 3822.8, 300 sec: 3790.5). Total num frames: 2035712. Throughput: 0: 969.3. Samples: 508872. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2024-11-11 14:23:14,545][00562] Avg episode reward: [(0, '17.297')]
[2024-11-11 14:23:14,560][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000497_2035712.pth...
[2024-11-11 14:23:14,723][03122] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000273_1118208.pth
[2024-11-11 14:23:14,744][03122] Saving new best policy, reward=17.297!
[2024-11-11 14:23:18,676][03135] Updated weights for policy 0, policy_version 500 (0.0024)
[2024-11-11 14:23:19,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3762.8). Total num frames: 2048000. Throughput: 0: 918.7. Samples: 512608. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:23:19,539][00562] Avg episode reward: [(0, '18.508')]
[2024-11-11 14:23:19,553][03122] Saving new best policy, reward=18.508!
[2024-11-11 14:23:24,536][00562] Fps is (10 sec: 3687.2, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2072576. Throughput: 0: 910.7. Samples: 515588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:23:24,538][00562] Avg episode reward: [(0, '17.975')]
[2024-11-11 14:23:28,016][03135] Updated weights for policy 0, policy_version 510 (0.0013)
[2024-11-11 14:23:29,537][00562] Fps is (10 sec: 4505.0, 60 sec: 3822.8, 300 sec: 3804.4). Total num frames: 2093056. Throughput: 0: 950.5. Samples: 522452. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:23:29,545][00562] Avg episode reward: [(0, '17.632')]
[2024-11-11 14:23:34,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 2105344. Throughput: 0: 944.7. Samples: 527398. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:23:34,543][00562] Avg episode reward: [(0, '18.036')]
[2024-11-11 14:23:39,536][00562] Fps is (10 sec: 3277.3, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 2125824. Throughput: 0: 923.7. Samples: 529740. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:23:39,542][00562] Avg episode reward: [(0, '18.040')]
[2024-11-11 14:23:39,830][03135] Updated weights for policy 0, policy_version 520 (0.0023)
[2024-11-11 14:23:44,536][00562] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2150400. Throughput: 0: 939.6. Samples: 536414. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:23:44,542][00562] Avg episode reward: [(0, '18.160')]
[2024-11-11 14:23:49,536][00562] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 2166784. Throughput: 0: 958.8. Samples: 541944. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:23:49,542][00562] Avg episode reward: [(0, '19.216')]
[2024-11-11 14:23:49,543][03122] Saving new best policy, reward=19.216!
[2024-11-11 14:23:50,734][03135] Updated weights for policy 0, policy_version 530 (0.0014)
[2024-11-11 14:23:54,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3790.5). Total num frames: 2183168. Throughput: 0: 926.4. Samples: 543880. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:23:54,543][00562] Avg episode reward: [(0, '19.125')]
[2024-11-11 14:23:59,536][00562] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 2203648. Throughput: 0: 915.8. Samples: 550082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:23:59,540][00562] Avg episode reward: [(0, '18.306')]
[2024-11-11 14:24:00,831][03135] Updated weights for policy 0, policy_version 540 (0.0028)
[2024-11-11 14:24:04,536][00562] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2224128. Throughput: 0: 982.9. Samples: 556838. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:24:04,538][00562] Avg episode reward: [(0, '17.906')]
[2024-11-11 14:24:09,536][00562] Fps is (10 sec: 3686.3, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 2240512. Throughput: 0: 962.2. Samples: 558888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:24:09,541][00562] Avg episode reward: [(0, '17.494')]
[2024-11-11 14:24:12,425][03135] Updated weights for policy 0, policy_version 550 (0.0024)
[2024-11-11 14:24:14,536][00562] Fps is (10 sec: 3686.5, 60 sec: 3754.8, 300 sec: 3818.3). Total num frames: 2260992. Throughput: 0: 928.3. Samples: 564222. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:24:14,543][00562] Avg episode reward: [(0, '17.795')]
[2024-11-11 14:24:19,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2281472. Throughput: 0: 973.9. Samples: 571224. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:24:19,544][00562] Avg episode reward: [(0, '17.263')]
[2024-11-11 14:24:22,313][03135] Updated weights for policy 0, policy_version 560 (0.0018)
[2024-11-11 14:24:24,537][00562] Fps is (10 sec: 3686.1, 60 sec: 3754.6, 300 sec: 3818.3). Total num frames: 2297856. Throughput: 0: 978.9. Samples: 573792. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:24:24,539][00562] Avg episode reward: [(0, '17.846')]
[2024-11-11 14:24:29,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 2318336. Throughput: 0: 937.1. Samples: 578584. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:24:29,544][00562] Avg episode reward: [(0, '18.910')]
[2024-11-11 14:24:32,729][03135] Updated weights for policy 0, policy_version 570 (0.0031)
[2024-11-11 14:24:34,536][00562] Fps is (10 sec: 4506.0, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2342912. Throughput: 0: 968.3. Samples: 585518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:24:34,539][00562] Avg episode reward: [(0, '19.948')]
[2024-11-11 14:24:34,549][03122] Saving new best policy, reward=19.948!
[2024-11-11 14:24:39,536][00562] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3846.2). Total num frames: 2359296. Throughput: 0: 999.1. Samples: 588840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:24:39,549][00562] Avg episode reward: [(0, '19.368')]
[2024-11-11 14:24:44,415][03135] Updated weights for policy 0, policy_version 580 (0.0024)
[2024-11-11 14:24:44,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 2375680. Throughput: 0: 955.0. Samples: 593056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:24:44,538][00562] Avg episode reward: [(0, '20.561')]
[2024-11-11 14:24:44,546][03122] Saving new best policy, reward=20.561!
[2024-11-11 14:24:49,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2396160. Throughput: 0: 951.2. Samples: 599644. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:24:49,538][00562] Avg episode reward: [(0, '20.524')]
[2024-11-11 14:24:53,193][03135] Updated weights for policy 0, policy_version 590 (0.0025)
[2024-11-11 14:24:54,536][00562] Fps is (10 sec: 4505.5, 60 sec: 3959.4, 300 sec: 3873.8). Total num frames: 2420736. Throughput: 0: 980.6. Samples: 603014. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:24:54,540][00562] Avg episode reward: [(0, '19.929')]
[2024-11-11 14:24:59,542][00562] Fps is (10 sec: 3684.2, 60 sec: 3822.5, 300 sec: 3832.1). Total num frames: 2433024. Throughput: 0: 975.2. Samples: 608110. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:24:59,545][00562] Avg episode reward: [(0, '19.025')]
[2024-11-11 14:25:04,536][00562] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2453504. Throughput: 0: 950.8. Samples: 614012. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:25:04,538][00562] Avg episode reward: [(0, '18.559')]
[2024-11-11 14:25:04,664][03135] Updated weights for policy 0, policy_version 600 (0.0028)
[2024-11-11 14:25:09,536][00562] Fps is (10 sec: 4508.4, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2478080. Throughput: 0: 973.1. Samples: 617580. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:25:09,538][00562] Avg episode reward: [(0, '18.975')]
[2024-11-11 14:25:14,538][00562] Fps is (10 sec: 4095.3, 60 sec: 3891.1, 300 sec: 3846.1). Total num frames: 2494464. Throughput: 0: 995.4. Samples: 623378. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:25:14,543][00562] Avg episode reward: [(0, '19.347')]
[2024-11-11 14:25:14,559][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000609_2494464.pth...
[2024-11-11 14:25:14,724][03122] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth
[2024-11-11 14:25:15,624][03135] Updated weights for policy 0, policy_version 610 (0.0032)
[2024-11-11 14:25:19,538][00562] Fps is (10 sec: 3276.2, 60 sec: 3822.8, 300 sec: 3818.3). Total num frames: 2510848. Throughput: 0: 952.2. Samples: 628368. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:25:19,542][00562] Avg episode reward: [(0, '18.871')]
[2024-11-11 14:25:24,536][00562] Fps is (10 sec: 4096.7, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2535424. Throughput: 0: 947.9. Samples: 631496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:25:24,542][00562] Avg episode reward: [(0, '19.056')]
[2024-11-11 14:25:24,980][03135] Updated weights for policy 0, policy_version 620 (0.0026)
[2024-11-11 14:25:29,538][00562] Fps is (10 sec: 4505.5, 60 sec: 3959.4, 300 sec: 3859.9). Total num frames: 2555904. Throughput: 0: 1006.5. Samples: 638350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:25:29,540][00562] Avg episode reward: [(0, '18.963')]
[2024-11-11 14:25:34,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 2568192. Throughput: 0: 954.9. Samples: 642616. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:25:34,539][00562] Avg episode reward: [(0, '18.796')]
[2024-11-11 14:25:36,392][03135] Updated weights for policy 0, policy_version 630 (0.0023)
[2024-11-11 14:25:39,536][00562] Fps is (10 sec: 3687.1, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2592768. Throughput: 0: 958.7. Samples: 646154. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:25:39,538][00562] Avg episode reward: [(0, '19.304')]
[2024-11-11 14:25:44,536][00562] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3873.8). Total num frames: 2617344. Throughput: 0: 1002.5. Samples: 653216. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:25:44,539][00562] Avg episode reward: [(0, '19.259')]
[2024-11-11 14:25:45,777][03135] Updated weights for policy 0, policy_version 640 (0.0039)
[2024-11-11 14:25:49,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2629632. Throughput: 0: 975.9. Samples: 657928. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:25:49,539][00562] Avg episode reward: [(0, '19.747')]
[2024-11-11 14:25:54,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3832.2). Total num frames: 2650112. Throughput: 0: 956.8. Samples: 660636. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:25:54,543][00562] Avg episode reward: [(0, '19.441')]
[2024-11-11 14:25:56,442][03135] Updated weights for policy 0, policy_version 650 (0.0032)
[2024-11-11 14:25:59,536][00562] Fps is (10 sec: 4505.6, 60 sec: 4028.1, 300 sec: 3873.8). Total num frames: 2674688. Throughput: 0: 984.3. Samples: 667670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:25:59,538][00562] Avg episode reward: [(0, '19.029')]
[2024-11-11 14:26:04,539][00562] Fps is (10 sec: 4094.8, 60 sec: 3959.3, 300 sec: 3846.0). Total num frames: 2691072. Throughput: 0: 996.0. Samples: 673188. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
[2024-11-11 14:26:04,542][00562] Avg episode reward: [(0, '19.359')]
[2024-11-11 14:26:07,949][03135] Updated weights for policy 0, policy_version 660 (0.0031)
[2024-11-11 14:26:09,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2707456. Throughput: 0: 973.6. Samples: 675308. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:26:09,538][00562] Avg episode reward: [(0, '19.579')]
[2024-11-11 14:26:14,536][00562] Fps is (10 sec: 4097.2, 60 sec: 3959.6, 300 sec: 3860.0). Total num frames: 2732032. Throughput: 0: 973.4. Samples: 682150. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:26:14,546][00562] Avg episode reward: [(0, '18.167')]
[2024-11-11 14:26:16,721][03135] Updated weights for policy 0, policy_version 670 (0.0020)
[2024-11-11 14:26:19,536][00562] Fps is (10 sec: 4505.6, 60 sec: 4027.9, 300 sec: 3860.0). Total num frames: 2752512. Throughput: 0: 1017.9. Samples: 688422. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:26:19,538][00562] Avg episode reward: [(0, '18.763')]
[2024-11-11 14:26:24,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2768896. Throughput: 0: 986.2. Samples: 690532. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:26:24,538][00562] Avg episode reward: [(0, '18.673')]
[2024-11-11 14:26:27,909][03135] Updated weights for policy 0, policy_version 680 (0.0024)
[2024-11-11 14:26:29,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.3, 300 sec: 3846.1). Total num frames: 2789376. Throughput: 0: 963.3. Samples: 696564. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:26:29,544][00562] Avg episode reward: [(0, '17.968')]
[2024-11-11 14:26:34,537][00562] Fps is (10 sec: 4505.1, 60 sec: 4095.9, 300 sec: 3873.8). Total num frames: 2813952. Throughput: 0: 1016.3. Samples: 703662. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:26:34,540][00562] Avg episode reward: [(0, '18.548')]
[2024-11-11 14:26:38,381][03135] Updated weights for policy 0, policy_version 690 (0.0019)
[2024-11-11 14:26:39,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2826240. Throughput: 0: 1006.8. Samples: 705944. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:26:39,541][00562] Avg episode reward: [(0, '18.296')]
[2024-11-11 14:26:44,536][00562] Fps is (10 sec: 3277.2, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2846720. Throughput: 0: 965.7. Samples: 711128. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:26:44,541][00562] Avg episode reward: [(0, '17.230')]
[2024-11-11 14:26:48,080][03135] Updated weights for policy 0, policy_version 700 (0.0031)
[2024-11-11 14:26:49,536][00562] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3860.0). Total num frames: 2871296. Throughput: 0: 1000.8. Samples: 718222. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:26:49,545][00562] Avg episode reward: [(0, '17.083')]
[2024-11-11 14:26:54,537][00562] Fps is (10 sec: 4095.5, 60 sec: 3959.4, 300 sec: 3846.1). Total num frames: 2887680. Throughput: 0: 1019.0. Samples: 721164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:26:54,543][00562] Avg episode reward: [(0, '17.814')]
[2024-11-11 14:26:59,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2904064. Throughput: 0: 965.1. Samples: 725578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:26:59,543][00562] Avg episode reward: [(0, '18.477')]
[2024-11-11 14:26:59,565][03135] Updated weights for policy 0, policy_version 710 (0.0029)
[2024-11-11 14:27:04,543][00562] Fps is (10 sec: 4093.5, 60 sec: 3959.2, 300 sec: 3859.9). Total num frames: 2928640. Throughput: 0: 983.2. Samples: 732674. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:27:04,549][00562] Avg episode reward: [(0, '19.283')]
[2024-11-11 14:27:08,764][03135] Updated weights for policy 0, policy_version 720 (0.0028)
[2024-11-11 14:27:09,536][00562] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3873.8). Total num frames: 2949120. Throughput: 0: 1014.0. Samples: 736160. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:27:09,540][00562] Avg episode reward: [(0, '20.200')]
[2024-11-11 14:27:14,536][00562] Fps is (10 sec: 3689.1, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2965504. Throughput: 0: 984.0. Samples: 740842. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:27:14,538][00562] Avg episode reward: [(0, '18.441')]
[2024-11-11 14:27:14,550][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000724_2965504.pth...
[2024-11-11 14:27:14,671][03122] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000497_2035712.pth
[2024-11-11 14:27:19,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2985984. Throughput: 0: 966.7. Samples: 747164. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:27:19,538][00562] Avg episode reward: [(0, '18.515')]
[2024-11-11 14:27:19,552][03135] Updated weights for policy 0, policy_version 730 (0.0013)
[2024-11-11 14:27:24,537][00562] Fps is (10 sec: 4504.9, 60 sec: 4027.6, 300 sec: 3887.7). Total num frames: 3010560. Throughput: 0: 987.8. Samples: 750398. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:27:24,542][00562] Avg episode reward: [(0, '18.392')]
[2024-11-11 14:27:29,537][00562] Fps is (10 sec: 3686.0, 60 sec: 3891.1, 300 sec: 3859.9). Total num frames: 3022848. Throughput: 0: 991.1. Samples: 755730. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:27:29,539][00562] Avg episode reward: [(0, '17.663')]
[2024-11-11 14:27:31,246][03135] Updated weights for policy 0, policy_version 740 (0.0023)
[2024-11-11 14:27:34,536][00562] Fps is (10 sec: 3277.3, 60 sec: 3823.0, 300 sec: 3860.0). Total num frames: 3043328. Throughput: 0: 960.1. Samples: 761426. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:27:34,544][00562] Avg episode reward: [(0, '18.847')]
[2024-11-11 14:27:39,536][00562] Fps is (10 sec: 4506.0, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 3067904. Throughput: 0: 973.3. Samples: 764960. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:27:39,543][00562] Avg episode reward: [(0, '18.547')]
[2024-11-11 14:27:39,839][03135] Updated weights for policy 0, policy_version 750 (0.0013)
[2024-11-11 14:27:44,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3084288. Throughput: 0: 1009.1. Samples: 770986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:27:44,540][00562] Avg episode reward: [(0, '19.671')]
[2024-11-11 14:27:49,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 3104768. Throughput: 0: 962.2. Samples: 775968. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:27:49,537][00562] Avg episode reward: [(0, '20.647')]
[2024-11-11 14:27:49,540][03122] Saving new best policy, reward=20.647!
[2024-11-11 14:27:51,277][03135] Updated weights for policy 0, policy_version 760 (0.0017)
[2024-11-11 14:27:54,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3125248. Throughput: 0: 958.9. Samples: 779310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:27:54,543][00562] Avg episode reward: [(0, '20.763')]
[2024-11-11 14:27:54,555][03122] Saving new best policy, reward=20.763!
[2024-11-11 14:27:59,537][00562] Fps is (10 sec: 4095.6, 60 sec: 4027.7, 300 sec: 3901.6). Total num frames: 3145728. Throughput: 0: 1007.4. Samples: 786178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:27:59,539][00562] Avg episode reward: [(0, '20.604')]
[2024-11-11 14:28:01,918][03135] Updated weights for policy 0, policy_version 770 (0.0014)
[2024-11-11 14:28:04,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.7, 300 sec: 3887.7). Total num frames: 3162112. Throughput: 0: 961.4. Samples: 790426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:28:04,539][00562] Avg episode reward: [(0, '19.923')]
[2024-11-11 14:28:09,536][00562] Fps is (10 sec: 3686.8, 60 sec: 3891.2, 300 sec: 3887.8). Total num frames: 3182592. Throughput: 0: 964.2. Samples: 793784. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:28:09,543][00562] Avg episode reward: [(0, '18.911')]
[2024-11-11 14:28:11,370][03135] Updated weights for policy 0, policy_version 780 (0.0016)
[2024-11-11 14:28:14,536][00562] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 3207168. Throughput: 0: 1001.4. Samples: 800794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:28:14,538][00562] Avg episode reward: [(0, '19.310')]
[2024-11-11 14:28:19,538][00562] Fps is (10 sec: 3685.7, 60 sec: 3891.1, 300 sec: 3887.7). Total num frames: 3219456. Throughput: 0: 982.7. Samples: 805648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:28:19,543][00562] Avg episode reward: [(0, '19.464')]
[2024-11-11 14:28:23,046][03135] Updated weights for policy 0, policy_version 790 (0.0027)
[2024-11-11 14:28:24,536][00562] Fps is (10 sec: 3276.7, 60 sec: 3823.0, 300 sec: 3887.7). Total num frames: 3239936. Throughput: 0: 956.8. Samples: 808016. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:28:24,539][00562] Avg episode reward: [(0, '20.023')]
[2024-11-11 14:28:29,536][00562] Fps is (10 sec: 4506.4, 60 sec: 4027.8, 300 sec: 3929.4). Total num frames: 3264512. Throughput: 0: 978.3. Samples: 815008. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-11-11 14:28:29,538][00562] Avg episode reward: [(0, '20.631')]
[2024-11-11 14:28:32,363][03135] Updated weights for policy 0, policy_version 800 (0.0015)
[2024-11-11 14:28:34,536][00562] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 3280896. Throughput: 0: 995.2. Samples: 820750. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:28:34,542][00562] Avg episode reward: [(0, '21.092')]
[2024-11-11 14:28:34,561][03122] Saving new best policy, reward=21.092!
[2024-11-11 14:28:39,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3887.7). Total num frames: 3297280. Throughput: 0: 966.7. Samples: 822812. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:28:39,538][00562] Avg episode reward: [(0, '20.886')]
[2024-11-11 14:28:43,414][03135] Updated weights for policy 0, policy_version 810 (0.0022)
[2024-11-11 14:28:44,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 3321856. Throughput: 0: 957.8. Samples: 829276. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:28:44,542][00562] Avg episode reward: [(0, '19.328')]
[2024-11-11 14:28:49,536][00562] Fps is (10 sec: 4505.5, 60 sec: 3959.4, 300 sec: 3929.4). Total num frames: 3342336. Throughput: 0: 1011.5. Samples: 835946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:28:49,540][00562] Avg episode reward: [(0, '20.569')]
[2024-11-11 14:28:54,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 3354624. Throughput: 0: 983.5. Samples: 838042. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:28:54,540][00562] Avg episode reward: [(0, '20.043')]
[2024-11-11 14:28:54,723][03135] Updated weights for policy 0, policy_version 820 (0.0017)
[2024-11-11 14:28:59,536][00562] Fps is (10 sec: 3686.5, 60 sec: 3891.3, 300 sec: 3915.5). Total num frames: 3379200. Throughput: 0: 953.2. Samples: 843686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:28:59,542][00562] Avg episode reward: [(0, '18.447')]
[2024-11-11 14:29:03,547][03135] Updated weights for policy 0, policy_version 830 (0.0029)
[2024-11-11 14:29:04,536][00562] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 3403776. Throughput: 0: 1002.9. Samples: 850778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:29:04,541][00562] Avg episode reward: [(0, '18.528')]
[2024-11-11 14:29:09,536][00562] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 3416064. Throughput: 0: 1007.3. Samples: 853346. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:29:09,545][00562] Avg episode reward: [(0, '19.173')]
[2024-11-11 14:29:14,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 3436544. Throughput: 0: 962.7. Samples: 858330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:29:14,543][00562] Avg episode reward: [(0, '18.941')]
[2024-11-11 14:29:14,552][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000839_3436544.pth...
[2024-11-11 14:29:14,688][03122] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000609_2494464.pth
[2024-11-11 14:29:14,788][03135] Updated weights for policy 0, policy_version 840 (0.0025)
[2024-11-11 14:29:19,536][00562] Fps is (10 sec: 4505.7, 60 sec: 4027.9, 300 sec: 3943.3). Total num frames: 3461120. Throughput: 0: 989.2. Samples: 865264. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:29:19,542][00562] Avg episode reward: [(0, '20.902')]
[2024-11-11 14:29:24,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 3477504. Throughput: 0: 1016.5. Samples: 868554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:29:24,542][00562] Avg episode reward: [(0, '21.155')]
[2024-11-11 14:29:24,553][03122] Saving new best policy, reward=21.155!
[2024-11-11 14:29:25,327][03135] Updated weights for policy 0, policy_version 850 (0.0025)
[2024-11-11 14:29:29,536][00562] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 3493888. Throughput: 0: 965.4. Samples: 872718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:29:29,545][00562] Avg episode reward: [(0, '21.123')]
[2024-11-11 14:29:34,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 3518464. Throughput: 0: 969.6. Samples: 879576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:29:34,541][00562] Avg episode reward: [(0, '20.929')]
[2024-11-11 14:29:35,193][03135] Updated weights for policy 0, policy_version 860 (0.0026)
[2024-11-11 14:29:39,536][00562] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 3538944. Throughput: 0: 1002.3. Samples: 883144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:29:39,538][00562] Avg episode reward: [(0, '20.835')]
[2024-11-11 14:29:44,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 3551232. Throughput: 0: 987.0. Samples: 888100. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:29:44,542][00562] Avg episode reward: [(0, '20.317')]
[2024-11-11 14:29:46,450][03135] Updated weights for policy 0, policy_version 870 (0.0030)
[2024-11-11 14:29:49,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 3575808. Throughput: 0: 966.3. Samples: 894262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:29:49,538][00562] Avg episode reward: [(0, '21.075')]
[2024-11-11 14:29:54,536][00562] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3957.2). Total num frames: 3600384. Throughput: 0: 987.7. Samples: 897792. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:29:54,538][00562] Avg episode reward: [(0, '21.177')]
[2024-11-11 14:29:54,546][03122] Saving new best policy, reward=21.177!
[2024-11-11 14:29:55,461][03135] Updated weights for policy 0, policy_version 880 (0.0033)
[2024-11-11 14:29:59,538][00562] Fps is (10 sec: 3685.6, 60 sec: 3891.1, 300 sec: 3929.4). Total num frames: 3612672. Throughput: 0: 998.1. Samples: 903246. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-11-11 14:29:59,542][00562] Avg episode reward: [(0, '19.835')]
[2024-11-11 14:30:04,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 3633152. Throughput: 0: 956.1. Samples: 908288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:30:04,542][00562] Avg episode reward: [(0, '20.637')]
[2024-11-11 14:30:06,895][03135] Updated weights for policy 0, policy_version 890 (0.0029)
[2024-11-11 14:30:09,536][00562] Fps is (10 sec: 4506.6, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 3657728. Throughput: 0: 960.6. Samples: 911780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:30:09,539][00562] Avg episode reward: [(0, '20.359')]
[2024-11-11 14:30:14,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3674112. Throughput: 0: 1016.9. Samples: 918478. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:30:14,542][00562] Avg episode reward: [(0, '19.161')]
[2024-11-11 14:30:18,074][03135] Updated weights for policy 0, policy_version 900 (0.0013)
[2024-11-11 14:30:19,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 3690496. Throughput: 0: 960.4. Samples: 922794. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:30:19,540][00562] Avg episode reward: [(0, '19.307')]
[2024-11-11 14:30:24,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 3715072. Throughput: 0: 959.4. Samples: 926316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:30:24,539][00562] Avg episode reward: [(0, '20.115')]
[2024-11-11 14:30:27,067][03135] Updated weights for policy 0, policy_version 910 (0.0042)
[2024-11-11 14:30:29,536][00562] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 3735552. Throughput: 0: 1002.1. Samples: 933196. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:30:29,540][00562] Avg episode reward: [(0, '20.229')]
[2024-11-11 14:30:34,536][00562] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 3747840. Throughput: 0: 968.5. Samples: 937844. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:30:34,546][00562] Avg episode reward: [(0, '20.060')]
[2024-11-11 14:30:38,637][03135] Updated weights for policy 0, policy_version 920 (0.0019)
[2024-11-11 14:30:39,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 3772416. Throughput: 0: 953.4. Samples: 940696. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:30:39,543][00562] Avg episode reward: [(0, '21.008')]
[2024-11-11 14:30:44,538][00562] Fps is (10 sec: 4504.7, 60 sec: 4027.6, 300 sec: 3943.2). Total num frames: 3792896. Throughput: 0: 985.7. Samples: 947602. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-11-11 14:30:44,544][00562] Avg episode reward: [(0, '22.849')]
[2024-11-11 14:30:44,552][03122] Saving new best policy, reward=22.849!
[2024-11-11 14:30:48,980][03135] Updated weights for policy 0, policy_version 930 (0.0017)
[2024-11-11 14:30:49,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 3809280. Throughput: 0: 987.6. Samples: 952728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:30:49,541][00562] Avg episode reward: [(0, '23.123')]
[2024-11-11 14:30:49,547][03122] Saving new best policy, reward=23.123!
[2024-11-11 14:30:54,536][00562] Fps is (10 sec: 3277.6, 60 sec: 3754.7, 300 sec: 3901.6). Total num frames: 3825664. Throughput: 0: 956.2. Samples: 954808. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:30:54,539][00562] Avg episode reward: [(0, '24.388')]
[2024-11-11 14:30:54,547][03122] Saving new best policy, reward=24.388!
[2024-11-11 14:30:59,079][03135] Updated weights for policy 0, policy_version 940 (0.0023)
[2024-11-11 14:30:59,536][00562] Fps is (10 sec: 4096.0, 60 sec: 3959.6, 300 sec: 3929.4). Total num frames: 3850240. Throughput: 0: 958.2. Samples: 961598. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:30:59,544][00562] Avg episode reward: [(0, '23.414')]
[2024-11-11 14:31:04,536][00562] Fps is (10 sec: 4095.8, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 3866624. Throughput: 0: 996.1. Samples: 967618. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:31:04,544][00562] Avg episode reward: [(0, '23.652')]
[2024-11-11 14:31:09,536][00562] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3901.6). Total num frames: 3883008. Throughput: 0: 966.4. Samples: 969804. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:31:09,538][00562] Avg episode reward: [(0, '24.082')]
[2024-11-11 14:31:10,466][03135] Updated weights for policy 0, policy_version 950 (0.0017)
[2024-11-11 14:31:14,536][00562] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 3907584. Throughput: 0: 950.8. Samples: 975984. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:31:14,538][00562] Avg episode reward: [(0, '21.893')]
[2024-11-11 14:31:14,547][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000954_3907584.pth...
[2024-11-11 14:31:14,665][03122] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000724_2965504.pth
[2024-11-11 14:31:19,537][00562] Fps is (10 sec: 4505.2, 60 sec: 3959.4, 300 sec: 3929.4). Total num frames: 3928064. Throughput: 0: 999.0. Samples: 982798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-11-11 14:31:19,539][00562] Avg episode reward: [(0, '20.911')]
[2024-11-11 14:31:19,945][03135] Updated weights for policy 0, policy_version 960 (0.0022)
[2024-11-11 14:31:24,536][00562] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 3944448. Throughput: 0: 981.1. Samples: 984846. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:31:24,543][00562] Avg episode reward: [(0, '22.390')]
[2024-11-11 14:31:29,536][00562] Fps is (10 sec: 3686.7, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 3964928. Throughput: 0: 944.8. Samples: 990116. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-11-11 14:31:29,540][00562] Avg episode reward: [(0, '21.640')]
[2024-11-11 14:31:31,036][03135] Updated weights for policy 0, policy_version 970 (0.0018)
[2024-11-11 14:31:34,536][00562] Fps is (10 sec: 4505.7, 60 sec: 4027.8, 300 sec: 3943.3). Total num frames: 3989504. Throughput: 0: 985.9. Samples: 997094. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-11-11 14:31:34,545][00562] Avg episode reward: [(0, '21.698')]
[2024-11-11 14:31:39,536][00562] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 4001792. Throughput: 0: 1002.7. Samples: 999930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-11-11 14:31:39,546][00562] Avg episode reward: [(0, '21.392')]
[2024-11-11 14:31:39,657][03122] Stopping Batcher_0...
[2024-11-11 14:31:39,659][03122] Loop batcher_evt_loop terminating...
[2024-11-11 14:31:39,664][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-11-11 14:31:39,660][00562] Component Batcher_0 stopped!
[2024-11-11 14:31:39,766][03135] Weights refcount: 2 0
[2024-11-11 14:31:39,772][00562] Component InferenceWorker_p0-w0 stopped!
[2024-11-11 14:31:39,778][03135] Stopping InferenceWorker_p0-w0...
[2024-11-11 14:31:39,778][03135] Loop inference_proc0-0_evt_loop terminating...
[2024-11-11 14:31:39,854][03122] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000839_3436544.pth
[2024-11-11 14:31:39,872][03122] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-11-11 14:31:40,081][00562] Component LearnerWorker_p0 stopped!
[2024-11-11 14:31:40,088][03122] Stopping LearnerWorker_p0...
[2024-11-11 14:31:40,088][03122] Loop learner_proc0_evt_loop terminating...
[2024-11-11 14:31:40,394][00562] Component RolloutWorker_w1 stopped!
[2024-11-11 14:31:40,405][03137] Stopping RolloutWorker_w1...
[2024-11-11 14:31:40,405][03137] Loop rollout_proc1_evt_loop terminating...
[2024-11-11 14:31:40,449][03143] Stopping RolloutWorker_w7...
[2024-11-11 14:31:40,451][00562] Component RolloutWorker_w7 stopped!
[2024-11-11 14:31:40,450][03143] Loop rollout_proc7_evt_loop terminating...
[2024-11-11 14:31:40,471][03141] Stopping RolloutWorker_w5...
[2024-11-11 14:31:40,472][03141] Loop rollout_proc5_evt_loop terminating...
[2024-11-11 14:31:40,473][00562] Component RolloutWorker_w5 stopped!
[2024-11-11 14:31:40,483][00562] Component RolloutWorker_w3 stopped!
[2024-11-11 14:31:40,490][03139] Stopping RolloutWorker_w3...
[2024-11-11 14:31:40,490][03139] Loop rollout_proc3_evt_loop terminating...
[2024-11-11 14:31:40,541][03138] Stopping RolloutWorker_w2...
[2024-11-11 14:31:40,540][00562] Component RolloutWorker_w2 stopped!
[2024-11-11 14:31:40,541][03138] Loop rollout_proc2_evt_loop terminating...
[2024-11-11 14:31:40,577][03140] Stopping RolloutWorker_w4...
[2024-11-11 14:31:40,577][03140] Loop rollout_proc4_evt_loop terminating...
[2024-11-11 14:31:40,577][00562] Component RolloutWorker_w4 stopped!
[2024-11-11 14:31:40,591][00562] Component RolloutWorker_w0 stopped!
[2024-11-11 14:31:40,590][03136] Stopping RolloutWorker_w0...
[2024-11-11 14:31:40,593][03136] Loop rollout_proc0_evt_loop terminating...
[2024-11-11 14:31:40,636][00562] Component RolloutWorker_w6 stopped!
[2024-11-11 14:31:40,638][00562] Waiting for process learner_proc0 to stop...
[2024-11-11 14:31:40,641][03142] Stopping RolloutWorker_w6...
[2024-11-11 14:31:40,641][03142] Loop rollout_proc6_evt_loop terminating...
[2024-11-11 14:31:41,983][00562] Waiting for process inference_proc0-0 to join...
[2024-11-11 14:31:41,987][00562] Waiting for process rollout_proc0 to join...
[2024-11-11 14:31:44,119][00562] Waiting for process rollout_proc1 to join...
[2024-11-11 14:31:44,143][00562] Waiting for process rollout_proc2 to join...
[2024-11-11 14:31:44,149][00562] Waiting for process rollout_proc3 to join...
[2024-11-11 14:31:44,154][00562] Waiting for process rollout_proc4 to join...
[2024-11-11 14:31:44,157][00562] Waiting for process rollout_proc5 to join...
[2024-11-11 14:31:44,161][00562] Waiting for process rollout_proc6 to join...
[2024-11-11 14:31:44,164][00562] Waiting for process rollout_proc7 to join...
[2024-11-11 14:31:44,167][00562] Batcher 0 profile tree view:
batching: 28.3437, releasing_batches: 0.0330
[2024-11-11 14:31:44,170][00562] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0025
  wait_policy_total: 436.3030
update_model: 8.7112
  weight_update: 0.0019
one_step: 0.0036
  handle_policy_step: 583.4895
    deserialize: 15.2080, stack: 3.1268, obs_to_device_normalize: 124.0045, forward: 294.0283, send_messages: 29.0137
    prepare_outputs: 88.5107
      to_cpu: 52.8766
[2024-11-11 14:31:44,172][00562] Learner 0 profile tree view:
misc: 0.0051, prepare_batch: 13.6783
train: 75.4392
  epoch_init: 0.0055, minibatch_init: 0.0159, losses_postprocess: 0.5740, kl_divergence: 0.5243, after_optimizer: 33.4716
  calculate_losses: 27.7655
    losses_init: 0.0037, forward_head: 1.4214, bptt_initial: 18.8187, tail: 1.2498, advantages_returns: 0.2608, losses: 3.7434
    bptt: 1.9478
      bptt_forward_core: 1.8665
  update: 12.4283
    clip: 1.0064
[2024-11-11 14:31:44,174][00562] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.4060, enqueue_policy_requests: 106.8350, env_step: 839.8568, overhead: 14.1801, complete_rollouts: 7.3456
save_policy_outputs: 22.4906
  split_output_tensors: 8.6830
[2024-11-11 14:31:44,176][00562] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.3708, enqueue_policy_requests: 109.4797, env_step: 834.1560, overhead: 14.2467, complete_rollouts: 7.0637
save_policy_outputs: 21.3815
  split_output_tensors: 8.4240
[2024-11-11 14:31:44,178][00562] Loop Runner_EvtLoop terminating...
[2024-11-11 14:31:44,180][00562] Runner profile tree view:
main_loop: 1103.4782
[2024-11-11 14:31:44,181][00562] Collected {0: 4005888}, FPS: 3630.2
[2024-11-11 14:31:56,379][00562] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-11-11 14:31:56,381][00562] Overriding arg 'num_workers' with value 1 passed from command line
[2024-11-11 14:31:56,383][00562] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-11-11 14:31:56,385][00562] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-11-11 14:31:56,387][00562] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-11-11 14:31:56,388][00562] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-11-11 14:31:56,389][00562] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2024-11-11 14:31:56,391][00562] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-11-11 14:31:56,392][00562] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2024-11-11 14:31:56,393][00562] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2024-11-11 14:31:56,394][00562] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-11-11 14:31:56,395][00562] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-11-11 14:31:56,396][00562] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-11-11 14:31:56,397][00562] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-11-11 14:31:56,398][00562] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-11-11 14:31:56,446][00562] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-11-11 14:31:56,450][00562] RunningMeanStd input shape: (3, 72, 128)
[2024-11-11 14:31:56,453][00562] RunningMeanStd input shape: (1,)
[2024-11-11 14:31:56,468][00562] ConvEncoder: input_channels=3
[2024-11-11 14:31:56,569][00562] Conv encoder output size: 512
[2024-11-11 14:31:56,571][00562] Policy head output size: 512
[2024-11-11 14:31:56,748][00562] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-11-11 14:31:57,562][00562] Num frames 100...
[2024-11-11 14:31:57,684][00562] Num frames 200...
[2024-11-11 14:31:57,807][00562] Num frames 300...
[2024-11-11 14:31:57,936][00562] Num frames 400...
[2024-11-11 14:31:58,058][00562] Num frames 500...
[2024-11-11 14:31:58,185][00562] Num frames 600...
[2024-11-11 14:31:58,309][00562] Num frames 700...
[2024-11-11 14:31:58,449][00562] Avg episode rewards: #0: 18.690, true rewards: #0: 7.690
[2024-11-11 14:31:58,451][00562] Avg episode reward: 18.690, avg true_objective: 7.690
[2024-11-11 14:31:58,493][00562] Num frames 800...
[2024-11-11 14:31:58,614][00562] Num frames 900...
[2024-11-11 14:31:58,737][00562] Num frames 1000...
[2024-11-11 14:31:58,857][00562] Num frames 1100...
[2024-11-11 14:31:58,999][00562] Num frames 1200...
[2024-11-11 14:31:59,134][00562] Num frames 1300...
[2024-11-11 14:31:59,257][00562] Num frames 1400...
[2024-11-11 14:31:59,325][00562] Avg episode rewards: #0: 14.545, true rewards: #0: 7.045
[2024-11-11 14:31:59,326][00562] Avg episode reward: 14.545, avg true_objective: 7.045
[2024-11-11 14:31:59,436][00562] Num frames 1500...
[2024-11-11 14:31:59,558][00562] Num frames 1600...
[2024-11-11 14:31:59,682][00562] Num frames 1700...
[2024-11-11 14:31:59,804][00562] Num frames 1800...
[2024-11-11 14:31:59,925][00562] Num frames 1900...
[2024-11-11 14:32:00,054][00562] Num frames 2000...
[2024-11-11 14:32:00,184][00562] Num frames 2100...
[2024-11-11 14:32:00,310][00562] Num frames 2200...
[2024-11-11 14:32:00,433][00562] Num frames 2300...
[2024-11-11 14:32:00,554][00562] Num frames 2400...
[2024-11-11 14:32:00,676][00562] Num frames 2500...
[2024-11-11 14:32:00,797][00562] Num frames 2600...
[2024-11-11 14:32:00,918][00562] Num frames 2700...
[2024-11-11 14:32:01,046][00562] Num frames 2800...
[2024-11-11 14:32:01,177][00562] Num frames 2900...
[2024-11-11 14:32:01,303][00562] Num frames 3000...
[2024-11-11 14:32:01,425][00562] Num frames 3100...
[2024-11-11 14:32:01,546][00562] Num frames 3200...
[2024-11-11 14:32:01,658][00562] Avg episode rewards: #0: 23.487, true rewards: #0: 10.820
[2024-11-11 14:32:01,659][00562] Avg episode reward: 23.487, avg true_objective: 10.820
[2024-11-11 14:32:01,727][00562] Num frames 3300...
[2024-11-11 14:32:01,850][00562] Num frames 3400...
[2024-11-11 14:32:01,969][00562] Num frames 3500...
[2024-11-11 14:32:02,102][00562] Num frames 3600...
[2024-11-11 14:32:02,271][00562] Avg episode rewards: #0: 20.220, true rewards: #0: 9.220
[2024-11-11 14:32:02,273][00562] Avg episode reward: 20.220, avg true_objective: 9.220
[2024-11-11 14:32:02,299][00562] Num frames 3700...
[2024-11-11 14:32:02,467][00562] Num frames 3800...
[2024-11-11 14:32:02,632][00562] Num frames 3900...
[2024-11-11 14:32:02,795][00562] Num frames 4000...
[2024-11-11 14:32:02,960][00562] Num frames 4100...
[2024-11-11 14:32:03,131][00562] Num frames 4200...
[2024-11-11 14:32:03,295][00562] Num frames 4300...
[2024-11-11 14:32:03,462][00562] Num frames 4400...
[2024-11-11 14:32:03,635][00562] Num frames 4500...
[2024-11-11 14:32:03,813][00562] Num frames 4600...
[2024-11-11 14:32:03,987][00562] Num frames 4700...
[2024-11-11 14:32:04,175][00562] Num frames 4800...
[2024-11-11 14:32:04,247][00562] Avg episode rewards: #0: 20.816, true rewards: #0: 9.616
[2024-11-11 14:32:04,249][00562] Avg episode reward: 20.816, avg true_objective: 9.616
[2024-11-11 14:32:04,413][00562] Num frames 4900...
[2024-11-11 14:32:04,546][00562] Num frames 5000...
[2024-11-11 14:32:04,668][00562] Num frames 5100...
[2024-11-11 14:32:04,787][00562] Num frames 5200...
[2024-11-11 14:32:04,904][00562] Num frames 5300...
[2024-11-11 14:32:05,020][00562] Avg episode rewards: #0: 18.587, true rewards: #0: 8.920
[2024-11-11 14:32:05,022][00562] Avg episode reward: 18.587, avg true_objective: 8.920
[2024-11-11 14:32:05,084][00562] Num frames 5400...
[2024-11-11 14:32:05,221][00562] Num frames 5500...
[2024-11-11 14:32:05,342][00562] Num frames 5600...
[2024-11-11 14:32:05,465][00562] Num frames 5700...
[2024-11-11 14:32:05,583][00562] Num frames 5800...
[2024-11-11 14:32:05,703][00562] Num frames 5900...
[2024-11-11 14:32:05,823][00562] Num frames 6000...
[2024-11-11 14:32:05,954][00562] Num frames 6100...
[2024-11-11 14:32:06,132][00562] Avg episode rewards: #0: 18.704, true rewards: #0: 8.847
[2024-11-11 14:32:06,133][00562] Avg episode reward: 18.704, avg true_objective: 8.847
[2024-11-11 14:32:06,145][00562] Num frames 6200...
[2024-11-11 14:32:06,276][00562] Num frames 6300...
[2024-11-11 14:32:06,398][00562] Num frames 6400...
[2024-11-11 14:32:06,517][00562] Num frames 6500...
[2024-11-11 14:32:06,636][00562] Num frames 6600...
[2024-11-11 14:32:06,754][00562] Num frames 6700...
[2024-11-11 14:32:06,875][00562] Num frames 6800...
[2024-11-11 14:32:06,997][00562] Num frames 6900...
[2024-11-11 14:32:07,135][00562] Num frames 7000...
[2024-11-11 14:32:07,243][00562] Avg episode rewards: #0: 18.555, true rewards: #0: 8.805
[2024-11-11 14:32:07,245][00562] Avg episode reward: 18.555, avg true_objective: 8.805
[2024-11-11 14:32:07,315][00562] Num frames 7100...
[2024-11-11 14:32:07,436][00562] Num frames 7200...
[2024-11-11 14:32:07,556][00562] Num frames 7300...
[2024-11-11 14:32:07,674][00562] Num frames 7400...
[2024-11-11 14:32:07,796][00562] Num frames 7500...
[2024-11-11 14:32:07,915][00562] Num frames 7600...
[2024-11-11 14:32:08,037][00562] Num frames 7700...
[2024-11-11 14:32:08,167][00562] Num frames 7800...
[2024-11-11 14:32:08,295][00562] Num frames 7900...
[2024-11-11 14:32:08,416][00562] Num frames 8000...
[2024-11-11 14:32:08,535][00562] Num frames 8100...
[2024-11-11 14:32:08,656][00562] Num frames 8200...
[2024-11-11 14:32:08,777][00562] Num frames 8300...
[2024-11-11 14:32:08,900][00562] Num frames 8400...
[2024-11-11 14:32:09,020][00562] Num frames 8500...
[2024-11-11 14:32:09,147][00562] Num frames 8600...
[2024-11-11 14:32:09,275][00562] Num frames 8700...
[2024-11-11 14:32:09,398][00562] Num frames 8800...
[2024-11-11 14:32:09,519][00562] Num frames 8900...
[2024-11-11 14:32:09,641][00562] Num frames 9000...
[2024-11-11 14:32:09,763][00562] Num frames 9100...
[2024-11-11 14:32:09,871][00562] Avg episode rewards: #0: 22.715, true rewards: #0: 10.160
[2024-11-11 14:32:09,872][00562] Avg episode reward: 22.715, avg true_objective: 10.160
[2024-11-11 14:32:09,944][00562] Num frames 9200...
[2024-11-11 14:32:10,061][00562] Num frames 9300...
[2024-11-11 14:32:10,193][00562] Num frames 9400...
[2024-11-11 14:32:10,320][00562] Num frames 9500...
[2024-11-11 14:32:10,442][00562] Num frames 9600...
[2024-11-11 14:32:10,564][00562] Avg episode rewards: #0: 21.256, true rewards: #0: 9.656
[2024-11-11 14:32:10,565][00562] Avg episode reward: 21.256, avg true_objective: 9.656
[2024-11-11 14:33:08,223][00562] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2024-11-11 14:41:13,430][00562] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-11-11 14:41:13,432][00562] Overriding arg 'num_workers' with value 1 passed from command line
[2024-11-11 14:41:13,434][00562] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-11-11 14:41:13,435][00562] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-11-11 14:41:13,437][00562] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-11-11 14:41:13,439][00562] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-11-11 14:41:13,441][00562] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2024-11-11 14:41:13,442][00562] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-11-11 14:41:13,443][00562] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2024-11-11 14:41:13,444][00562] Adding new argument 'hf_repository'='usamabuttar/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2024-11-11 14:41:13,445][00562] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-11-11 14:41:13,446][00562] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-11-11 14:41:13,447][00562] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-11-11 14:41:13,448][00562] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-11-11 14:41:13,449][00562] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-11-11 14:41:13,478][00562] RunningMeanStd input shape: (3, 72, 128)
[2024-11-11 14:41:13,480][00562] RunningMeanStd input shape: (1,)
[2024-11-11 14:41:13,492][00562] ConvEncoder: input_channels=3
[2024-11-11 14:41:13,529][00562] Conv encoder output size: 512
[2024-11-11 14:41:13,530][00562] Policy head output size: 512
[2024-11-11 14:41:13,551][00562] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-11-11 14:41:13,972][00562] Num frames 100...
[2024-11-11 14:41:14,107][00562] Num frames 200...
[2024-11-11 14:41:14,247][00562] Num frames 300...
[2024-11-11 14:41:14,369][00562] Num frames 400...
[2024-11-11 14:41:14,489][00562] Num frames 500...
[2024-11-11 14:41:14,614][00562] Num frames 600...
[2024-11-11 14:41:14,732][00562] Num frames 700...
[2024-11-11 14:41:14,866][00562] Num frames 800...
[2024-11-11 14:41:14,988][00562] Num frames 900...
[2024-11-11 14:41:15,110][00562] Num frames 1000...
[2024-11-11 14:41:15,240][00562] Num frames 1100...
[2024-11-11 14:41:15,363][00562] Num frames 1200...
[2024-11-11 14:41:15,482][00562] Num frames 1300...
[2024-11-11 14:41:15,603][00562] Num frames 1400...
[2024-11-11 14:41:15,727][00562] Num frames 1500...
[2024-11-11 14:41:15,847][00562] Num frames 1600...
[2024-11-11 14:41:15,969][00562] Num frames 1700...
[2024-11-11 14:41:16,089][00562] Num frames 1800...
[2024-11-11 14:41:16,214][00562] Num frames 1900...
[2024-11-11 14:41:16,343][00562] Num frames 2000...
[2024-11-11 14:41:16,469][00562] Num frames 2100...
[2024-11-11 14:41:16,521][00562] Avg episode rewards: #0: 59.999, true rewards: #0: 21.000
[2024-11-11 14:41:16,524][00562] Avg episode reward: 59.999, avg true_objective: 21.000
[2024-11-11 14:41:16,643][00562] Num frames 2200...
[2024-11-11 14:41:16,761][00562] Num frames 2300...
[2024-11-11 14:41:16,875][00562] Num frames 2400...
[2024-11-11 14:41:16,993][00562] Num frames 2500...
[2024-11-11 14:41:17,115][00562] Num frames 2600...
[2024-11-11 14:41:17,236][00562] Num frames 2700...
[2024-11-11 14:41:17,363][00562] Num frames 2800...
[2024-11-11 14:41:17,485][00562] Num frames 2900...
[2024-11-11 14:41:17,603][00562] Num frames 3000...
[2024-11-11 14:41:17,724][00562] Num frames 3100...
[2024-11-11 14:41:17,848][00562] Num frames 3200...
[2024-11-11 14:41:17,937][00562] Avg episode rewards: #0: 41.600, true rewards: #0: 16.100
[2024-11-11 14:41:17,940][00562] Avg episode reward: 41.600, avg true_objective: 16.100
[2024-11-11 14:41:18,074][00562] Num frames 3300...
[2024-11-11 14:41:18,236][00562] Num frames 3400...
[2024-11-11 14:41:18,407][00562] Num frames 3500...
[2024-11-11 14:41:18,570][00562] Num frames 3600...
[2024-11-11 14:41:18,738][00562] Num frames 3700...
[2024-11-11 14:41:18,899][00562] Num frames 3800...
[2024-11-11 14:41:19,060][00562] Num frames 3900...
[2024-11-11 14:41:19,233][00562] Num frames 4000...
[2024-11-11 14:41:19,416][00562] Num frames 4100...
[2024-11-11 14:41:19,591][00562] Num frames 4200...
[2024-11-11 14:41:19,766][00562] Num frames 4300...
[2024-11-11 14:41:19,941][00562] Num frames 4400...
[2024-11-11 14:41:20,124][00562] Num frames 4500...
[2024-11-11 14:41:20,297][00562] Num frames 4600...
[2024-11-11 14:41:20,452][00562] Num frames 4700...
[2024-11-11 14:41:20,577][00562] Num frames 4800...
[2024-11-11 14:41:20,701][00562] Num frames 4900...
[2024-11-11 14:41:20,822][00562] Num frames 5000...
[2024-11-11 14:41:20,946][00562] Num frames 5100...
[2024-11-11 14:41:21,066][00562] Num frames 5200...
[2024-11-11 14:41:21,195][00562] Num frames 5300...
[2024-11-11 14:41:21,276][00562] Avg episode rewards: #0: 45.733, true rewards: #0: 17.733
[2024-11-11 14:41:21,278][00562] Avg episode reward: 45.733, avg true_objective: 17.733
[2024-11-11 14:41:21,380][00562] Num frames 5400...
[2024-11-11 14:41:21,505][00562] Num frames 5500...
[2024-11-11 14:41:21,624][00562] Num frames 5600...
[2024-11-11 14:41:21,747][00562] Num frames 5700...
[2024-11-11 14:41:21,899][00562] Num frames 5800...
[2024-11-11 14:41:22,018][00562] Num frames 5900...
[2024-11-11 14:41:22,170][00562] Avg episode rewards: #0: 37.435, true rewards: #0: 14.935
[2024-11-11 14:41:22,172][00562] Avg episode reward: 37.435, avg true_objective: 14.935
[2024-11-11 14:41:22,206][00562] Num frames 6000...
[2024-11-11 14:41:22,325][00562] Num frames 6100...
[2024-11-11 14:41:22,454][00562] Num frames 6200...
[2024-11-11 14:41:22,607][00562] Num frames 6300...
[2024-11-11 14:41:22,728][00562] Num frames 6400...
[2024-11-11 14:41:22,845][00562] Num frames 6500...
[2024-11-11 14:41:22,965][00562] Num frames 6600...
[2024-11-11 14:41:23,085][00562] Num frames 6700...
[2024-11-11 14:41:23,213][00562] Num frames 6800...
[2024-11-11 14:41:23,334][00562] Num frames 6900...
[2024-11-11 14:41:23,466][00562] Num frames 7000...
[2024-11-11 14:41:23,598][00562] Num frames 7100...
[2024-11-11 14:41:23,720][00562] Num frames 7200...
[2024-11-11 14:41:23,843][00562] Num frames 7300...
[2024-11-11 14:41:23,963][00562] Num frames 7400...
[2024-11-11 14:41:24,073][00562] Avg episode rewards: #0: 36.892, true rewards: #0: 14.892
[2024-11-11 14:41:24,075][00562] Avg episode reward: 36.892, avg true_objective: 14.892
[2024-11-11 14:41:24,148][00562] Num frames 7500...
[2024-11-11 14:41:24,267][00562] Num frames 7600...
[2024-11-11 14:41:24,388][00562] Num frames 7700...
[2024-11-11 14:41:24,517][00562] Num frames 7800...
[2024-11-11 14:41:24,610][00562] Avg episode rewards: #0: 31.383, true rewards: #0: 13.050
[2024-11-11 14:41:24,612][00562] Avg episode reward: 31.383, avg true_objective: 13.050
[2024-11-11 14:41:24,699][00562] Num frames 7900...
[2024-11-11 14:41:24,817][00562] Num frames 8000...
[2024-11-11 14:41:24,937][00562] Num frames 8100...
[2024-11-11 14:41:25,058][00562] Num frames 8200...
[2024-11-11 14:41:25,185][00562] Num frames 8300...
[2024-11-11 14:41:25,311][00562] Num frames 8400...
[2024-11-11 14:41:25,431][00562] Num frames 8500...
[2024-11-11 14:41:25,559][00562] Num frames 8600...
[2024-11-11 14:41:25,690][00562] Num frames 8700...
[2024-11-11 14:41:25,809][00562] Num frames 8800...
[2024-11-11 14:41:25,930][00562] Num frames 8900...
[2024-11-11 14:41:26,084][00562] Avg episode rewards: #0: 30.403, true rewards: #0: 12.831
[2024-11-11 14:41:26,086][00562] Avg episode reward: 30.403, avg true_objective: 12.831
[2024-11-11 14:41:26,118][00562] Num frames 9000...
[2024-11-11 14:41:26,241][00562] Num frames 9100...
[2024-11-11 14:41:26,362][00562] Num frames 9200...
[2024-11-11 14:41:26,485][00562] Num frames 9300...
[2024-11-11 14:41:26,645][00562] Num frames 9400...
[2024-11-11 14:41:26,768][00562] Num frames 9500...
[2024-11-11 14:41:26,856][00562] Avg episode rewards: #0: 27.657, true rewards: #0: 11.908
[2024-11-11 14:41:26,858][00562] Avg episode reward: 27.657, avg true_objective: 11.908
[2024-11-11 14:41:26,948][00562] Num frames 9600...
[2024-11-11 14:41:27,067][00562] Num frames 9700...
[2024-11-11 14:41:27,195][00562] Num frames 9800...
[2024-11-11 14:41:27,316][00562] Num frames 9900...
[2024-11-11 14:41:27,440][00562] Num frames 10000...
[2024-11-11 14:41:27,562][00562] Num frames 10100...
[2024-11-11 14:41:27,693][00562] Num frames 10200...
[2024-11-11 14:41:27,861][00562] Avg episode rewards: #0: 25.993, true rewards: #0: 11.438
[2024-11-11 14:41:27,863][00562] Avg episode reward: 25.993, avg true_objective: 11.438
[2024-11-11 14:41:27,874][00562] Num frames 10300...
[2024-11-11 14:41:27,998][00562] Num frames 10400...
[2024-11-11 14:41:28,081][00562] Avg episode rewards: #0: 23.522, true rewards: #0: 10.422
[2024-11-11 14:41:28,082][00562] Avg episode reward: 23.522, avg true_objective: 10.422
[2024-11-11 14:42:30,928][00562] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2024-11-11 14:42:38,969][00562] The model has been pushed to https://huggingface.co/usamabuttar/rl_course_vizdoom_health_gathering_supreme
[2024-11-11 14:45:46,383][00562] Loading legacy config file train_dir/doom_health_gathering_supreme_2222/cfg.json instead of train_dir/doom_health_gathering_supreme_2222/config.json
[2024-11-11 14:45:46,385][00562] Loading existing experiment configuration from train_dir/doom_health_gathering_supreme_2222/config.json
[2024-11-11 14:45:46,387][00562] Overriding arg 'experiment' with value 'doom_health_gathering_supreme_2222' passed from command line
[2024-11-11 14:45:46,389][00562] Overriding arg 'train_dir' with value 'train_dir' passed from command line
[2024-11-11 14:45:46,390][00562] Overriding arg 'num_workers' with value 1 passed from command line
[2024-11-11 14:45:46,396][00562] Adding new argument 'lr_adaptive_min'=1e-06 that is not in the saved config file!
[2024-11-11 14:45:46,397][00562] Adding new argument 'lr_adaptive_max'=0.01 that is not in the saved config file!
[2024-11-11 14:45:46,398][00562] Adding new argument 'env_gpu_observations'=True that is not in the saved config file!
[2024-11-11 14:45:46,401][00562] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-11-11 14:45:46,402][00562] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-11-11 14:45:46,403][00562] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-11-11 14:45:46,404][00562] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-11-11 14:45:46,405][00562] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2024-11-11 14:45:46,407][00562] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-11-11 14:45:46,408][00562] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2024-11-11 14:45:46,409][00562] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2024-11-11 14:45:46,410][00562] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-11-11 14:45:46,410][00562] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-11-11 14:45:46,411][00562] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-11-11 14:45:46,412][00562] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-11-11 14:45:46,414][00562] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-11-11 14:45:46,458][00562] RunningMeanStd input shape: (3, 72, 128)
[2024-11-11 14:45:46,460][00562] RunningMeanStd input shape: (1,)
[2024-11-11 14:45:46,472][00562] ConvEncoder: input_channels=3
[2024-11-11 14:45:46,522][00562] Conv encoder output size: 512
[2024-11-11 14:45:46,524][00562] Policy head output size: 512
[2024-11-11 14:45:46,546][00562] Loading state from checkpoint train_dir/doom_health_gathering_supreme_2222/checkpoint_p0/checkpoint_000539850_4422451200.pth...
[2024-11-11 14:45:46,964][00562] Num frames 100...
[2024-11-11 14:45:47,093][00562] Num frames 200...
[2024-11-11 14:45:47,243][00562] Num frames 300...
[2024-11-11 14:45:47,373][00562] Num frames 400...
[2024-11-11 14:45:47,505][00562] Num frames 500...
[2024-11-11 14:45:47,627][00562] Num frames 600...
[2024-11-11 14:45:47,752][00562] Num frames 700...
[2024-11-11 14:45:47,877][00562] Num frames 800...
[2024-11-11 14:45:48,011][00562] Num frames 900...
[2024-11-11 14:45:48,141][00562] Num frames 1000...
[2024-11-11 14:45:48,263][00562] Num frames 1100...
[2024-11-11 14:45:48,387][00562] Num frames 1200...
[2024-11-11 14:45:48,521][00562] Num frames 1300...
[2024-11-11 14:45:48,640][00562] Num frames 1400...
[2024-11-11 14:45:48,762][00562] Num frames 1500...
[2024-11-11 14:45:48,886][00562] Num frames 1600...
[2024-11-11 14:45:49,006][00562] Num frames 1700...
[2024-11-11 14:45:49,132][00562] Num frames 1800...
[2024-11-11 14:45:49,251][00562] Num frames 1900...
[2024-11-11 14:45:49,381][00562] Num frames 2000...
[2024-11-11 14:45:49,511][00562] Num frames 2100...
[2024-11-11 14:45:49,564][00562] Avg episode rewards: #0: 65.998, true rewards: #0: 21.000
[2024-11-11 14:45:49,567][00562] Avg episode reward: 65.998, avg true_objective: 21.000
[2024-11-11 14:45:49,685][00562] Num frames 2200...
[2024-11-11 14:45:49,804][00562] Num frames 2300...
[2024-11-11 14:45:49,925][00562] Num frames 2400...
[2024-11-11 14:45:50,044][00562] Num frames 2500...
[2024-11-11 14:45:50,174][00562] Num frames 2600...
[2024-11-11 14:45:50,292][00562] Num frames 2700...
[2024-11-11 14:45:50,418][00562] Num frames 2800...
[2024-11-11 14:45:50,548][00562] Num frames 2900...
[2024-11-11 14:45:50,672][00562] Num frames 3000...
[2024-11-11 14:45:50,795][00562] Num frames 3100...
[2024-11-11 14:45:50,918][00562] Num frames 3200...
[2024-11-11 14:45:51,039][00562] Num frames 3300...
[2024-11-11 14:45:51,166][00562] Num frames 3400...
[2024-11-11 14:45:51,294][00562] Num frames 3500...
[2024-11-11 14:45:51,420][00562] Num frames 3600...
[2024-11-11 14:45:51,542][00562] Num frames 3700...
[2024-11-11 14:45:51,670][00562] Num frames 3800...
[2024-11-11 14:45:51,796][00562] Num frames 3900...
[2024-11-11 14:45:51,916][00562] Num frames 4000...
[2024-11-11 14:45:52,040][00562] Num frames 4100...
[2024-11-11 14:45:52,176][00562] Num frames 4200...
[2024-11-11 14:45:52,228][00562] Avg episode rewards: #0: 63.999, true rewards: #0: 21.000
[2024-11-11 14:45:52,230][00562] Avg episode reward: 63.999, avg true_objective: 21.000
[2024-11-11 14:45:52,363][00562] Num frames 4300...
[2024-11-11 14:45:52,491][00562] Num frames 4400...
[2024-11-11 14:45:52,625][00562] Num frames 4500...
[2024-11-11 14:45:52,786][00562] Num frames 4600...
[2024-11-11 14:45:52,956][00562] Num frames 4700...
[2024-11-11 14:45:53,124][00562] Num frames 4800...
[2024-11-11 14:45:53,284][00562] Num frames 4900...
[2024-11-11 14:45:53,450][00562] Num frames 5000...
[2024-11-11 14:45:53,623][00562] Num frames 5100...
[2024-11-11 14:45:53,794][00562] Num frames 5200...
[2024-11-11 14:45:53,959][00562] Num frames 5300...
[2024-11-11 14:45:54,134][00562] Num frames 5400...
[2024-11-11 14:45:54,309][00562] Num frames 5500...
[2024-11-11 14:45:54,499][00562] Num frames 5600...
[2024-11-11 14:45:54,676][00562] Num frames 5700...
[2024-11-11 14:45:54,861][00562] Num frames 5800...
[2024-11-11 14:45:55,035][00562] Num frames 5900...
[2024-11-11 14:45:55,207][00562] Num frames 6000...
[2024-11-11 14:45:55,329][00562] Num frames 6100...
[2024-11-11 14:45:55,453][00562] Num frames 6200...
[2024-11-11 14:45:55,580][00562] Num frames 6300...
[2024-11-11 14:45:55,633][00562] Avg episode rewards: #0: 65.332, true rewards: #0: 21.000
[2024-11-11 14:45:55,634][00562] Avg episode reward: 65.332, avg true_objective: 21.000
[2024-11-11 14:45:55,771][00562] Num frames 6400...
[2024-11-11 14:45:55,897][00562] Num frames 6500...
[2024-11-11 14:45:56,019][00562] Num frames 6600...
[2024-11-11 14:45:56,148][00562] Num frames 6700...
[2024-11-11 14:45:56,271][00562] Num frames 6800...
[2024-11-11 14:45:56,393][00562] Num frames 6900...
[2024-11-11 14:45:56,515][00562] Num frames 7000...
[2024-11-11 14:45:56,636][00562] Num frames 7100...
[2024-11-11 14:45:56,756][00562] Num frames 7200...
[2024-11-11 14:45:56,884][00562] Num frames 7300...
[2024-11-11 14:45:57,003][00562] Num frames 7400...
[2024-11-11 14:45:57,131][00562] Num frames 7500...
[2024-11-11 14:45:57,251][00562] Num frames 7600...
[2024-11-11 14:45:57,375][00562] Num frames 7700...
[2024-11-11 14:45:57,497][00562] Num frames 7800...
[2024-11-11 14:45:57,621][00562] Num frames 7900...
[2024-11-11 14:45:57,772][00562] Num frames 8000...
[2024-11-11 14:45:57,908][00562] Num frames 8100...
[2024-11-11 14:45:58,033][00562] Num frames 8200...
[2024-11-11 14:45:58,171][00562] Num frames 8300...
[2024-11-11 14:45:58,304][00562] Num frames 8400...
[2024-11-11 14:45:58,356][00562] Avg episode rewards: #0: 65.499, true rewards: #0: 21.000
[2024-11-11 14:45:58,358][00562] Avg episode reward: 65.499, avg true_objective: 21.000
[2024-11-11 14:45:58,482][00562] Num frames 8500...
[2024-11-11 14:45:58,607][00562] Num frames 8600...
[2024-11-11 14:45:58,727][00562] Num frames 8700...
[2024-11-11 14:45:58,857][00562] Num frames 8800...
[2024-11-11 14:45:58,986][00562] Num frames 8900...
[2024-11-11 14:45:59,121][00562] Num frames 9000...
[2024-11-11 14:45:59,242][00562] Num frames 9100...
[2024-11-11 14:45:59,368][00562] Num frames 9200...
[2024-11-11 14:45:59,499][00562] Num frames 9300...
[2024-11-11 14:45:59,621][00562] Num frames 9400...
[2024-11-11 14:45:59,745][00562] Num frames 9500...
[2024-11-11 14:45:59,873][00562] Num frames 9600...
[2024-11-11 14:45:59,998][00562] Num frames 9700...
[2024-11-11 14:46:00,127][00562] Num frames 9800...
[2024-11-11 14:46:00,247][00562] Num frames 9900...
[2024-11-11 14:46:00,371][00562] Num frames 10000...
[2024-11-11 14:46:00,494][00562] Num frames 10100...
[2024-11-11 14:46:00,616][00562] Num frames 10200...
[2024-11-11 14:46:00,738][00562] Num frames 10300...
[2024-11-11 14:46:00,860][00562] Num frames 10400...
[2024-11-11 14:46:00,995][00562] Num frames 10500...
[2024-11-11 14:46:01,047][00562] Avg episode rewards: #0: 65.399, true rewards: #0: 21.000
[2024-11-11 14:46:01,049][00562] Avg episode reward: 65.399, avg true_objective: 21.000
[2024-11-11 14:46:01,179][00562] Num frames 10600...
[2024-11-11 14:46:01,304][00562] Num frames 10700...
[2024-11-11 14:46:01,428][00562] Num frames 10800...
[2024-11-11 14:46:01,550][00562] Num frames 10900...
[2024-11-11 14:46:01,672][00562] Num frames 11000...
[2024-11-11 14:46:01,797][00562] Num frames 11100...
[2024-11-11 14:46:01,927][00562] Num frames 11200...
[2024-11-11 14:46:02,050][00562] Num frames 11300...
[2024-11-11 14:46:02,182][00562] Num frames 11400...
[2024-11-11 14:46:02,308][00562] Num frames 11500...
[2024-11-11 14:46:02,435][00562] Num frames 11600...
[2024-11-11 14:46:02,559][00562] Num frames 11700...
[2024-11-11 14:46:02,685][00562] Num frames 11800...
[2024-11-11 14:46:02,810][00562] Num frames 11900...
[2024-11-11 14:46:02,935][00562] Num frames 12000...
[2024-11-11 14:46:03,064][00562] Num frames 12100...
[2024-11-11 14:46:03,194][00562] Num frames 12200...
[2024-11-11 14:46:03,319][00562] Num frames 12300...
[2024-11-11 14:46:03,458][00562] Num frames 12400...
[2024-11-11 14:46:03,581][00562] Num frames 12500...
[2024-11-11 14:46:03,712][00562] Num frames 12600...
[2024-11-11 14:46:03,765][00562] Avg episode rewards: #0: 65.499, true rewards: #0: 21.000
[2024-11-11 14:46:03,767][00562] Avg episode reward: 65.499, avg true_objective: 21.000
[2024-11-11 14:46:03,893][00562] Num frames 12700...
[2024-11-11 14:46:04,027][00562] Num frames 12800...
[2024-11-11 14:46:04,159][00562] Num frames 12900...
[2024-11-11 14:46:04,286][00562] Num frames 13000...
[2024-11-11 14:46:04,409][00562] Num frames 13100...
[2024-11-11 14:46:04,532][00562] Num frames 13200...
[2024-11-11 14:46:04,656][00562] Num frames 13300...
[2024-11-11 14:46:04,781][00562] Num frames 13400...
[2024-11-11 14:46:04,904][00562] Num frames 13500...
[2024-11-11 14:46:05,035][00562] Num frames 13600...
[2024-11-11 14:46:05,176][00562] Num frames 13700...
[2024-11-11 14:46:05,376][00562] Num frames 13800...
[2024-11-11 14:46:05,564][00562] Num frames 13900...
[2024-11-11 14:46:05,734][00562] Num frames 14000...
[2024-11-11 14:46:05,905][00562] Num frames 14100...
[2024-11-11 14:46:06,082][00562] Num frames 14200...
[2024-11-11 14:46:06,249][00562] Num frames 14300...
[2024-11-11 14:46:06,422][00562] Num frames 14400...
[2024-11-11 14:46:06,597][00562] Num frames 14500...
[2024-11-11 14:46:06,775][00562] Num frames 14600...
[2024-11-11 14:46:06,950][00562] Num frames 14700...
[2024-11-11 14:46:07,005][00562] Avg episode rewards: #0: 65.427, true rewards: #0: 21.000
[2024-11-11 14:46:07,007][00562] Avg episode reward: 65.427, avg true_objective: 21.000
[2024-11-11 14:46:07,194][00562] Num frames 14800...
[2024-11-11 14:46:07,367][00562] Num frames 14900...
[2024-11-11 14:46:07,538][00562] Num frames 15000...
[2024-11-11 14:46:07,719][00562] Num frames 15100...
[2024-11-11 14:46:07,869][00562] Num frames 15200...
[2024-11-11 14:46:07,991][00562] Num frames 15300...
[2024-11-11 14:46:08,126][00562] Num frames 15400...
[2024-11-11 14:46:08,250][00562] Num frames 15500...
[2024-11-11 14:46:08,373][00562] Num frames 15600...
[2024-11-11 14:46:08,503][00562] Num frames 15700...
[2024-11-11 14:46:08,628][00562] Num frames 15800...
[2024-11-11 14:46:08,753][00562] Num frames 15900...
[2024-11-11 14:46:08,878][00562] Num frames 16000...
[2024-11-11 14:46:09,002][00562] Num frames 16100...
[2024-11-11 14:46:09,140][00562] Num frames 16200...
[2024-11-11 14:46:09,264][00562] Num frames 16300...
[2024-11-11 14:46:09,397][00562] Num frames 16400...
[2024-11-11 14:46:09,524][00562] Num frames 16500...
[2024-11-11 14:46:09,653][00562] Num frames 16600...
[2024-11-11 14:46:09,778][00562] Num frames 16700...
[2024-11-11 14:46:09,906][00562] Num frames 16800...
[2024-11-11 14:46:09,958][00562] Avg episode rewards: #0: 64.874, true rewards: #0: 21.000
[2024-11-11 14:46:09,960][00562] Avg episode reward: 64.874, avg true_objective: 21.000
[2024-11-11 14:46:10,082][00562] Num frames 16900...
[2024-11-11 14:46:10,220][00562] Num frames 17000...
[2024-11-11 14:46:10,344][00562] Num frames 17100...
[2024-11-11 14:46:10,468][00562] Num frames 17200...
[2024-11-11 14:46:10,589][00562] Num frames 17300...
[2024-11-11 14:46:10,713][00562] Num frames 17400...
[2024-11-11 14:46:10,835][00562] Num frames 17500...
[2024-11-11 14:46:10,962][00562] Num frames 17600...
[2024-11-11 14:46:11,086][00562] Num frames 17700...
[2024-11-11 14:46:11,224][00562] Num frames 17800...
[2024-11-11 14:46:11,348][00562] Num frames 17900...
[2024-11-11 14:46:11,471][00562] Num frames 18000...
[2024-11-11 14:46:11,596][00562] Num frames 18100...
[2024-11-11 14:46:11,719][00562] Num frames 18200...
[2024-11-11 14:46:11,843][00562] Num frames 18300...
[2024-11-11 14:46:11,906][00562] Avg episode rewards: #0: 62.670, true rewards: #0: 20.338
[2024-11-11 14:46:11,908][00562] Avg episode reward: 62.670, avg true_objective: 20.338
[2024-11-11 14:46:12,031][00562] Num frames 18400...
[2024-11-11 14:46:12,163][00562] Num frames 18500...
[2024-11-11 14:46:12,293][00562] Num frames 18600...
[2024-11-11 14:46:12,421][00562] Num frames 18700...
[2024-11-11 14:46:12,544][00562] Num frames 18800...
[2024-11-11 14:46:12,665][00562] Num frames 18900...
[2024-11-11 14:46:12,792][00562] Num frames 19000...
[2024-11-11 14:46:12,897][00562] Avg episode rewards: #0: 57.739, true rewards: #0: 19.040
[2024-11-11 14:46:12,899][00562] Avg episode reward: 57.739, avg true_objective: 19.040
[2024-11-11 14:48:09,151][00562] Replay video saved to train_dir/doom_health_gathering_supreme_2222/replay.mp4!
[2024-11-11 14:50:05,788][00562] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-11-11 14:50:05,790][00562] Overriding arg 'num_workers' with value 1 passed from command line
[2024-11-11 14:50:05,791][00562] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-11-11 14:50:05,793][00562] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-11-11 14:50:05,795][00562] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-11-11 14:50:05,796][00562] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-11-11 14:50:05,797][00562] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2024-11-11 14:50:05,799][00562] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-11-11 14:50:05,800][00562] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2024-11-11 14:50:05,802][00562] Adding new argument 'hf_repository'='usamabuttar/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2024-11-11 14:50:05,803][00562] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-11-11 14:50:05,808][00562] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-11-11 14:50:05,809][00562] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-11-11 14:50:05,810][00562] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-11-11 14:50:05,811][00562] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-11-11 14:50:05,840][00562] RunningMeanStd input shape: (3, 72, 128)
[2024-11-11 14:50:05,841][00562] RunningMeanStd input shape: (1,)
[2024-11-11 14:50:05,855][00562] ConvEncoder: input_channels=3
[2024-11-11 14:50:05,894][00562] Conv encoder output size: 512
[2024-11-11 14:50:05,896][00562] Policy head output size: 512
[2024-11-11 14:50:05,914][00562] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-11-11 14:50:06,364][00562] Num frames 100...
[2024-11-11 14:50:06,482][00562] Num frames 200...
[2024-11-11 14:50:06,601][00562] Num frames 300...
[2024-11-11 14:50:06,722][00562] Num frames 400...
[2024-11-11 14:50:06,848][00562] Num frames 500...
[2024-11-11 14:50:06,972][00562] Num frames 600...
[2024-11-11 14:50:07,093][00562] Num frames 700...
[2024-11-11 14:50:07,215][00562] Num frames 800...
[2024-11-11 14:50:07,333][00562] Num frames 900...
[2024-11-11 14:50:07,455][00562] Num frames 1000...
[2024-11-11 14:50:07,596][00562] Avg episode rewards: #0: 23.690, true rewards: #0: 10.690
[2024-11-11 14:50:07,598][00562] Avg episode reward: 23.690, avg true_objective: 10.690
[2024-11-11 14:50:07,638][00562] Num frames 1100...
[2024-11-11 14:50:07,756][00562] Num frames 1200...
[2024-11-11 14:50:07,880][00562] Num frames 1300...
[2024-11-11 14:50:08,006][00562] Num frames 1400...
[2024-11-11 14:50:08,129][00562] Num frames 1500...
[2024-11-11 14:50:08,246][00562] Num frames 1600...
[2024-11-11 14:50:08,364][00562] Num frames 1700...
[2024-11-11 14:50:08,484][00562] Num frames 1800...
[2024-11-11 14:50:08,605][00562] Num frames 1900...
[2024-11-11 14:50:08,727][00562] Num frames 2000...
[2024-11-11 14:50:08,854][00562] Num frames 2100...
[2024-11-11 14:50:08,982][00562] Num frames 2200...
[2024-11-11 14:50:09,078][00562] Avg episode rewards: #0: 24.160, true rewards: #0: 11.160
[2024-11-11 14:50:09,080][00562] Avg episode reward: 24.160, avg true_objective: 11.160
[2024-11-11 14:50:09,171][00562] Num frames 2300...
[2024-11-11 14:50:09,291][00562] Num frames 2400...
[2024-11-11 14:50:09,412][00562] Num frames 2500...
[2024-11-11 14:50:09,535][00562] Num frames 2600...
[2024-11-11 14:50:09,658][00562] Num frames 2700...
[2024-11-11 14:50:09,781][00562] Num frames 2800...
[2024-11-11 14:50:09,909][00562] Num frames 2900...
[2024-11-11 14:50:10,031][00562] Num frames 3000...
[2024-11-11 14:50:10,159][00562] Num frames 3100...
[2024-11-11 14:50:10,278][00562] Num frames 3200...
[2024-11-11 14:50:10,401][00562] Num frames 3300...
[2024-11-11 14:50:10,525][00562] Num frames 3400...
[2024-11-11 14:50:10,647][00562] Num frames 3500...
[2024-11-11 14:50:10,766][00562] Num frames 3600...
[2024-11-11 14:50:10,889][00562] Num frames 3700...
[2024-11-11 14:50:11,058][00562] Num frames 3800...
[2024-11-11 14:50:11,236][00562] Num frames 3900...
[2024-11-11 14:50:11,402][00562] Num frames 4000...
[2024-11-11 14:50:11,574][00562] Num frames 4100...
[2024-11-11 14:50:11,740][00562] Num frames 4200...
[2024-11-11 14:50:11,908][00562] Num frames 4300...
[2024-11-11 14:50:12,024][00562] Avg episode rewards: #0: 34.440, true rewards: #0: 14.440
[2024-11-11 14:50:12,028][00562] Avg episode reward: 34.440, avg true_objective: 14.440
[2024-11-11 14:50:12,154][00562] Num frames 4400...
[2024-11-11 14:50:12,323][00562] Num frames 4500...
[2024-11-11 14:50:12,489][00562] Num frames 4600...
[2024-11-11 14:50:12,660][00562] Num frames 4700...
[2024-11-11 14:50:12,831][00562] Num frames 4800...
[2024-11-11 14:50:13,006][00562] Num frames 4900...
[2024-11-11 14:50:13,180][00562] Num frames 5000...
[2024-11-11 14:50:13,351][00562] Num frames 5100...
[2024-11-11 14:50:13,502][00562] Num frames 5200...
[2024-11-11 14:50:13,618][00562] Num frames 5300...
[2024-11-11 14:50:13,741][00562] Num frames 5400...
[2024-11-11 14:50:13,878][00562] Num frames 5500...
[2024-11-11 14:50:14,014][00562] Num frames 5600...
[2024-11-11 14:50:14,143][00562] Num frames 5700...
[2024-11-11 14:50:14,265][00562] Num frames 5800...
[2024-11-11 14:50:14,385][00562] Num frames 5900...
[2024-11-11 14:50:14,503][00562] Num frames 6000...
[2024-11-11 14:50:14,622][00562] Num frames 6100...
[2024-11-11 14:50:14,742][00562] Num frames 6200...
[2024-11-11 14:50:14,862][00562] Num frames 6300...
[2024-11-11 14:50:14,983][00562] Num frames 6400...
[2024-11-11 14:50:15,077][00562] Avg episode rewards: #0: 40.329, true rewards: #0: 16.080
[2024-11-11 14:50:15,079][00562] Avg episode reward: 40.329, avg true_objective: 16.080
[2024-11-11 14:50:15,166][00562] Num frames 6500...
[2024-11-11 14:50:15,282][00562] Num frames 6600...
[2024-11-11 14:50:15,406][00562] Num frames 6700...
[2024-11-11 14:50:15,525][00562] Num frames 6800...
[2024-11-11 14:50:15,644][00562] Num frames 6900...
[2024-11-11 14:50:15,765][00562] Num frames 7000...
[2024-11-11 14:50:15,883][00562] Num frames 7100...
[2024-11-11 14:50:16,005][00562] Num frames 7200...
[2024-11-11 14:50:16,202][00562] Avg episode rewards: #0: 35.794, true rewards: #0: 14.594
[2024-11-11 14:50:16,204][00562] Avg episode reward: 35.794, avg true_objective: 14.594
[2024-11-11 14:50:16,211][00562] Num frames 7300...
[2024-11-11 14:50:16,329][00562] Num frames 7400...
[2024-11-11 14:50:16,450][00562] Num frames 7500...
[2024-11-11 14:50:16,570][00562] Num frames 7600...
[2024-11-11 14:50:16,691][00562] Num frames 7700...
[2024-11-11 14:50:16,819][00562] Num frames 7800...
[2024-11-11 14:50:16,936][00562] Num frames 7900...
[2024-11-11 14:50:17,074][00562] Num frames 8000...
[2024-11-11 14:50:17,210][00562] Num frames 8100...
[2024-11-11 14:50:17,327][00562] Num frames 8200...
[2024-11-11 14:50:17,452][00562] Num frames 8300...
[2024-11-11 14:50:17,571][00562] Num frames 8400...
[2024-11-11 14:50:17,648][00562] Avg episode rewards: #0: 33.528, true rewards: #0: 14.028
[2024-11-11 14:50:17,649][00562] Avg episode reward: 33.528, avg true_objective: 14.028
[2024-11-11 14:50:17,750][00562] Num frames 8500...
[2024-11-11 14:50:17,866][00562] Num frames 8600...
[2024-11-11 14:50:17,984][00562] Num frames 8700...
[2024-11-11 14:50:18,117][00562] Num frames 8800...
[2024-11-11 14:50:18,251][00562] Avg episode rewards: #0: 29.521, true rewards: #0: 12.664
[2024-11-11 14:50:18,253][00562] Avg episode reward: 29.521, avg true_objective: 12.664
[2024-11-11 14:50:18,295][00562] Num frames 8900...
[2024-11-11 14:50:18,411][00562] Num frames 9000...
[2024-11-11 14:50:18,530][00562] Num frames 9100...
[2024-11-11 14:50:18,654][00562] Num frames 9200...
[2024-11-11 14:50:18,768][00562] Avg episode rewards: #0: 26.311, true rewards: #0: 11.561
[2024-11-11 14:50:18,770][00562] Avg episode reward: 26.311, avg true_objective: 11.561
[2024-11-11 14:50:18,837][00562] Num frames 9300...
[2024-11-11 14:50:18,960][00562] Num frames 9400...
[2024-11-11 14:50:19,081][00562] Num frames 9500...
[2024-11-11 14:50:19,221][00562] Num frames 9600...
[2024-11-11 14:50:19,339][00562] Num frames 9700...
[2024-11-11 14:50:19,458][00562] Num frames 9800...
[2024-11-11 14:50:19,579][00562] Num frames 9900...
[2024-11-11 14:50:19,698][00562] Num frames 10000...
[2024-11-11 14:50:19,819][00562] Num frames 10100...
[2024-11-11 14:50:19,975][00562] Avg episode rewards: #0: 25.426, true rewards: #0: 11.316
[2024-11-11 14:50:19,977][00562] Avg episode reward: 25.426, avg true_objective: 11.316
[2024-11-11 14:50:19,999][00562] Num frames 10200...
[2024-11-11 14:50:20,124][00562] Num frames 10300...
[2024-11-11 14:50:20,252][00562] Num frames 10400...
[2024-11-11 14:50:20,374][00562] Num frames 10500...
[2024-11-11 14:50:20,497][00562] Num frames 10600...
[2024-11-11 14:50:20,617][00562] Num frames 10700...
[2024-11-11 14:50:20,739][00562] Num frames 10800...
[2024-11-11 14:50:20,863][00562] Avg episode rewards: #0: 24.356, true rewards: #0: 10.856
[2024-11-11 14:50:20,865][00562] Avg episode reward: 24.356, avg true_objective: 10.856
[2024-11-11 14:51:25,155][00562] Replay video saved to /content/train_dir/default_experiment/replay.mp4!