Hugging Face's logo

saxelsso
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
saxelsso commited on
Commit
dc68905
·
verified ·
1 Parent(s): b993144

Second Push

Browse files
Files changed (7) hide show
  1. SoccerTwos.onnx +2 -2
  2. SoccerTwos/checkpoint.pt +2 -2
  3. config.json +1 -1
  4. configuration.yaml +4 -4
  5. run_logs/Player-0.log +23 -390
  6. run_logs/timers.json +187 -187
  7. run_logs/training_status.json +25 -25
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f72e1981d8ff84fa01216a1d4fd8d5ab7ea8887d2686ef567de4dd84a3710d6b
3
- size 2820313
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a48d9eaad548b991c55f5c345f59f153fa83572a4df1d914ccd6c2b0e3f28e
3
+ size 1768747
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04bce1f6d6a9c5a8ebd02756ac9bd2961e68fcd742c93bb574b0d35ea50cf381
3
- size 34739782
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c38b64d70736ade85683413e7a469c5dba9d44fc4ee6a856dae8f18bc7964c
3
+ size 28431030
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.00028, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 20000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos4", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}
configuration.yaml CHANGED
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 2048
7
  buffer_size: 20480
8
- learning_rate: 0.00028
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -17,7 +17,7 @@ behaviors:
17
  network_settings:
18
  normalize: false
19
  hidden_units: 512
20
- num_layers: 3
21
  vis_encode_type: simple
22
  memory: null
23
  goal_conditioning_type: hyper
@@ -37,7 +37,7 @@ behaviors:
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
- max_steps: 20000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
@@ -71,7 +71,7 @@ engine_settings:
71
  no_graphics_monitor: false
72
  environment_parameters: null
73
  checkpoint_settings:
74
- run_id: SoccerTwos4
75
  initialize_from: null
76
  load_model: false
77
  resume: false
 
5
  hyperparameters:
6
  batch_size: 2048
7
  buffer_size: 20480
8
+ learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
17
  network_settings:
18
  normalize: false
19
  hidden_units: 512
20
+ num_layers: 2
21
  vis_encode_type: simple
22
  memory: null
23
  goal_conditioning_type: hyper
 
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
+ max_steps: 50000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
 
71
  no_graphics_monitor: false
72
  environment_parameters: null
73
  checkpoint_settings:
74
+ run_id: SoccerTwos2
75
  initialize_from: null
76
  load_model: false
77
  resume: false
run_logs/Player-0.log CHANGED
@@ -11,7 +11,7 @@ NullGfxDevice:
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
- - Completed reload, in 0.044 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -36,7 +36,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
36
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
37
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
38
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
39
- UnloadTime: 0.514665 ms
40
  Registered Communicator in Agent.
41
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
42
  requesting resize 84 x 84
@@ -439,380 +439,13 @@ TOO LONG
439
  TOO LONG
440
  TOO LONG
441
  TOO LONG
442
- TOO LONG
443
- TOO LONG
444
- TOO LONG
445
- TOO LONG
446
- TOO LONG
447
- TOO LONG
448
- TOO LONG
449
- TOO LONG
450
- TOO LONG
451
- TOO LONG
452
- TOO LONG
453
- TOO LONG
454
- TOO LONG
455
- TOO LONG
456
- TOO LONG
457
- TOO LONG
458
- TOO LONG
459
- TOO LONG
460
- TOO LONG
461
- TOO LONG
462
- TOO LONG
463
- TOO LONG
464
- TOO LONG
465
- TOO LONG
466
- TOO LONG
467
- TOO LONG
468
- TOO LONG
469
- TOO LONG
470
- TOO LONG
471
- TOO LONG
472
- TOO LONG
473
- TOO LONG
474
- TOO LONG
475
- TOO LONG
476
- TOO LONG
477
- TOO LONG
478
- TOO LONG
479
- TOO LONG
480
- TOO LONG
481
- TOO LONG
482
- TOO LONG
483
- TOO LONG
484
- TOO LONG
485
- TOO LONG
486
- TOO LONG
487
- TOO LONG
488
- TOO LONG
489
- TOO LONG
490
- TOO LONG
491
- TOO LONG
492
- TOO LONG
493
- TOO LONG
494
- TOO LONG
495
- TOO LONG
496
- TOO LONG
497
- TOO LONG
498
- TOO LONG
499
- TOO LONG
500
- TOO LONG
501
- TOO LONG
502
- TOO LONG
503
- TOO LONG
504
- TOO LONG
505
- TOO LONG
506
- TOO LONG
507
- TOO LONG
508
- TOO LONG
509
- TOO LONG
510
- TOO LONG
511
- TOO LONG
512
- TOO LONG
513
- TOO LONG
514
- TOO LONG
515
- TOO LONG
516
- TOO LONG
517
- TOO LONG
518
- TOO LONG
519
- TOO LONG
520
- TOO LONG
521
- TOO LONG
522
- TOO LONG
523
- TOO LONG
524
- TOO LONG
525
- TOO LONG
526
- TOO LONG
527
- TOO LONG
528
- TOO LONG
529
- TOO LONG
530
- TOO LONG
531
- TOO LONG
532
- TOO LONG
533
- TOO LONG
534
- TOO LONG
535
- TOO LONG
536
- TOO LONG
537
- TOO LONG
538
- TOO LONG
539
- TOO LONG
540
- TOO LONG
541
- TOO LONG
542
- TOO LONG
543
- TOO LONG
544
- TOO LONG
545
- TOO LONG
546
- TOO LONG
547
- TOO LONG
548
- TOO LONG
549
- TOO LONG
550
- TOO LONG
551
- TOO LONG
552
- TOO LONG
553
- TOO LONG
554
- TOO LONG
555
- TOO LONG
556
- TOO LONG
557
- TOO LONG
558
- TOO LONG
559
- TOO LONG
560
- TOO LONG
561
- TOO LONG
562
- TOO LONG
563
- TOO LONG
564
- TOO LONG
565
- TOO LONG
566
- TOO LONG
567
- TOO LONG
568
- TOO LONG
569
- TOO LONG
570
- TOO LONG
571
- TOO LONG
572
- TOO LONG
573
- TOO LONG
574
- TOO LONG
575
- TOO LONG
576
- TOO LONG
577
- TOO LONG
578
- TOO LONG
579
- TOO LONG
580
- TOO LONG
581
- TOO LONG
582
- TOO LONG
583
- TOO LONG
584
- TOO LONG
585
- TOO LONG
586
- TOO LONG
587
- TOO LONG
588
- TOO LONG
589
- TOO LONG
590
- TOO LONG
591
- TOO LONG
592
- TOO LONG
593
- TOO LONG
594
- TOO LONG
595
- TOO LONG
596
- TOO LONG
597
- TOO LONG
598
- TOO LONG
599
- TOO LONG
600
- TOO LONG
601
- TOO LONG
602
- TOO LONG
603
- TOO LONG
604
- TOO LONG
605
- TOO LONG
606
- TOO LONG
607
- TOO LONG
608
- TOO LONG
609
- TOO LONG
610
- TOO LONG
611
- TOO LONG
612
- TOO LONG
613
- TOO LONG
614
- TOO LONG
615
- TOO LONG
616
- TOO LONG
617
- TOO LONG
618
- TOO LONG
619
- TOO LONG
620
- TOO LONG
621
- TOO LONG
622
- TOO LONG
623
- TOO LONG
624
- TOO LONG
625
- TOO LONG
626
- TOO LONG
627
- TOO LONG
628
- TOO LONG
629
- TOO LONG
630
- TOO LONG
631
- TOO LONG
632
- TOO LONG
633
- TOO LONG
634
- TOO LONG
635
- TOO LONG
636
- TOO LONG
637
- TOO LONG
638
- TOO LONG
639
- TOO LONG
640
- TOO LONG
641
- TOO LONG
642
- TOO LONG
643
- TOO LONG
644
- TOO LONG
645
- TOO LONG
646
- TOO LONG
647
- TOO LONG
648
- TOO LONG
649
- TOO LONG
650
- TOO LONG
651
- TOO LONG
652
- TOO LONG
653
- TOO LONG
654
- TOO LONG
655
- TOO LONG
656
- TOO LONG
657
- TOO LONG
658
- TOO LONG
659
- TOO LONG
660
- TOO LONG
661
- TOO LONG
662
- TOO LONG
663
- TOO LONG
664
- TOO LONG
665
- TOO LONG
666
- TOO LONG
667
- TOO LONG
668
- TOO LONG
669
- TOO LONG
670
- TOO LONG
671
- TOO LONG
672
- TOO LONG
673
- TOO LONG
674
- TOO LONG
675
- TOO LONG
676
- TOO LONG
677
- TOO LONG
678
- TOO LONG
679
- TOO LONG
680
- TOO LONG
681
- TOO LONG
682
- TOO LONG
683
- TOO LONG
684
- TOO LONG
685
- TOO LONG
686
- TOO LONG
687
- TOO LONG
688
- TOO LONG
689
- TOO LONG
690
- TOO LONG
691
- TOO LONG
692
- TOO LONG
693
- TOO LONG
694
- TOO LONG
695
- TOO LONG
696
- TOO LONG
697
- TOO LONG
698
- TOO LONG
699
- TOO LONG
700
- TOO LONG
701
- TOO LONG
702
- TOO LONG
703
- TOO LONG
704
- TOO LONG
705
- TOO LONG
706
- TOO LONG
707
- TOO LONG
708
- TOO LONG
709
- TOO LONG
710
- TOO LONG
711
- TOO LONG
712
- TOO LONG
713
- TOO LONG
714
- TOO LONG
715
- TOO LONG
716
- TOO LONG
717
- TOO LONG
718
- TOO LONG
719
- TOO LONG
720
- TOO LONG
721
- TOO LONG
722
- TOO LONG
723
- TOO LONG
724
- TOO LONG
725
- TOO LONG
726
- TOO LONG
727
- TOO LONG
728
- TOO LONG
729
- TOO LONG
730
- TOO LONG
731
- TOO LONG
732
- TOO LONG
733
- TOO LONG
734
- TOO LONG
735
- TOO LONG
736
- TOO LONG
737
- TOO LONG
738
- TOO LONG
739
- TOO LONG
740
- TOO LONG
741
- TOO LONG
742
- TOO LONG
743
- TOO LONG
744
- TOO LONG
745
- TOO LONG
746
- TOO LONG
747
- TOO LONG
748
- TOO LONG
749
- TOO LONG
750
- TOO LONG
751
- TOO LONG
752
- TOO LONG
753
- TOO LONG
754
- TOO LONG
755
- TOO LONG
756
- TOO LONG
757
- TOO LONG
758
- TOO LONG
759
- TOO LONG
760
- TOO LONG
761
- TOO LONG
762
- TOO LONG
763
- TOO LONG
764
- TOO LONG
765
- TOO LONG
766
- TOO LONG
767
- TOO LONG
768
- TOO LONG
769
- TOO LONG
770
- TOO LONG
771
- TOO LONG
772
- TOO LONG
773
- TOO LONG
774
- TOO LONG
775
- TOO LONG
776
- TOO LONG
777
- TOO LONG
778
- TOO LONG
779
- TOO LONG
780
- TOO LONG
781
- TOO LONG
782
- TOO LONG
783
- TOO LONG
784
- TOO LONG
785
- TOO LONG
786
- TOO LONG
787
- TOO LONG
788
- TOO LONG
789
- TOO LONG
790
- TOO LONG
791
- TOO LONG
792
- TOO LONG
793
- TOO LONG
794
- TOO LONG
795
- TOO LONG
796
- TOO LONG
797
- TOO LONG
798
- TOO LONG
799
- TOO LONG
800
- TOO LONG
801
- TOO LONG
802
- TOO LONG
803
- TOO LONG
804
- TOO LONG
805
- TOO LONG
806
- TOO LONG
807
- TOO LONG
808
- TOO LONG
809
- TOO LONG
810
  Setting up 16 worker threads for Enlighten.
811
  Memory Statistics:
812
  [ALLOC_TEMP_TLS] TLS Allocator
813
  StackAllocators :
814
  [ALLOC_TEMP_MAIN]
815
- Peak usage frame count: [8.0 KB-16.0 KB]: 377440 frames, [2.0 MB-4.0 MB]: 1 frames
816
  Initial Block Size 4.0 MB
817
  Current Block Size 4.0 MB
818
  Peak Allocated Bytes 2.1 MB
@@ -857,12 +490,12 @@ Memory Statistics:
857
  Current Block Size 256.0 KB
858
  Peak Allocated Bytes 0 B
859
  Overflow Count 0
860
- [ALLOC_TEMP_Job.Worker 17]
861
  Initial Block Size 256.0 KB
862
  Current Block Size 256.0 KB
863
  Peak Allocated Bytes 0 B
864
  Overflow Count 0
865
- [ALLOC_TEMP_Job.Worker 14]
866
  Initial Block Size 256.0 KB
867
  Current Block Size 256.0 KB
868
  Peak Allocated Bytes 0 B
@@ -952,15 +585,15 @@ Memory Statistics:
952
  Current Block Size 256.0 KB
953
  Peak Allocated Bytes 0 B
954
  Overflow Count 0
955
- [ALLOC_TEMP_Job.Worker 21]
956
  Initial Block Size 256.0 KB
957
  Current Block Size 256.0 KB
958
  Peak Allocated Bytes 0 B
959
  Overflow Count 0
960
- [ALLOC_TEMP_Job.Worker 26]
961
  Initial Block Size 256.0 KB
962
  Current Block Size 256.0 KB
963
- Peak Allocated Bytes 0.7 KB
964
  Overflow Count 0
965
  [ALLOC_TEMP_Job.Worker 5]
966
  Initial Block Size 256.0 KB
@@ -1062,15 +695,15 @@ Memory Statistics:
1062
  Current Block Size 256.0 KB
1063
  Peak Allocated Bytes 0 B
1064
  Overflow Count 0
1065
- [ALLOC_TEMP_Job.Worker 12]
1066
  Initial Block Size 256.0 KB
1067
  Current Block Size 256.0 KB
1068
  Peak Allocated Bytes 0 B
1069
  Overflow Count 0
1070
- [ALLOC_TEMP_Job.Worker 19]
1071
  Initial Block Size 256.0 KB
1072
  Current Block Size 256.0 KB
1073
- Peak Allocated Bytes 0 B
1074
  Overflow Count 0
1075
  [ALLOC_TEMP_Loading.AsyncRead]
1076
  Initial Block Size 64.0 KB
@@ -1078,22 +711,22 @@ Memory Statistics:
1078
  Peak Allocated Bytes 128 B
1079
  Overflow Count 0
1080
  [ALLOC_DEFAULT] Dual Thread Allocator
1081
- Peak main deferred allocation count 6
1082
  [ALLOC_BUCKET]
1083
  Large Block size 4.0 MB
1084
  Used Block count 1
1085
  Peak Allocated bytes 1.0 MB
1086
  [ALLOC_DEFAULT_MAIN]
1087
- Peak usage frame count: [4.0 MB-8.0 MB]: 377441 frames
1088
  Requested Block Size 16.0 MB
1089
  Peak Block count 1
1090
- Peak Allocated memory 4.7 MB
1091
  Peak Large allocation bytes 0 B
1092
  [ALLOC_DEFAULT_THREAD]
1093
- Peak usage frame count: [16.0 MB-32.0 MB]: 377441 frames
1094
  Requested Block Size 16.0 MB
1095
  Peak Block count 1
1096
- Peak Allocated memory 17.5 MB
1097
  Peak Large allocation bytes 16.0 MB
1098
  [ALLOC_TEMP_JOB_1_FRAME]
1099
  Initial Block Size 2.0 MB
@@ -1122,13 +755,13 @@ Memory Statistics:
1122
  Used Block count 1
1123
  Peak Allocated bytes 1.0 MB
1124
  [ALLOC_GFX_MAIN]
1125
- Peak usage frame count: [32.0 KB-64.0 KB]: 377440 frames, [64.0 KB-128.0 KB]: 1 frames
1126
  Requested Block Size 16.0 MB
1127
  Peak Block count 1
1128
  Peak Allocated memory 65.6 KB
1129
  Peak Large allocation bytes 0 B
1130
  [ALLOC_GFX_THREAD]
1131
- Peak usage frame count: [128.0 KB-256.0 KB]: 377441 frames
1132
  Requested Block Size 16.0 MB
1133
  Peak Block count 1
1134
  Peak Allocated memory 173.5 KB
@@ -1140,13 +773,13 @@ Memory Statistics:
1140
  Used Block count 1
1141
  Peak Allocated bytes 1.0 MB
1142
  [ALLOC_CACHEOBJECTS_MAIN]
1143
- Peak usage frame count: [0.5 MB-1.0 MB]: 377441 frames
1144
  Requested Block Size 4.0 MB
1145
  Peak Block count 1
1146
  Peak Allocated memory 0.6 MB
1147
  Peak Large allocation bytes 0 B
1148
  [ALLOC_CACHEOBJECTS_THREAD]
1149
- Peak usage frame count: [0.5 MB-1.0 MB]: 377440 frames, [4.0 MB-8.0 MB]: 1 frames
1150
  Requested Block Size 4.0 MB
1151
  Peak Block count 2
1152
  Peak Allocated memory 4.5 MB
@@ -1158,13 +791,13 @@ Memory Statistics:
1158
  Used Block count 1
1159
  Peak Allocated bytes 1.0 MB
1160
  [ALLOC_TYPETREE_MAIN]
1161
- Peak usage frame count: [0-1.0 KB]: 377441 frames
1162
  Requested Block Size 2.0 MB
1163
  Peak Block count 1
1164
  Peak Allocated memory 1.0 KB
1165
  Peak Large allocation bytes 0 B
1166
  [ALLOC_TYPETREE_THREAD]
1167
- Peak usage frame count: [1.0 KB-2.0 KB]: 377440 frames, [2.0 KB-4.0 KB]: 1 frames
1168
  Requested Block Size 2.0 MB
1169
  Peak Block count 1
1170
  Peak Allocated memory 2.2 KB
 
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
+ - Completed reload, in 0.042 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
36
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
37
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
38
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
39
+ UnloadTime: 0.395896 ms
40
  Registered Communicator in Agent.
41
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
42
  requesting resize 84 x 84
 
439
  TOO LONG
440
  TOO LONG
441
  TOO LONG
442
+ GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
443
  Setting up 16 worker threads for Enlighten.
444
  Memory Statistics:
445
  [ALLOC_TEMP_TLS] TLS Allocator
446
  StackAllocators :
447
  [ALLOC_TEMP_MAIN]
448
+ Peak usage frame count: [8.0 KB-16.0 KB]: 409577 frames, [2.0 MB-4.0 MB]: 1 frames
449
  Initial Block Size 4.0 MB
450
  Current Block Size 4.0 MB
451
  Peak Allocated Bytes 2.1 MB
 
490
  Current Block Size 256.0 KB
491
  Peak Allocated Bytes 0 B
492
  Overflow Count 0
493
+ [ALLOC_TEMP_Job.Worker 14]
494
  Initial Block Size 256.0 KB
495
  Current Block Size 256.0 KB
496
  Peak Allocated Bytes 0 B
497
  Overflow Count 0
498
+ [ALLOC_TEMP_Job.Worker 17]
499
  Initial Block Size 256.0 KB
500
  Current Block Size 256.0 KB
501
  Peak Allocated Bytes 0 B
 
585
  Current Block Size 256.0 KB
586
  Peak Allocated Bytes 0 B
587
  Overflow Count 0
588
+ [ALLOC_TEMP_Job.Worker 26]
589
  Initial Block Size 256.0 KB
590
  Current Block Size 256.0 KB
591
  Peak Allocated Bytes 0 B
592
  Overflow Count 0
593
+ [ALLOC_TEMP_Job.Worker 21]
594
  Initial Block Size 256.0 KB
595
  Current Block Size 256.0 KB
596
+ Peak Allocated Bytes 0 B
597
  Overflow Count 0
598
  [ALLOC_TEMP_Job.Worker 5]
599
  Initial Block Size 256.0 KB
 
695
  Current Block Size 256.0 KB
696
  Peak Allocated Bytes 0 B
697
  Overflow Count 0
698
+ [ALLOC_TEMP_Job.Worker 19]
699
  Initial Block Size 256.0 KB
700
  Current Block Size 256.0 KB
701
  Peak Allocated Bytes 0 B
702
  Overflow Count 0
703
+ [ALLOC_TEMP_Job.Worker 12]
704
  Initial Block Size 256.0 KB
705
  Current Block Size 256.0 KB
706
+ Peak Allocated Bytes 0.7 KB
707
  Overflow Count 0
708
  [ALLOC_TEMP_Loading.AsyncRead]
709
  Initial Block Size 64.0 KB
 
711
  Peak Allocated Bytes 128 B
712
  Overflow Count 0
713
  [ALLOC_DEFAULT] Dual Thread Allocator
714
+ Peak main deferred allocation count 5
715
  [ALLOC_BUCKET]
716
  Large Block size 4.0 MB
717
  Used Block count 1
718
  Peak Allocated bytes 1.0 MB
719
  [ALLOC_DEFAULT_MAIN]
720
+ Peak usage frame count: [4.0 MB-8.0 MB]: 409578 frames
721
  Requested Block Size 16.0 MB
722
  Peak Block count 1
723
+ Peak Allocated memory 4.8 MB
724
  Peak Large allocation bytes 0 B
725
  [ALLOC_DEFAULT_THREAD]
726
+ Peak usage frame count: [16.0 MB-32.0 MB]: 409578 frames
727
  Requested Block Size 16.0 MB
728
  Peak Block count 1
729
+ Peak Allocated memory 17.4 MB
730
  Peak Large allocation bytes 16.0 MB
731
  [ALLOC_TEMP_JOB_1_FRAME]
732
  Initial Block Size 2.0 MB
 
755
  Used Block count 1
756
  Peak Allocated bytes 1.0 MB
757
  [ALLOC_GFX_MAIN]
758
+ Peak usage frame count: [32.0 KB-64.0 KB]: 409577 frames, [64.0 KB-128.0 KB]: 1 frames
759
  Requested Block Size 16.0 MB
760
  Peak Block count 1
761
  Peak Allocated memory 65.6 KB
762
  Peak Large allocation bytes 0 B
763
  [ALLOC_GFX_THREAD]
764
+ Peak usage frame count: [128.0 KB-256.0 KB]: 409578 frames
765
  Requested Block Size 16.0 MB
766
  Peak Block count 1
767
  Peak Allocated memory 173.5 KB
 
773
  Used Block count 1
774
  Peak Allocated bytes 1.0 MB
775
  [ALLOC_CACHEOBJECTS_MAIN]
776
+ Peak usage frame count: [0.5 MB-1.0 MB]: 409578 frames
777
  Requested Block Size 4.0 MB
778
  Peak Block count 1
779
  Peak Allocated memory 0.6 MB
780
  Peak Large allocation bytes 0 B
781
  [ALLOC_CACHEOBJECTS_THREAD]
782
+ Peak usage frame count: [0.5 MB-1.0 MB]: 409577 frames, [4.0 MB-8.0 MB]: 1 frames
783
  Requested Block Size 4.0 MB
784
  Peak Block count 2
785
  Peak Allocated memory 4.5 MB
 
791
  Used Block count 1
792
  Peak Allocated bytes 1.0 MB
793
  [ALLOC_TYPETREE_MAIN]
794
+ Peak usage frame count: [0-1.0 KB]: 409578 frames
795
  Requested Block Size 2.0 MB
796
  Peak Block count 1
797
  Peak Allocated memory 1.0 KB
798
  Peak Large allocation bytes 0 B
799
  [ALLOC_TYPETREE_THREAD]
800
+ Peak usage frame count: [1.0 KB-2.0 KB]: 409577 frames, [2.0 KB-4.0 KB]: 1 frames
801
  Requested Block Size 2.0 MB
802
  Peak Block count 1
803
  Peak Allocated memory 2.2 KB
run_logs/timers.json CHANGED
@@ -2,261 +2,261 @@
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 1.5211048126220703,
6
- "min": 1.476548194885254,
7
- "max": 3.2958028316497803,
8
- "count": 2000
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 31200.90234375,
12
- "min": 22282.751953125,
13
- "max": 167252.453125,
14
- "count": 2000
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 53.78260869565217,
18
- "min": 39.57377049180328,
19
  "max": 999.0,
20
- "count": 2000
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 19792.0,
24
  "min": 7992.0,
25
- "max": 28004.0,
26
- "count": 2000
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1641.277962416223,
30
- "min": 1188.6358631860387,
31
- "max": 1708.475750895904,
32
- "count": 1959
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 301995.14508458506,
36
- "min": 2377.2717263720774,
37
- "max": 405506.3032981086,
38
- "count": 1959
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 19999988.0,
42
- "min": 9020.0,
43
- "max": 19999988.0,
44
- "count": 2000
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 19999988.0,
48
- "min": 9020.0,
49
- "max": 19999988.0,
50
- "count": 2000
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": -0.0679478868842125,
54
- "min": -0.14309346675872803,
55
- "max": 0.2183915078639984,
56
- "count": 2000
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": -12.434463500976562,
60
- "min": -24.815961837768555,
61
- "max": 27.298938751220703,
62
- "count": 2000
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": -0.06905563920736313,
66
- "min": -0.1443253755569458,
67
- "max": 0.21502287685871124,
68
- "count": 2000
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": -12.637182235717773,
72
- "min": -24.977676391601562,
73
- "max": 26.877859115600586,
74
- "count": 2000
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 2000
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 2000
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": -0.044415299358263695,
90
- "min": -0.49319999747806126,
91
- "max": 0.523711105187734,
92
- "count": 2000
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": -8.127999782562256,
96
- "min": -64.13520020246506,
97
- "max": 56.56079936027527,
98
- "count": 2000
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": -0.044415299358263695,
102
- "min": -0.49319999747806126,
103
- "max": 0.523711105187734,
104
- "count": 2000
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": -8.127999782562256,
108
- "min": -64.13520020246506,
109
- "max": 56.56079936027527,
110
- "count": 2000
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 2000
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 2000
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
- "value": 0.02640004381020044,
126
- "min": 0.010798875237863588,
127
- "max": 0.02640004381020044,
128
- "count": 967
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
- "value": 0.02640004381020044,
132
- "min": 0.010798875237863588,
133
- "max": 0.02640004381020044,
134
- "count": 967
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
- "value": 0.11056271269917488,
138
- "min": 1.052262676163688e-06,
139
- "max": 0.12310012206435203,
140
- "count": 967
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
- "value": 0.11056271269917488,
144
- "min": 1.052262676163688e-06,
145
- "max": 0.12310012206435203,
146
- "count": 967
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
- "value": 0.11206656396389007,
150
- "min": 1.1784684393963593e-06,
151
- "max": 0.125435005625089,
152
- "count": 967
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
- "value": 0.11206656396389007,
156
- "min": 1.1784684393963593e-06,
157
- "max": 0.125435005625089,
158
- "count": 967
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
- "value": 0.00028000000000000003,
162
- "min": 0.00028000000000000003,
163
- "max": 0.00028000000000000014,
164
- "count": 967
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
- "value": 0.00028000000000000003,
168
- "min": 0.00028000000000000003,
169
- "max": 0.00028000000000000014,
170
- "count": 967
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
  "min": 0.20000000000000004,
175
  "max": 0.20000000000000007,
176
- "count": 967
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
  "min": 0.20000000000000004,
181
  "max": 0.20000000000000007,
182
- "count": 967
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
  "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
- "count": 967
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
  "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
- "count": 967
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1736456628",
200
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
201
- "command_line_arguments": "/home/stefan/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos4 --no-graphics --torch-device cuda",
202
  "mlagents_version": "1.2.0.dev0",
203
  "mlagents_envs_version": "1.2.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.5.1+cu124",
206
  "numpy_version": "1.23.5",
207
- "end_time_seconds": "1736490066"
208
  },
209
- "total": 33437.400116431,
210
  "count": 1,
211
- "self": 0.9705501009884756,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.010827789010363631,
215
  "count": 1,
216
- "self": 0.010827789010363631
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 33436.418738541004,
220
  "count": 1,
221
- "self": 18.93817964529444,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 2.7808433200407308,
225
- "count": 100,
226
- "self": 2.7808433200407308
227
  },
228
  "TrainerController.advance": {
229
- "total": 33414.512366370676,
230
- "count": 1380077,
231
- "self": 17.30346309610468,
232
  "children": {
233
  "env_step": {
234
- "total": 25428.50867014556,
235
- "count": 1380077,
236
- "self": 15341.696329102138,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 10074.721002559134,
240
- "count": 1380077,
241
- "self": 112.96048573686858,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 9961.760516822265,
245
- "count": 2516294,
246
- "self": 9961.760516822265
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 12.091338484286098,
252
- "count": 1380077,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 33395.48432955134,
257
- "count": 1380077,
258
  "is_parallel": true,
259
- "self": 20157.45130626636,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
@@ -265,48 +265,48 @@
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
- "total": 0.0017420509975636378,
269
  "count": 2,
270
  "is_parallel": true,
271
- "self": 0.00048666601651348174,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
- "total": 0.001255384981050156,
275
  "count": 8,
276
  "is_parallel": true,
277
- "self": 0.001255384981050156
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
- "total": 0.01918356100213714,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.00036849599564448,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
- "total": 0.0002736970054684207,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.0002736970054684207
292
  },
293
  "communicator.exchange": {
294
- "total": 0.017360081008519046,
295
  "count": 1,
296
  "is_parallel": true,
297
- "self": 0.017360081008519046
298
  },
299
  "steps_from_proto": {
300
- "total": 0.0011812869925051928,
301
  "count": 2,
302
  "is_parallel": true,
303
- "self": 0.0002823469985742122,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
- "total": 0.0008989399939309806,
307
  "count": 8,
308
  "is_parallel": true,
309
- "self": 0.0008989399939309806
310
  }
311
  }
312
  }
@@ -315,50 +315,50 @@
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
- "total": 13237.9236681818,
319
- "count": 1380076,
320
  "is_parallel": true,
321
- "self": 446.39074623255874,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
- "total": 291.0593243048352,
325
- "count": 1380076,
326
  "is_parallel": true,
327
- "self": 291.0593243048352
328
  },
329
  "communicator.exchange": {
330
- "total": 11110.65195204984,
331
- "count": 1380076,
332
  "is_parallel": true,
333
- "self": 11110.65195204984
334
  },
335
  "steps_from_proto": {
336
- "total": 1389.8216455945658,
337
- "count": 2760152,
338
  "is_parallel": true,
339
- "self": 302.1495512562833,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
- "total": 1087.6720943382825,
343
- "count": 11040608,
344
  "is_parallel": true,
345
- "self": 1087.6720943382825
346
  }
347
  }
348
  }
349
  }
350
  },
351
  "steps_from_proto": {
352
- "total": 0.10935510318086017,
353
- "count": 198,
354
  "is_parallel": true,
355
- "self": 0.024676639237441123,
356
  "children": {
357
  "_process_rank_one_or_two_observation": {
358
- "total": 0.08467846394341905,
359
- "count": 792,
360
  "is_parallel": true,
361
- "self": 0.08467846394341905
362
  }
363
  }
364
  }
@@ -369,31 +369,31 @@
369
  }
370
  },
371
  "trainer_advance": {
372
- "total": 7968.700233129013,
373
- "count": 1380077,
374
- "self": 149.00522160236142,
375
  "children": {
376
  "process_trajectory": {
377
- "total": 4680.821699632623,
378
- "count": 1380077,
379
- "self": 4673.2879647226655,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
- "total": 7.533734909957275,
383
- "count": 40,
384
- "self": 7.533734909957275
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
- "total": 3138.873311894029,
390
- "count": 967,
391
- "self": 1487.647303281352,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
- "total": 1651.226008612677,
395
- "count": 29019,
396
- "self": 1651.226008612677
397
  }
398
  }
399
  }
@@ -402,19 +402,19 @@
402
  }
403
  },
404
  "trainer_threads": {
405
- "total": 6.299960659816861e-07,
406
  "count": 1,
407
- "self": 6.299960659816861e-07
408
  },
409
  "TrainerController._save_models": {
410
- "total": 0.18734857499657664,
411
  "count": 1,
412
- "self": 0.001968117998330854,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
- "total": 0.1853804569982458,
416
  "count": 1,
417
- "self": 0.1853804569982458
418
  }
419
  }
420
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.671779990196228,
6
+ "min": 1.483157753944397,
7
+ "max": 3.29573392868042,
8
+ "count": 2172
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 33328.60546875,
12
+ "min": 21977.736328125,
13
+ "max": 113948.734375,
14
+ "count": 2172
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 60.44578313253012,
18
+ "min": 40.98360655737705,
19
  "max": 999.0,
20
+ "count": 2172
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 20068.0,
24
  "min": 7992.0,
25
+ "max": 30456.0,
26
+ "count": 2172
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1539.0438597037996,
30
+ "min": 1201.7416295213911,
31
+ "max": 1632.7729248992605,
32
+ "count": 2169
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 255481.28071083073,
36
+ "min": 2407.9198778528084,
37
+ "max": 393499.67341582046,
38
+ "count": 2169
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 21719990.0,
42
+ "min": 9976.0,
43
+ "max": 21719990.0,
44
+ "count": 2172
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 21719990.0,
48
+ "min": 9976.0,
49
+ "max": 21719990.0,
50
+ "count": 2172
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.0039015451911836863,
54
+ "min": -0.16042177379131317,
55
+ "max": 0.18803301453590393,
56
+ "count": 2172
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -0.6437549591064453,
60
+ "min": -29.35718536376953,
61
+ "max": 25.85744285583496,
62
+ "count": 2172
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.0019325704779475927,
66
+ "min": -0.16366998851299286,
67
+ "max": 0.18803183734416962,
68
+ "count": 2172
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -0.3188741207122803,
72
+ "min": -29.809600830078125,
73
+ "max": 24.820201873779297,
74
+ "count": 2172
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 2172
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 2172
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": 0.049229092308969206,
90
+ "min": -0.615013333161672,
91
+ "max": 0.49932221902741325,
92
+ "count": 2172
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": 8.12280023097992,
96
+ "min": -58.684799790382385,
97
+ "max": 63.74240005016327,
98
+ "count": 2172
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": 0.049229092308969206,
102
+ "min": -0.615013333161672,
103
+ "max": 0.49932221902741325,
104
+ "count": 2172
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": 8.12280023097992,
108
+ "min": -58.684799790382385,
109
+ "max": 63.74240005016327,
110
+ "count": 2172
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 2172
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 2172
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.013729617009327436,
126
+ "min": 0.010989157442721383,
127
+ "max": 0.025509973475709557,
128
+ "count": 1052
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.013729617009327436,
132
+ "min": 0.010989157442721383,
133
+ "max": 0.025509973475709557,
134
+ "count": 1052
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.1058132159213225,
138
+ "min": 0.0009146183729171753,
139
+ "max": 0.1211084894835949,
140
+ "count": 1052
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.1058132159213225,
144
+ "min": 0.0009146183729171753,
145
+ "max": 0.1211084894835949,
146
+ "count": 1052
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.10755141600966453,
150
+ "min": 0.0009252421053436896,
151
+ "max": 0.12316837261120478,
152
+ "count": 1052
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.10755141600966453,
156
+ "min": 0.0009252421053436896,
157
+ "max": 0.12316837261120478,
158
+ "count": 1052
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 1052
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 1052
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
  "min": 0.20000000000000004,
175
  "max": 0.20000000000000007,
176
+ "count": 1052
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
  "min": 0.20000000000000004,
181
  "max": 0.20000000000000007,
182
+ "count": 1052
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
  "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
+ "count": 1052
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
  "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
+ "count": 1052
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1736415869",
200
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
201
+ "command_line_arguments": "/home/stefan/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos2 --no-graphics --torch-device cuda",
202
  "mlagents_version": "1.2.0.dev0",
203
  "mlagents_envs_version": "1.2.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.5.1+cu124",
206
  "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1736451844"
208
  },
209
+ "total": 35974.67269840401,
210
  "count": 1,
211
+ "self": 0.40740082100819563,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.010543634001805913,
215
  "count": 1,
216
+ "self": 0.010543634001805913
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 35974.254753949,
220
  "count": 1,
221
+ "self": 20.7283982641311,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 2.7039670909798588,
225
+ "count": 109,
226
+ "self": 2.7039670909798588
227
  },
228
  "TrainerController.advance": {
229
+ "total": 35950.661532302875,
230
+ "count": 1498144,
231
+ "self": 19.332999862155702,
232
  "children": {
233
  "env_step": {
234
+ "total": 27302.5172698968,
235
+ "count": 1498144,
236
+ "self": 16589.43508921757,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 10700.206373095512,
240
+ "count": 1498144,
241
+ "self": 123.36394279388333,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 10576.842430301629,
245
+ "count": 2730560,
246
+ "self": 10576.842430301629
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 12.875807583717688,
252
+ "count": 1498143,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 35929.36511270509,
257
+ "count": 1498143,
258
  "is_parallel": true,
259
+ "self": 21602.363495709753,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.0017083109996747226,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.0005188049835851416,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.001189506016089581,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.001189506016089581
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.02624909100268269,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.00038735600537620485,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.00039570599619764835,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.00039570599619764835
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.024261833001219202,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.024261833001219202
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.0012041959998896345,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.0002781369985314086,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.0009260590013582259,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.0009260590013582259
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
+ "total": 14326.880298964265,
319
+ "count": 1498142,
320
  "is_parallel": true,
321
+ "self": 481.7784100755889,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
+ "total": 320.9030825123482,
325
+ "count": 1498142,
326
  "is_parallel": true,
327
+ "self": 320.9030825123482
328
  },
329
  "communicator.exchange": {
330
+ "total": 12007.851514953283,
331
+ "count": 1498142,
332
  "is_parallel": true,
333
+ "self": 12007.851514953283
334
  },
335
  "steps_from_proto": {
336
+ "total": 1516.3472914230442,
337
+ "count": 2996284,
338
  "is_parallel": true,
339
+ "self": 327.8235669827118,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
+ "total": 1188.5237244403324,
343
+ "count": 11985136,
344
  "is_parallel": true,
345
+ "self": 1188.5237244403324
346
  }
347
  }
348
  }
349
  }
350
  },
351
  "steps_from_proto": {
352
+ "total": 0.12131803107331507,
353
+ "count": 216,
354
  "is_parallel": true,
355
+ "self": 0.026903044199571013,
356
  "children": {
357
  "_process_rank_one_or_two_observation": {
358
+ "total": 0.09441498687374406,
359
+ "count": 864,
360
  "is_parallel": true,
361
+ "self": 0.09441498687374406
362
  }
363
  }
364
  }
 
369
  }
370
  },
371
  "trainer_advance": {
372
+ "total": 8628.811262543917,
373
+ "count": 1498143,
374
+ "self": 161.23468632528238,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 5099.0348406058765,
378
+ "count": 1498143,
379
+ "self": 5092.362769061881,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
+ "total": 6.672071543995116,
383
+ "count": 43,
384
+ "self": 6.672071543995116
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
+ "total": 3368.541735612758,
390
+ "count": 1052,
391
+ "self": 1602.0031282262353,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
+ "total": 1766.538607386523,
395
+ "count": 31569,
396
+ "self": 1766.538607386523
397
  }
398
  }
399
  }
 
402
  }
403
  },
404
  "trainer_threads": {
405
+ "total": 7.300113793462515e-07,
406
  "count": 1,
407
+ "self": 7.300113793462515e-07
408
  },
409
  "TrainerController._save_models": {
410
+ "total": 0.16085556100006215,
411
  "count": 1,
412
+ "self": 0.001240865996805951,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
+ "total": 0.1596146950032562,
416
  "count": 1,
417
+ "self": 0.1596146950032562
418
  }
419
  }
420
  }
run_logs/training_status.json CHANGED
@@ -2,59 +2,59 @@
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
- "steps": 18499966,
6
- "file_path": "results/SoccerTwos4/SoccerTwos/SoccerTwos-18499966.onnx",
7
  "reward": 0.0,
8
- "creation_time": 1736487528.9478052,
9
  "auxillary_file_paths": [
10
- "results/SoccerTwos4/SoccerTwos/SoccerTwos-18499966.pt"
11
  ]
12
  },
13
  {
14
- "steps": 18999977,
15
- "file_path": "results/SoccerTwos4/SoccerTwos/SoccerTwos-18999977.onnx",
16
  "reward": 0.0,
17
- "creation_time": 1736488375.5893888,
18
  "auxillary_file_paths": [
19
- "results/SoccerTwos4/SoccerTwos/SoccerTwos-18999977.pt"
20
  ]
21
  },
22
  {
23
- "steps": 19499974,
24
- "file_path": "results/SoccerTwos4/SoccerTwos/SoccerTwos-19499974.onnx",
25
  "reward": 0.0,
26
- "creation_time": 1736489221.5790186,
27
  "auxillary_file_paths": [
28
- "results/SoccerTwos4/SoccerTwos/SoccerTwos-19499974.pt"
29
  ]
30
  },
31
  {
32
- "steps": 19999988,
33
- "file_path": "results/SoccerTwos4/SoccerTwos/SoccerTwos-19999988.onnx",
34
  "reward": 0.0,
35
- "creation_time": 1736490065.1545298,
36
  "auxillary_file_paths": [
37
- "results/SoccerTwos4/SoccerTwos/SoccerTwos-19999988.pt"
38
  ]
39
  },
40
  {
41
- "steps": 20000096,
42
- "file_path": "results/SoccerTwos4/SoccerTwos/SoccerTwos-20000096.onnx",
43
  "reward": 0.0,
44
- "creation_time": 1736490065.3754652,
45
  "auxillary_file_paths": [
46
- "results/SoccerTwos4/SoccerTwos/SoccerTwos-20000096.pt"
47
  ]
48
  }
49
  ],
50
- "elo": 1644.9639826116972,
51
  "final_checkpoint": {
52
- "steps": 20000096,
53
- "file_path": "results/SoccerTwos4/SoccerTwos.onnx",
54
  "reward": 0.0,
55
- "creation_time": 1736490065.3754652,
56
  "auxillary_file_paths": [
57
- "results/SoccerTwos4/SoccerTwos/SoccerTwos-20000096.pt"
58
  ]
59
  }
60
  },
 
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
+ "steps": 19999980,
6
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-19999980.onnx",
7
  "reward": 0.0,
8
+ "creation_time": 1736448985.2888618,
9
  "auxillary_file_paths": [
10
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-19999980.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 20499991,
15
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-20499991.onnx",
16
  "reward": 0.0,
17
+ "creation_time": 1736449809.9148192,
18
  "auxillary_file_paths": [
19
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-20499991.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 20999933,
24
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-20999933.onnx",
25
  "reward": 0.0,
26
+ "creation_time": 1736450640.0455768,
27
  "auxillary_file_paths": [
28
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-20999933.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 21499984,
33
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-21499984.onnx",
34
  "reward": 0.0,
35
+ "creation_time": 1736451458.8435163,
36
  "auxillary_file_paths": [
37
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-21499984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 21729750,
42
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-21729750.onnx",
43
  "reward": 0.0,
44
+ "creation_time": 1736451843.9072433,
45
  "auxillary_file_paths": [
46
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-21729750.pt"
47
  ]
48
  }
49
  ],
50
+ "elo": 1543.5812182782277,
51
  "final_checkpoint": {
52
+ "steps": 21729750,
53
+ "file_path": "results/SoccerTwos2/SoccerTwos.onnx",
54
  "reward": 0.0,
55
+ "creation_time": 1736451843.9072433,
56
  "auxillary_file_paths": [
57
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-21729750.pt"
58
  ]
59
  }
60
  },