Hugging Face's logo

Flickinshots
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Flickinshots commited on
Commit
14aaf12
·
verified ·
1 Parent(s): 4e39c25

First 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.1750334766.fed6bebfa710.3169.0 +3 -0
  14. run_logs/Player-0.log +4 -4
  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 sha256:7276d10ac1b53464d3514b2dd943b16fbe9c582111eac515b1ef15853c4afa59
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76faa27de4f094585c40c551281cc908c95c05647fa6e86a8309ee0dbf88539c
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4d4e150cc3096cbc8fb775ab23be3585fe9cd62aa6fb78c56649ea56b0721ea
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af6ae237c936f54cf0d927463695d429374e26578fcba1d90be66e63be70ffa
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca711b33232ea354055f1527bad865ed9bde0c0bb809e2ed260aca64d5a5b36f
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11803d0a2b0c2769237ba0632998c386f1a4790117712ddc8fa48ed956f0cf6
3
  size 3850564
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7276d10ac1b53464d3514b2dd943b16fbe9c582111eac515b1ef15853c4afa59
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76faa27de4f094585c40c551281cc908c95c05647fa6e86a8309ee0dbf88539c
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaf097758f1b0a2679d6789e1652447c2ebc15b24762913795a11acd553e414c
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f9ef6259d4cdbdf78a324e2da083252f89d5c0cace31849a02251719208efd
3
  size 3850564
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7276d10ac1b53464d3514b2dd943b16fbe9c582111eac515b1ef15853c4afa59
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76faa27de4f094585c40c551281cc908c95c05647fa6e86a8309ee0dbf88539c
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69cb18178c92f1b3884087ddda16e18bbc84441b0ee09ce0c0d08f1380e88f9d
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f45ef81b6e7f69114a1b51deccafdbaac57f3c15c2f956ac502b575904d20a82
3
  size 3850564
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39e640f6188c935ffedd4a0be7d34b3bfffa329d96527426df88372ce27811ec
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7851024b341219af9c353f239f41138af1b124a14538845dda193a794b6677e
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07bb3bdbe0907c3d1d75cacbaa5d021317974f2c0ec1d85ef4936ce9ec2dba1f
3
  size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93d73ed8dc3e5a7b9ceef6fd21c0c53b5664d794ebd291415eb9693a32107a96
3
  size 3850487
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7434f10e9c37a1d8d8dc2de3a46e790a4beb97c1e4486a2c15972990b2f7a88
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060bc2881d3ea8935493c06b08bf629561ee8b6a5f499bd66ff6521095463e29
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f53ec51b9313bf0b844885fe4684b4a3308d242387dbd79f2a37aafbe1ef892d
3
  size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff5cebed4fe6ef39f21a0bd379f068a1db1e3c36630720e48036a04430cfe97
3
  size 3850487
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d1c252df3c93da6af677c704b0e060e81b05f2539db8a908c935f5fb7694b0f
3
  size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a8fb73eed9a8ec6f4c186e1fca873a50c79b2bc8bad90ef8429064042f1017
3
  size 3849717
SnowballTarget/events.out.tfevents.1750334766.fed6bebfa710.3169.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1935cf5c061d505c0ed0b7de8b9f393442202aeb0c028d54077c29e175d71605
3
+ size 28236
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 0.091 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: 0.811148 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.
@@ -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]: 4915 frames, [64.0 KB-128.0 KB]: 543 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
 
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 0.092 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: 0.696619 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.
 
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]: 4826 frames, [64.0 KB-128.0 KB]: 632 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]: 5458 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.7483605146408081,
6
- "min": 0.7483605146408081,
7
- "max": 2.8574256896972656,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7112.41845703125,
12
- "min": 7112.41845703125,
13
- "max": 29168.6015625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.800681114196777,
30
- "min": 0.1739872395992279,
31
- "max": 12.800681114196777,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2496.1328125,
36
- "min": 33.75352478027344,
37
- "max": 2607.27734375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07512074474567164,
42
- "min": 0.06166309507862738,
43
- "max": 0.07596792522007507,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.30048297898268655,
48
- "min": 0.2466523803145095,
49
- "max": 0.349630879836731,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.20164215871516394,
54
- "min": 0.1027141789364738,
55
- "max": 0.29410325797165143,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8065686348606558,
60
- "min": 0.4108567157458952,
61
- "max": 1.470516289858257,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.318181818181817,
114
- "min": 3.022727272727273,
115
- "max": 25.318181818181817,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1114.0,
120
- "min": 133.0,
121
- "max": 1374.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.318181818181817,
126
- "min": 3.022727272727273,
127
- "max": 25.318181818181817,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1114.0,
132
- "min": 133.0,
133
- "max": 1374.0,
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": "1750324661",
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": "1750325080"
160
  },
161
- "total": 418.936644676,
162
  "count": 1,
163
- "self": 0.4412346289999505,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.023346316000015577,
167
  "count": 1,
168
- "self": 0.023346316000015577
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 418.47206373100005,
172
  "count": 1,
173
- "self": 0.36146288200870913,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.4319992700000057,
177
  "count": 1,
178
- "self": 3.4319992700000057
179
  },
180
  "TrainerController.advance": {
181
- "total": 414.5973837089913,
182
  "count": 18192,
183
- "self": 0.3770558650045359,
184
  "children": {
185
  "env_step": {
186
- "total": 295.674319322987,
187
  "count": 18192,
188
- "self": 227.32290671497492,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 68.14338877701039,
192
  "count": 18192,
193
- "self": 1.2550377190335666,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 66.88835105797682,
197
  "count": 18192,
198
- "self": 66.88835105797682
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.20802383100169664,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 416.7332518259901,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 217.7258410059934,
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": 0.00569632199994885,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.00419642599990766,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014998960000411898,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014998960000411898
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.035054938000030234,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.000606639000125142,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00043779299994639587,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00043779299994639587
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03219719699995949,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03219719699995949
250
  },
251
  "steps_from_proto": {
252
- "total": 0.001813308999999208,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003764729999602423,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014368360000389657,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014368360000389657
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 199.00741081999672,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.675061540986121,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.160277422011063,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.160277422011063
280
  },
281
  "communicator.exchange": {
282
- "total": 153.73987094899894,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 153.73987094899894
286
  },
287
  "steps_from_proto": {
288
- "total": 30.432200908000596,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.515426713059583,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 24.916774194941013,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 24.916774194941013
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 118.54600852099975,
311
  "count": 18192,
312
- "self": 0.4481660490081367,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 25.421623678992773,
316
  "count": 18192,
317
- "self": 25.028060677992812,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.39356300099996133,
321
  "count": 4,
322
- "self": 0.39356300099996133
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 92.67621879299884,
328
  "count": 90,
329
- "self": 37.61476022200418,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 55.06145857099466,
333
  "count": 4587,
334
- "self": 55.06145857099466
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 8.910001270123757e-07,
344
  "count": 1,
345
- "self": 8.910001270123757e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08121697899991887,
349
  "count": 1,
350
- "self": 0.00081540899986976,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.0804015700000491,
354
  "count": 1,
355
- "self": 0.0804015700000491
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9118658304214478,
6
+ "min": 0.89549320936203,
7
+ "max": 2.8518598079681396,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8666.373046875,
12
+ "min": 8666.373046875,
13
+ "max": 29111.78515625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.177143096923828,
30
+ "min": 0.36337044835090637,
31
+ "max": 13.177143096923828,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2569.54296875,
36
+ "min": 70.49386596679688,
37
+ "max": 2687.5322265625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.05987863670452498,
42
+ "min": 0.05987863670452498,
43
+ "max": 0.07550312518364723,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.23951454681809992,
48
+ "min": 0.23951454681809992,
49
+ "max": 0.3775156259182361,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.23068397083118852,
54
+ "min": 0.10636232049243213,
55
+ "max": 0.28024065728281056,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.9227358833247541,
60
+ "min": 0.42544928196972853,
61
+ "max": 1.2245127190561855,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.5,
114
+ "min": 3.0,
115
+ "max": 25.763636363636362,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1122.0,
120
+ "min": 132.0,
121
+ "max": 1417.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.5,
126
+ "min": 3.0,
127
+ "max": 25.763636363636362,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1122.0,
132
+ "min": 132.0,
133
+ "max": 1417.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1750334765",
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": "1750335237"
160
  },
161
+ "total": 472.42420688,
162
  "count": 1,
163
+ "self": 0.42733578199994326,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.02165976900005262,
167
  "count": 1,
168
+ "self": 0.02165976900005262
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 471.975211329,
172
  "count": 1,
173
+ "self": 0.4117504800049687,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.081813526000019,
177
  "count": 1,
178
+ "self": 2.081813526000019
179
  },
180
  "TrainerController.advance": {
181
+ "total": 469.39152770999505,
182
  "count": 18192,
183
+ "self": 0.44034819098561684,
184
  "children": {
185
  "env_step": {
186
+ "total": 337.41831338900215,
187
  "count": 18192,
188
+ "self": 259.2917776039822,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 77.88391608200408,
192
  "count": 18192,
193
+ "self": 1.3852040070090084,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 76.49871207499507,
197
  "count": 18192,
198
+ "self": 76.49871207499507
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2426197030158619,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 469.986186083999,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 242.51586252698797,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0021987559999843143,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000682367000024442,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015163889999598723,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015163889999598723
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.07267303399999037,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006348299999672236,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004327049999801602,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004327049999801602
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.06940554900000961,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.06940554900000961
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021999500000333683,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004360420000466547,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017639079999867135,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0017639079999867135
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 227.470323557011,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 10.631709639025019,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 6.025030793995256,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 6.025030793995256
280
  },
281
  "communicator.exchange": {
282
+ "total": 175.0300370349961,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 175.0300370349961
286
  },
287
  "steps_from_proto": {
288
+ "total": 35.783546088994626,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 6.430568098970639,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 29.352977990023987,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 29.352977990023987
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 131.53286613000728,
311
  "count": 18192,
312
+ "self": 0.47714595900703216,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 30.304337811000437,
316
  "count": 18192,
317
+ "self": 29.76381739600049,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.5405204149999463,
321
  "count": 4,
322
+ "self": 0.5405204149999463
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 100.75138235999981,
328
  "count": 90,
329
+ "self": 42.11543741399896,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 58.63594494600085,
333
  "count": 4587,
334
+ "self": 58.63594494600085
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.1360000371496426e-06,
344
  "count": 1,
345
+ "self": 1.1360000371496426e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.09011847699991904,
349
  "count": 1,
350
+ "self": 0.0008169929999439773,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.08930148399997506,
354
  "count": 1,
355
+ "self": 0.08930148399997506
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": 15.0,
8
- "creation_time": 1750324768.4259803,
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": 22.363636363636363,
17
- "creation_time": 1750324874.594789,
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": 23.818181818181817,
26
- "creation_time": 1750324977.219264,
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": 1750325079.5809543,
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": 1750325079.673492,
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": 1750325079.673492,
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": 13.818181818181818,
8
+ "creation_time": 1750334884.8675563,
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": 23.545454545454547,
17
+ "creation_time": 1750335002.8110943,
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": 26.636363636363637,
26
+ "creation_time": 1750335120.4470363,
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": 24.545454545454547,
35
+ "creation_time": 1750335237.324234,
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": 24.545454545454547,
44
+ "creation_time": 1750335237.4263759,
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": 24.545454545454547,
54
+ "creation_time": 1750335237.4263759,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]