Hugging Face's logo

manuu01
/
SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
manuu01 commited on
Commit
fff94c8
·
1 Parent(s): f81a4ee

First Push

Browse files
Files changed (12) hide show
  1. SoccerTwos.onnx +1 -1
  2. SoccerTwos/SoccerTwos-1499348.onnx +3 -0
  3. SoccerTwos/SoccerTwos-1499348.pt +3 -0
  4. SoccerTwos/SoccerTwos-1751370.onnx +3 -0
  5. SoccerTwos/SoccerTwos-1751370.pt +3 -0
  6. SoccerTwos/checkpoint.pt +1 -1
  7. SoccerTwos/events.out.tfevents.1690802701.720334159a77.15840.0 +3 -0
  8. config.json +1 -1
  9. configuration.yaml +4 -4
  10. run_logs/Player-0.log +15 -116
  11. run_logs/timers.json +195 -195
  12. run_logs/training_status.json +22 -4
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ef1eb322310a49fa4a0c37900dccb7abab7c893fea104866beadcf2e6e828c4
3
  size 886472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48150e39dc2c50405322ebf49893eeb1a7ac7ad1074c34f575627af617da3ed9
3
  size 886472
SoccerTwos/SoccerTwos-1499348.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894fbb92845a014ada39e6150671509bc8df6364ac1bed45a6dadf800343bb9b
3
+ size 886472
SoccerTwos/SoccerTwos-1499348.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5442bb11dc569f8ce6c5ac373acac76d617a69079b4c580b4f11835b51e69772
3
+ size 10304625
SoccerTwos/SoccerTwos-1751370.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48150e39dc2c50405322ebf49893eeb1a7ac7ad1074c34f575627af617da3ed9
3
+ size 886472
SoccerTwos/SoccerTwos-1751370.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936e004681d77604d78e4f383393a2690c8a69b40b4c5185f7f683183434bc99
3
+ size 10304625
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64ca3307ebf4b78bd394f33cc176d3ea4c07e1a35b39af044a3ada0a32e4adda
3
  size 10304625
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936e004681d77604d78e4f383393a2690c8a69b40b4c5185f7f683183434bc99
3
  size 10304625
SoccerTwos/events.out.tfevents.1690802701.720334159a77.15840.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:462f0f9fd035cf0fa641d77e01f1d35b446935ff666d8334a0421b5508e6056f
3
+ size 659078
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.00068, "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": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 1000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "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": 0.0006, "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": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 1750000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 2048
7
  buffer_size: 20480
8
- learning_rate: 0.00068
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -37,7 +37,7 @@ behaviors:
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
- max_steps: 1000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
@@ -72,8 +72,8 @@ checkpoint_settings:
72
  run_id: SoccerTwos
73
  initialize_from: null
74
  load_model: false
75
- resume: false
76
- force: true
77
  train_model: false
78
  inference: false
79
  results_dir: results
 
5
  hyperparameters:
6
  batch_size: 2048
7
  buffer_size: 20480
8
+ learning_rate: 0.0006
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
+ max_steps: 1750000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
 
72
  run_id: SoccerTwos
73
  initialize_from: null
74
  load_model: false
75
+ resume: true
76
+ force: false
77
  train_model: false
78
  inference: false
79
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.114 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -56,7 +56,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
56
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
57
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
58
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
59
- UnloadTime: 0.884234 ms
60
  Registered Communicator in Agent.
61
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
62
  requesting resize 84 x 84
@@ -320,113 +320,12 @@ TOO LONG
320
  TOO LONG
321
  TOO LONG
322
  TOO LONG
323
- TOO LONG
324
- TOO LONG
325
- TOO LONG
326
- TOO LONG
327
- TOO LONG
328
- TOO LONG
329
- TOO LONG
330
- TOO LONG
331
- TOO LONG
332
- TOO LONG
333
- TOO LONG
334
- TOO LONG
335
- TOO LONG
336
- TOO LONG
337
- TOO LONG
338
- TOO LONG
339
- TOO LONG
340
- TOO LONG
341
- TOO LONG
342
- TOO LONG
343
- TOO LONG
344
- TOO LONG
345
- TOO LONG
346
- TOO LONG
347
- TOO LONG
348
- TOO LONG
349
- TOO LONG
350
- TOO LONG
351
- TOO LONG
352
- TOO LONG
353
- TOO LONG
354
- TOO LONG
355
- TOO LONG
356
- TOO LONG
357
- TOO LONG
358
- TOO LONG
359
- TOO LONG
360
- TOO LONG
361
- TOO LONG
362
- TOO LONG
363
- TOO LONG
364
- TOO LONG
365
- TOO LONG
366
- TOO LONG
367
- TOO LONG
368
- TOO LONG
369
- TOO LONG
370
- TOO LONG
371
- TOO LONG
372
- TOO LONG
373
- TOO LONG
374
- TOO LONG
375
- TOO LONG
376
- TOO LONG
377
- TOO LONG
378
- TOO LONG
379
- TOO LONG
380
- TOO LONG
381
- TOO LONG
382
- TOO LONG
383
- TOO LONG
384
- TOO LONG
385
- TOO LONG
386
- TOO LONG
387
- TOO LONG
388
- TOO LONG
389
- TOO LONG
390
- TOO LONG
391
- TOO LONG
392
- TOO LONG
393
- TOO LONG
394
- TOO LONG
395
- TOO LONG
396
- TOO LONG
397
- TOO LONG
398
- TOO LONG
399
- TOO LONG
400
- TOO LONG
401
- TOO LONG
402
- TOO LONG
403
- TOO LONG
404
- TOO LONG
405
- TOO LONG
406
- TOO LONG
407
- TOO LONG
408
- TOO LONG
409
- TOO LONG
410
- TOO LONG
411
- TOO LONG
412
- TOO LONG
413
- TOO LONG
414
- TOO LONG
415
- TOO LONG
416
- TOO LONG
417
- TOO LONG
418
- TOO LONG
419
- TOO LONG
420
- TOO LONG
421
- TOO LONG
422
- TOO LONG
423
- TOO LONG
424
  Setting up 1 worker threads for Enlighten.
425
  Memory Statistics:
426
  [ALLOC_TEMP_TLS] TLS Allocator
427
  StackAllocators :
428
  [ALLOC_TEMP_MAIN]
429
- Peak usage frame count: [8.0 KB-16.0 KB]: 19313 frames, [2.0 MB-4.0 MB]: 1 frames
430
  Initial Block Size 4.0 MB
431
  Current Block Size 4.0 MB
432
  Peak Allocated Bytes 2.1 MB
@@ -542,22 +441,22 @@ Memory Statistics:
542
  Peak Allocated Bytes 0 B
543
  Overflow Count 0
544
  [ALLOC_DEFAULT] Dual Thread Allocator
545
- Peak main deferred allocation count 3
546
  [ALLOC_BUCKET]
547
  Large Block size 4.0 MB
548
  Used Block count 1
549
  Peak Allocated bytes 1.0 MB
550
  [ALLOC_DEFAULT_MAIN]
551
- Peak usage frame count: [4.0 MB-8.0 MB]: 19314 frames
552
  Requested Block Size 16.0 MB
553
  Peak Block count 1
554
- Peak Allocated memory 4.6 MB
555
  Peak Large allocation bytes 0 B
556
  [ALLOC_DEFAULT_THREAD]
557
- Peak usage frame count: [16.0 MB-32.0 MB]: 19314 frames
558
  Requested Block Size 16.0 MB
559
  Peak Block count 1
560
- Peak Allocated memory 17.6 MB
561
  Peak Large allocation bytes 16.0 MB
562
  [ALLOC_TEMP_JOB_1_FRAME]
563
  Initial Block Size 2.0 MB
@@ -586,13 +485,13 @@ Memory Statistics:
586
  Used Block count 1
587
  Peak Allocated bytes 1.0 MB
588
  [ALLOC_GFX_MAIN]
589
- Peak usage frame count: [32.0 KB-64.0 KB]: 19313 frames, [64.0 KB-128.0 KB]: 1 frames
590
  Requested Block Size 16.0 MB
591
  Peak Block count 1
592
  Peak Allocated memory 65.6 KB
593
  Peak Large allocation bytes 0 B
594
  [ALLOC_GFX_THREAD]
595
- Peak usage frame count: [128.0 KB-256.0 KB]: 19314 frames
596
  Requested Block Size 16.0 MB
597
  Peak Block count 1
598
  Peak Allocated memory 173.5 KB
@@ -604,16 +503,16 @@ Memory Statistics:
604
  Used Block count 1
605
  Peak Allocated bytes 1.0 MB
606
  [ALLOC_CACHEOBJECTS_MAIN]
607
- Peak usage frame count: [0.5 MB-1.0 MB]: 19314 frames
608
  Requested Block Size 4.0 MB
609
  Peak Block count 1
610
  Peak Allocated memory 0.6 MB
611
  Peak Large allocation bytes 0 B
612
  [ALLOC_CACHEOBJECTS_THREAD]
613
- Peak usage frame count: [0.5 MB-1.0 MB]: 19313 frames, [4.0 MB-8.0 MB]: 1 frames
614
  Requested Block Size 4.0 MB
615
  Peak Block count 2
616
- Peak Allocated memory 4.5 MB
617
  Peak Large allocation bytes 0 B
618
  [ALLOC_TYPETREE] Dual Thread Allocator
619
  Peak main deferred allocation count 0
@@ -622,13 +521,13 @@ Memory Statistics:
622
  Used Block count 1
623
  Peak Allocated bytes 1.0 MB
624
  [ALLOC_TYPETREE_MAIN]
625
- Peak usage frame count: [0-1.0 KB]: 19314 frames
626
  Requested Block Size 2.0 MB
627
  Peak Block count 1
628
  Peak Allocated memory 1.0 KB
629
  Peak Large allocation bytes 0 B
630
  [ALLOC_TYPETREE_THREAD]
631
- Peak usage frame count: [1.0 KB-2.0 KB]: 19313 frames, [2.0 KB-4.0 KB]: 1 frames
632
  Requested Block Size 2.0 MB
633
  Peak Block count 1
634
  Peak Allocated memory 2.2 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.077 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
56
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
57
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
58
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
59
+ UnloadTime: 0.738608 ms
60
  Registered Communicator in Agent.
61
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
62
  requesting resize 84 x 84
 
320
  TOO LONG
321
  TOO LONG
322
  TOO LONG
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
323
  Setting up 1 worker threads for Enlighten.
324
  Memory Statistics:
325
  [ALLOC_TEMP_TLS] TLS Allocator
326
  StackAllocators :
327
  [ALLOC_TEMP_MAIN]
328
+ Peak usage frame count: [8.0 KB-16.0 KB]: 14567 frames, [2.0 MB-4.0 MB]: 1 frames
329
  Initial Block Size 4.0 MB
330
  Current Block Size 4.0 MB
331
  Peak Allocated Bytes 2.1 MB
 
441
  Peak Allocated Bytes 0 B
442
  Overflow Count 0
443
  [ALLOC_DEFAULT] Dual Thread Allocator
444
+ Peak main deferred allocation count 7
445
  [ALLOC_BUCKET]
446
  Large Block size 4.0 MB
447
  Used Block count 1
448
  Peak Allocated bytes 1.0 MB
449
  [ALLOC_DEFAULT_MAIN]
450
+ Peak usage frame count: [4.0 MB-8.0 MB]: 14568 frames
451
  Requested Block Size 16.0 MB
452
  Peak Block count 1
453
+ Peak Allocated memory 4.9 MB
454
  Peak Large allocation bytes 0 B
455
  [ALLOC_DEFAULT_THREAD]
456
+ Peak usage frame count: [16.0 MB-32.0 MB]: 14568 frames
457
  Requested Block Size 16.0 MB
458
  Peak Block count 1
459
+ Peak Allocated memory 17.3 MB
460
  Peak Large allocation bytes 16.0 MB
461
  [ALLOC_TEMP_JOB_1_FRAME]
462
  Initial Block Size 2.0 MB
 
485
  Used Block count 1
486
  Peak Allocated bytes 1.0 MB
487
  [ALLOC_GFX_MAIN]
488
+ Peak usage frame count: [32.0 KB-64.0 KB]: 14567 frames, [64.0 KB-128.0 KB]: 1 frames
489
  Requested Block Size 16.0 MB
490
  Peak Block count 1
491
  Peak Allocated memory 65.6 KB
492
  Peak Large allocation bytes 0 B
493
  [ALLOC_GFX_THREAD]
494
+ Peak usage frame count: [128.0 KB-256.0 KB]: 14568 frames
495
  Requested Block Size 16.0 MB
496
  Peak Block count 1
497
  Peak Allocated memory 173.5 KB
 
503
  Used Block count 1
504
  Peak Allocated bytes 1.0 MB
505
  [ALLOC_CACHEOBJECTS_MAIN]
506
+ Peak usage frame count: [0.5 MB-1.0 MB]: 14568 frames
507
  Requested Block Size 4.0 MB
508
  Peak Block count 1
509
  Peak Allocated memory 0.6 MB
510
  Peak Large allocation bytes 0 B
511
  [ALLOC_CACHEOBJECTS_THREAD]
512
+ Peak usage frame count: [0.5 MB-1.0 MB]: 14567 frames, [4.0 MB-8.0 MB]: 1 frames
513
  Requested Block Size 4.0 MB
514
  Peak Block count 2
515
+ Peak Allocated memory 4.4 MB
516
  Peak Large allocation bytes 0 B
517
  [ALLOC_TYPETREE] Dual Thread Allocator
518
  Peak main deferred allocation count 0
 
521
  Used Block count 1
522
  Peak Allocated bytes 1.0 MB
523
  [ALLOC_TYPETREE_MAIN]
524
+ Peak usage frame count: [0-1.0 KB]: 14568 frames
525
  Requested Block Size 2.0 MB
526
  Peak Block count 1
527
  Peak Allocated memory 1.0 KB
528
  Peak Large allocation bytes 0 B
529
  [ALLOC_TYPETREE_THREAD]
530
+ Peak usage frame count: [1.0 KB-2.0 KB]: 14567 frames, [2.0 KB-4.0 KB]: 1 frames
531
  Requested Block Size 2.0 MB
532
  Peak Block count 1
533
  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": 3.20469331741333,
6
- "min": 3.1498255729675293,
7
- "max": 3.295821189880371,
8
- "count": 100
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 63683.6640625,
12
- "min": 23662.3125,
13
- "max": 137044.90625,
14
- "count": 100
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 722.125,
18
- "min": 395.38461538461536,
19
  "max": 999.0,
20
- "count": 100
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 23108.0,
24
- "min": 13184.0,
25
- "max": 28296.0,
26
- "count": 100
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1189.4461274867413,
30
- "min": 1187.0826509133083,
31
- "max": 1201.0977912678125,
32
- "count": 97
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 11894.461274867412,
36
- "min": 2379.8159612660293,
37
- "max": 28826.346990427497,
38
- "count": 97
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 999682.0,
42
- "min": 9164.0,
43
- "max": 999682.0,
44
- "count": 100
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 999682.0,
48
- "min": 9164.0,
49
- "max": 999682.0,
50
- "count": 100
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": -0.006089978851377964,
54
- "min": -0.04162906855344772,
55
- "max": 0.009263280779123306,
56
- "count": 100
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": -0.09134968370199203,
60
- "min": -0.8325814008712769,
61
- "max": 0.14792299270629883,
62
- "count": 100
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": -0.0059285550378263,
66
- "min": -0.04162818193435669,
67
- "max": 0.009343601763248444,
68
- "count": 100
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": -0.08892832696437836,
72
- "min": -0.8325636386871338,
73
- "max": 0.1494976282119751,
74
- "count": 100
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 100
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 100
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": -0.06562666520476342,
90
- "min": -0.6666666666666666,
91
- "max": 0.2659999983651297,
92
- "count": 100
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": -0.9843999780714512,
96
- "min": -10.875400021672249,
97
- "max": 4.179599940776825,
98
- "count": 100
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": -0.06562666520476342,
102
- "min": -0.6666666666666666,
103
- "max": 0.2659999983651297,
104
- "count": 100
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": -0.9843999780714512,
108
- "min": -10.875400021672249,
109
- "max": 4.179599940776825,
110
- "count": 100
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 100
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 100
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
- "value": 0.01881867732760535,
126
- "min": 0.011796388934211184,
127
- "max": 0.020308070812219133,
128
- "count": 47
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
- "value": 0.01881867732760535,
132
- "min": 0.011796388934211184,
133
- "max": 0.020308070812219133,
134
- "count": 47
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
- "value": 0.0033486348033572237,
138
- "min": 0.00041875260261197886,
139
- "max": 0.005762043905754884,
140
- "count": 47
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
- "value": 0.0033486348033572237,
144
- "min": 0.00041875260261197886,
145
- "max": 0.005762043905754884,
146
- "count": 47
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
- "value": 0.0033458727644756435,
150
- "min": 0.00041858676316527027,
151
- "max": 0.005755889120822152,
152
- "count": 47
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
- "value": 0.0033458727644756435,
156
- "min": 0.00041858676316527027,
157
- "max": 0.005755889120822152,
158
- "count": 47
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
- "value": 0.00068,
162
- "min": 0.00068,
163
- "max": 0.00068,
164
- "count": 47
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
- "value": 0.00068,
168
- "min": 0.00068,
169
- "max": 0.00068,
170
- "count": 47
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
  "min": 0.20000000000000007,
175
  "max": 0.20000000000000007,
176
- "count": 47
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
  "min": 0.20000000000000007,
181
  "max": 0.20000000000000007,
182
- "count": 47
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
  "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
- "count": 47
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
  "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
- "count": 47
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1690800381",
200
  "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
201
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
202
  "mlagents_version": "0.31.0.dev0",
203
  "mlagents_envs_version": "0.31.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
- "end_time_seconds": "1690802601"
208
  },
209
- "total": 2220.368459278,
210
  "count": 1,
211
- "self": 0.4373778620001758,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.04981371899998521,
215
  "count": 1,
216
- "self": 0.04981371899998521
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 2219.881267697,
220
  "count": 1,
221
- "self": 1.5373706650602799,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 5.757256694999796,
225
  "count": 5,
226
- "self": 5.757256694999796
227
  },
228
  "TrainerController.advance": {
229
- "total": 2212.38414801794,
230
- "count": 64956,
231
- "self": 1.6082940969035917,
232
  "children": {
233
  "env_step": {
234
- "total": 1779.804463524048,
235
- "count": 64956,
236
- "self": 1413.6381486379898,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 365.2640501449905,
240
- "count": 64956,
241
- "self": 10.623131436970425,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 354.6409187080201,
245
- "count": 128756,
246
- "self": 354.6409187080201
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 0.9022647410677109,
252
- "count": 64956,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 2215.5072469429488,
257
- "count": 64956,
258
  "is_parallel": true,
259
- "self": 1013.1376595699385,
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": 0.004715123999858406,
269
  "count": 2,
270
  "is_parallel": true,
271
- "self": 0.0009646319997500541,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
- "total": 0.003750492000108352,
275
  "count": 8,
276
  "is_parallel": true,
277
- "self": 0.003750492000108352
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
- "total": 0.03943582800002332,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.001177486000187855,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
- "total": 0.0008184289999917382,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.0008184289999917382
292
  },
293
  "communicator.exchange": {
294
- "total": 0.0338838370000758,
295
  "count": 1,
296
  "is_parallel": true,
297
- "self": 0.0338838370000758
298
  },
299
  "steps_from_proto": {
300
- "total": 0.003556075999767927,
301
  "count": 2,
302
  "is_parallel": true,
303
- "self": 0.0006104629999299505,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
- "total": 0.0029456129998379765,
307
  "count": 8,
308
  "is_parallel": true,
309
- "self": 0.0029456129998379765
310
  }
311
  }
312
  }
@@ -314,53 +314,53 @@
314
  }
315
  }
316
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
317
  "UnityEnvironment.step": {
318
- "total": 1202.3592523920104,
319
- "count": 64955,
320
  "is_parallel": true,
321
- "self": 73.24904941608384,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
- "total": 46.21440717892074,
325
- "count": 64955,
326
  "is_parallel": true,
327
- "self": 46.21440717892074
328
  },
329
  "communicator.exchange": {
330
- "total": 846.7622102650166,
331
- "count": 64955,
332
  "is_parallel": true,
333
- "self": 846.7622102650166
334
  },
335
  "steps_from_proto": {
336
- "total": 236.13358553198918,
337
- "count": 129910,
338
  "is_parallel": true,
339
- "self": 38.77184689510568,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
- "total": 197.3617386368835,
343
- "count": 519640,
344
  "is_parallel": true,
345
- "self": 197.3617386368835
346
  }
347
  }
348
  }
349
  }
350
- },
351
- "steps_from_proto": {
352
- "total": 0.010334980999914478,
353
- "count": 8,
354
- "is_parallel": true,
355
- "self": 0.0019170109994774975,
356
- "children": {
357
- "_process_rank_one_or_two_observation": {
358
- "total": 0.00841797000043698,
359
- "count": 32,
360
- "is_parallel": true,
361
- "self": 0.00841797000043698
362
- }
363
- }
364
  }
365
  }
366
  }
@@ -369,31 +369,31 @@
369
  }
370
  },
371
  "trainer_advance": {
372
- "total": 430.971390396988,
373
- "count": 64956,
374
- "self": 14.58198351796068,
375
  "children": {
376
  "process_trajectory": {
377
- "total": 107.66038898502825,
378
- "count": 64956,
379
- "self": 107.24490091502844,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
- "total": 0.41548806999981025,
383
- "count": 2,
384
- "self": 0.41548806999981025
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
- "total": 308.72901789399907,
390
- "count": 47,
391
- "self": 217.1962228049954,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
- "total": 91.53279508900368,
395
- "count": 1410,
396
- "self": 91.53279508900368
397
  }
398
  }
399
  }
@@ -402,19 +402,19 @@
402
  }
403
  },
404
  "trainer_threads": {
405
- "total": 1.0819999261002522e-06,
406
  "count": 1,
407
- "self": 1.0819999261002522e-06
408
  },
409
  "TrainerController._save_models": {
410
- "total": 0.2024912370002312,
411
  "count": 1,
412
- "self": 0.0016045230004237965,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
- "total": 0.2008867139998074,
416
  "count": 1,
417
- "self": 0.2008867139998074
418
  }
419
  }
420
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.1499600410461426,
6
+ "min": 3.131804943084717,
7
+ "max": 3.2054200172424316,
8
+ "count": 75
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 62394.40625,
12
+ "min": 23642.75390625,
13
+ "max": 107458.1953125,
14
+ "count": 75
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 898.3333333333334,
18
+ "min": 374.61538461538464,
19
  "max": 999.0,
20
+ "count": 75
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 21560.0,
24
+ "min": 12860.0,
25
+ "max": 24332.0,
26
+ "count": 75
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1180.009652463314,
30
+ "min": 1175.3909421129385,
31
+ "max": 1195.0985680196525,
32
+ "count": 74
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 4720.038609853256,
36
+ "min": 2353.013531603022,
37
+ "max": 21287.174162322914,
38
+ "count": 74
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 1749370.0,
42
+ "min": 1009872.0,
43
+ "max": 1749370.0,
44
+ "count": 75
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 1749370.0,
48
+ "min": 1009872.0,
49
+ "max": 1749370.0,
50
+ "count": 75
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.006868889555335045,
54
+ "min": -0.012761061079800129,
55
+ "max": 0.00510790292173624,
56
+ "count": 75
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -0.07555778324604034,
60
+ "min": -0.20322734117507935,
61
+ "max": 0.06640274077653885,
62
+ "count": 75
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.007158401422202587,
66
+ "min": -0.01327992882579565,
67
+ "max": 0.003901140997186303,
68
+ "count": 75
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -0.07874241471290588,
72
+ "min": -0.20052023231983185,
73
+ "max": 0.05071483179926872,
74
+ "count": 75
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 75
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 75
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.45454545454545453,
90
+ "min": -0.8571428571428571,
91
+ "max": 0.2841142937541008,
92
+ "count": 75
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -5.0,
96
+ "min": -18.0,
97
+ "max": 3.977600112557411,
98
+ "count": 75
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.45454545454545453,
102
+ "min": -0.8571428571428571,
103
+ "max": 0.2841142937541008,
104
+ "count": 75
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -5.0,
108
+ "min": -18.0,
109
+ "max": 3.977600112557411,
110
+ "count": 75
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 75
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 75
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.01296827703966604,
126
+ "min": 0.01035859460826032,
127
+ "max": 0.020192706960369834,
128
+ "count": 35
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.01296827703966604,
132
+ "min": 0.01035859460826032,
133
+ "max": 0.020192706960369834,
134
+ "count": 35
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.003657562037309011,
138
+ "min": 0.00014975956655689516,
139
+ "max": 0.005848652799613774,
140
+ "count": 35
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.003657562037309011,
144
+ "min": 0.00014975956655689516,
145
+ "max": 0.005848652799613774,
146
+ "count": 35
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.003660974717543771,
150
+ "min": 0.00014970306795779228,
151
+ "max": 0.005846056481823325,
152
+ "count": 35
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.003660974717543771,
156
+ "min": 0.00014970306795779228,
157
+ "max": 0.005846056481823325,
158
+ "count": 35
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0006,
162
+ "min": 0.0006,
163
+ "max": 0.0006,
164
+ "count": 35
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0006,
168
+ "min": 0.0006,
169
+ "max": 0.0006,
170
+ "count": 35
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
  "min": 0.20000000000000007,
175
  "max": 0.20000000000000007,
176
+ "count": 35
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
  "min": 0.20000000000000007,
181
  "max": 0.20000000000000007,
182
+ "count": 35
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
  "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
+ "count": 35
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
  "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
+ "count": 35
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1690802700",
200
  "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
201
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
202
  "mlagents_version": "0.31.0.dev0",
203
  "mlagents_envs_version": "0.31.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1690804337"
208
  },
209
+ "total": 1637.1034265750004,
210
  "count": 1,
211
+ "self": 0.43743649599946366,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.03295709200028796,
215
  "count": 1,
216
+ "self": 0.03295709200028796
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 1636.6330329870007,
220
  "count": 1,
221
+ "self": 1.2384253270329282,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 4.411428540999623,
225
  "count": 5,
226
+ "self": 4.411428540999623
227
  },
228
  "TrainerController.advance": {
229
+ "total": 1630.7821262879688,
230
+ "count": 48986,
231
+ "self": 1.2025667649395473,
232
  "children": {
233
  "env_step": {
234
+ "total": 1315.8824931099662,
235
+ "count": 48986,
236
+ "self": 1041.419592850044,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 273.7847717199202,
240
+ "count": 48986,
241
+ "self": 8.683908176870318,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 265.10086354304985,
245
+ "count": 97116,
246
+ "self": 265.10086354304985
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 0.6781285400020352,
252
+ "count": 48986,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 1632.950228529011,
257
+ "count": 48986,
258
  "is_parallel": true,
259
+ "self": 746.0876349919381,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.0030742639996788057,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.0008186979998754396,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.002255565999803366,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.002255565999803366
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.04315224199990553,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.0011571050004022254,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.000832507999803056,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.000832507999803056
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.0375344529998074,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.0375344529998074
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.0036281759998928464,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.0006268569991334516,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.003001319000759395,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.003001319000759395
310
  }
311
  }
312
  }
 
314
  }
315
  }
316
  },
317
+ "steps_from_proto": {
318
+ "total": 0.009482113999638386,
319
+ "count": 8,
320
+ "is_parallel": true,
321
+ "self": 0.0016659079992678016,
322
+ "children": {
323
+ "_process_rank_one_or_two_observation": {
324
+ "total": 0.007816206000370585,
325
+ "count": 32,
326
+ "is_parallel": true,
327
+ "self": 0.007816206000370585
328
+ }
329
+ }
330
+ },
331
  "UnityEnvironment.step": {
332
+ "total": 886.8531114230732,
333
+ "count": 48985,
334
  "is_parallel": true,
335
+ "self": 54.70159705391279,
336
  "children": {
337
  "UnityEnvironment._generate_step_input": {
338
+ "total": 34.29807094397165,
339
+ "count": 48985,
340
  "is_parallel": true,
341
+ "self": 34.29807094397165
342
  },
343
  "communicator.exchange": {
344
+ "total": 623.1118497290272,
345
+ "count": 48985,
346
  "is_parallel": true,
347
+ "self": 623.1118497290272
348
  },
349
  "steps_from_proto": {
350
+ "total": 174.74159369616154,
351
+ "count": 97970,
352
  "is_parallel": true,
353
+ "self": 28.404607733481043,
354
  "children": {
355
  "_process_rank_one_or_two_observation": {
356
+ "total": 146.3369859626805,
357
+ "count": 391880,
358
  "is_parallel": true,
359
+ "self": 146.3369859626805
360
  }
361
  }
362
  }
363
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
364
  }
365
  }
366
  }
 
369
  }
370
  },
371
  "trainer_advance": {
372
+ "total": 313.6970664130631,
373
+ "count": 48986,
374
+ "self": 9.754627132033875,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 77.68253720902749,
378
+ "count": 48986,
379
+ "self": 77.46875197402778,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
+ "total": 0.2137852349997047,
383
+ "count": 1,
384
+ "self": 0.2137852349997047
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
+ "total": 226.25990207200175,
390
+ "count": 35,
391
+ "self": 158.34996710201494,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
+ "total": 67.90993496998681,
395
+ "count": 1050,
396
+ "self": 67.90993496998681
397
  }
398
  }
399
  }
 
402
  }
403
  },
404
  "trainer_threads": {
405
+ "total": 1.4509996617562138e-06,
406
  "count": 1,
407
+ "self": 1.4509996617562138e-06
408
  },
409
  "TrainerController._save_models": {
410
+ "total": 0.20105137999962608,
411
  "count": 1,
412
+ "self": 0.0015652529991712072,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
+ "total": 0.19948612700045487,
416
  "count": 1,
417
+ "self": 0.19948612700045487
418
  }
419
  }
420
  }
run_logs/training_status.json CHANGED
@@ -27,16 +27,34 @@
27
  "auxillary_file_paths": [
28
  "results/SoccerTwos/SoccerTwos/SoccerTwos-1001682.pt"
29
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  }
31
  ],
32
- "elo": 1190.1290962287674,
33
  "final_checkpoint": {
34
- "steps": 1001682,
35
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
36
  "reward": 0.0,
37
- "creation_time": 1690802601.1996052,
38
  "auxillary_file_paths": [
39
- "results/SoccerTwos/SoccerTwos/SoccerTwos-1001682.pt"
40
  ]
41
  }
42
  },
 
27
  "auxillary_file_paths": [
28
  "results/SoccerTwos/SoccerTwos/SoccerTwos-1001682.pt"
29
  ]
30
+ },
31
+ {
32
+ "steps": 1499348,
33
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1499348.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1690803798.3821926,
36
+ "auxillary_file_paths": [
37
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-1499348.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 1751370,
42
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1751370.onnx",
43
+ "reward": 0.0,
44
+ "creation_time": 1690804337.4087615,
45
+ "auxillary_file_paths": [
46
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-1751370.pt"
47
+ ]
48
  }
49
  ],
50
+ "elo": 1179.2832617291297,
51
  "final_checkpoint": {
52
+ "steps": 1751370,
53
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
  "reward": 0.0,
55
+ "creation_time": 1690804337.4087615,
56
  "auxillary_file_paths": [
57
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-1751370.pt"
58
  ]
59
  }
60
  },