Hugging Face's logo

cmjaramile
/
ppo-SnowballTarget2

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
cmjaramile commited on
Commit
a3da6c5
·
verified ·
1 Parent(s): 2de84b3

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.1783024232.8dd7c3fe047b.28631.0 +3 -0
  14. run_logs/Player-0.log +7 -7
  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 sha256:7c074b0288b91b7cef607f42ff1a0edbe51a419cefd79fe519a413c2a70a1ee5
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8286e4c0658c52160aa1dc46895d234f6be68c896fbfd0cddd993f89a2c31b7
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:466e9c4627f4b89cdc86dbd58ca6ad189221fda96da79493cd7d9aa31d20fef9
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda687711fdfe6ed4a6c4be836990e60a63227bdf46096ac270dc0274eef1eec
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d12a70bcf52f9555f92e153a11a422a5ff7bd17f4d94387b1767f2ecc62cd66b
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c1996adcde7ca7878fef8db03e9ee8a51f0665522401e31396523b9a599994
3
  size 3849902
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c074b0288b91b7cef607f42ff1a0edbe51a419cefd79fe519a413c2a70a1ee5
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8286e4c0658c52160aa1dc46895d234f6be68c896fbfd0cddd993f89a2c31b7
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a32bee4362fa42f0600eb85b6a52196c3c2606b47a487603e69b38c0a7d32663
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db9b092a9a474393e34af92365db3b009f3e7a5ce52003e4eb6dc48a446def62
3
  size 3849902
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c074b0288b91b7cef607f42ff1a0edbe51a419cefd79fe519a413c2a70a1ee5
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8286e4c0658c52160aa1dc46895d234f6be68c896fbfd0cddd993f89a2c31b7
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69731f1ef379362c6ee7ac04ae2f589ae0a3d2f613d07a84683d2ebfb2b48645
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b92f8c41f3653e5f9e14e9cf5abbc77197c2046d381cb313905ee29c958a17
3
  size 3849902
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54e586c6a8fc555fbf5c0e375d3f44d1044a41c444e22befdc2af7f72fdec4ee
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:040f353c399e5fc0ad19a98162cd2ac6b9377610e3b83e1614250276c3d61a39
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c53a1b087c40d0c76b920af7979bcaee2c981eb020a16ad3e5befc62ba71974
3
  size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a00f769e4a40d67e58de410c0acd5803108d67e7c9b36dc9882cb9aaad87657
3
  size 3849827
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cc93a21b833f96dc56b885154560cfd8ea294ec17810388c91dd60efcaa6d7c
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4cf1ce385648cb73729bf185fe956f803d0a0da2ee42703eca8cf71a3cf8efa
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8f6b37f3572c4816cf80c17d88fcc3202a351d4de8f83e333027adcf7124582
3
  size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65adb20c929a60011ddccf3922e204b832ca5c636098a6fc12a903be26d371b
3
  size 3849827
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:886bb8c30f0bab31ffbd8fe7df822147f6427b24e0640002b2c53766717b5524
3
  size 3849077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dee7070b8bffb67f7cf2f5c8094f7ebe22e0132d5ec7d50033965ad8f78b799
3
  size 3849077
SnowballTarget/events.out.tfevents.1783024232.8dd7c3fe047b.28631.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b991f9a008c13abc653768c7c7e7207f0378a8f85da9b9a3b9a59944a7fc3b10
3
+ size 28186
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.118 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
- UnloadTime: 0.814736 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
@@ -166,7 +166,7 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 42
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
@@ -175,13 +175,13 @@ Memory Statistics:
175
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 7.2 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.2 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
@@ -210,10 +210,10 @@ Memory Statistics:
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
- Peak usage frame count: [32.0 KB-64.0 KB]: 4919 frames, [64.0 KB-128.0 KB]: 539 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
  Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.151 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.808772 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 48
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
 
175
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.3 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4898 frames, [64.0 KB-128.0 KB]: 560 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
  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": 0.7170038819313049,
6
- "min": 0.7170038819313049,
7
- "max": 2.849374532699585,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 6814.40478515625,
12
- "min": 6814.40478515625,
13
- "max": 29086.416015625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.871124267578125,
30
- "min": 0.31479066610336304,
31
- "max": 12.871124267578125,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2509.869140625,
36
- "min": 61.06938934326172,
37
- "max": 2610.96142578125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07426913766177641,
42
- "min": 0.062340034129567144,
43
- "max": 0.07728020640694441,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.29707655064710564,
48
- "min": 0.24936013651826858,
49
- "max": 0.38640103203472204,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.19394765940367006,
54
- "min": 0.12874440204434318,
55
- "max": 0.2811643300103206,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7757906376146803,
60
- "min": 0.5149776081773727,
61
- "max": 1.3864895006020863,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.454545454545453,
114
- "min": 3.5454545454545454,
115
- "max": 25.681818181818183,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1120.0,
120
- "min": 156.0,
121
- "max": 1392.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.454545454545453,
126
- "min": 3.5454545454545454,
127
- "max": 25.681818181818183,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1120.0,
132
- "min": 156.0,
133
- "max": 1392.0,
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": "1783022791",
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 /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics --force",
154
  "mlagents_version": "1.2.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1783023580"
160
  },
161
- "total": 789.139154603,
162
  "count": 1,
163
- "self": 0.9505620250001812,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.03804915199998504,
167
  "count": 1,
168
- "self": 0.03804915199998504
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 788.1505434259998,
172
  "count": 1,
173
- "self": 0.5642361140489811,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.984056598999814,
177
  "count": 1,
178
- "self": 3.984056598999814
179
  },
180
  "TrainerController.advance": {
181
- "total": 783.3918465949519,
182
  "count": 18192,
183
- "self": 0.5569624301406293,
184
  "children": {
185
  "env_step": {
186
- "total": 593.9856056248818,
187
  "count": 18192,
188
- "self": 488.390564265801,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 105.25798858102007,
192
  "count": 18192,
193
- "self": 1.8763829380568495,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 103.38160564296322,
197
  "count": 18192,
198
- "self": 103.38160564296322
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.33705277806075173,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 780.7887304509841,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 352.06102459597514,
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": 0.004853637000451272,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0007601290008096839,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.004093507999641588,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.004093507999641588
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.09955226599959133,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006345179999698303,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0023351079998974456,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0023351079998974456
244
  },
245
  "communicator.exchange": {
246
- "total": 0.08962097899984656,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.08962097899984656
250
  },
251
  "steps_from_proto": {
252
- "total": 0.006961660999877495,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003846850022455328,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.006576975997631962,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.006576975997631962
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 428.72770585500894,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 12.516839495273416,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.7071867639260745,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.7071867639260745
280
  },
281
  "communicator.exchange": {
282
- "total": 340.036357533967,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 340.036357533967
286
  },
287
  "steps_from_proto": {
288
- "total": 70.46732206184242,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 12.606582177909331,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 57.86073988393309,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 57.86073988393309
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 188.8492785399294,
311
  "count": 18192,
312
- "self": 0.7245181098915054,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 38.977636828044524,
316
  "count": 18192,
317
- "self": 38.19412665204436,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.7835101760001635,
321
  "count": 4,
322
- "self": 0.7835101760001635
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 149.14712360199337,
328
  "count": 90,
329
- "self": 71.63568960995963,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 77.51143399203374,
333
  "count": 4587,
334
- "self": 77.51143399203374
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.27099974633893e-06,
344
  "count": 1,
345
- "self": 1.27099974633893e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.21040284699938638,
349
  "count": 1,
350
- "self": 0.0009470219993090723,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.2094558250000773,
354
  "count": 1,
355
- "self": 0.2094558250000773
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6637901067733765,
6
+ "min": 0.6637901067733765,
7
+ "max": 2.868617296218872,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6308.6611328125,
12
+ "min": 6308.6611328125,
13
+ "max": 29282.845703125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.00213623046875,
30
+ "min": 0.22362938523292542,
31
+ "max": 13.00213623046875,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2535.41650390625,
36
+ "min": 43.38410186767578,
37
+ "max": 2630.990234375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06490169358035999,
42
+ "min": 0.06169103981147048,
43
+ "max": 0.0759720364886829,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.25960677432143997,
48
+ "min": 0.2467641592458819,
49
+ "max": 0.3798601824434145,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.20159022122913717,
54
+ "min": 0.09974760613655306,
55
+ "max": 0.294673148206636,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.8063608849165487,
60
+ "min": 0.39899042454621225,
61
+ "max": 1.47336574103318,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.5,
114
+ "min": 2.8181818181818183,
115
+ "max": 25.581818181818182,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1122.0,
120
+ "min": 124.0,
121
+ "max": 1407.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.5,
126
+ "min": 2.8181818181818183,
127
+ "max": 25.581818181818182,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1122.0,
132
+ "min": 124.0,
133
+ "max": 1407.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1783024231",
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 /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics --force",
154
  "mlagents_version": "1.2.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1783025012"
160
  },
161
+ "total": 781.1094181970002,
162
  "count": 1,
163
+ "self": 1.0077948580010343,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.07508707599936315,
167
  "count": 1,
168
+ "self": 0.07508707599936315
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 780.0265362629998,
172
  "count": 1,
173
+ "self": 0.5993564480586429,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.1641971710005237,
177
  "count": 1,
178
+ "self": 3.1641971710005237
179
  },
180
  "TrainerController.advance": {
181
+ "total": 776.1401747229402,
182
  "count": 18192,
183
+ "self": 0.5426467248471454,
184
  "children": {
185
  "env_step": {
186
+ "total": 585.5073013620331,
187
  "count": 18192,
188
+ "self": 482.6799854431156,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 102.5145659509626,
192
  "count": 18192,
193
+ "self": 1.8301177749281123,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 100.6844481760345,
197
  "count": 18192,
198
+ "self": 100.6844481760345
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.3127499679549146,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 773.4744462541075,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 348.7597558611924,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0030379059999177116,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007762840004943428,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002261621999423369,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002261621999423369
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0681476850004401,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005914710000070045,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003753849996428471,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003753849996428471
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.06316776800031221,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.06316776800031221
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0040130610004780465,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004270270010238164,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.00358603399945423,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.00358603399945423
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 424.71469039291514,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 12.404453058036779,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.698063156921307,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 5.698063156921307
280
  },
281
  "communicator.exchange": {
282
+ "total": 337.8958448980029,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 337.8958448980029
286
  },
287
  "steps_from_proto": {
288
+ "total": 68.71632927995415,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 12.651767452993226,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 56.064561826960926,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 56.064561826960926
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 190.09022663605992,
311
  "count": 18192,
312
+ "self": 0.6566085130007195,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 38.172711078060274,
316
  "count": 18192,
317
+ "self": 37.59512009605987,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.5775909820004017,
321
  "count": 4,
322
+ "self": 0.5775909820004017
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 151.26090704499893,
328
  "count": 90,
329
+ "self": 72.41980554298789,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 78.84110150201104,
333
  "count": 4587,
334
+ "self": 78.84110150201104
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.2480004443204962e-06,
344
  "count": 1,
345
+ "self": 1.2480004443204962e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.12280667300001369,
349
  "count": 1,
350
+ "self": 0.0016504940003869706,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.12115617899962672,
354
  "count": 1,
355
+ "self": 0.12115617899962672
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 17.363636363636363,
8
- "creation_time": 1783022988.6344864,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 23.727272727272727,
17
- "creation_time": 1783023191.540275,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 23.90909090909091,
26
- "creation_time": 1783023383.856865,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.818181818181817,
35
- "creation_time": 1783023579.5983684,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 26.818181818181817,
44
- "creation_time": 1783023579.831131,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
- "reward": 26.818181818181817,
54
- "creation_time": 1783023579.831131,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 15.909090909090908,
8
+ "creation_time": 1783024429.0581794,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 23.636363636363637,
17
+ "creation_time": 1783024626.7224686,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.727272727272727,
26
+ "creation_time": 1783024824.1989028,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 24.727272727272727,
35
+ "creation_time": 1783025011.170492,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 24.727272727272727,
44
+ "creation_time": 1783025011.308774,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
+ "reward": 24.727272727272727,
54
+ "creation_time": 1783025011.308774,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]