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
dd0f3b3
·
1 Parent(s): fff94c8

First Push

Browse files
Files changed (12) hide show
  1. SoccerTwos.onnx +1 -1
  2. SoccerTwos/SoccerTwos-1999160.onnx +3 -0
  3. SoccerTwos/SoccerTwos-1999160.pt +3 -0
  4. SoccerTwos/SoccerTwos-2251936.onnx +3 -0
  5. SoccerTwos/SoccerTwos-2251936.pt +3 -0
  6. SoccerTwos/checkpoint.pt +1 -1
  7. SoccerTwos/events.out.tfevents.1690804446.720334159a77.23069.0 +3 -0
  8. config.json +1 -1
  9. configuration.yaml +2 -2
  10. run_logs/Player-0.log +16 -74
  11. run_logs/timers.json +190 -190
  12. run_logs/training_status.json +22 -22
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48150e39dc2c50405322ebf49893eeb1a7ac7ad1074c34f575627af617da3ed9
3
  size 886472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d8fa1c483924b28248ed69c6c6a9c2156086ef46f1893584811cd194e535fb
3
  size 886472
SoccerTwos/SoccerTwos-1999160.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d958441c49450fd19994f8dd8df6b830c2dcd789229bae53b59d6dd53411b299
3
+ size 886472
SoccerTwos/SoccerTwos-1999160.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18d40358585d76d7f1902ad35e505021f635fcf249f8a037a07edaa4c580f23c
3
+ size 10304625
SoccerTwos/SoccerTwos-2251936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d8fa1c483924b28248ed69c6c6a9c2156086ef46f1893584811cd194e535fb
3
+ size 886472
SoccerTwos/SoccerTwos-2251936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b389f4e61a8548581d3f6c2a198dabc6c0a186f13faf4910d4d8e6b601b70aab
3
+ size 10304625
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:936e004681d77604d78e4f383393a2690c8a69b40b4c5185f7f683183434bc99
3
  size 10304625
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b389f4e61a8548581d3f6c2a198dabc6c0a186f13faf4910d4d8e6b601b70aab
3
  size 10304625
SoccerTwos/events.out.tfevents.1690804446.720334159a77.23069.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:597042ebcbe8b8e7a17ecd3c485ef5c11d9eedd8573b5c7de4a3f40a17c9fc0d
3
+ size 408331
config.json CHANGED
@@ -1 +1 @@
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}
 
1
+ {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.00055, "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": 2250000, "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: 0.0006
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: 1750000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
 
5
  hyperparameters:
6
  batch_size: 2048
7
  buffer_size: 20480
8
+ learning_rate: 0.00055
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: 2250000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
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 0.077 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)
@@ -56,7 +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: 0.738608 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
@@ -262,70 +262,12 @@ TOO LONG
262
  TOO LONG
263
  TOO LONG
264
  TOO LONG
265
- TOO LONG
266
- TOO LONG
267
- TOO LONG
268
- TOO LONG
269
- TOO LONG
270
- TOO LONG
271
- TOO LONG
272
- TOO LONG
273
- TOO LONG
274
- TOO LONG
275
- TOO LONG
276
- TOO LONG
277
- TOO LONG
278
- TOO LONG
279
- TOO LONG
280
- TOO LONG
281
- TOO LONG
282
- TOO LONG
283
- TOO LONG
284
- TOO LONG
285
- TOO LONG
286
- TOO LONG
287
- TOO LONG
288
- TOO LONG
289
- TOO LONG
290
- TOO LONG
291
- TOO LONG
292
- TOO LONG
293
- TOO LONG
294
- TOO LONG
295
- TOO LONG
296
- TOO LONG
297
- TOO LONG
298
- TOO LONG
299
- TOO LONG
300
- TOO LONG
301
- TOO LONG
302
- TOO LONG
303
- TOO LONG
304
- TOO LONG
305
- TOO LONG
306
- TOO LONG
307
- TOO LONG
308
- TOO LONG
309
- TOO LONG
310
- TOO LONG
311
- TOO LONG
312
- TOO LONG
313
- TOO LONG
314
- TOO LONG
315
- TOO LONG
316
- TOO LONG
317
- TOO LONG
318
- TOO LONG
319
- TOO LONG
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
@@ -353,7 +295,7 @@ Memory Statistics:
353
  [ALLOC_TEMP_Job.Worker 0]
354
  Initial Block Size 256.0 KB
355
  Current Block Size 256.0 KB
356
- Peak Allocated Bytes 0.7 KB
357
  Overflow Count 0
358
  [ALLOC_TEMP_Background Job.Worker 10]
359
  Initial Block Size 32.0 KB
@@ -441,22 +383,22 @@ Memory Statistics:
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
@@ -485,13 +427,13 @@ Memory Statistics:
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
@@ -503,16 +445,16 @@ Memory Statistics:
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
@@ -521,13 +463,13 @@ Memory Statistics:
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
 
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 0.119 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: 0.941001 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
 
262
  TOO LONG
263
  TOO LONG
264
  TOO LONG
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
265
  Setting up 1 worker threads for Enlighten.
266
  Memory Statistics:
267
  [ALLOC_TEMP_TLS] TLS Allocator
268
  StackAllocators :
269
  [ALLOC_TEMP_MAIN]
270
+ Peak usage frame count: [8.0 KB-16.0 KB]: 9764 frames, [2.0 MB-4.0 MB]: 1 frames
271
  Initial Block Size 4.0 MB
272
  Current Block Size 4.0 MB
273
  Peak Allocated Bytes 2.1 MB
 
295
  [ALLOC_TEMP_Job.Worker 0]
296
  Initial Block Size 256.0 KB
297
  Current Block Size 256.0 KB
298
+ Peak Allocated Bytes 0 B
299
  Overflow Count 0
300
  [ALLOC_TEMP_Background Job.Worker 10]
301
  Initial Block Size 32.0 KB
 
383
  Peak Allocated Bytes 0 B
384
  Overflow Count 0
385
  [ALLOC_DEFAULT] Dual Thread Allocator
386
+ Peak main deferred allocation count 5
387
  [ALLOC_BUCKET]
388
  Large Block size 4.0 MB
389
  Used Block count 1
390
  Peak Allocated bytes 1.0 MB
391
  [ALLOC_DEFAULT_MAIN]
392
+ Peak usage frame count: [4.0 MB-8.0 MB]: 9765 frames
393
  Requested Block Size 16.0 MB
394
  Peak Block count 1
395
+ Peak Allocated memory 4.6 MB
396
  Peak Large allocation bytes 0 B
397
  [ALLOC_DEFAULT_THREAD]
398
+ Peak usage frame count: [16.0 MB-32.0 MB]: 9765 frames
399
  Requested Block Size 16.0 MB
400
  Peak Block count 1
401
+ Peak Allocated memory 17.6 MB
402
  Peak Large allocation bytes 16.0 MB
403
  [ALLOC_TEMP_JOB_1_FRAME]
404
  Initial Block Size 2.0 MB
 
427
  Used Block count 1
428
  Peak Allocated bytes 1.0 MB
429
  [ALLOC_GFX_MAIN]
430
+ Peak usage frame count: [32.0 KB-64.0 KB]: 9764 frames, [64.0 KB-128.0 KB]: 1 frames
431
  Requested Block Size 16.0 MB
432
  Peak Block count 1
433
  Peak Allocated memory 65.6 KB
434
  Peak Large allocation bytes 0 B
435
  [ALLOC_GFX_THREAD]
436
+ Peak usage frame count: [128.0 KB-256.0 KB]: 9765 frames
437
  Requested Block Size 16.0 MB
438
  Peak Block count 1
439
  Peak Allocated memory 173.5 KB
 
445
  Used Block count 1
446
  Peak Allocated bytes 1.0 MB
447
  [ALLOC_CACHEOBJECTS_MAIN]
448
+ Peak usage frame count: [0.5 MB-1.0 MB]: 9765 frames
449
  Requested Block Size 4.0 MB
450
  Peak Block count 1
451
  Peak Allocated memory 0.6 MB
452
  Peak Large allocation bytes 0 B
453
  [ALLOC_CACHEOBJECTS_THREAD]
454
+ Peak usage frame count: [0.5 MB-1.0 MB]: 9764 frames, [4.0 MB-8.0 MB]: 1 frames
455
  Requested Block Size 4.0 MB
456
  Peak Block count 2
457
+ Peak Allocated memory 4.5 MB
458
  Peak Large allocation bytes 0 B
459
  [ALLOC_TYPETREE] Dual Thread Allocator
460
  Peak main deferred allocation count 0
 
463
  Used Block count 1
464
  Peak Allocated bytes 1.0 MB
465
  [ALLOC_TYPETREE_MAIN]
466
+ Peak usage frame count: [0-1.0 KB]: 9765 frames
467
  Requested Block Size 2.0 MB
468
  Peak Block count 1
469
  Peak Allocated memory 1.0 KB
470
  Peak Large allocation bytes 0 B
471
  [ALLOC_TYPETREE_THREAD]
472
+ Peak usage frame count: [1.0 KB-2.0 KB]: 9764 frames, [2.0 KB-4.0 KB]: 1 frames
473
  Requested Block Size 2.0 MB
474
  Peak Block count 1
475
  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": 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",
@@ -204,59 +204,59 @@
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,
@@ -265,48 +265,48 @@
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
  }
@@ -315,48 +315,48 @@
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
  }
@@ -369,31 +369,31 @@
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
  }
@@ -402,19 +402,19 @@
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
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.151453971862793,
6
+ "min": 3.127227544784546,
7
+ "max": 3.1760921478271484,
8
+ "count": 50
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 64037.54296875,
12
+ "min": 20419.759765625,
13
+ "max": 111017.0,
14
+ "count": 50
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 638.5,
18
+ "min": 478.72727272727275,
19
  "max": 999.0,
20
+ "count": 50
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 20432.0,
24
+ "min": 11828.0,
25
+ "max": 27064.0,
26
+ "count": 50
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1174.2121493977888,
30
+ "min": 1165.2629482200864,
31
+ "max": 1181.0289495804443,
32
+ "count": 47
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 9393.69719518231,
36
+ "min": 2336.271198475225,
37
+ "max": 16434.89980380847,
38
+ "count": 47
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 2249936.0,
42
+ "min": 1759929.0,
43
+ "max": 2249936.0,
44
+ "count": 50
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 2249936.0,
48
+ "min": 1759929.0,
49
+ "max": 2249936.0,
50
+ "count": 50
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.0031177180353552103,
54
+ "min": -0.00878502894192934,
55
+ "max": 0.0031177180353552103,
56
+ "count": 50
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 0.049883488565683365,
60
+ "min": -0.15813052654266357,
61
+ "max": 0.049883488565683365,
62
+ "count": 50
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.004119338467717171,
66
+ "min": -0.008890403434634209,
67
+ "max": 0.004119338467717171,
68
+ "count": 50
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 0.06590941548347473,
72
+ "min": -0.16002726554870605,
73
+ "max": 0.06590941548347473,
74
+ "count": 50
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 50
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 50
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.0622749999165535,
90
+ "min": -0.6666666666666666,
91
+ "max": 0.2682857151542391,
92
+ "count": 50
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -0.996399998664856,
96
+ "min": -10.0,
97
+ "max": 3.7560000121593475,
98
+ "count": 50
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.0622749999165535,
102
+ "min": -0.6666666666666666,
103
+ "max": 0.2682857151542391,
104
+ "count": 50
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -0.996399998664856,
108
+ "min": -10.0,
109
+ "max": 3.7560000121593475,
110
+ "count": 50
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 50
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 50
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.014403438732309344,
126
+ "min": 0.010229992038633402,
127
+ "max": 0.019984069629572332,
128
+ "count": 23
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.014403438732309344,
132
+ "min": 0.010229992038633402,
133
+ "max": 0.019984069629572332,
134
+ "count": 23
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.003362401939618091,
138
+ "min": 0.00013077333521020287,
139
+ "max": 0.0043448854548235735,
140
+ "count": 23
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.003362401939618091,
144
+ "min": 0.00013077333521020287,
145
+ "max": 0.0043448854548235735,
146
+ "count": 23
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.0034127482950376967,
150
+ "min": 0.00013574239558996246,
151
+ "max": 0.0044469629181548955,
152
+ "count": 23
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.0034127482950376967,
156
+ "min": 0.00013574239558996246,
157
+ "max": 0.0044469629181548955,
158
+ "count": 23
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0005499999999999999,
162
+ "min": 0.0005499999999999999,
163
+ "max": 0.00055,
164
+ "count": 23
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0005499999999999999,
168
+ "min": 0.0005499999999999999,
169
+ "max": 0.00055,
170
+ "count": 23
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
+ "min": 0.2,
175
  "max": 0.20000000000000007,
176
+ "count": 23
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
+ "min": 0.2,
181
  "max": 0.20000000000000007,
182
+ "count": 23
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
+ "min": 0.005,
187
  "max": 0.005000000000000001,
188
+ "count": 23
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
+ "min": 0.005,
193
  "max": 0.005000000000000001,
194
+ "count": 23
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1690804445",
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",
 
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1690805540"
208
  },
209
+ "total": 1095.4753349929997,
210
  "count": 1,
211
+ "self": 0.38822889600032795,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.03129372500006866,
215
  "count": 1,
216
+ "self": 0.03129372500006866
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 1095.0558123719993,
220
  "count": 1,
221
+ "self": 0.7822017468861304,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 5.9570331720005925,
225
+ "count": 4,
226
+ "self": 5.9570331720005925
227
  },
228
  "TrainerController.advance": {
229
+ "total": 1088.1120374991133,
230
+ "count": 32835,
231
+ "self": 0.8069334171414084,
232
  "children": {
233
  "env_step": {
234
+ "total": 882.2106680920333,
235
+ "count": 32835,
236
+ "self": 699.2274848741445,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 182.54068637993714,
240
+ "count": 32835,
241
+ "self": 5.318234501108236,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 177.2224518788289,
245
+ "count": 65094,
246
+ "self": 177.2224518788289
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 0.44249683795169403,
252
+ "count": 32835,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 1092.3884063230407,
257
+ "count": 32835,
258
  "is_parallel": true,
259
+ "self": 498.6851029291065,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.00451230700036831,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.0009606280018488178,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.003551678998519492,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.003551678998519492
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.07229993299915805,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.001307245998759754,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0007551199996669311,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.0007551199996669311
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.06639388900021004,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.06639388900021004
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.0038436780005213222,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.0006122100003267406,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.0032314680001945817,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.0032314680001945817
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "steps_from_proto": {
318
+ "total": 0.007196964998911426,
319
+ "count": 6,
320
  "is_parallel": true,
321
+ "self": 0.0013209269991421024,
322
  "children": {
323
  "_process_rank_one_or_two_observation": {
324
+ "total": 0.0058760379997693235,
325
+ "count": 24,
326
  "is_parallel": true,
327
+ "self": 0.0058760379997693235
328
  }
329
  }
330
  },
331
  "UnityEnvironment.step": {
332
+ "total": 593.6961064289353,
333
+ "count": 32834,
334
  "is_parallel": true,
335
+ "self": 36.63282161472853,
336
  "children": {
337
  "UnityEnvironment._generate_step_input": {
338
+ "total": 23.15455671015843,
339
+ "count": 32834,
340
  "is_parallel": true,
341
+ "self": 23.15455671015843
342
  },
343
  "communicator.exchange": {
344
+ "total": 416.26482188099453,
345
+ "count": 32834,
346
  "is_parallel": true,
347
+ "self": 416.26482188099453
348
  },
349
  "steps_from_proto": {
350
+ "total": 117.64390622305382,
351
+ "count": 65668,
352
  "is_parallel": true,
353
+ "self": 19.087857136731145,
354
  "children": {
355
  "_process_rank_one_or_two_observation": {
356
+ "total": 98.55604908632267,
357
+ "count": 262672,
358
  "is_parallel": true,
359
+ "self": 98.55604908632267
360
  }
361
  }
362
  }
 
369
  }
370
  },
371
  "trainer_advance": {
372
+ "total": 205.09443598993857,
373
+ "count": 32835,
374
+ "self": 6.719612829871949,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 50.66163941806735,
378
+ "count": 32835,
379
+ "self": 50.458558852067654,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
+ "total": 0.2030805659996986,
383
  "count": 1,
384
+ "self": 0.2030805659996986
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
+ "total": 147.71318374199927,
390
+ "count": 23,
391
+ "self": 103.30691072398713,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
+ "total": 44.40627301801214,
395
+ "count": 693,
396
+ "self": 44.40627301801214
397
  }
398
  }
399
  }
 
402
  }
403
  },
404
  "trainer_threads": {
405
+ "total": 9.93999492493458e-07,
406
  "count": 1,
407
+ "self": 9.93999492493458e-07
408
  },
409
  "TrainerController._save_models": {
410
+ "total": 0.20453895999980887,
411
  "count": 1,
412
+ "self": 0.0014291139996203128,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
+ "total": 0.20310984600018855,
416
  "count": 1,
417
+ "self": 0.20310984600018855
418
  }
419
  }
420
  }
run_logs/training_status.json CHANGED
@@ -1,24 +1,6 @@
1
  {
2
  "SoccerTwos": {
3
  "checkpoints": [
4
- {
5
- "steps": 499856,
6
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499856.onnx",
7
- "reward": 0.0,
8
- "creation_time": 1690801495.3440523,
9
- "auxillary_file_paths": [
10
- "results/SoccerTwos/SoccerTwos/SoccerTwos-499856.pt"
11
- ]
12
- },
13
- {
14
- "steps": 999682,
15
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-999682.onnx",
16
- "reward": 0.0,
17
- "creation_time": 1690802600.8288352,
18
- "auxillary_file_paths": [
19
- "results/SoccerTwos/SoccerTwos/SoccerTwos-999682.pt"
20
- ]
21
- },
22
  {
23
  "steps": 1001682,
24
  "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1001682.onnx",
@@ -45,16 +27,34 @@
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
  },
 
1
  {
2
  "SoccerTwos": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 1001682,
6
  "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1001682.onnx",
 
27
  "auxillary_file_paths": [
28
  "results/SoccerTwos/SoccerTwos/SoccerTwos-1751370.pt"
29
  ]
30
+ },
31
+ {
32
+ "steps": 1999160,
33
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1999160.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1690804996.4361818,
36
+ "auxillary_file_paths": [
37
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-1999160.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 2251936,
42
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2251936.onnx",
43
+ "reward": 0.0,
44
+ "creation_time": 1690805540.2085571,
45
+ "auxillary_file_paths": [
46
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-2251936.pt"
47
+ ]
48
  }
49
  ],
50
+ "elo": 1175.6017727005901,
51
  "final_checkpoint": {
52
+ "steps": 2251936,
53
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
  "reward": 0.0,
55
+ "creation_time": 1690805540.2085571,
56
  "auxillary_file_paths": [
57
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-2251936.pt"
58
  ]
59
  }
60
  },