Hugging Face's logo

oookayamaswallow
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
oookayamaswallow commited on
Commit
503b8e5
•
1 Parent(s): 793f5d3

回しなおしたので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 +3 -0
  7. SnowballTarget/SnowballTarget-200112.pt +3 -0
  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.1722437512.3b1cc1825e7f.2558.0 +3 -0
  14. run_logs/Player-0.log +7 -7
  15. run_logs/timers.json +112 -112
  16. run_logs/training_status.json +17 -17
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea66f37ff1d022dfd548f70448aa9f2bb81537ef845afbd262e542154009c8bb
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4339ea3d45a1280ad998a5053dca8257d5258cc4fcdfdcc920968eff4bfec70a
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e07067420e5fa3e7e3c8fa5d13263bc60e73078272fe1f2359a522a3e0a5938
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75e99296bd1abaa408833829023c8a3ac7714b5e04c7145d58c7dbec3f258f5
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7af94e2535739af0e6b318b3deea867fb1c5ece5d2207918c67c8274f280d46
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0430aa263356292e6a4fc988470fe456960b1686ed12d8e4a2ee1ad93039ad75
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea66f37ff1d022dfd548f70448aa9f2bb81537ef845afbd262e542154009c8bb
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4339ea3d45a1280ad998a5053dca8257d5258cc4fcdfdcc920968eff4bfec70a
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a948fa9c0aa493b11f9031ef84047080f2c4695bff3b07d7fd2c4b71b9698673
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d764b1d38bd953581037f31a9c723e25b31dec3e95b1bc4102f1249d19c2881
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4339ea3d45a1280ad998a5053dca8257d5258cc4fcdfdcc920968eff4bfec70a
3
+ size 650646
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e172392f43c715a26b376f71f76189612dd22f3255233c30282713b882cc214
3
+ size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aff2a3b2ebfbe7ba64c4966d0660a7a9519a590bc7e53a4c5d274f0daed01f9f
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad3be657823f3621d55bae1fbfb14d40e13d7eda0ba10c8a31ded1d8c11a4a1
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93d71b157f6b0e86805865cce07105167f77ceee89846b09b9c47bdccc8868b4
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a82e65b3d03c45aff54dc1f7da426890240e1359a5930c0a53dae76c5caf8f83
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2736edaf450b1a43bbb78d027170b99f6a8a62152962041b9171e1a821469319
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb205f6827446c22aa99b974a133cfb238ff1c6021d7ae6cf194762bf417af76
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:672c8b75dd4b5a8c816f6abaca68648bd26727e41e5189eec99215f9b2f38d81
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f7139beed9246d2281f15d97421d5d2a28dbe5ff86031b5c37efe6badae23cb
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b783bbd42e619e56d2e227ab1b6c531295dbbbf00fd67b5f81d80bc10d98ff7
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d21c4c5eae9f1426dac91747309f948a8080b76dbce0ea3e0b796cbdcb232b
3
  size 3849250
SnowballTarget/events.out.tfevents.1722437512.3b1cc1825e7f.2558.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26b1c744f4eecd848d606b473c538ea6daabf00a7bccadcd2323b35e79c1e2c3
3
+ size 23586
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: 0.629360 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 38
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -178,13 +178,13 @@ Memory Statistics:
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5461 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]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.7 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]: 5160 frames, [64.0 KB-128.0 KB]: 301 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]: 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 0.085 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: 0.643681 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 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
 
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 6.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
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
  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]: 4520 frames, [64.0 KB-128.0 KB]: 941 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
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8370972275733948,
6
- "min": 0.8370972275733948,
7
- "max": 2.8588879108428955,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7992.6044921875,
12
- "min": 7992.6044921875,
13
- "max": 29309.318359375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.7811861038208,
30
- "min": 0.2791458070278168,
31
- "max": 12.972125053405762,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2492.331298828125,
36
- "min": 54.15428924560547,
37
- "max": 2645.44580078125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06738024796519027,
54
- "min": 0.06291451561107761,
55
- "max": 0.07693827273871968,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.26952099186076106,
60
- "min": 0.25165806244431044,
61
- "max": 0.3846913636935984,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20532643261785602,
66
- "min": 0.12644542183147234,
67
- "max": 0.2712783714719847,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8213057304714241,
72
- "min": 0.5057816873258894,
73
- "max": 1.3563918573599234,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.113636363636363,
114
- "min": 3.477272727272727,
115
- "max": 25.636363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1105.0,
120
- "min": 153.0,
121
- "max": 1410.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.113636363636363,
126
- "min": 3.477272727272727,
127
- "max": 25.636363636363637,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1105.0,
132
- "min": 153.0,
133
- "max": 1410.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1722423914",
152
  "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1722424390"
160
  },
161
- "total": 475.9005632330002,
162
  "count": 1,
163
- "self": 0.43157541400023547,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.07085516400002234,
167
  "count": 1,
168
- "self": 0.07085516400002234
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 475.3981326549999,
172
  "count": 1,
173
- "self": 0.6526122389834654,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.798851610999918,
177
  "count": 1,
178
- "self": 2.798851610999918
179
  },
180
  "TrainerController.advance": {
181
- "total": 471.83864539701653,
182
- "count": 18201,
183
- "self": 0.3056806940360275,
184
  "children": {
185
  "env_step": {
186
- "total": 471.5329647029805,
187
- "count": 18201,
188
- "self": 307.6519660479971,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 163.5759928999928,
192
- "count": 18201,
193
- "self": 1.5889170349994401,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 161.98707586499336,
197
- "count": 18201,
198
- "self": 161.98707586499336
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.3050057549905887,
204
- "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 473.9386841219996,
209
- "count": 18201,
210
  "is_parallel": true,
211
- "self": 240.2492969940074,
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": 0.005626583000093888,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003965077000202655,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.001661505999891233,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.001661505999891233
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03818623500001195,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007201499997790961,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003840470001250651,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003840470001250651
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03497716600008971,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03497716600008971
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0021048720000180765,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00040893599975788675,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016959360002601898,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016959360002601898
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 233.68938712799218,
271
- "count": 18200,
272
  "is_parallel": true,
273
- "self": 10.48078469994607,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.682723615992472,
277
- "count": 18200,
278
  "is_parallel": true,
279
- "self": 5.682723615992472
280
  },
281
  "communicator.exchange": {
282
- "total": 182.06767561701872,
283
- "count": 18200,
284
  "is_parallel": true,
285
- "self": 182.06767561701872
286
  },
287
  "steps_from_proto": {
288
- "total": 35.45820319503491,
289
- "count": 18200,
290
  "is_parallel": true,
291
- "self": 6.866202692986008,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 28.592000502048904,
295
- "count": 182000,
296
  "is_parallel": true,
297
- "self": 28.592000502048904
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00016744699996706913,
313
  "count": 1,
314
- "self": 0.00016744699996706913,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 465.90514656193136,
324
- "count": 683845,
325
  "is_parallel": true,
326
- "self": 14.992023835956616,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 259.1903054119739,
330
- "count": 683845,
331
  "is_parallel": true,
332
- "self": 258.483158951974,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.7071464599998762,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.7071464599998762
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 191.72281731400085,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 61.20790993500623,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 130.51490737899462,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 130.51490737899462
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.10785596100004113,
364
  "count": 1,
365
- "self": 0.0009831899999426241,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.10687277100009851,
369
  "count": 1,
370
- "self": 0.10687277100009851
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9279464483261108,
6
+ "min": 0.9279464483261108,
7
+ "max": 2.8677165508270264,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8870.240234375,
12
+ "min": 8870.240234375,
13
+ "max": 29431.375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.866422653198242,
30
+ "min": 0.523067057132721,
31
+ "max": 12.866422653198242,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2508.952392578125,
36
+ "min": 101.47500610351562,
37
+ "max": 2603.08154296875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07161606462661403,
54
+ "min": 0.059430613687293896,
55
+ "max": 0.07543190238499722,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2864642585064561,
60
+ "min": 0.24383551273072668,
61
+ "max": 0.3664145125127535,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19725944554688885,
66
+ "min": 0.13280159980286937,
67
+ "max": 0.2857901934315176,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7890377821875554,
72
+ "min": 0.5312063992114775,
73
+ "max": 1.4289509671575882,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.386363636363637,
114
+ "min": 3.772727272727273,
115
+ "max": 25.386363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1117.0,
120
+ "min": 166.0,
121
+ "max": 1394.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.386363636363637,
126
+ "min": 3.772727272727273,
127
+ "max": 25.386363636363637,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1117.0,
132
+ "min": 166.0,
133
+ "max": 1394.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1722437511",
152
  "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1722437955"
160
  },
161
+ "total": 444.19406977899996,
162
  "count": 1,
163
+ "self": 0.4393552169999566,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05927546500004155,
167
  "count": 1,
168
+ "self": 0.05927546500004155
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 443.69543909699996,
172
  "count": 1,
173
+ "self": 0.552766290995578,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.6011603629999627,
177
  "count": 1,
178
+ "self": 2.6011603629999627
179
  },
180
  "TrainerController.advance": {
181
+ "total": 440.44331370600446,
182
+ "count": 18203,
183
+ "self": 0.2658895780105013,
184
  "children": {
185
  "env_step": {
186
+ "total": 440.17742412799396,
187
+ "count": 18203,
188
+ "self": 282.4349340459853,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 157.46905357400078,
192
+ "count": 18203,
193
+ "self": 1.4491038109950978,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 156.01994976300568,
197
+ "count": 18203,
198
+ "self": 156.01994976300568
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.273436508007876,
204
+ "count": 18203,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 442.5050466840081,
209
+ "count": 18203,
210
  "is_parallel": true,
211
+ "self": 226.02941221299625,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005070621000072606,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0034363440001925483,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016342769998800577,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0016342769998800577
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03632970800003932,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006902890002038475,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00039318599999660364,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00039318599999660364
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03314641399992979,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03314641399992979
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0020998189999090755,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004139989998748206,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001685820000034255,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001685820000034255
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 216.47563447101186,
271
+ "count": 18202,
272
  "is_parallel": true,
273
+ "self": 10.03200970801845,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.421959038996306,
277
+ "count": 18202,
278
  "is_parallel": true,
279
+ "self": 5.421959038996306
280
  },
281
  "communicator.exchange": {
282
+ "total": 167.45527470798493,
283
+ "count": 18202,
284
  "is_parallel": true,
285
+ "self": 167.45527470798493
286
  },
287
  "steps_from_proto": {
288
+ "total": 33.566391016012176,
289
+ "count": 18202,
290
  "is_parallel": true,
291
+ "self": 6.409855371027106,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 27.15653564498507,
295
+ "count": 182020,
296
  "is_parallel": true,
297
+ "self": 27.15653564498507
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00012729999991734076,
313
  "count": 1,
314
+ "self": 0.00012729999991734076,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 434.8873482930567,
324
+ "count": 664273,
325
  "is_parallel": true,
326
+ "self": 14.27057802308559,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 238.71339789897104,
330
+ "count": 664273,
331
  "is_parallel": true,
332
+ "self": 237.831125574971,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.8822723240000414,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.8822723240000414
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 181.90337237100005,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 56.46925150899801,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 125.43412086200203,
350
+ "count": 4584,
351
  "is_parallel": true,
352
+ "self": 125.43412086200203
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09807143700004417,
364
  "count": 1,
365
+ "self": 0.001021087000026455,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.09705035000001772,
369
  "count": 1,
370
+ "self": 0.09705035000001772
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": 13.727272727272727,
8
- "creation_time": 1722424037.7389624,
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": 22.272727272727273,
17
- "creation_time": 1722424154.241657,
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": 26.454545454545453,
26
- "creation_time": 1722424273.3359752,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +31,29 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.363636363636363,
35
- "creation_time": 1722424390.0827732,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200200,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
43
- "reward": 25.5,
44
- "creation_time": 1722424390.2436185,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200200,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.5,
54
- "creation_time": 1722424390.2436185,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 12.818181818181818,
8
+ "creation_time": 1722437626.392807,
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": 20.181818181818183,
17
+ "creation_time": 1722437736.1302896,
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": 25.545454545454547,
26
+ "creation_time": 1722437845.9644635,
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": 25.09090909090909,
35
+ "creation_time": 1722437954.9149222,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.09090909090909,
44
+ "creation_time": 1722437955.0402806,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 25.09090909090909,
54
+ "creation_time": 1722437955.0402806,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },