Hugging Face's logo

carlosq
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
carlosq commited on
Commit
89684ab
•
1 Parent(s): b283f40

Second Push

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.1717508988.8afeb1794dbf.2488.0 +3 -0
  14. run_logs/Player-0.log +6 -6
  15. run_logs/timers.json +99 -99
  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 sha256:1b42f8aa087a94432738ebb2667be4b2d7d69a014d2bf1c9fa4b9553f4b62c07
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420cddb479346823e4dd232d7bf3eff9a7ee3a6b691f43fe47bb64b80fdef534
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f55cc12d787594584e20b4358bcbded663b0e29f31c4ae5bebb1a946ef72c27a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce01e428f22dbe85e3e96d80b81d64d424fbc67090956129748f24efeba7ee40
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efd37783095f7418d58cf271c62a83ecf9c0c62899754c4f3e67aabee3def274
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a9c9863f9e4dd734c08746a912256d7ec6a28baa4b661c54696cd8193b79f20
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b42f8aa087a94432738ebb2667be4b2d7d69a014d2bf1c9fa4b9553f4b62c07
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420cddb479346823e4dd232d7bf3eff9a7ee3a6b691f43fe47bb64b80fdef534
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0722efa0fa4797df5fce69e79d8970e01441a13ca381ffabaa786caa94d0436
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2910ee964017bfece65b0504775a5068d32321ca3e55935a74d310fbf0017807
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b42f8aa087a94432738ebb2667be4b2d7d69a014d2bf1c9fa4b9553f4b62c07
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420cddb479346823e4dd232d7bf3eff9a7ee3a6b691f43fe47bb64b80fdef534
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eb6b673d2241039718cf770b7c0dba08e3547053327c74c7a4c912aa72ae36e
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff6d6b0a488c731ba98afaecaa3d9f6cc3e1de541b22890755d370aca627227
3
  size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c34c20cd422423a9440244a4356091858c34923e7afc1adfde74b3c4ce2a84d
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8220fcc667b166db9452bcafd4f7fa1696760a2007292db2e0496f8f2d8ce18
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93479077a4378ef21e2d4ca4e325497ef12ea1107801df3c2fc31b6f2ce83209
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005ab1675bc015fb6fb20e8b1fe72d17a751127a787c73df6fe76f5775993983
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c78ce7849605bce561b989a0593311393926e740cf3651821bae3688b3806b1
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc61b118a679ea151a4ed7d0374d1018ac93e80d6f9e36bcb56baaadce08f5a
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:557d9b9227242da45ff6409962ff9235b2f80d849cec3161f517e55dd28c95ca
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d534570367dca753c6b07895e6152987de063ee3765857ed2db801ee568d7013
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfd5218504bed1ad1213cfcba3949b62126aa705861b18524063181c6609696d
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce3425f6402d566404ba546887b4d041b47e1e0221397b61908e91a411fe7b0d
3
  size 3849250
SnowballTarget/events.out.tfevents.1717508988.8afeb1794dbf.2488.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13693487b0d677e121f92b87297f2f1737fed0d21289e7214514c2ee5e0f5c4
3
+ size 23670
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 0.089 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: 0.699232 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.
@@ -169,7 +169,7 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -184,7 +184,7 @@ Memory Statistics:
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -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]: 4879 frames, [64.0 KB-128.0 KB]: 582 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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 0.126 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: 0.881887 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.
 
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 37
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
 
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.9 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
 
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]: 4585 frames, [64.0 KB-128.0 KB]: 876 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]: 5461 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9859325885772705,
6
- "min": 0.9730374813079834,
7
- "max": 2.8631248474121094,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9413.6845703125,
12
- "min": 9413.6845703125,
13
- "max": 29352.755859375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.909087181091309,
30
- "min": 0.2758808135986328,
31
- "max": 12.909087181091309,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2517.27197265625,
36
- "min": 53.520877838134766,
37
- "max": 2597.32958984375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06520190748172656,
54
- "min": 0.06227102151808817,
55
- "max": 0.07441185108253587,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.26080762992690626,
60
- "min": 0.2490840860723527,
61
- "max": 0.37205925541267937,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20347246819851444,
66
- "min": 0.124856798715579,
67
- "max": 0.29419127844420134,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8138898727940578,
72
- "min": 0.499427194862316,
73
- "max": 1.4421731221909615,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.863636363636363,
114
- "min": 3.6363636363636362,
115
- "max": 25.863636363636363,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1138.0,
120
- "min": 160.0,
121
- "max": 1394.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.863636363636363,
126
- "min": 3.6363636363636362,
127
- "max": 25.863636363636363,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1138.0,
132
- "min": 160.0,
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": "1716624363",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
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": "1.1.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1716624805"
160
  },
161
- "total": 441.781463742,
162
  "count": 1,
163
- "self": 0.43647613300004195,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.0569991990000176,
167
  "count": 1,
168
- "self": 0.0569991990000176
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 441.28798840999997,
172
  "count": 1,
173
- "self": 0.5302731120025328,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.9572008149999647,
177
  "count": 1,
178
- "self": 2.9572008149999647
179
  },
180
  "TrainerController.advance": {
181
- "total": 437.7063747199974,
182
  "count": 18201,
183
- "self": 0.2500895809914141,
184
  "children": {
185
  "env_step": {
186
- "total": 437.456285139006,
187
  "count": 18201,
188
- "self": 284.05463036000833,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 153.12804244499347,
192
  "count": 18201,
193
- "self": 1.4288832209932707,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 151.6991592240002,
197
  "count": 18201,
198
- "self": 151.6991592240002
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2736123340042127,
204
  "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 440.0266215949989,
209
  "count": 18201,
210
  "is_parallel": true,
211
- "self": 222.52259101299938,
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": 0.004907012999979088,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003415052999798718,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014919600001803701,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014919600001803701
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.044636711000009655,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007237430000373024,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00039786999997204475,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00039786999997204475
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03463614800000414,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03463614800000414
250
  },
251
  "steps_from_proto": {
252
- "total": 0.008878949999996166,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005708789999516739,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.008308071000044492,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.008308071000044492
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 217.50403058199953,
271
  "count": 18200,
272
  "is_parallel": true,
273
- "self": 10.048652350009093,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.147551899994198,
277
  "count": 18200,
278
  "is_parallel": true,
279
- "self": 5.147551899994198
280
  },
281
  "communicator.exchange": {
282
- "total": 169.83221881400306,
283
  "count": 18200,
284
  "is_parallel": true,
285
- "self": 169.83221881400306
286
  },
287
  "steps_from_proto": {
288
- "total": 32.47560751799318,
289
  "count": 18200,
290
  "is_parallel": true,
291
- "self": 5.9743851800125185,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.501222337980664,
295
  "count": 182000,
296
  "is_parallel": true,
297
- "self": 26.501222337980664
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011915599998246762,
313
  "count": 1,
314
- "self": 0.00011915599998246762,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 432.36911055603315,
324
- "count": 662874,
325
  "is_parallel": true,
326
- "self": 13.609090680037696,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 239.89426180099503,
330
- "count": 662874,
331
  "is_parallel": true,
332
- "self": 238.85071361699482,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.0435481840002012,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.0435481840002012
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 178.86575807500043,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 55.61841529600264,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 123.24734277899779,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 123.24734277899779
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09402060700006132,
364
  "count": 1,
365
- "self": 0.0009930050000548363,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09302760200000648,
369
  "count": 1,
370
- "self": 0.09302760200000648
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0019701719284058,
6
+ "min": 1.0019701719284058,
7
+ "max": 2.8738925457000732,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9566.8115234375,
12
+ "min": 9566.8115234375,
13
+ "max": 29526.37109375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.924033164978027,
30
+ "min": 0.3537145256996155,
31
+ "max": 12.924033164978027,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2520.1865234375,
36
+ "min": 68.62062072753906,
37
+ "max": 2603.72119140625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06724965259424572,
54
+ "min": 0.06089129457056212,
55
+ "max": 0.07462373430935972,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.26899861037698286,
60
+ "min": 0.24356517828224847,
61
+ "max": 0.37311867154679856,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.17851804160312107,
66
+ "min": 0.1296411275603425,
67
+ "max": 0.27650778652990565,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7140721664124843,
72
+ "min": 0.51856451024137,
73
+ "max": 1.2984937029142003,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.681818181818183,
114
+ "min": 3.5,
115
+ "max": 25.681818181818183,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1130.0,
120
+ "min": 154.0,
121
+ "max": 1397.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.681818181818183,
126
+ "min": 3.5,
127
+ "max": 25.681818181818183,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1130.0,
132
+ "min": 154.0,
133
+ "max": 1397.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1717508987",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
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": "1.1.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1717509438"
160
  },
161
+ "total": 450.950478869,
162
  "count": 1,
163
+ "self": 0.43460661799997524,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.08434326999997666,
167
  "count": 1,
168
+ "self": 0.08434326999997666
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 450.43152898100004,
172
  "count": 1,
173
+ "self": 0.5677419910022081,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.3792666759999292,
177
  "count": 1,
178
+ "self": 3.3792666759999292
179
  },
180
  "TrainerController.advance": {
181
+ "total": 446.396478768998,
182
  "count": 18201,
183
+ "self": 0.28037120098917967,
184
  "children": {
185
  "env_step": {
186
+ "total": 446.11610756800883,
187
  "count": 18201,
188
+ "self": 291.4872458690098,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 154.34312965199626,
192
  "count": 18201,
193
+ "self": 1.4598988950075409,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 152.88323075698872,
197
  "count": 18201,
198
+ "self": 152.88323075698872
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2857320470027389,
204
  "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 449.3060285460001,
209
  "count": 18201,
210
  "is_parallel": true,
211
+ "self": 226.424932869999,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.006582831000059741,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.004122744000028433,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002460087000031308,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002460087000031308
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03619192799999382,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006816950000256838,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003891349999776139,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003891349999776139
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03317099999992479,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03317099999992479
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019500980000657364,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00036032000048180635,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.00158977799958393,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.00158977799958393
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 222.8810956760011,
271
  "count": 18200,
272
  "is_parallel": true,
273
+ "self": 10.29917420699303,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.364845220000575,
277
  "count": 18200,
278
  "is_parallel": true,
279
+ "self": 5.364845220000575
280
  },
281
  "communicator.exchange": {
282
+ "total": 174.0986276730075,
283
  "count": 18200,
284
  "is_parallel": true,
285
+ "self": 174.0986276730075
286
  },
287
  "steps_from_proto": {
288
+ "total": 33.11844857599999,
289
  "count": 18200,
290
  "is_parallel": true,
291
+ "self": 6.269228363018669,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.849220212981322,
295
  "count": 182000,
296
  "is_parallel": true,
297
+ "self": 26.849220212981322
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00011540199989212852,
313
  "count": 1,
314
+ "self": 0.00011540199989212852,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 441.0731136010006,
324
+ "count": 668774,
325
  "is_parallel": true,
326
+ "self": 13.878266203965268,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 243.748400845035,
330
+ "count": 668774,
331
  "is_parallel": true,
332
+ "self": 243.0441920840351,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.7042087609999044,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.7042087609999044
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 183.44644655200034,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 59.76644125400003,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 123.68000529800031,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 123.68000529800031
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.08792614300000423,
364
  "count": 1,
365
+ "self": 0.000969076000046698,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.08695706699995753,
369
  "count": 1,
370
+ "self": 0.08695706699995753
371
  }
372
  }
373
  }
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": 14.454545454545455,
8
- "creation_time": 1716624477.8743184,
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": 22.727272727272727,
17
- "creation_time": 1716624587.412283,
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": 25.181818181818183,
26
- "creation_time": 1716624697.065249,
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": 26.09090909090909,
35
- "creation_time": 1716624804.914689,
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": 26.09090909090909,
44
- "creation_time": 1716624805.0371835,
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": 26.09090909090909,
54
- "creation_time": 1716624805.0371835,
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": 12.454545454545455,
8
+ "creation_time": 1717509103.0740745,
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": 21.636363636363637,
17
+ "creation_time": 1717509214.9274127,
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": 25.09090909090909,
26
+ "creation_time": 1717509327.1838572,
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": 25.454545454545453,
35
+ "creation_time": 1717509437.8803637,
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": 25.454545454545453,
44
+ "creation_time": 1717509437.996128,
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": 25.454545454545453,
54
+ "creation_time": 1717509437.996128,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]