Hugging Face's logo

Balab2021
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
Balab2021 commited on
Commit
3aece8a
·
verified ·
1 Parent(s): 109456c

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 +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1738695992.dc31ca6975df.3541.0 +3 -0
  14. run_logs/Player-0.log +11 -11
  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:b0b60dcddaf16ddbe80a9632c80932dafc468b8b4a2cb5f107c3f38d9de66227
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779efa3c484e73fb6d504e8765cc8b7d266e730ddbac51551d9d7bb33ebc3284
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a34c34e8885226549991d6e834a6765c28f0f16afa0f2701cc3a158281203bc
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f365050f24ad8d9645e3741eedac948d0143ad3a3f7bfa5f3088123a733fc37d
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54cfc63e91e7e99e9c700c271479ec1c1668378021aa0c50e5c078b2e3bda846
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a969b5bbbee67cb44ed850a3e286aefa312bf124162d7f9d874c16a04a3398c
3
+ size 3849115
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0b60dcddaf16ddbe80a9632c80932dafc468b8b4a2cb5f107c3f38d9de66227
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779efa3c484e73fb6d504e8765cc8b7d266e730ddbac51551d9d7bb33ebc3284
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:836004ee159db3cfd66685b984f2bdfab1ecb5e3b47afbbd1f883de6051d4aa6
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2008705e2433c7c9f6f3a3f8a3c044f1f3cac16836a77d00354b0e621529748d
3
+ size 3849115
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0b60dcddaf16ddbe80a9632c80932dafc468b8b4a2cb5f107c3f38d9de66227
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779efa3c484e73fb6d504e8765cc8b7d266e730ddbac51551d9d7bb33ebc3284
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c0b0fee5b01d93c1084ee60988484ffe6586e6058d0c7e183ecc61b19daf650
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3e4f3f3e16b006ebdf47a2ce7a7eac921bbfdeed3713ce0d353cfea51eca5e
3
+ size 3849115
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed09cff30f6e634ecf56905088e4608f3a54ea33013ca53e43b1a03bb4f3b2d4
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c83ce6f3cec4c32c85abcfe4ed293a8c4039dd00d9b80eff7b538ae6f3fd9cd
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c10db3e52a742704fbbfb38d48d3a023af16b4c0d169f98bf9b5d607fdccd46e
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b05681293acc7519613085911ebffed51ad08dca2cee03794eb38dad67d465e
3
+ size 3849040
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52b697c87ce88b6dd3da203358bb82c65b33f5cd1fcebe64b04888f2fff21d31
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f7fc9bf6e67effbdaa7da521798e0c9d155e9db3726eeeddbc4862b9b9e330
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:486445b30e952f71b811ccd19b11ba8de50ae12be638fa1241e5d03c56bc60db
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e687bd4ac81e2423424f8a27bc87deec4f81e305fcc19c5a9af36e3f28ef1f3c
3
+ size 3849040
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f942c4c9571b11444f628e563ad7e84aa97881e681bb2c84a6b61e3a00fa94ba
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a130886d2522f1a8582ba63508733b40b4dcd666838ced098d8b268521a37fc
3
+ size 3848290
SnowballTarget/events.out.tfevents.1738695992.dc31ca6975df.3541.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52fc77913fcd027df33d3f4a52d86a3f926bef01253d71ff3c3e22941b59c49e
3
+ size 23443
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 0.134 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: 0.831998 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.
@@ -169,23 +169,23 @@ 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
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 22.7 MB
182
- Peak Large allocation bytes 16.0 MB
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [1.0 MB-2.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 1.7 MB
188
- Peak Large allocation bytes 0 B
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
191
  Used Block Count 1
@@ -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]: 4797 frames, [64.0 KB-128.0 KB]: 661 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
 
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 0.165 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: 0.945072 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 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
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 6.8 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
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.5 MB
188
+ Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
191
  Used Block Count 1
 
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]: 4952 frames, [64.0 KB-128.0 KB]: 506 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": 0.8443519473075867,
6
- "min": 0.8443519473075867,
7
- "max": 2.8481428623199463,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8024.720703125,
12
- "min": 8024.720703125,
13
- "max": 29073.841796875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.956758499145508,
30
- "min": 0.37598514556884766,
31
- "max": 12.956758499145508,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2526.56787109375,
36
- "min": 72.94111633300781,
37
- "max": 2641.5810546875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06843561053620742,
42
- "min": 0.0638919589557119,
43
- "max": 0.07644554432652727,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2737424421448297,
48
- "min": 0.2593425857671808,
49
- "max": 0.38222772163263635,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.18003323842205254,
54
- "min": 0.12962720706241718,
55
- "max": 0.2919185297746284,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7201329536882102,
60
- "min": 0.5185088282496687,
61
- "max": 1.459592648873142,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.477272727272727,
114
- "min": 3.5,
115
- "max": 25.654545454545456,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1121.0,
120
- "min": 154.0,
121
- "max": 1411.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.477272727272727,
126
- "min": 3.5,
127
- "max": 25.654545454545456,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1121.0,
132
- "min": 154.0,
133
- "max": 1411.0,
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": "1738691251",
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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1738691674"
160
  },
161
- "total": 422.77412286899994,
162
  "count": 1,
163
- "self": 0.7975625689999788,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.02845033300002342,
167
  "count": 1,
168
- "self": 0.02845033300002342
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 421.94810996699994,
172
  "count": 1,
173
- "self": 0.318993835010815,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.4423002689999294,
177
  "count": 1,
178
- "self": 3.4423002689999294
179
  },
180
  "TrainerController.advance": {
181
- "total": 418.0491113449892,
182
  "count": 18192,
183
- "self": 0.33862268597351886,
184
  "children": {
185
  "env_step": {
186
- "total": 293.69544626800655,
187
  "count": 18192,
188
- "self": 223.08328248201178,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 70.41702777599846,
192
  "count": 18192,
193
- "self": 1.195437468007185,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 69.22159030799128,
197
  "count": 18192,
198
- "self": 69.22159030799128
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.19513600999630398,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 420.25199088500733,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 224.49596176400837,
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": 0.006066460000056395,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.00414990199976728,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0019165580002891147,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0019165580002891147
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03397144500002014,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.000585247000117306,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00040851599999314203,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00040851599999314203
244
  },
245
  "communicator.exchange": {
246
- "total": 0.031237638999982664,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.031237638999982664
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0017400429999270273,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003297820001080254,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014102609998190019,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014102609998190019
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 195.75602912099896,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.505440498023518,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.215559988991458,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.215559988991458
280
  },
281
  "communicator.exchange": {
282
- "total": 150.8996677029819,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 150.8996677029819
286
  },
287
  "steps_from_proto": {
288
- "total": 30.135360931002083,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.254522200032966,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 24.880838730969117,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 24.880838730969117
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 124.01504239100916,
311
  "count": 18192,
312
- "self": 0.41235903600488655,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 26.640687834004098,
316
  "count": 18192,
317
- "self": 26.056008029004033,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.5846798050000643,
321
  "count": 4,
322
- "self": 0.5846798050000643
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 96.96199552100018,
328
  "count": 90,
329
- "self": 38.961756425994736,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 58.00023909500544,
333
  "count": 4587,
334
- "self": 58.00023909500544
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.2120001429138938e-06,
344
  "count": 1,
345
- "self": 1.2120001429138938e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.13770330599982117,
349
  "count": 1,
350
- "self": 0.0019186749998425512,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.13578463099997862,
354
  "count": 1,
355
- "self": 0.13578463099997862
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9734007716178894,
6
+ "min": 0.9734007716178894,
7
+ "max": 2.840930938720703,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9251.201171875,
12
+ "min": 9251.201171875,
13
+ "max": 29000.22265625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.17613697052002,
30
+ "min": 0.4330487549304962,
31
+ "max": 13.17613697052002,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2569.3466796875,
36
+ "min": 84.01145935058594,
37
+ "max": 2668.453125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.07505593754945485,
42
+ "min": 0.06181131327182847,
43
+ "max": 0.0768056135184095,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.3002237501978194,
48
+ "min": 0.24724525308731388,
49
+ "max": 0.3774971572223448,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.21283396779029978,
54
+ "min": 0.13966708885067525,
55
+ "max": 0.3056896312564027,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.8513358711611991,
60
+ "min": 0.558668355402701,
61
+ "max": 1.5284481562820136,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.431818181818183,
114
+ "min": 4.386363636363637,
115
+ "max": 25.78181818181818,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1119.0,
120
+ "min": 193.0,
121
+ "max": 1418.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.431818181818183,
126
+ "min": 4.386363636363637,
127
+ "max": 25.78181818181818,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1119.0,
132
+ "min": 193.0,
133
+ "max": 1418.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1738695991",
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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1738696575"
160
  },
161
+ "total": 584.37370413,
162
  "count": 1,
163
+ "self": 0.5375780050000003,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.034259703999964586,
167
  "count": 1,
168
+ "self": 0.034259703999964586
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 583.801866421,
172
  "count": 1,
173
+ "self": 0.6244589130036502,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.83298597299995,
177
  "count": 1,
178
+ "self": 3.83298597299995
179
  },
180
  "TrainerController.advance": {
181
+ "total": 579.2568668949962,
182
  "count": 18192,
183
+ "self": 0.6379939019873291,
184
  "children": {
185
  "env_step": {
186
+ "total": 401.8304817430088,
187
  "count": 18192,
188
+ "self": 340.992025279009,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 60.464567351998994,
192
  "count": 18192,
193
+ "self": 2.2110836829936034,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 58.25348366900539,
197
  "count": 18192,
198
+ "self": 58.25348366900539
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.37388911200082475,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 581.6121238170072,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 287.4441795400029,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.007298810000065714,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.004943506000131492,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002355303999934222,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002355303999934222
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0466708709999466,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0009063349998541526,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00043911400007345947,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00043911400007345947
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.042967144000044755,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.042967144000044755
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0023582779999742343,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00044907300002705597,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0019092049999471783,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0019092049999471783
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 294.16794427700427,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 13.56301541300229,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.549516758011805,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 7.549516758011805
280
  },
281
  "communicator.exchange": {
282
+ "total": 231.68514345299673,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 231.68514345299673
286
  },
287
  "steps_from_proto": {
288
+ "total": 41.370268652993445,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 8.110472834992265,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 33.25979581800118,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 33.25979581800118
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 176.78839125000002,
311
  "count": 18192,
312
+ "self": 0.7981750700071188,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 32.92713713399189,
316
  "count": 18192,
317
+ "self": 32.36163306799142,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.5655040660004715,
321
  "count": 4,
322
+ "self": 0.5655040660004715
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 143.063079046001,
328
  "count": 90,
329
+ "self": 52.004258849997655,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 91.05882019600335,
333
  "count": 4587,
334
+ "self": 91.05882019600335
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 2.0360000689834123e-06,
344
  "count": 1,
345
+ "self": 2.0360000689834123e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.08755260400016596,
349
  "count": 1,
350
+ "self": 0.0011940210001739615,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.086358582999992,
354
  "count": 1,
355
+ "self": 0.086358582999992
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": 13.454545454545455,
8
- "creation_time": 1738691359.3194463,
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": 22.636363636363637,
17
- "creation_time": 1738691465.732682,
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": 25.09090909090909,
26
- "creation_time": 1738691570.7595005,
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": 25.545454545454547,
35
- "creation_time": 1738691673.3005302,
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": 25.545454545454547,
44
- "creation_time": 1738691673.4554505,
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": 25.545454545454547,
54
- "creation_time": 1738691673.4554505,
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": 15.545454545454545,
8
+ "creation_time": 1738696138.8758106,
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": 24.181818181818183,
17
+ "creation_time": 1738696282.5089393,
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": 25.272727272727273,
26
+ "creation_time": 1738696431.0480936,
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": 25.818181818181817,
35
+ "creation_time": 1738696575.0262353,
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": 25.818181818181817,
44
+ "creation_time": 1738696575.1288495,
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": 25.818181818181817,
54
+ "creation_time": 1738696575.1288495,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]