Hugging Face's logo

DeepNuc
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
DeepNuc commited on
Commit
4a68640
·
verified ·
1 Parent(s): a1cc44f

initial

Browse files
Files changed (16) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +1 -1
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +1 -1
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +1 -1
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1753102127.34cb6f71292c.7991.0 +3 -0
  14. run_logs/Player-0.log +5 -5
  15. run_logs/timers.json +97 -97
  16. run_logs/training_status.json +12 -12
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bacedba4b78eec8d5cf27ad37691ed6688885c68bcaf6b50fb508ab6b1fab095
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071bf7ca8ff7f0a1b30d7559967f4cd05df1bf1e1af3cf119f4ce5335c2c54f5
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c033fe4f806cd115c797695a12d3f29492ad7894060a492326f84913a41d8325
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ea4c84fd96b3c7884ae1511d83b4585ac2b4c3e38d96850a9e416aebd08d01b
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a20ce94d6f0b2c3affdecb8b981bee4c1f47afe20a5308367d032b399f53363
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12968a21ee0268ddedd31507c22d0bf29e17aa19ba9cbdc191d1a873c9f45600
3
  size 3850564
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bacedba4b78eec8d5cf27ad37691ed6688885c68bcaf6b50fb508ab6b1fab095
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071bf7ca8ff7f0a1b30d7559967f4cd05df1bf1e1af3cf119f4ce5335c2c54f5
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2548d2c01c6fadd5d5e79d076b72803d5dc47afd47b7f1861f69598c4fe0c4ff
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c83599e9a7e23993c2a63b74edb14e2176d219f46def8e4b4e9a0d498d814b03
3
  size 3850564
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bacedba4b78eec8d5cf27ad37691ed6688885c68bcaf6b50fb508ab6b1fab095
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071bf7ca8ff7f0a1b30d7559967f4cd05df1bf1e1af3cf119f4ce5335c2c54f5
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a73503121091a60ae5c285eeda9e28b0eb43b6265303494a85a13ce18fb8b828
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff6a8e3b0f52ad53e9341788aba1125d03971a89152af440a1168331c93d4c1e
3
  size 3850564
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40157c1961e4bffb31ed7fbc7317a79883fe85af5cff7a1854aa25789bfa106a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dbdff7fb88e59eef5205bd2b9cd48305324e008d118924c17ecd797ea8c7579
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dc7474cb1104e23687e73d96a2fcfdf2a9af6bd97dfcbf94ea673966d962b86
3
  size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c20c808228fc7c84d252fccd74d36ab3d2646b2db1d94c458d0f3b953e8a6b
3
  size 3850487
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3e5378b72573c4eb86bdb6f16935d88d4416d4ff868356a55132d90ab94af3e
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe46883ee85c6f52048a7889f74d3669ebd6d4fc7dcb14fba3761309245146c
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:750f3e115aabd3476285db05e8feeb0ef6018c21d6c34e2e6c53fa9d81ab77ad
3
  size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d50085ca148689e307e2208eafde0f6ca7fba911d8d0f5f021efbefd683bed1a
3
  size 3850487
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e42e48b903d3b2106e2efd6a2d71f800a1634828127171fa15cc0425ebab7415
3
  size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec047f261e6036f55ebddf05f1d0dd40b8b4700ed7af6741cad75b68f2faf34
3
  size 3849717
SnowballTarget/events.out.tfevents.1753102127.34cb6f71292c.7991.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7857008faa05bbebff92ba3b34566b8600e2d4cc3e5ca1c8184a31fc9105b836
3
+ size 23751
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.081 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.597401 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -178,7 +178,7 @@ Memory Statistics:
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
@@ -213,10 +213,10 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 5096 frames, [64.0 KB-128.0 KB]: 362 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.0 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
 
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.116 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
+ UnloadTime: 0.893298 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
 
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 6.7 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
 
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5053 frames, [64.0 KB-128.0 KB]: 405 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8341730237007141,
6
- "min": 0.8341730237007141,
7
- "max": 2.8457767963409424,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7927.98046875,
12
- "min": 7927.98046875,
13
- "max": 29049.689453125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.851177215576172,
30
- "min": 0.35692304372787476,
31
- "max": 12.851177215576172,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2505.9794921875,
36
- "min": 69.24307250976562,
37
- "max": 2620.1240234375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06505630723523056,
42
- "min": 0.06303499460513835,
43
- "max": 0.07352660592090722,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.26022522894092226,
48
- "min": 0.2521399784205534,
49
- "max": 0.35194617026889535,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.21918063954103226,
54
- "min": 0.1555260308383617,
55
- "max": 0.29233640800504124,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.876722558164129,
60
- "min": 0.6221041233534468,
61
- "max": 1.4616820400252062,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.454545454545453,
114
- "min": 4.0227272727272725,
115
- "max": 25.477272727272727,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1120.0,
120
- "min": 177.0,
121
- "max": 1394.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.454545454545453,
126
- "min": 4.0227272727272725,
127
- "max": 25.477272727272727,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1120.0,
132
- "min": 177.0,
133
- "max": 1394.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1753090472",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.7.1+cu126",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1753090886"
160
  },
161
- "total": 414.1384144639999,
162
  "count": 1,
163
- "self": 0.43905865599958815,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.024182618000168077,
167
  "count": 1,
168
- "self": 0.024182618000168077
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 413.6751731900001,
172
  "count": 1,
173
- "self": 0.3488043259828828,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.3102108519999547,
177
  "count": 1,
178
- "self": 3.3102108519999547
179
  },
180
  "TrainerController.advance": {
181
- "total": 409.93913893201784,
182
  "count": 18192,
183
- "self": 0.36675198302123135,
184
  "children": {
185
  "env_step": {
186
- "total": 292.22198356998206,
187
  "count": 18192,
188
- "self": 223.70340762602882,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 68.31251290597856,
192
  "count": 18192,
193
- "self": 1.2308301859936819,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 67.08168271998488,
197
  "count": 18192,
198
- "self": 67.08168271998488
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.20606303797467262,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 412.3207576219713,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 216.59629072694952,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +217,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.005665499000087948,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004214249999904496,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014512490001834522,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014512490001834522
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.05941087900009734,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005441770003926649,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00037983099991834024,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00037983099991834024
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04756991699991886,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04756991699991886
250
  },
251
  "steps_from_proto": {
252
- "total": 0.010916953999867474,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00037162900002840615,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.010545324999839067,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.010545324999839067
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 195.7244668950218,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.57556773201668,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.234663475959223,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.234663475959223
280
  },
281
  "communicator.exchange": {
282
- "total": 150.67827912403504,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 150.67827912403504
286
  },
287
  "steps_from_proto": {
288
- "total": 30.23595656301086,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.384626312061982,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 24.851330250948877,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 24.851330250948877
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 117.35040337901455,
311
  "count": 18192,
312
- "self": 0.44042342100419773,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 25.19073006700978,
316
  "count": 18192,
317
- "self": 24.78716842301037,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.4035616439994101,
321
  "count": 4,
322
- "self": 0.4035616439994101
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 91.71924989100057,
328
  "count": 90,
329
- "self": 37.910295413004405,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 53.80895447799617,
333
  "count": 4587,
334
- "self": 53.80895447799617
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.0559997463133186e-06,
344
  "count": 1,
345
- "self": 1.0559997463133186e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.07701802399969893,
349
  "count": 1,
350
- "self": 0.0007665749994885118,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07625144900021041,
354
  "count": 1,
355
- "self": 0.07625144900021041
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8000791668891907,
6
+ "min": 0.8000791668891907,
7
+ "max": 2.827587366104126,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7603.9521484375,
12
+ "min": 7603.9521484375,
13
+ "max": 28864.01171875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.81591510772705,
30
+ "min": 0.45649686455726624,
31
+ "max": 12.81591510772705,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2499.103515625,
36
+ "min": 88.56039428710938,
37
+ "max": 2608.8681640625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06552691837800119,
42
+ "min": 0.06552691837800119,
43
+ "max": 0.07390902149742104,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.26210767351200476,
48
+ "min": 0.26210767351200476,
49
+ "max": 0.3646972959786402,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.19553150528786228,
54
+ "min": 0.15062941040492198,
55
+ "max": 0.29914741765926867,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7821260211514491,
60
+ "min": 0.6025176416196879,
61
+ "max": 1.389694567112362,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 24.727272727272727,
114
+ "min": 4.136363636363637,
115
+ "max": 25.386363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1088.0,
120
+ "min": 182.0,
121
+ "max": 1386.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 24.727272727272727,
126
+ "min": 4.136363636363637,
127
+ "max": 25.386363636363637,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1088.0,
132
+ "min": 182.0,
133
+ "max": 1386.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1753102127",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.7.1+cu126",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1753102537"
160
  },
161
+ "total": 410.63436702700005,
162
  "count": 1,
163
+ "self": 0.3867308710000543,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.02832920299988473,
167
  "count": 1,
168
+ "self": 0.02832920299988473
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 410.2193069530001,
172
  "count": 1,
173
+ "self": 0.3295558649740542,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.3678142189999107,
177
  "count": 1,
178
+ "self": 3.3678142189999107
179
  },
180
  "TrainerController.advance": {
181
+ "total": 406.4423945580263,
182
  "count": 18192,
183
+ "self": 0.3712666920396259,
184
  "children": {
185
  "env_step": {
186
+ "total": 291.99846468798523,
187
  "count": 18192,
188
+ "self": 223.82985881096215,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 67.9717048750133,
192
  "count": 18192,
193
+ "self": 1.1956251410017558,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 66.77607973401155,
197
  "count": 18192,
198
+ "self": 66.77607973401155
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.19690100200978122,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 408.99407021800175,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 211.7187144449938,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0061728040000161855,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.004027966999956334,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0021448370000598516,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0021448370000598516
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.034142139999858045,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005493300002399337,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00037635899980159593,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00037635899980159593
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03146191799987719,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03146191799987719
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0017545329999393289,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00033688900020933943,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014176439997299894,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0014176439997299894
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 197.27535577300796,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 9.714519340012657,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.35285547999365,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 5.35285547999365
280
  },
281
  "communicator.exchange": {
282
+ "total": 151.05641219497693,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 151.05641219497693
286
  },
287
  "steps_from_proto": {
288
+ "total": 31.151568758024723,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 5.466508001920374,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 25.68506075610435,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 25.68506075610435
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 114.07266317800145,
311
  "count": 18192,
312
+ "self": 0.381435851999413,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 25.16646871800208,
316
  "count": 18192,
317
+ "self": 24.778297106002128,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.388171611999951,
321
  "count": 4,
322
+ "self": 0.388171611999951
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 88.52475860799996,
328
  "count": 90,
329
+ "self": 36.13230206198796,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 52.392456546012,
333
  "count": 4587,
334
+ "self": 52.392456546012
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 9.189998309011571e-07,
344
  "count": 1,
345
+ "self": 9.189998309011571e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.07954139200001009,
349
  "count": 1,
350
+ "self": 0.0007900049999989278,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.07875138700001116,
354
  "count": 1,
355
+ "self": 0.07875138700001116
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.272727272727273,
8
- "creation_time": 1753090578.7840436,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 22.181818181818183,
17
- "creation_time": 1753090681.7501934,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 25.636363636363637,
26
- "creation_time": 1753090784.9216647,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.272727272727273,
35
- "creation_time": 1753090886.348682,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.272727272727273,
44
- "creation_time": 1753090886.4370186,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.272727272727273,
54
- "creation_time": 1753090886.4370186,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 16.363636363636363,
8
+ "creation_time": 1753102232.4719942,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 23.181818181818183,
17
+ "creation_time": 1753102335.0040035,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 24.90909090909091,
26
+ "creation_time": 1753102436.1066542,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 24.636363636363637,
35
+ "creation_time": 1753102537.1660855,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 24.636363636363637,
44
+ "creation_time": 1753102537.2562122,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 24.636363636363637,
54
+ "creation_time": 1753102537.2562122,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]