Hugging Face's logo

Dash10107
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
Dash10107 commited on
Commit
03a9805
·
verified ·
1 Parent(s): abb0d17

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.1775405465.712e0dfc5b62.21231.0 +3 -0
  14. run_logs/Player-0.log +7 -7
  15. run_logs/timers.json +97 -97
  16. run_logs/training_status.json +9 -9
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d46dd753eeaa1e9cefbea07ee0d342798db503c77d9ef5f8ed66d8e07c4c5273
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f262547dddfe3efba2000a0fb3dbe5a2a75d9e98a7c1a4dd5f614ae7d484032c
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b7effaa76ae8132261ad067f7c3abd85235973ca1785a61d9747d000d67bc72
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cbb9cec07dc05ca0c3c6e086ec36e2ab7c7017cf755c9062e88e8d90a5a640c
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cfe135add3528609d49e399fcbc05a87eb9fbdf77fb7b29346d4503270dc224
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3caadf0defe2b34e922733d6a177bdab5ee75bb6c97cd29b6238faa2b7915f1
3
  size 3849902
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d46dd753eeaa1e9cefbea07ee0d342798db503c77d9ef5f8ed66d8e07c4c5273
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f262547dddfe3efba2000a0fb3dbe5a2a75d9e98a7c1a4dd5f614ae7d484032c
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a8e48d06b54a1cacce34ebae44f13c0623768bfa1e9e874b2d3946c42a00cca
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07da1015593a865e0c21e5d562b7ad9518f038bc42dd880bce78e0ac8e0ae405
3
  size 3849902
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d46dd753eeaa1e9cefbea07ee0d342798db503c77d9ef5f8ed66d8e07c4c5273
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f262547dddfe3efba2000a0fb3dbe5a2a75d9e98a7c1a4dd5f614ae7d484032c
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:253db226490e0a4f921427cb4ded3786cfc83a5fd8450516f1e0bb0110a8708d
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd5922b23c518746801cdb71d40ef9c2fd83674028be1e8f3b42115881ea090
3
  size 3849902
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:203ead767a62f3c2ea92f26b37e82e929f624efc258a15fa2b5b38c7d3faa831
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01be73f9f9de903b58ee9a1b944fa84416b1e0ead8d6fc66a554c6288f41c695
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:697d02e7a8f971cce6d3055e3d6150cd0a22816ffe1848678b84bc796f41229c
3
  size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:417aa5e122966db03a6d47158f2b95439f3c39b9a658ccdb50ae26691bc20d23
3
  size 3849827
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a126588adfe981f7fd6f38da72878866ce8def0dcdd8291e1b70ceaae4686843
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94b04367693d62fc1438ee0cf4a6a8c443811ea510a6576dd83945c5a1ed1f2
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:416a51513cdb5c306e5064501557c450925c90d7c1bfc0b4d3dde49ddafbe63f
3
  size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8651dd158f19374ed5208e1ae42db4d71366279f71c61640411a59b380a3ee9f
3
  size 3849827
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98d4f4f83d08bf6b49f6759133f028b8f81460525e31481c01e78900f90c5210
3
  size 3849077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e545aa6e400a75ba207ca17ab69e15ab14ff84dc3519809ab797c9506ecd1c
3
  size 3849077
SnowballTarget/events.out.tfevents.1775405465.712e0dfc5b62.21231.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9afe53b7edda1430dd3085e974c416c372388434fc37a2339047afdc4d0c772f
3
+ size 23413
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 0.184 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: 0.791924 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 40
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]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.9 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
@@ -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]: 4887 frames, [64.0 KB-128.0 KB]: 571 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 0.083 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: 0.670592 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 46
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]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 7.2 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 17.3 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]: 4910 frames, [64.0 KB-128.0 KB]: 548 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": 0.9175716042518616,
6
- "min": 0.9175716042518616,
7
- "max": 2.8604841232299805,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8720.6005859375,
12
- "min": 8720.6005859375,
13
- "max": 29199.822265625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.62380599975586,
30
- "min": 0.40353110432624817,
31
- "max": 12.62380599975586,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2461.64208984375,
36
- "min": 78.2850341796875,
37
- "max": 2570.72998046875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06944550067347854,
42
- "min": 0.061923922327182745,
43
- "max": 0.07377128831622208,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2777820026939142,
48
- "min": 0.24769568930873098,
49
- "max": 0.3688564415811104,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.18746326944115116,
54
- "min": 0.12822627135798992,
55
- "max": 0.2966029584846076,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7498530777646046,
60
- "min": 0.5129050854319597,
61
- "max": 1.416343836807737,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 24.954545454545453,
114
- "min": 3.3181818181818183,
115
- "max": 24.954545454545453,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1098.0,
120
- "min": 146.0,
121
- "max": 1352.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.954545454545453,
126
- "min": 3.3181818181818183,
127
- "max": 24.954545454545453,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1098.0,
132
- "min": 146.0,
133
- "max": 1352.0,
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": "1775377997",
152
  "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
153
  "command_line_arguments": "/usr/local/envs/mlagents_env/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": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1775378456"
160
  },
161
- "total": 458.618279583,
162
  "count": 1,
163
- "self": 0.48451832599994304,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.024322219000055156,
167
  "count": 1,
168
- "self": 0.024322219000055156
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 458.109439038,
172
  "count": 1,
173
- "self": 0.3847746899956519,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.2633003040000403,
177
  "count": 1,
178
- "self": 3.2633003040000403
179
  },
180
  "TrainerController.advance": {
181
- "total": 454.3830790210043,
182
  "count": 18192,
183
- "self": 0.41255707299876576,
184
  "children": {
185
  "env_step": {
186
- "total": 330.09558147201346,
187
  "count": 18192,
188
- "self": 256.2435408010417,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 73.6218870449951,
192
  "count": 18192,
193
- "self": 1.3287382619799928,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 72.29314878301511,
197
  "count": 18192,
198
- "self": 72.29314878301511
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2301536259766408,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 456.0846615999923,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 231.42301241697623,
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": 0.0044937449999906676,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003028695000011794,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014650499999788735,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014650499999788735
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03546518799998921,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005919210000229214,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00041776900002332695,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00041776900002332695
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03253681199998937,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03253681199998937
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019186859999535955,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00037411599976167054,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001544570000191925,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001544570000191925
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 224.66164918301604,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.463147620025211,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.551475239003935,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.551475239003935
280
  },
281
  "communicator.exchange": {
282
- "total": 170.47612076099006,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 170.47612076099006
286
  },
287
  "steps_from_proto": {
288
- "total": 38.170905562996836,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.770339997979704,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 31.400565565017132,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 31.400565565017132
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 123.87494047599205,
311
  "count": 18192,
312
- "self": 0.4616350430044349,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 27.75948314498669,
316
  "count": 18192,
317
- "self": 27.349243805986816,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.4102393389998724,
321
  "count": 4,
322
- "self": 0.4102393389998724
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 95.65382228800092,
328
  "count": 90,
329
- "self": 38.886955908988284,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 56.76686637901264,
333
  "count": 4587,
334
- "self": 56.76686637901264
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.120001323026372e-07,
344
  "count": 1,
345
- "self": 9.120001323026372e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.07828411099990262,
349
  "count": 1,
350
- "self": 0.0007694949997585354,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07751461600014409,
354
  "count": 1,
355
- "self": 0.07751461600014409
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8001843094825745,
6
+ "min": 0.7810786366462708,
7
+ "max": 2.852370262145996,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7604.95166015625,
12
+ "min": 7584.771484375,
13
+ "max": 29116.99609375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.926309585571289,
30
+ "min": 0.35359281301498413,
31
+ "max": 12.967205047607422,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2520.63037109375,
36
+ "min": 68.59700775146484,
37
+ "max": 2658.277099609375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.07279257838201694,
42
+ "min": 0.06216460053909424,
43
+ "max": 0.07464350587688386,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.29117031352806777,
48
+ "min": 0.24865840215637697,
49
+ "max": 0.37321752938441927,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.19421470084903286,
54
+ "min": 0.14227578715608435,
55
+ "max": 0.2971154254148988,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7768588033961314,
60
+ "min": 0.5691031486243374,
61
+ "max": 1.4169321887049018,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.59090909090909,
114
+ "min": 3.659090909090909,
115
+ "max": 25.89090909090909,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1126.0,
120
+ "min": 161.0,
121
+ "max": 1424.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.59090909090909,
126
+ "min": 3.659090909090909,
127
+ "max": 25.89090909090909,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1126.0,
132
+ "min": 161.0,
133
+ "max": 1424.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1775405464",
152
  "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
153
  "command_line_arguments": "/usr/local/envs/mlagents_env/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": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1775405935"
160
  },
161
+ "total": 470.5865948840001,
162
  "count": 1,
163
+ "self": 0.4325928540001769,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.024757393999607302,
167
  "count": 1,
168
+ "self": 0.024757393999607302
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 470.1292446360003,
172
  "count": 1,
173
+ "self": 0.39135168393477215,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.2286389789996974,
177
  "count": 1,
178
+ "self": 3.2286389789996974
179
  },
180
  "TrainerController.advance": {
181
+ "total": 466.42796577106583,
182
  "count": 18192,
183
+ "self": 0.3970598829419032,
184
  "children": {
185
  "env_step": {
186
+ "total": 338.68519418206415,
187
  "count": 18192,
188
+ "self": 260.3526380600615,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 78.10144090098493,
192
  "count": 18192,
193
+ "self": 1.3388363329222557,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 76.76260456806267,
197
  "count": 18192,
198
+ "self": 76.76260456806267
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.23111522101771698,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 468.1163399180705,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 239.91233963010654,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005170728000848612,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003718176002621476,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014525519982271362,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014525519982271362
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.07548064799993881,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0016334279998773127,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003909050001311698,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003909050001311698
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.06939225899986923,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.06939225899986923
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0040640560000611,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00040516800072509795,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0036588879993360024,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0036588879993360024
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 228.20400028796394,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 10.235004658947219,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 6.009571189944836,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 6.009571189944836
280
  },
281
  "communicator.exchange": {
282
+ "total": 173.59037900203202,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 173.59037900203202
286
  },
287
  "steps_from_proto": {
288
+ "total": 38.36904543703986,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 7.034971935117028,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 31.33407350192283,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 31.33407350192283
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 127.34571170605977,
311
  "count": 18192,
312
+ "self": 0.4893014881417912,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 28.142108856912273,
316
  "count": 18192,
317
+ "self": 27.693001023912984,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.4491078329992888,
321
  "count": 4,
322
+ "self": 0.4491078329992888
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 98.71430136100571,
328
  "count": 90,
329
+ "self": 38.94215977598742,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 59.77214158501829,
333
  "count": 4587,
334
+ "self": 59.77214158501829
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 5.45900002180133e-06,
344
  "count": 1,
345
+ "self": 5.45900002180133e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.08128274299997429,
349
  "count": 1,
350
+ "self": 0.0007735229992249515,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.08050922000074934,
354
  "count": 1,
355
+ "self": 0.08050922000074934
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": 15.818181818181818,
8
- "creation_time": 1775378114.7695756,
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": 21.545454545454547,
17
- "creation_time": 1775378226.2736897,
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": 24.636363636363637,
26
- "creation_time": 1775378338.0607066,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -32,7 +32,7 @@
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
  "reward": 25.545454545454547,
35
- "creation_time": 1775378455.7334733,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -41,7 +41,7 @@
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
  "reward": 25.545454545454547,
44
- "creation_time": 1775378455.8242965,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -51,7 +51,7 @@
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
  "reward": 25.545454545454547,
54
- "creation_time": 1775378455.8242965,
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": 16.90909090909091,
8
+ "creation_time": 1775405582.322297,
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": 22.818181818181817,
17
+ "creation_time": 1775405700.960981,
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": 26.454545454545453,
26
+ "creation_time": 1775405819.3212316,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
  "reward": 25.545454545454547,
35
+ "creation_time": 1775405934.8485796,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
  "reward": 25.545454545454547,
44
+ "creation_time": 1775405934.9418423,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
  "reward": 25.545454545454547,
54
+ "creation_time": 1775405934.9418423,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]