nlamot commited on
Commit
47cd992
1 Parent(s): 5c58095

10M steps, increased learning rate with linear scheduler

Browse files
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8171b9f22f3de0dfac49f68c4df948d5cda20dc11b6a2d73b5e244d153896472
3
  size 1768747
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03619a542b658ecd6cbb3d9622e7ceedf7c91bffb499d3ffe4379e73cb8d99f1
3
  size 1768747
SoccerTwos/SoccerTwos-10000180.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03619a542b658ecd6cbb3d9622e7ceedf7c91bffb499d3ffe4379e73cb8d99f1
3
+ size 1768747
SoccerTwos/SoccerTwos-10000180.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf2617282af0cec18607ee4d7db88dc65920459a612f766625aea1c31f81354
3
+ size 28430482
SoccerTwos/SoccerTwos-8499872.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68806773524a03c2b728334643013dc61551c5ee0dd1b314355ef476498f18fd
3
+ size 1768747
SoccerTwos/SoccerTwos-8499872.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38e7b9bfc9296dd277014c73db2b9017c4f4384d5e3dd1cfc6f40b5f44ebbd8e
3
+ size 28430358
SoccerTwos/SoccerTwos-8999958.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea22ee0f34553843b26385e0bb2e31e752694338074fdd570ced047da073ccef
3
+ size 1768747
SoccerTwos/SoccerTwos-8999958.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be92998cb948b03f6129c0b1feb970f0562c17f05ef30514f3fa983d8f77dd29
3
+ size 28430358
SoccerTwos/SoccerTwos-9499928.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4eac4ea0e6859aa55e743e799fc735d6948a74e70bf36eaefb0a6e1be2e9ac
3
+ size 1768747
SoccerTwos/SoccerTwos-9499928.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fabcfb5c36354cb1f7a91df2e04b5bcb112d4ae4f6d00b43f0f67cb90a9ef37
3
+ size 28430358
SoccerTwos/SoccerTwos-9999962.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03619a542b658ecd6cbb3d9622e7ceedf7c91bffb499d3ffe4379e73cb8d99f1
3
+ size 1768747
SoccerTwos/SoccerTwos-9999962.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce8a20a48cc08457607c17781129ded606114221477e352ce2b6e89586d8e619
3
+ size 28430358
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:722fe59ebe4db88e2dd4d2191dfc0ba389035dbf97e91c45a728de4768562749
3
  size 28429366
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a0f0b918bbd5ee299916d5d441286fa3b232800e3a12ef7d593c1f13f8a502
3
  size 28429366
SoccerTwos/events.out.tfevents.1703855990.nilss-mbp.lan.63432.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9843a985611ef4ed491f19e429eb314a3583aa551fac477561c944aac4a300
3
+ size 10069153
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 250000, "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.app", "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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 10000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 250000, "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.app", "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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -37,7 +37,7 @@ behaviors:
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
- max_steps: 5000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
 
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
+ max_steps: 10000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
run_logs/Player-0.log CHANGED
@@ -10,7 +10,7 @@ NullGfxDevice:
10
  Renderer: Null Device
11
  Vendor: Unity Technologies
12
  Begin MonoManager ReloadAssembly
13
- - Completed reload, in 0.034 seconds
14
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
15
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -35,7 +35,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
35
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
36
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
37
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
38
- UnloadTime: 0.204709 ms
39
  Registered Communicator in Agent.
40
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
41
  TOO LONG
@@ -475,74 +475,13 @@ 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
- Thread 0x1711cf000 may have been prematurely finalized
540
  Setting up 6 worker threads for Enlighten.
541
  Memory Statistics:
542
  [ALLOC_TEMP_TLS] TLS Allocator
543
  StackAllocators :
544
  [ALLOC_TEMP_MAIN]
545
- Peak usage frame count: [8.0 KB-16.0 KB]: 94692 frames, [2.0 MB-4.0 MB]: 1 frames
546
  Initial Block Size 4.0 MB
547
  Current Block Size 4.0 MB
548
  Peak Allocated Bytes 2.1 MB
@@ -570,7 +509,7 @@ Memory Statistics:
570
  [ALLOC_TEMP_Job.Worker 0]
571
  Initial Block Size 256.0 KB
572
  Current Block Size 256.0 KB
573
- Peak Allocated Bytes 0 B
574
  Overflow Count 0
575
  [ALLOC_TEMP_Background Job.Worker 10]
576
  Initial Block Size 32.0 KB
@@ -605,7 +544,7 @@ Memory Statistics:
605
  [ALLOC_TEMP_Job.Worker 3]
606
  Initial Block Size 256.0 KB
607
  Current Block Size 256.0 KB
608
- Peak Allocated Bytes 0.7 KB
609
  Overflow Count 0
610
  [ALLOC_TEMP_Background Job.Worker 12]
611
  Initial Block Size 32.0 KB
@@ -713,22 +652,22 @@ Memory Statistics:
713
  Peak Allocated Bytes 0 B
714
  Overflow Count 0
715
  [ALLOC_DEFAULT] Dual Thread Allocator
716
- Peak main deferred allocation count 6
717
  [ALLOC_BUCKET]
718
  Large Block size 4.0 MB
719
  Used Block count 1
720
  Peak Allocated bytes 1.0 MB
721
  [ALLOC_DEFAULT_MAIN]
722
- Peak usage frame count: [4.0 MB-8.0 MB]: 94693 frames
723
  Requested Block Size 16.0 MB
724
  Peak Block count 1
725
  Peak Allocated memory 5.0 MB
726
  Peak Large allocation bytes 0 B
727
  [ALLOC_DEFAULT_THREAD]
728
- Peak usage frame count: [16.0 MB-32.0 MB]: 94693 frames
729
  Requested Block Size 16.0 MB
730
  Peak Block count 1
731
- Peak Allocated memory 17.4 MB
732
  Peak Large allocation bytes 16.0 MB
733
  [ALLOC_TEMP_JOB_1_FRAME]
734
  Initial Block Size 2.0 MB
@@ -757,13 +696,13 @@ Memory Statistics:
757
  Used Block count 1
758
  Peak Allocated bytes 1.0 MB
759
  [ALLOC_GFX_MAIN]
760
- Peak usage frame count: [32.0 KB-64.0 KB]: 94692 frames, [64.0 KB-128.0 KB]: 1 frames
761
  Requested Block Size 16.0 MB
762
  Peak Block count 1
763
  Peak Allocated memory 65.6 KB
764
  Peak Large allocation bytes 0 B
765
  [ALLOC_GFX_THREAD]
766
- Peak usage frame count: [128.0 KB-256.0 KB]: 94693 frames
767
  Requested Block Size 16.0 MB
768
  Peak Block count 1
769
  Peak Allocated memory 173.5 KB
@@ -775,13 +714,13 @@ Memory Statistics:
775
  Used Block count 1
776
  Peak Allocated bytes 1.0 MB
777
  [ALLOC_CACHEOBJECTS_MAIN]
778
- Peak usage frame count: [0.5 MB-1.0 MB]: 94693 frames
779
  Requested Block Size 4.0 MB
780
  Peak Block count 1
781
  Peak Allocated memory 0.6 MB
782
  Peak Large allocation bytes 0 B
783
  [ALLOC_CACHEOBJECTS_THREAD]
784
- Peak usage frame count: [0.5 MB-1.0 MB]: 94692 frames, [2.0 MB-4.0 MB]: 1 frames
785
  Requested Block Size 4.0 MB
786
  Peak Block count 1
787
  Peak Allocated memory 3.4 MB
@@ -793,13 +732,13 @@ Memory Statistics:
793
  Used Block count 1
794
  Peak Allocated bytes 1.0 MB
795
  [ALLOC_TYPETREE_MAIN]
796
- Peak usage frame count: [0-1.0 KB]: 94693 frames
797
  Requested Block Size 2.0 MB
798
  Peak Block count 1
799
  Peak Allocated memory 1.0 KB
800
  Peak Large allocation bytes 0 B
801
  [ALLOC_TYPETREE_THREAD]
802
- Peak usage frame count: [1.0 KB-2.0 KB]: 94692 frames, [2.0 KB-4.0 KB]: 1 frames
803
  Requested Block Size 2.0 MB
804
  Peak Block count 1
805
  Peak Allocated memory 2.2 KB
 
10
  Renderer: Null Device
11
  Vendor: Unity Technologies
12
  Begin MonoManager ReloadAssembly
13
+ - Completed reload, in 0.035 seconds
14
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
15
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
35
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
36
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
37
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
38
+ UnloadTime: 0.254209 ms
39
  Registered Communicator in Agent.
40
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
41
  TOO LONG
 
475
  TOO LONG
476
  TOO LONG
477
  TOO LONG
478
+ Thread 0x16f8ef000 may have been prematurely finalized
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
479
  Setting up 6 worker threads for Enlighten.
480
  Memory Statistics:
481
  [ALLOC_TEMP_TLS] TLS Allocator
482
  StackAllocators :
483
  [ALLOC_TEMP_MAIN]
484
+ Peak usage frame count: [8.0 KB-16.0 KB]: 188671 frames, [2.0 MB-4.0 MB]: 1 frames
485
  Initial Block Size 4.0 MB
486
  Current Block Size 4.0 MB
487
  Peak Allocated Bytes 2.1 MB
 
509
  [ALLOC_TEMP_Job.Worker 0]
510
  Initial Block Size 256.0 KB
511
  Current Block Size 256.0 KB
512
+ Peak Allocated Bytes 0.7 KB
513
  Overflow Count 0
514
  [ALLOC_TEMP_Background Job.Worker 10]
515
  Initial Block Size 32.0 KB
 
544
  [ALLOC_TEMP_Job.Worker 3]
545
  Initial Block Size 256.0 KB
546
  Current Block Size 256.0 KB
547
+ Peak Allocated Bytes 0 B
548
  Overflow Count 0
549
  [ALLOC_TEMP_Background Job.Worker 12]
550
  Initial Block Size 32.0 KB
 
652
  Peak Allocated Bytes 0 B
653
  Overflow Count 0
654
  [ALLOC_DEFAULT] Dual Thread Allocator
655
+ Peak main deferred allocation count 4
656
  [ALLOC_BUCKET]
657
  Large Block size 4.0 MB
658
  Used Block count 1
659
  Peak Allocated bytes 1.0 MB
660
  [ALLOC_DEFAULT_MAIN]
661
+ Peak usage frame count: [4.0 MB-8.0 MB]: 188672 frames
662
  Requested Block Size 16.0 MB
663
  Peak Block count 1
664
  Peak Allocated memory 5.0 MB
665
  Peak Large allocation bytes 0 B
666
  [ALLOC_DEFAULT_THREAD]
667
+ Peak usage frame count: [16.0 MB-32.0 MB]: 188672 frames
668
  Requested Block Size 16.0 MB
669
  Peak Block count 1
670
+ Peak Allocated memory 17.5 MB
671
  Peak Large allocation bytes 16.0 MB
672
  [ALLOC_TEMP_JOB_1_FRAME]
673
  Initial Block Size 2.0 MB
 
696
  Used Block count 1
697
  Peak Allocated bytes 1.0 MB
698
  [ALLOC_GFX_MAIN]
699
+ Peak usage frame count: [32.0 KB-64.0 KB]: 188671 frames, [64.0 KB-128.0 KB]: 1 frames
700
  Requested Block Size 16.0 MB
701
  Peak Block count 1
702
  Peak Allocated memory 65.6 KB
703
  Peak Large allocation bytes 0 B
704
  [ALLOC_GFX_THREAD]
705
+ Peak usage frame count: [128.0 KB-256.0 KB]: 188672 frames
706
  Requested Block Size 16.0 MB
707
  Peak Block count 1
708
  Peak Allocated memory 173.5 KB
 
714
  Used Block count 1
715
  Peak Allocated bytes 1.0 MB
716
  [ALLOC_CACHEOBJECTS_MAIN]
717
+ Peak usage frame count: [0.5 MB-1.0 MB]: 188672 frames
718
  Requested Block Size 4.0 MB
719
  Peak Block count 1
720
  Peak Allocated memory 0.6 MB
721
  Peak Large allocation bytes 0 B
722
  [ALLOC_CACHEOBJECTS_THREAD]
723
+ Peak usage frame count: [0.5 MB-1.0 MB]: 188671 frames, [2.0 MB-4.0 MB]: 1 frames
724
  Requested Block Size 4.0 MB
725
  Peak Block count 1
726
  Peak Allocated memory 3.4 MB
 
732
  Used Block count 1
733
  Peak Allocated bytes 1.0 MB
734
  [ALLOC_TYPETREE_MAIN]
735
+ Peak usage frame count: [0-1.0 KB]: 188672 frames
736
  Requested Block Size 2.0 MB
737
  Peak Block count 1
738
  Peak Allocated memory 1.0 KB
739
  Peak Large allocation bytes 0 B
740
  [ALLOC_TYPETREE_THREAD]
741
+ Peak usage frame count: [1.0 KB-2.0 KB]: 188671 frames, [2.0 KB-4.0 KB]: 1 frames
742
  Requested Block Size 2.0 MB
743
  Peak Block count 1
744
  Peak Allocated memory 2.2 KB
run_logs/timers.json CHANGED
@@ -2,201 +2,201 @@
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 1.755637288093567,
6
- "min": 1.7151814699172974,
7
- "max": 3.295724630355835,
8
- "count": 499
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 36910.51953125,
12
- "min": 13612.6572265625,
13
- "max": 172905.75,
14
- "count": 499
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 63.6125,
18
- "min": 39.645161290322584,
19
  "max": 999.0,
20
- "count": 499
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 20356.0,
24
- "min": 10692.0,
25
- "max": 31500.0,
26
- "count": 499
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1540.6404213531655,
30
- "min": 1197.4957713356807,
31
- "max": 1576.4143309371482,
32
- "count": 478
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 246502.4674165065,
36
- "min": 2399.421175774324,
37
- "max": 363079.2013600959,
38
- "count": 478
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 4999972.0,
42
- "min": 9254.0,
43
- "max": 4999972.0,
44
- "count": 500
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 4999972.0,
48
- "min": 9254.0,
49
- "max": 4999972.0,
50
- "count": 500
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": -0.034482039511203766,
54
- "min": -0.10746785998344421,
55
- "max": 0.16136549413204193,
56
- "count": 500
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": -5.517126083374023,
60
- "min": -22.675718307495117,
61
- "max": 27.432022094726562,
62
- "count": 500
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": -0.034504301846027374,
66
- "min": -0.11580751091241837,
67
- "max": 0.1590351015329361,
68
- "count": 500
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": -5.520688533782959,
72
- "min": -24.43538475036621,
73
- "max": 26.952106475830078,
74
- "count": 500
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 500
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 500
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": -0.08047500103712082,
90
- "min": -0.5921090895479376,
91
- "max": 0.4576799988746643,
92
- "count": 500
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": -12.876000165939331,
96
- "min": -66.35360014438629,
97
- "max": 60.00919944047928,
98
- "count": 500
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": -0.08047500103712082,
102
- "min": -0.5921090895479376,
103
- "max": 0.4576799988746643,
104
- "count": 500
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": -12.876000165939331,
108
- "min": -66.35360014438629,
109
- "max": 60.00919944047928,
110
- "count": 500
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 500
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 500
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
- "value": 0.015034021192695946,
126
- "min": 0.010941779592152064,
127
- "max": 0.024873137117053072,
128
- "count": 239
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
- "value": 0.015034021192695946,
132
- "min": 0.010941779592152064,
133
- "max": 0.024873137117053072,
134
- "count": 239
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
- "value": 0.11739198019107183,
138
- "min": 3.1021232795562052e-06,
139
- "max": 0.1251884085436662,
140
- "count": 239
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
- "value": 0.11739198019107183,
144
- "min": 3.1021232795562052e-06,
145
- "max": 0.1251884085436662,
146
- "count": 239
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
- "value": 0.11775108724832535,
150
- "min": 3.304618659664508e-06,
151
- "max": 0.1258082126577695,
152
- "count": 239
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
- "value": 0.11775108724832535,
156
- "min": 3.304618659664508e-06,
157
- "max": 0.1258082126577695,
158
- "count": 239
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
- "value": 1.0132997973599917e-06,
162
- "min": 1.0132997973599917e-06,
163
- "max": 0.0004968980006203998,
164
- "count": 239
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
- "value": 1.0132997973599917e-06,
168
- "min": 1.0132997973599917e-06,
169
- "max": 0.0004968980006203998,
170
- "count": 239
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
- "value": 0.10020264000000001,
174
- "min": 0.10020264000000001,
175
- "max": 0.19937960000000005,
176
- "count": 239
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
- "value": 0.10020264000000001,
180
- "min": 0.10020264000000001,
181
- "max": 0.19937960000000005,
182
- "count": 239
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
- "value": 2.0111735999999927e-05,
186
- "min": 2.0111735999999927e-05,
187
- "max": 0.004969042040000001,
188
- "count": 239
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
- "value": 2.0111735999999927e-05,
192
- "min": 2.0111735999999927e-05,
193
- "max": 0.004969042040000001,
194
- "count": 239
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1703848764",
200
  "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]",
201
  "command_line_arguments": "/opt/homebrew/Caskroom/miniconda/base/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force",
202
  "mlagents_version": "1.1.0.dev0",
@@ -204,103 +204,103 @@
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.1.2",
206
  "numpy_version": "1.23.5",
207
- "end_time_seconds": "1703853889"
208
  },
209
- "total": 5124.430119083001,
210
  "count": 1,
211
- "self": 0.19001916600973345,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.012270416977116838,
215
  "count": 1,
216
- "self": 0.012270416977116838
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 5124.227829500014,
220
  "count": 1,
221
- "self": 2.531355981802335,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 1.5887895020714495,
225
- "count": 20,
226
- "self": 1.5887895020714495
227
  },
228
  "TrainerController.advance": {
229
- "total": 5119.955040642148,
230
- "count": 341985,
231
- "self": 2.185286336200079,
232
  "children": {
233
  "env_step": {
234
- "total": 2303.891035468987,
235
- "count": 341985,
236
- "self": 1941.7491068352829,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 360.6655651805049,
240
- "count": 341985,
241
- "self": 11.17105897743022,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 349.4945062030747,
245
- "count": 631296,
246
- "self": 349.4945062030747
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 1.4763634531991556,
252
- "count": 341985,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 5119.23122701954,
257
- "count": 341985,
258
  "is_parallel": true,
259
- "self": 3492.6540978672565,
260
  "children": {
261
  "steps_from_proto": {
262
- "total": 0.013060167053481564,
263
- "count": 40,
264
  "is_parallel": true,
265
- "self": 0.0021915972174610943,
266
  "children": {
267
  "_process_rank_one_or_two_observation": {
268
- "total": 0.01086856983602047,
269
- "count": 160,
270
  "is_parallel": true,
271
- "self": 0.01086856983602047
272
  }
273
  }
274
  },
275
  "UnityEnvironment.step": {
276
- "total": 1626.5640689852298,
277
- "count": 341985,
278
  "is_parallel": true,
279
- "self": 78.99318619386759,
280
  "children": {
281
  "UnityEnvironment._generate_step_input": {
282
- "total": 37.23996753204847,
283
- "count": 341985,
284
  "is_parallel": true,
285
- "self": 37.23996753204847
286
  },
287
  "communicator.exchange": {
288
- "total": 1310.1512493426271,
289
- "count": 341985,
290
  "is_parallel": true,
291
- "self": 1310.1512493426271
292
  },
293
  "steps_from_proto": {
294
- "total": 200.17966591668664,
295
- "count": 683970,
296
  "is_parallel": true,
297
- "self": 30.950994182756403,
298
  "children": {
299
  "_process_rank_one_or_two_observation": {
300
- "total": 169.22867173393024,
301
- "count": 2735880,
302
  "is_parallel": true,
303
- "self": 169.22867173393024
304
  }
305
  }
306
  }
@@ -313,31 +313,31 @@
313
  }
314
  },
315
  "trainer_advance": {
316
- "total": 2813.8787188369606,
317
- "count": 341985,
318
- "self": 21.16630858287681,
319
  "children": {
320
  "process_trajectory": {
321
- "total": 556.1312195862702,
322
- "count": 341985,
323
- "self": 554.5936779602489,
324
  "children": {
325
  "RLTrainer._checkpoint": {
326
- "total": 1.537541626021266,
327
- "count": 10,
328
- "self": 1.537541626021266
329
  }
330
  }
331
  },
332
  "_update_policy": {
333
- "total": 2236.5811906678136,
334
- "count": 239,
335
- "self": 242.41541127837263,
336
  "children": {
337
  "TorchPOCAOptimizer.update": {
338
- "total": 1994.165779389441,
339
- "count": 7185,
340
- "self": 1994.165779389441
341
  }
342
  }
343
  }
@@ -346,19 +346,19 @@
346
  }
347
  },
348
  "trainer_threads": {
349
- "total": 3.3300602808594704e-07,
350
  "count": 1,
351
- "self": 3.3300602808594704e-07
352
  },
353
  "TrainerController._save_models": {
354
- "total": 0.15264304098673165,
355
  "count": 1,
356
- "self": 0.000656957970932126,
357
  "children": {
358
  "RLTrainer._checkpoint": {
359
- "total": 0.15198608301579952,
360
  "count": 1,
361
- "self": 0.15198608301579952
362
  }
363
  }
364
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.1532409191131592,
6
+ "min": 1.1196668148040771,
7
+ "max": 3.2957353591918945,
8
+ "count": 1000
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 23987.41015625,
12
+ "min": 7871.72021484375,
13
+ "max": 112492.0390625,
14
+ "count": 1000
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 62.79746835443038,
18
+ "min": 45.00917431192661,
19
  "max": 999.0,
20
+ "count": 1000
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19844.0,
24
+ "min": 7992.0,
25
+ "max": 30788.0,
26
+ "count": 1000
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1709.0109510622178,
30
+ "min": 1190.391640367494,
31
+ "max": 1720.9898581771342,
32
+ "count": 991
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 270023.7302678304,
36
+ "min": 2381.3820137520165,
37
+ "max": 367918.0238814893,
38
+ "count": 991
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 9999962.0,
42
+ "min": 9412.0,
43
+ "max": 9999962.0,
44
+ "count": 1000
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 9999962.0,
48
+ "min": 9412.0,
49
+ "max": 9999962.0,
50
+ "count": 1000
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.01338563859462738,
54
+ "min": -0.11655034869909286,
55
+ "max": 0.16845153272151947,
56
+ "count": 1000
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 2.1149308681488037,
60
+ "min": -22.494216918945312,
61
+ "max": 23.403825759887695,
62
+ "count": 1000
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.014068040996789932,
66
+ "min": -0.11802836507558823,
67
+ "max": 0.17341575026512146,
68
+ "count": 1000
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 2.222750425338745,
72
+ "min": -22.422487258911133,
73
+ "max": 22.71746253967285,
74
+ "count": 1000
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 1000
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 1000
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.0220329112644437,
90
+ "min": -0.5286444425582886,
91
+ "max": 0.40512195447596105,
92
+ "count": 1000
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -3.4811999797821045,
96
+ "min": -57.29039967060089,
97
+ "max": 47.71400010585785,
98
+ "count": 1000
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.0220329112644437,
102
+ "min": -0.5286444425582886,
103
+ "max": 0.40512195447596105,
104
+ "count": 1000
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -3.4811999797821045,
108
+ "min": -57.29039967060089,
109
+ "max": 47.71400010585785,
110
+ "count": 1000
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 1000
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 1000
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.018708063105683927,
126
+ "min": 0.01079763230518438,
127
+ "max": 0.0237867681561814,
128
+ "count": 482
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.018708063105683927,
132
+ "min": 0.01079763230518438,
133
+ "max": 0.0237867681561814,
134
+ "count": 482
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.10804408763845762,
138
+ "min": 0.0008606591868253115,
139
+ "max": 0.1229787160952886,
140
+ "count": 482
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.10804408763845762,
144
+ "min": 0.0008606591868253115,
145
+ "max": 0.1229787160952886,
146
+ "count": 482
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.10806638523936271,
150
+ "min": 0.0008650216366125581,
151
+ "max": 0.12314595381418864,
152
+ "count": 482
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.10806638523936271,
156
+ "min": 0.0008650216366125581,
157
+ "max": 0.12314595381418864,
158
+ "count": 482
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 7.12599857500005e-07,
162
+ "min": 7.12599857500005e-07,
163
+ "max": 0.0004986521002695799,
164
+ "count": 482
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 7.12599857500005e-07,
168
+ "min": 7.12599857500005e-07,
169
+ "max": 0.0004986521002695799,
170
+ "count": 482
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.10014250000000001,
174
+ "min": 0.10014250000000001,
175
+ "max": 0.19973042,
176
+ "count": 482
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.10014250000000001,
180
+ "min": 0.10014250000000001,
181
+ "max": 0.19973042,
182
+ "count": 482
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 1.7110750000000053e-05,
186
+ "min": 1.7110750000000053e-05,
187
+ "max": 0.004986547957999999,
188
+ "count": 482
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 1.7110750000000053e-05,
192
+ "min": 1.7110750000000053e-05,
193
+ "max": 0.004986547957999999,
194
+ "count": 482
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1703855988",
200
  "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]",
201
  "command_line_arguments": "/opt/homebrew/Caskroom/miniconda/base/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force",
202
  "mlagents_version": "1.1.0.dev0",
 
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.1.2",
206
  "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1703866208"
208
  },
209
+ "total": 10219.73770537498,
210
  "count": 1,
211
+ "self": 0.19493024999974295,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.013058999989880249,
215
  "count": 1,
216
+ "self": 0.013058999989880249
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 10219.529716124991,
220
  "count": 1,
221
+ "self": 4.421711311646504,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 1.822008292976534,
225
+ "count": 40,
226
+ "self": 1.822008292976534
227
  },
228
  "TrainerController.advance": {
229
+ "total": 10213.13215393637,
230
+ "count": 681034,
231
+ "self": 3.9921176846837625,
232
  "children": {
233
  "env_step": {
234
+ "total": 4570.680127619009,
235
+ "count": 681034,
236
+ "self": 3851.7968664654472,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 715.9787979857938,
240
+ "count": 681034,
241
+ "self": 21.6306824052881,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 694.3481155805057,
245
+ "count": 1257830,
246
+ "self": 694.3481155805057
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 2.9044631677679718,
252
+ "count": 681034,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 10211.220314579754,
257
+ "count": 681034,
258
  "is_parallel": true,
259
+ "self": 6963.624994570651,
260
  "children": {
261
  "steps_from_proto": {
262
+ "total": 0.025804257107665762,
263
+ "count": 80,
264
  "is_parallel": true,
265
+ "self": 0.00424826008384116,
266
  "children": {
267
  "_process_rank_one_or_two_observation": {
268
+ "total": 0.021555997023824602,
269
+ "count": 320,
270
  "is_parallel": true,
271
+ "self": 0.021555997023824602
272
  }
273
  }
274
  },
275
  "UnityEnvironment.step": {
276
+ "total": 3247.569515751995,
277
+ "count": 681034,
278
  "is_parallel": true,
279
+ "self": 157.49633839310263,
280
  "children": {
281
  "UnityEnvironment._generate_step_input": {
282
+ "total": 75.07220318031614,
283
+ "count": 681034,
284
  "is_parallel": true,
285
+ "self": 75.07220318031614
286
  },
287
  "communicator.exchange": {
288
+ "total": 2617.271251162514,
289
+ "count": 681034,
290
  "is_parallel": true,
291
+ "self": 2617.271251162514
292
  },
293
  "steps_from_proto": {
294
+ "total": 397.72972301606205,
295
+ "count": 1362068,
296
  "is_parallel": true,
297
+ "self": 61.088766790606314,
298
  "children": {
299
  "_process_rank_one_or_two_observation": {
300
+ "total": 336.64095622545574,
301
+ "count": 5448272,
302
  "is_parallel": true,
303
+ "self": 336.64095622545574
304
  }
305
  }
306
  }
 
313
  }
314
  },
315
  "trainer_advance": {
316
+ "total": 5638.459908632678,
317
+ "count": 681034,
318
+ "self": 41.62850201164838,
319
  "children": {
320
  "process_trajectory": {
321
+ "total": 1114.3295763299102,
322
+ "count": 681034,
323
+ "self": 1111.2247817909229,
324
  "children": {
325
  "RLTrainer._checkpoint": {
326
+ "total": 3.104794538987335,
327
+ "count": 20,
328
+ "self": 3.104794538987335
329
  }
330
  }
331
  },
332
  "_update_policy": {
333
+ "total": 4482.501830291119,
334
+ "count": 482,
335
+ "self": 476.7318739280745,
336
  "children": {
337
  "TorchPOCAOptimizer.update": {
338
+ "total": 4005.769956363045,
339
+ "count": 14469,
340
+ "self": 4005.769956363045
341
  }
342
  }
343
  }
 
346
  }
347
  },
348
  "trainer_threads": {
349
+ "total": 2.500019036233425e-07,
350
  "count": 1,
351
+ "self": 2.500019036233425e-07
352
  },
353
  "TrainerController._save_models": {
354
+ "total": 0.15384233399527147,
355
  "count": 1,
356
+ "self": 0.0008283340139314532,
357
  "children": {
358
  "RLTrainer._checkpoint": {
359
+ "total": 0.15301399998134002,
360
  "count": 1,
361
+ "self": 0.15301399998134002
362
  }
363
  }
364
  }
run_logs/training_status.json CHANGED
@@ -2,59 +2,59 @@
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
- "steps": 3499990,
6
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499990.onnx",
7
  "reward": 0.0,
8
- "creation_time": 1703852337.048543,
9
  "auxillary_file_paths": [
10
- "results/SoccerTwos/SoccerTwos/SoccerTwos-3499990.pt"
11
  ]
12
  },
13
  {
14
- "steps": 3999988,
15
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999988.onnx",
16
  "reward": 0.0,
17
- "creation_time": 1703852850.532505,
18
  "auxillary_file_paths": [
19
- "results/SoccerTwos/SoccerTwos/SoccerTwos-3999988.pt"
20
  ]
21
  },
22
  {
23
- "steps": 4499985,
24
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499985.onnx",
25
  "reward": 0.0,
26
- "creation_time": 1703853379.401021,
27
  "auxillary_file_paths": [
28
- "results/SoccerTwos/SoccerTwos/SoccerTwos-4499985.pt"
29
  ]
30
  },
31
  {
32
- "steps": 4999972,
33
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999972.onnx",
34
  "reward": 0.0,
35
- "creation_time": 1703853888.732385,
36
  "auxillary_file_paths": [
37
- "results/SoccerTwos/SoccerTwos/SoccerTwos-4999972.pt"
38
  ]
39
  },
40
  {
41
- "steps": 5000376,
42
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5000376.onnx",
43
  "reward": 0.0,
44
- "creation_time": 1703853888.9599922,
45
  "auxillary_file_paths": [
46
- "results/SoccerTwos/SoccerTwos/SoccerTwos-5000376.pt"
47
  ]
48
  }
49
  ],
50
- "elo": 1543.402385883174,
51
  "final_checkpoint": {
52
- "steps": 5000376,
53
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
  "reward": 0.0,
55
- "creation_time": 1703853888.9599922,
56
  "auxillary_file_paths": [
57
- "results/SoccerTwos/SoccerTwos/SoccerTwos-5000376.pt"
58
  ]
59
  }
60
  },
 
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
+ "steps": 8499872,
6
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499872.onnx",
7
  "reward": 0.0,
8
+ "creation_time": 1703864672.0303428,
9
  "auxillary_file_paths": [
10
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-8499872.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 8999958,
15
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999958.onnx",
16
  "reward": 0.0,
17
+ "creation_time": 1703865186.172404,
18
  "auxillary_file_paths": [
19
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-8999958.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 9499928,
24
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499928.onnx",
25
  "reward": 0.0,
26
+ "creation_time": 1703865694.776364,
27
  "auxillary_file_paths": [
28
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-9499928.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 9999962,
33
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999962.onnx",
34
  "reward": 0.0,
35
+ "creation_time": 1703866208.272885,
36
  "auxillary_file_paths": [
37
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-9999962.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 10000180,
42
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000180.onnx",
43
  "reward": 0.0,
44
+ "creation_time": 1703866208.445204,
45
  "auxillary_file_paths": [
46
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-10000180.pt"
47
  ]
48
  }
49
  ],
50
+ "elo": 1709.4646768149448,
51
  "final_checkpoint": {
52
+ "steps": 10000180,
53
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
  "reward": 0.0,
55
+ "creation_time": 1703866208.445204,
56
  "auxillary_file_paths": [
57
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-10000180.pt"
58
  ]
59
  }
60
  },