Hugging Face's logo

Tingwen
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
Tingwen commited on
Commit
86a4f7f
•
1 Parent(s): 1c40553

First Push

Browse files
Files changed (8) hide show
  1. SoccerTwos.onnx +3 -0
  2. SoccerTwos/SoccerTwos-572784.onnx +3 -0
  3. SoccerTwos/SoccerTwos-572784.pt +3 -0
  4. SoccerTwos/checkpoint.pt +1 -1
  5. SoccerTwos/events.out.tfevents.1684631276.win.6400.0 +2 -2
  6. run_logs/Player-0.log +244 -0
  7. run_logs/timers.json +396 -14
  8. run_logs/training_status.json +31 -2
SoccerTwos.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5275c279bb8fc52b33cf0f0f7805b9ce4a4c6241ce6c3cf5a50aa3d726f5c6df
3
+ size 1764633
SoccerTwos/SoccerTwos-572784.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5275c279bb8fc52b33cf0f0f7805b9ce4a4c6241ce6c3cf5a50aa3d726f5c6df
3
+ size 1764633
SoccerTwos/SoccerTwos-572784.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a68fdb4ee28274156013949ba61bad41c5c1d2e2474c227b1be10b623740bd5
3
+ size 28422481
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9993c20750d953d4090f880d4b75fa83be596f52bace91b43b53a8ef089a5ecd
3
  size 28422481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a68fdb4ee28274156013949ba61bad41c5c1d2e2474c227b1be10b623740bd5
3
  size 28422481
SoccerTwos/events.out.tfevents.1684631276.win.6400.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f51299e0f353c7865ce2b8860a16ec0ca3a0247ee9cb61a0e5bf10153927f29
3
- size 506765
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971fd82dee052e4eb24e73eb87afd985b97d1e35ef2741cbce54a2b588e4f0d4
3
+ size 512216
run_logs/Player-0.log CHANGED
@@ -233,3 +233,247 @@ TOO LONG
233
  TOO LONG
234
  TOO LONG
235
  TOO LONG
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  TOO LONG
234
  TOO LONG
235
  TOO LONG
236
+ TOO LONG
237
+ TOO LONG
238
+ Setting up 4 worker threads for Enlighten.
239
+ Memory Statistics:
240
+ [ALLOC_TEMP_TLS] TLS Allocator
241
+ StackAllocators :
242
+ [ALLOC_TEMP_MAIN]
243
+ Peak usage frame count: [2.0 KB-4.0 KB]: 1 frames, [8.0 KB-16.0 KB]: 11185 frames, [2.0 MB-4.0 MB]: 1 frames
244
+ Initial Block Size 4.0 MB
245
+ Current Block Size 4.0 MB
246
+ Peak Allocated Bytes 2.1 MB
247
+ Overflow Count 0
248
+ [ALLOC_TEMP_Loading.AsyncRead]
249
+ Initial Block Size 64.0 KB
250
+ Current Block Size 64.0 KB
251
+ Peak Allocated Bytes 128 B
252
+ Overflow Count 0
253
+ [ALLOC_TEMP_Loading.PreloadManager]
254
+ Initial Block Size 256.0 KB
255
+ Current Block Size 300.0 KB
256
+ Peak Allocated Bytes 249.6 KB
257
+ Overflow Count 4
258
+ [ALLOC_TEMP_Background Job.Worker 8]
259
+ Initial Block Size 32.0 KB
260
+ Current Block Size 32.0 KB
261
+ Peak Allocated Bytes 0 B
262
+ Overflow Count 0
263
+ [ALLOC_TEMP_Job.Worker 6]
264
+ Initial Block Size 256.0 KB
265
+ Current Block Size 256.0 KB
266
+ Peak Allocated Bytes 0 B
267
+ Overflow Count 0
268
+ [ALLOC_TEMP_Job.Worker 0]
269
+ Initial Block Size 256.0 KB
270
+ Current Block Size 256.0 KB
271
+ Peak Allocated Bytes 0.7 KB
272
+ Overflow Count 0
273
+ [ALLOC_TEMP_Background Job.Worker 10]
274
+ Initial Block Size 32.0 KB
275
+ Current Block Size 32.0 KB
276
+ Peak Allocated Bytes 0 B
277
+ Overflow Count 0
278
+ [ALLOC_TEMP_Background Job.Worker 9]
279
+ Initial Block Size 32.0 KB
280
+ Current Block Size 32.0 KB
281
+ Peak Allocated Bytes 0 B
282
+ Overflow Count 0
283
+ [ALLOC_TEMP_Job.Worker 5]
284
+ Initial Block Size 256.0 KB
285
+ Current Block Size 256.0 KB
286
+ Peak Allocated Bytes 0 B
287
+ Overflow Count 0
288
+ [ALLOC_TEMP_Background Job.Worker 14]
289
+ Initial Block Size 32.0 KB
290
+ Current Block Size 32.0 KB
291
+ Peak Allocated Bytes 0 B
292
+ Overflow Count 0
293
+ [ALLOC_TEMP_Background Job.Worker 6]
294
+ Initial Block Size 32.0 KB
295
+ Current Block Size 32.0 KB
296
+ Peak Allocated Bytes 0 B
297
+ Overflow Count 0
298
+ [ALLOC_TEMP_Job.Worker 4]
299
+ Initial Block Size 256.0 KB
300
+ Current Block Size 256.0 KB
301
+ Peak Allocated Bytes 0 B
302
+ Overflow Count 0
303
+ [ALLOC_TEMP_Job.Worker 3]
304
+ Initial Block Size 256.0 KB
305
+ Current Block Size 256.0 KB
306
+ Peak Allocated Bytes 0 B
307
+ Overflow Count 0
308
+ [ALLOC_TEMP_Background Job.Worker 12]
309
+ Initial Block Size 32.0 KB
310
+ Current Block Size 32.0 KB
311
+ Peak Allocated Bytes 0 B
312
+ Overflow Count 0
313
+ [ALLOC_TEMP_EnlightenWorker] x 4
314
+ Initial Block Size 64.0 KB
315
+ Current Block Size 64.0 KB
316
+ Peak Allocated Bytes 0 B
317
+ Overflow Count 0
318
+ [ALLOC_TEMP_Background Job.Worker 15]
319
+ Initial Block Size 32.0 KB
320
+ Current Block Size 32.0 KB
321
+ Peak Allocated Bytes 0 B
322
+ Overflow Count 0
323
+ [ALLOC_TEMP_Background Job.Worker 1]
324
+ Initial Block Size 32.0 KB
325
+ Current Block Size 32.0 KB
326
+ Peak Allocated Bytes 0 B
327
+ Overflow Count 0
328
+ [ALLOC_TEMP_Background Job.Worker 2]
329
+ Initial Block Size 32.0 KB
330
+ Current Block Size 32.0 KB
331
+ Peak Allocated Bytes 0 B
332
+ Overflow Count 0
333
+ [ALLOC_TEMP_Background Job.Worker 7]
334
+ Initial Block Size 32.0 KB
335
+ Current Block Size 32.0 KB
336
+ Peak Allocated Bytes 0 B
337
+ Overflow Count 0
338
+ [ALLOC_TEMP_AssetGarbageCollectorHelper] x 7
339
+ Initial Block Size 64.0 KB
340
+ Current Block Size 64.0 KB
341
+ Peak Allocated Bytes 0 B
342
+ Overflow Count 0
343
+ [ALLOC_TEMP_Background Job.Worker 5]
344
+ Initial Block Size 32.0 KB
345
+ Current Block Size 32.0 KB
346
+ Peak Allocated Bytes 0 B
347
+ Overflow Count 0
348
+ [ALLOC_TEMP_Background Job.Worker 13]
349
+ Initial Block Size 32.0 KB
350
+ Current Block Size 32.0 KB
351
+ Peak Allocated Bytes 0 B
352
+ Overflow Count 0
353
+ [ALLOC_TEMP_Job.Worker 1]
354
+ Initial Block Size 256.0 KB
355
+ Current Block Size 256.0 KB
356
+ Peak Allocated Bytes 0 B
357
+ Overflow Count 0
358
+ [ALLOC_TEMP_Job.Worker 2]
359
+ Initial Block Size 256.0 KB
360
+ Current Block Size 256.0 KB
361
+ Peak Allocated Bytes 0 B
362
+ Overflow Count 0
363
+ [ALLOC_TEMP_Background Job.Worker 3]
364
+ Initial Block Size 32.0 KB
365
+ Current Block Size 32.0 KB
366
+ Peak Allocated Bytes 0 B
367
+ Overflow Count 0
368
+ [ALLOC_TEMP_Background Job.Worker 11]
369
+ Initial Block Size 32.0 KB
370
+ Current Block Size 32.0 KB
371
+ Peak Allocated Bytes 0 B
372
+ Overflow Count 0
373
+ [ALLOC_TEMP_Background Job.Worker 0]
374
+ Initial Block Size 32.0 KB
375
+ Current Block Size 32.0 KB
376
+ Peak Allocated Bytes 0 B
377
+ Overflow Count 0
378
+ [ALLOC_TEMP_Background Job.Worker 4]
379
+ Initial Block Size 32.0 KB
380
+ Current Block Size 32.0 KB
381
+ Peak Allocated Bytes 0 B
382
+ Overflow Count 0
383
+ [ALLOC_TEMP_BatchDeleteObjects]
384
+ Initial Block Size 64.0 KB
385
+ Current Block Size 64.0 KB
386
+ Peak Allocated Bytes 0 B
387
+ Overflow Count 0
388
+ [ALLOC_DEFAULT] Dual Thread Allocator
389
+ Peak main deferred allocation count 3
390
+ [ALLOC_BUCKET]
391
+ Large Block size 4.0 MB
392
+ Used Block count 1
393
+ Peak Allocated bytes 1.0 MB
394
+ [ALLOC_DEFAULT_MAIN]
395
+ Peak usage frame count: [4.0 MB-8.0 MB]: 11187 frames
396
+ Requested Block Size 16.0 MB
397
+ Peak Block count 1
398
+ Peak Allocated memory 5.0 MB
399
+ Peak Large allocation bytes 0 B
400
+ [ALLOC_DEFAULT_THREAD]
401
+ Peak usage frame count: [16.0 MB-32.0 MB]: 11187 frames
402
+ Requested Block Size 16.0 MB
403
+ Peak Block count 1
404
+ Peak Allocated memory 17.3 MB
405
+ Peak Large allocation bytes 16.0 MB
406
+ [ALLOC_TEMP_JOB_1_FRAME]
407
+ Initial Block Size 2.0 MB
408
+ Used Block Count 1
409
+ Overflow Count (too large) 0
410
+ Overflow Count (full) 0
411
+ [ALLOC_TEMP_JOB_2_FRAMES]
412
+ Initial Block Size 2.0 MB
413
+ Used Block Count 1
414
+ Overflow Count (too large) 0
415
+ Overflow Count (full) 0
416
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
417
+ Initial Block Size 2.0 MB
418
+ Used Block Count 2
419
+ Overflow Count (too large) 0
420
+ Overflow Count (full) 0
421
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
422
+ Initial Block Size 1.0 MB
423
+ Used Block Count 3
424
+ Overflow Count (too large) 0
425
+ Overflow Count (full) 0
426
+ [ALLOC_GFX] Dual Thread Allocator
427
+ Peak main deferred allocation count 0
428
+ [ALLOC_BUCKET]
429
+ Large Block size 4.0 MB
430
+ Used Block count 1
431
+ Peak Allocated bytes 1.0 MB
432
+ [ALLOC_GFX_MAIN]
433
+ Peak usage frame count: [32.0 KB-64.0 KB]: 11186 frames, [64.0 KB-128.0 KB]: 1 frames
434
+ Requested Block Size 16.0 MB
435
+ Peak Block count 1
436
+ Peak Allocated memory 65.6 KB
437
+ Peak Large allocation bytes 0 B
438
+ [ALLOC_GFX_THREAD]
439
+ Peak usage frame count: [128.0 KB-256.0 KB]: 11187 frames
440
+ Requested Block Size 16.0 MB
441
+ Peak Block count 1
442
+ Peak Allocated memory 173.5 KB
443
+ Peak Large allocation bytes 0 B
444
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
445
+ Peak main deferred allocation count 0
446
+ [ALLOC_BUCKET]
447
+ Large Block size 4.0 MB
448
+ Used Block count 1
449
+ Peak Allocated bytes 1.0 MB
450
+ [ALLOC_CACHEOBJECTS_MAIN]
451
+ Peak usage frame count: [0.5 MB-1.0 MB]: 11187 frames
452
+ Requested Block Size 4.0 MB
453
+ Peak Block count 1
454
+ Peak Allocated memory 0.6 MB
455
+ Peak Large allocation bytes 0 B
456
+ [ALLOC_CACHEOBJECTS_THREAD]
457
+ Peak usage frame count: [0.5 MB-1.0 MB]: 11186 frames, [4.0 MB-8.0 MB]: 1 frames
458
+ Requested Block Size 4.0 MB
459
+ Peak Block count 2
460
+ Peak Allocated memory 4.5 MB
461
+ Peak Large allocation bytes 0 B
462
+ [ALLOC_TYPETREE] Dual Thread Allocator
463
+ Peak main deferred allocation count 0
464
+ [ALLOC_BUCKET]
465
+ Large Block size 4.0 MB
466
+ Used Block count 1
467
+ Peak Allocated bytes 1.0 MB
468
+ [ALLOC_TYPETREE_MAIN]
469
+ Peak usage frame count: [0-1.0 KB]: 11187 frames
470
+ Requested Block Size 2.0 MB
471
+ Peak Block count 1
472
+ Peak Allocated memory 1.0 KB
473
+ Peak Large allocation bytes 0 B
474
+ [ALLOC_TYPETREE_THREAD]
475
+ Peak usage frame count: [1.0 KB-2.0 KB]: 11186 frames, [2.0 KB-4.0 KB]: 1 frames
476
+ Requested Block Size 2.0 MB
477
+ Peak Block count 1
478
+ Peak Allocated memory 2.2 KB
479
+ Peak Large allocation bytes 0 B
run_logs/timers.json CHANGED
@@ -1,40 +1,422 @@
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
- "start_time_seconds": "1684628613",
6
  "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
7
  "command_line_arguments": "/home/weber/workspace/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
8
  "mlagents_version": "0.31.0.dev0",
9
  "mlagents_envs_version": "0.31.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
- "pytorch_version": "1.11.0+cu102",
12
- "numpy_version": "1.21.2",
13
- "end_time_seconds": "1684628614"
14
  },
15
- "total": 0.8980415330006508,
16
  "count": 1,
17
- "self": 0.21888177200162318,
18
  "children": {
19
  "run_training.setup": {
20
- "total": 0.0069138399994699284,
21
  "count": 1,
22
- "self": 0.0069138399994699284
23
  },
24
  "TrainerController.start_learning": {
25
- "total": 0.6722459209995577,
26
  "count": 1,
27
- "self": 6.579500040970743e-05,
28
  "children": {
29
  "TrainerController._reset_env": {
30
- "total": 0.6720377940000617,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "count": 1,
32
- "self": 0.6720377940000617
33
  },
34
  "TrainerController._save_models": {
35
- "total": 0.00014233199908630922,
36
  "count": 1,
37
- "self": 0.00014233199908630922
 
 
 
 
 
 
 
38
  }
39
  }
40
  }
 
1
  {
2
  "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.1272294521331787,
6
+ "min": 3.1272294521331787,
7
+ "max": 3.2957687377929688,
8
+ "count": 57
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 78856.21875,
12
+ "min": 9470.4521484375,
13
+ "max": 111279.3828125,
14
+ "count": 57
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 606.5,
18
+ "min": 427.0833333333333,
19
+ "max": 999.0,
20
+ "count": 57
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19408.0,
24
+ "min": 16752.0,
25
+ "max": 23028.0,
26
+ "count": 57
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1195.7265099333702,
30
+ "min": 1185.9602509612184,
31
+ "max": 1202.1300950333368,
32
+ "count": 56
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 9565.812079466961,
36
+ "min": 2383.9087978849752,
37
+ "max": 23837.588585369856,
38
+ "count": 56
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 569694.0,
42
+ "min": 9748.0,
43
+ "max": 569694.0,
44
+ "count": 57
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 569694.0,
48
+ "min": 9748.0,
49
+ "max": 569694.0,
50
+ "count": 57
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.005025729537010193,
54
+ "min": -0.02216891013085842,
55
+ "max": 0.01984064094722271,
56
+ "count": 57
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -0.08041167259216309,
60
+ "min": -0.37861818075180054,
61
+ "max": 0.2948439121246338,
62
+ "count": 57
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.006355433724820614,
66
+ "min": -0.029016312211751938,
67
+ "max": 0.023159176111221313,
68
+ "count": 57
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -0.10168693959712982,
72
+ "min": -0.464260995388031,
73
+ "max": 0.346623033285141,
74
+ "count": 57
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 57
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 57
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.5,
90
+ "min": -0.5343733350435893,
91
+ "max": 0.3623555534415775,
92
+ "count": 57
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -8.0,
96
+ "min": -10.302800059318542,
97
+ "max": 6.522399961948395,
98
+ "count": 57
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.5,
102
+ "min": -0.5343733350435893,
103
+ "max": 0.3623555534415775,
104
+ "count": 57
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -8.0,
108
+ "min": -10.302800059318542,
109
+ "max": 6.522399961948395,
110
+ "count": 57
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 57
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 57
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.018109777154556164,
126
+ "min": 0.010637058871604191,
127
+ "max": 0.021666121548817804,
128
+ "count": 26
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.018109777154556164,
132
+ "min": 0.010637058871604191,
133
+ "max": 0.021666121548817804,
134
+ "count": 26
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.005658320236640672,
138
+ "min": 0.0015858658861058453,
139
+ "max": 0.008449819559852282,
140
+ "count": 26
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.005658320236640672,
144
+ "min": 0.0015858658861058453,
145
+ "max": 0.008449819559852282,
146
+ "count": 26
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.005775318403417866,
150
+ "min": 0.001676513000469034,
151
+ "max": 0.008451414930944642,
152
+ "count": 26
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.005775318403417866,
156
+ "min": 0.001676513000469034,
157
+ "max": 0.008451414930944642,
158
+ "count": 26
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 26
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 26
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 26
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 26
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 26
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 26
195
+ }
196
+ },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1684631275",
200
  "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
201
  "command_line_arguments": "/home/weber/workspace/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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",
206
+ "numpy_version": "1.20.0",
207
+ "end_time_seconds": "1684634126"
208
  },
209
+ "total": 2850.575393405001,
210
  "count": 1,
211
+ "self": 0.036576389997208025,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.008283941002446227,
215
  "count": 1,
216
+ "self": 0.008283941002446227
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 2850.530533074001,
220
  "count": 1,
221
+ "self": 0.7225042235368164,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 3.0621518840052886,
225
+ "count": 3,
226
+ "self": 3.0621518840052886
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 2846.563758171462,
230
+ "count": 37629,
231
+ "self": 0.6556139760868973,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 2671.116220367454,
235
+ "count": 37629,
236
+ "self": 2344.7956479436834,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 325.8067666995048,
240
+ "count": 37629,
241
+ "self": 3.8747202605518396,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 321.93204643895297,
245
+ "count": 74574,
246
+ "self": 321.93204643895297
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 0.5138057242656942,
252
+ "count": 37628,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 2848.4856919113154,
257
+ "count": 37628,
258
+ "is_parallel": true,
259
+ "self": 588.9607890253392,
260
+ "children": {
261
+ "run_training.setup": {
262
+ "total": 0.0,
263
+ "count": 0,
264
+ "is_parallel": true,
265
+ "self": 0.0,
266
+ "children": {
267
+ "steps_from_proto": {
268
+ "total": 0.00232988999778172,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.00045909500477137044,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.0018707949930103496,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.0018707949930103496
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.06547689999570139,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0001663470029598102,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.001254208997124806,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.001254208997124806
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.06209984599991003,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.06209984599991003
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.0019564979957067408,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.00029262800671858713,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0016638699889881536,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.0016638699889881536
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 2259.5210944379796,
319
+ "count": 37627,
320
+ "is_parallel": true,
321
+ "self": 6.1945704932149965,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 46.13824045883666,
325
+ "count": 37627,
326
+ "is_parallel": true,
327
+ "self": 46.13824045883666
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 2135.651376593043,
331
+ "count": 37627,
332
+ "is_parallel": true,
333
+ "self": 2135.651376593043
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 71.53690689288487,
337
+ "count": 75254,
338
+ "is_parallel": true,
339
+ "self": 10.340430876618484,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 61.19647601626639,
343
+ "count": 301016,
344
+ "is_parallel": true,
345
+ "self": 61.19647601626639
346
+ }
347
+ }
348
+ }
349
+ }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 0.003808447996561881,
353
+ "count": 4,
354
+ "is_parallel": true,
355
+ "self": 0.0005641619936795905,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.0032442860028822906,
359
+ "count": 16,
360
+ "is_parallel": true,
361
+ "self": 0.0032442860028822906
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ },
371
+ "trainer_advance": {
372
+ "total": 174.79192382792098,
373
+ "count": 37628,
374
+ "self": 5.510595201536489,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 65.68246822340734,
378
+ "count": 37628,
379
+ "self": 65.4896982124119,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 0.19277001099544577,
383
+ "count": 1,
384
+ "self": 0.19277001099544577
385
+ }
386
+ }
387
+ },
388
+ "_update_policy": {
389
+ "total": 103.59886040297715,
390
+ "count": 26,
391
+ "self": 57.751025248115184,
392
+ "children": {
393
+ "TorchPOCAOptimizer.update": {
394
+ "total": 45.84783515486197,
395
+ "count": 780,
396
+ "self": 45.84783515486197
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ },
404
+ "trainer_threads": {
405
+ "total": 6.609989213757217e-07,
406
  "count": 1,
407
+ "self": 6.609989213757217e-07
408
  },
409
  "TrainerController._save_models": {
410
+ "total": 0.18211813399830135,
411
  "count": 1,
412
+ "self": 0.0008386849949602038,
413
+ "children": {
414
+ "RLTrainer._checkpoint": {
415
+ "total": 0.18127944900334114,
416
+ "count": 1,
417
+ "self": 0.18127944900334114
418
+ }
419
+ }
420
  }
421
  }
422
  }
run_logs/training_status.json CHANGED
@@ -1,10 +1,39 @@
1
  {
2
  "SoccerTwos": {
3
- "elo": 1200.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  },
5
  "metadata": {
6
  "stats_format_version": "0.3.0",
7
  "mlagents_version": "0.31.0.dev0",
8
- "torch_version": "1.11.0+cu102"
9
  }
10
  }
 
1
  {
2
  "SoccerTwos": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 499988,
6
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499988.onnx",
7
+ "reward": 0.0,
8
+ "creation_time": 1684633762.8213258,
9
+ "auxillary_file_paths": [
10
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-499988.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 572784,
15
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-572784.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1684634126.1867166,
18
+ "auxillary_file_paths": [
19
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-572784.pt"
20
+ ]
21
+ }
22
+ ],
23
+ "elo": 1194.7221818418545,
24
+ "final_checkpoint": {
25
+ "steps": 572784,
26
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
27
+ "reward": 0.0,
28
+ "creation_time": 1684634126.1867166,
29
+ "auxillary_file_paths": [
30
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-572784.pt"
31
+ ]
32
+ }
33
  },
34
  "metadata": {
35
  "stats_format_version": "0.3.0",
36
  "mlagents_version": "0.31.0.dev0",
37
+ "torch_version": "1.11.0"
38
  }
39
  }