Hugging Face's logo

Wajid333
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
Wajid333 commited on
Commit
adfa85c
•
1 Parent(s): 8ebaa5a

First Push`

Browse files
Files changed (16) hide show
  1. SoccerTwos.onnx +1 -1
  2. SoccerTwos/SoccerTwos-4499986.onnx +3 -0
  3. SoccerTwos/SoccerTwos-4499986.pt +3 -0
  4. SoccerTwos/SoccerTwos-4999946.onnx +3 -0
  5. SoccerTwos/SoccerTwos-4999946.pt +3 -0
  6. SoccerTwos/SoccerTwos-5499994.onnx +3 -0
  7. SoccerTwos/SoccerTwos-5499994.pt +3 -0
  8. SoccerTwos/SoccerTwos-5999954.onnx +3 -0
  9. SoccerTwos/SoccerTwos-5999954.pt +3 -0
  10. SoccerTwos/SoccerTwos-6168430.onnx +3 -0
  11. SoccerTwos/SoccerTwos-6168430.pt +3 -0
  12. SoccerTwos/checkpoint.pt +1 -1
  13. SoccerTwos/events.out.tfevents.1707993120.DESKTOP-PCVNORB.13440.0 +3 -0
  14. run_logs/Player-0.log +0 -0
  15. run_logs/timers.json +172 -172
  16. run_logs/training_status.json +24 -24
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c04dc29fa8193889b14a299d4dcf526cf34816eb279c8168f7d653151d72b5f2
3
  size 1768747
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b32991f6d62a1a140419698cff0c5baa94fde7b900a5fec8a86745114fc0de0
3
  size 1768747
SoccerTwos/SoccerTwos-4499986.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47797d8c31774303c8e6f1a83ef04a48124b34b74db3dc106afc0713636863a
3
+ size 1768747
SoccerTwos/SoccerTwos-4499986.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b838666cb0fa9c690644ace6ff62583c30f490a102839d5e0f506ffe2304bb41
3
+ size 28430358
SoccerTwos/SoccerTwos-4999946.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02621d519aba4c63aeeda1bcf63562e8d8fbd2f79f29dcfa0d92b1ef0505b19
3
+ size 1768747
SoccerTwos/SoccerTwos-4999946.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83483f1cf37716301eac1a64ff6fbb0f6782079f901390c0719650bea49f3af3
3
+ size 28430358
SoccerTwos/SoccerTwos-5499994.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe670058d94218b4e3f038f4fd654ae7ccf0ee37c7158534a6c5bbd8d5818df
3
+ size 1768747
SoccerTwos/SoccerTwos-5499994.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a65bd2f4274b88b43d543b3186542502ed9ca23be724efacf75da1db98ebb8d
3
+ size 28430358
SoccerTwos/SoccerTwos-5999954.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31537c417e95cd246ce37d0e8b8d3e6a1a184c411a153907e007a95affaa0cfa
3
+ size 1768747
SoccerTwos/SoccerTwos-5999954.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71c94d56feeda663345a7fb3db0399daf57bbe00e13be11cfaa0ad2da414d2c
3
+ size 28430358
SoccerTwos/SoccerTwos-6168430.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b32991f6d62a1a140419698cff0c5baa94fde7b900a5fec8a86745114fc0de0
3
+ size 1768747
SoccerTwos/SoccerTwos-6168430.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5236c2255e07e1d146f2c613bd367bdcd79e2736c90b4f66580a5e33671e43d
3
+ size 28430358
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb521bf1cb10c0bcf2b1adef356dfa51a9b74059b20fb4e3aefe44ada08d9559
3
  size 28429366
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2502516a6ffaa994f236b808a66a6f0ef92f711ebc505376418f9de89e58a83
3
  size 28429366
SoccerTwos/events.out.tfevents.1707993120.DESKTOP-PCVNORB.13440.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d05b8413b1eeedf82227414e3cb072a4761b194d6df9ef6d8e632a5d774d780
3
+ size 5715384
run_logs/Player-0.log CHANGED
The diff for this file is too large to render. See raw diff
 
run_logs/timers.json CHANGED
@@ -2,305 +2,305 @@
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 3.1090173721313477,
6
- "min": 1.9680967330932617,
7
- "max": 3.2957119941711426,
8
- "count": 3050
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 69542.5,
12
- "min": 7779.02392578125,
13
- "max": 139825.21875,
14
- "count": 3050
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 999.0,
18
- "min": 432.09090909090907,
19
  "max": 999.0,
20
- "count": 3050
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 19980.0,
24
- "min": 4212.0,
25
- "max": 30640.0,
26
- "count": 3050
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1106.394028371355,
30
- "min": 1105.7761543980168,
31
- "max": 1202.6779590037042,
32
- "count": 834
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 4425.57611348542,
36
- "min": 2211.5523087960337,
37
- "max": 16433.644009425647,
38
- "count": 834
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 30499668.0,
42
- "min": 9338.0,
43
- "max": 30499668.0,
44
- "count": 3050
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 30499668.0,
48
- "min": 9338.0,
49
- "max": 30499668.0,
50
- "count": 3050
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": 0.001142252003774047,
54
- "min": -0.06821022182703018,
55
- "max": 0.029490983113646507,
56
- "count": 3050
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": 0.011422519572079182,
60
- "min": -1.023153305053711,
61
- "max": 0.29490983486175537,
62
- "count": 3050
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": 0.0011270389659330249,
66
- "min": -0.06816212832927704,
67
- "max": 0.026077916845679283,
68
- "count": 3050
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": 0.011270389892160892,
72
- "min": -1.0224319696426392,
73
- "max": 0.26077917218208313,
74
- "count": 3050
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 3050
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 3050
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": 0.0,
90
- "min": -0.7692307692307693,
91
- "max": 0.3462000002463659,
92
- "count": 3050
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": 0.0,
96
- "min": -10.307600021362305,
97
- "max": 6.134799897670746,
98
- "count": 3050
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": 0.0,
102
- "min": -0.7692307692307693,
103
- "max": 0.3462000002463659,
104
- "count": 3050
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": 0.0,
108
- "min": -10.307600021362305,
109
- "max": 6.134799897670746,
110
- "count": 3050
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 3050
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 3050
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
- "value": 0.01199939750416282,
126
- "min": 0.009683321138921504,
127
- "max": 0.0247808082223249,
128
- "count": 1405
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
- "value": 0.01199939750416282,
132
- "min": 0.009683321138921504,
133
- "max": 0.0247808082223249,
134
- "count": 1405
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
- "value": 1.6804577107620845e-08,
138
- "min": 1.6066720870400175e-10,
139
- "max": 0.024891944141461262,
140
- "count": 1405
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
- "value": 1.6804577107620845e-08,
144
- "min": 1.6066720870400175e-10,
145
- "max": 0.024891944141461262,
146
- "count": 1405
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
- "value": 1.6932955807883825e-08,
150
- "min": 1.881779200056203e-10,
151
- "max": 0.025511121548364338,
152
- "count": 1405
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
- "value": 1.6932955807883825e-08,
156
- "min": 1.881779200056203e-10,
157
- "max": 0.025511121548364338,
158
- "count": 1405
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
  "value": 0.0003,
162
  "min": 0.0003,
163
  "max": 0.0003,
164
- "count": 1405
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
  "value": 0.0003,
168
  "min": 0.0003,
169
  "max": 0.0003,
170
- "count": 1405
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
- "min": 0.19999999999999996,
175
  "max": 0.20000000000000007,
176
- "count": 1405
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
- "min": 0.19999999999999996,
181
  "max": 0.20000000000000007,
182
- "count": 1405
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
- "min": 0.005,
187
  "max": 0.005000000000000001,
188
- "count": 1405
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
- "min": 0.005,
193
  "max": 0.005000000000000001,
194
- "count": 1405
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1707909201",
200
  "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]",
201
- "command_line_arguments": "\\\\?\\C:\\Users\\WajidIQBAL\\anaconda3\\envs\\rlll\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
202
  "mlagents_version": "1.1.0.dev0",
203
  "mlagents_envs_version": "1.1.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.2.0+cpu",
206
  "numpy_version": "1.23.5",
207
- "end_time_seconds": "1707970458"
208
  },
209
- "total": 61257.0453976,
210
  "count": 1,
211
- "self": 0.4663060000020778,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.05751190000000861,
215
  "count": 1,
216
- "self": 0.05751190000000861
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 61256.5215797,
220
  "count": 1,
221
- "self": 29.80428909652983,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 13.804234599957908,
225
- "count": 152,
226
- "self": 13.804234599957908
227
  },
228
  "TrainerController.advance": {
229
- "total": 61212.81467410352,
230
- "count": 1983824,
231
- "self": 31.51725379947311,
232
  "children": {
233
  "env_step": {
234
- "total": 20554.860432702186,
235
- "count": 1983824,
236
- "self": 16081.39585360005,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 4453.426088601476,
240
- "count": 1983824,
241
- "self": 183.04756110322342,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 4270.378527498253,
245
- "count": 3941154,
246
- "self": 4270.378527498253
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 20.038490500658554,
252
- "count": 1983823,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 61217.14689130344,
257
- "count": 1983823,
258
  "is_parallel": true,
259
- "self": 48596.32925790934,
260
  "children": {
261
  "steps_from_proto": {
262
- "total": 0.17005310006243235,
263
- "count": 304,
264
  "is_parallel": true,
265
- "self": 0.031948700181146705,
266
  "children": {
267
  "_process_rank_one_or_two_observation": {
268
- "total": 0.13810439988128564,
269
- "count": 1216,
270
  "is_parallel": true,
271
- "self": 0.13810439988128564
272
  }
273
  }
274
  },
275
  "UnityEnvironment.step": {
276
- "total": 12620.647580294037,
277
- "count": 1983823,
278
  "is_parallel": true,
279
- "self": 748.5680125834697,
280
  "children": {
281
  "UnityEnvironment._generate_step_input": {
282
- "total": 504.62159380177127,
283
- "count": 1983823,
284
  "is_parallel": true,
285
- "self": 504.62159380177127
286
  },
287
  "communicator.exchange": {
288
- "total": 9258.36415170342,
289
- "count": 1983823,
290
  "is_parallel": true,
291
- "self": 9258.36415170342
292
  },
293
  "steps_from_proto": {
294
- "total": 2109.0938222053783,
295
- "count": 3967646,
296
  "is_parallel": true,
297
- "self": 388.4085669996657,
298
  "children": {
299
  "_process_rank_one_or_two_observation": {
300
- "total": 1720.6852552057126,
301
- "count": 15870584,
302
  "is_parallel": true,
303
- "self": 1720.6852552057126
304
  }
305
  }
306
  }
@@ -313,31 +313,31 @@
313
  }
314
  },
315
  "trainer_advance": {
316
- "total": 40626.43698760187,
317
- "count": 1983823,
318
- "self": 241.9663722038531,
319
  "children": {
320
  "process_trajectory": {
321
- "total": 3534.66847819801,
322
- "count": 1983823,
323
- "self": 3529.1874535979873,
324
  "children": {
325
  "RLTrainer._checkpoint": {
326
- "total": 5.481024600022465,
327
- "count": 61,
328
- "self": 5.481024600022465
329
  }
330
  }
331
  },
332
  "_update_policy": {
333
- "total": 36849.80213720001,
334
- "count": 1405,
335
- "self": 2789.5615048997497,
336
  "children": {
337
  "TorchPOCAOptimizer.update": {
338
- "total": 34060.24063230026,
339
- "count": 42165,
340
- "self": 34060.24063230026
341
  }
342
  }
343
  }
@@ -346,19 +346,19 @@
346
  }
347
  },
348
  "trainer_threads": {
349
- "total": 1.0999938240274787e-06,
350
  "count": 1,
351
- "self": 1.0999938240274787e-06
352
  },
353
  "TrainerController._save_models": {
354
- "total": 0.09838079999462934,
355
  "count": 1,
356
- "self": 0.0073776999925030395,
357
  "children": {
358
  "RLTrainer._checkpoint": {
359
- "total": 0.0910031000021263,
360
  "count": 1,
361
- "self": 0.0910031000021263
362
  }
363
  }
364
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.7994298934936523,
6
+ "min": 1.784654974937439,
7
+ "max": 3.295724630355835,
8
+ "count": 616
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 35815.8515625,
12
+ "min": 22801.48828125,
13
+ "max": 144439.0625,
14
+ "count": 616
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 83.96551724137932,
18
+ "min": 40.23770491803279,
19
  "max": 999.0,
20
+ "count": 616
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19480.0,
24
+ "min": 16532.0,
25
+ "max": 23552.0,
26
+ "count": 616
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1544.4499912357385,
30
+ "min": 1187.1566745841485,
31
+ "max": 1587.1553806467844,
32
+ "count": 581
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 179156.19898334568,
36
+ "min": 2378.2809550475304,
37
+ "max": 367584.5202686837,
38
+ "count": 581
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 6159916.0,
42
+ "min": 9206.0,
43
+ "max": 6159916.0,
44
+ "count": 616
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 6159916.0,
48
+ "min": 9206.0,
49
+ "max": 6159916.0,
50
+ "count": 616
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.01978658325970173,
54
+ "min": -0.14759381115436554,
55
+ "max": 0.1493956297636032,
56
+ "count": 616
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 2.295243740081787,
60
+ "min": -30.699512481689453,
61
+ "max": 25.657739639282227,
62
+ "count": 616
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.019230442121624947,
66
+ "min": -0.14938680827617645,
67
+ "max": 0.15320727229118347,
68
+ "count": 616
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 2.230731248855591,
72
+ "min": -31.07245635986328,
73
+ "max": 26.35165023803711,
74
+ "count": 616
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 616
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 616
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.10933793207694745,
90
+ "min": -0.6666666666666666,
91
+ "max": 0.38814857346670967,
92
+ "count": 616
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -12.683200120925903,
96
+ "min": -68.55400037765503,
97
+ "max": 63.01439988613129,
98
+ "count": 616
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.10933793207694745,
102
+ "min": -0.6666666666666666,
103
+ "max": 0.38814857346670967,
104
+ "count": 616
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -12.683200120925903,
108
+ "min": -68.55400037765503,
109
+ "max": 63.01439988613129,
110
+ "count": 616
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 616
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 616
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.014084834283373008,
126
+ "min": 0.010017290062387474,
127
+ "max": 0.024107007146812975,
128
+ "count": 296
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.014084834283373008,
132
+ "min": 0.010017290062387474,
133
+ "max": 0.024107007146812975,
134
+ "count": 296
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.08509936109185219,
138
+ "min": 3.064193956940168e-06,
139
+ "max": 0.12175564219554265,
140
+ "count": 296
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.08509936109185219,
144
+ "min": 3.064193956940168e-06,
145
+ "max": 0.12175564219554265,
146
+ "count": 296
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.08593981936573983,
150
+ "min": 3.0190435306091484e-06,
151
+ "max": 0.12396949579318364,
152
+ "count": 296
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.08593981936573983,
156
+ "min": 3.0190435306091484e-06,
157
+ "max": 0.12396949579318364,
158
+ "count": 296
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
  "value": 0.0003,
162
  "min": 0.0003,
163
  "max": 0.0003,
164
+ "count": 296
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
  "value": 0.0003,
168
  "min": 0.0003,
169
  "max": 0.0003,
170
+ "count": 296
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
  "max": 0.20000000000000007,
176
+ "count": 296
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
  "max": 0.20000000000000007,
182
+ "count": 296
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
+ "count": 296
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
+ "count": 296
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1707993115",
200
  "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]",
201
+ "command_line_arguments": "\\\\?\\C:\\Users\\WajidIQBAL\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
202
  "mlagents_version": "1.1.0.dev0",
203
  "mlagents_envs_version": "1.1.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.2.0+cpu",
206
  "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1708005500"
208
  },
209
+ "total": 12385.6348667,
210
  "count": 1,
211
+ "self": 0.4857663999991928,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.06063380000000507,
215
  "count": 1,
216
+ "self": 0.06063380000000507
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 12385.088466500001,
220
  "count": 1,
221
+ "self": 6.585726999135659,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 6.884737899997617,
225
+ "count": 31,
226
+ "self": 6.884737899997617
227
  },
228
  "TrainerController.advance": {
229
+ "total": 12371.525132200866,
230
+ "count": 421350,
231
+ "self": 6.878538901006323,
232
  "children": {
233
  "env_step": {
234
+ "total": 4259.456805300052,
235
+ "count": 421350,
236
+ "self": 3322.310926299174,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 932.8203095005636,
240
+ "count": 421350,
241
+ "self": 39.56607430120425,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 893.2542351993593,
245
+ "count": 780502,
246
+ "self": 893.2542351993593
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 4.325569500314714,
252
+ "count": 421350,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 12371.634103400815,
257
+ "count": 421350,
258
  "is_parallel": true,
259
+ "self": 9743.560618400781,
260
  "children": {
261
  "steps_from_proto": {
262
+ "total": 0.034617800001569776,
263
+ "count": 62,
264
  "is_parallel": true,
265
+ "self": 0.006468000008226227,
266
  "children": {
267
  "_process_rank_one_or_two_observation": {
268
+ "total": 0.02814979999334355,
269
+ "count": 248,
270
  "is_parallel": true,
271
+ "self": 0.02814979999334355
272
  }
273
  }
274
  },
275
  "UnityEnvironment.step": {
276
+ "total": 2628.0388672000327,
277
+ "count": 421350,
278
  "is_parallel": true,
279
+ "self": 142.92145099948175,
280
  "children": {
281
  "UnityEnvironment._generate_step_input": {
282
+ "total": 102.63063090013225,
283
+ "count": 421350,
284
  "is_parallel": true,
285
+ "self": 102.63063090013225
286
  },
287
  "communicator.exchange": {
288
+ "total": 1951.7629908998983,
289
+ "count": 421350,
290
  "is_parallel": true,
291
+ "self": 1951.7629908998983
292
  },
293
  "steps_from_proto": {
294
+ "total": 430.7237944005201,
295
+ "count": 842700,
296
  "is_parallel": true,
297
+ "self": 79.76688340053784,
298
  "children": {
299
  "_process_rank_one_or_two_observation": {
300
+ "total": 350.95691099998226,
301
+ "count": 3370800,
302
  "is_parallel": true,
303
+ "self": 350.95691099998226
304
  }
305
  }
306
  }
 
313
  }
314
  },
315
  "trainer_advance": {
316
+ "total": 8105.189787999808,
317
+ "count": 421350,
318
+ "self": 51.18202409964306,
319
  "children": {
320
  "process_trajectory": {
321
+ "total": 978.3013134001662,
322
+ "count": 421350,
323
+ "self": 977.2305326001656,
324
  "children": {
325
  "RLTrainer._checkpoint": {
326
+ "total": 1.070780800000648,
327
+ "count": 12,
328
+ "self": 1.070780800000648
329
  }
330
  }
331
  },
332
  "_update_policy": {
333
+ "total": 7075.706450499998,
334
+ "count": 296,
335
+ "self": 587.3439546000136,
336
  "children": {
337
  "TorchPOCAOptimizer.update": {
338
+ "total": 6488.362495899984,
339
+ "count": 8880,
340
+ "self": 6488.362495899984
341
  }
342
  }
343
  }
 
346
  }
347
  },
348
  "trainer_threads": {
349
+ "total": 8.000006346264854e-07,
350
  "count": 1,
351
+ "self": 8.000006346264854e-07
352
  },
353
  "TrainerController._save_models": {
354
+ "total": 0.09286860000065644,
355
  "count": 1,
356
+ "self": 0.0067882000003010035,
357
  "children": {
358
  "RLTrainer._checkpoint": {
359
+ "total": 0.08608040000035544,
360
  "count": 1,
361
+ "self": 0.08608040000035544
362
  }
363
  }
364
  }
run_logs/training_status.json CHANGED
@@ -2,59 +2,59 @@
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
- "steps": 28999152,
6
- "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-28999152.onnx",
7
  "reward": 0.0,
8
- "creation_time": 1707966345.4605298,
9
  "auxillary_file_paths": [
10
- "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-28999152.pt"
11
  ]
12
  },
13
  {
14
- "steps": 29499543,
15
- "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29499543.onnx",
16
  "reward": 0.0,
17
- "creation_time": 1707967671.520455,
18
  "auxillary_file_paths": [
19
- "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29499543.pt"
20
  ]
21
  },
22
  {
23
- "steps": 29999352,
24
- "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29999352.onnx",
25
  "reward": 0.0,
26
- "creation_time": 1707969033.0221674,
27
  "auxillary_file_paths": [
28
- "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29999352.pt"
29
  ]
30
  },
31
  {
32
- "steps": 30499668,
33
- "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30499668.onnx",
34
  "reward": 0.0,
35
- "creation_time": 1707970454.8388364,
36
  "auxillary_file_paths": [
37
- "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30499668.pt"
38
  ]
39
  },
40
  {
41
- "steps": 30504668,
42
- "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30504668.onnx",
43
  "reward": 0.0,
44
- "creation_time": 1707970458.4303687,
45
  "auxillary_file_paths": [
46
- "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30504668.pt"
47
  ]
48
  }
49
  ],
50
- "elo": 1106.8989734668996,
51
  "final_checkpoint": {
52
- "steps": 30504668,
53
  "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
54
  "reward": 0.0,
55
- "creation_time": 1707970458.4303687,
56
  "auxillary_file_paths": [
57
- "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30504668.pt"
58
  ]
59
  }
60
  },
 
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
+ "steps": 4499986,
6
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499986.onnx",
7
  "reward": 0.0,
8
+ "creation_time": 1708002231.5926924,
9
  "auxillary_file_paths": [
10
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499986.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 4999946,
15
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999946.onnx",
16
  "reward": 0.0,
17
+ "creation_time": 1708003207.9135444,
18
  "auxillary_file_paths": [
19
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999946.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 5499994,
24
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5499994.onnx",
25
  "reward": 0.0,
26
+ "creation_time": 1708004109.529231,
27
  "auxillary_file_paths": [
28
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5499994.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 5999954,
33
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5999954.onnx",
34
  "reward": 0.0,
35
+ "creation_time": 1708005110.0573041,
36
  "auxillary_file_paths": [
37
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5999954.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 6168430,
42
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6168430.onnx",
43
  "reward": 0.0,
44
+ "creation_time": 1708005500.280612,
45
  "auxillary_file_paths": [
46
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6168430.pt"
47
  ]
48
  }
49
  ],
50
+ "elo": 1544.3405730362754,
51
  "final_checkpoint": {
52
+ "steps": 6168430,
53
  "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
54
  "reward": 0.0,
55
+ "creation_time": 1708005500.280612,
56
  "auxillary_file_paths": [
57
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6168430.pt"
58
  ]
59
  }
60
  },