Hugging Face's logo

fivedoctors
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
fivedoctors commited on
Commit
f5b756d
·
verified ·
1 Parent(s): 48df4df

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.1746253412.d47b4b7ab28e.3773.0 +3 -0
  14. run_logs/Player-0.log +6 -10
  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 sha256:0fa9dd402a0fcf3e1e53e55139b541caaa08fa05a720fa010b5c165b52523950
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d377319d166e041179661b20468e414a16a17e1f49b8ffc8dd5febcdfe4678
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:235295764f711858721c176efcf56cb93455cbaa51da9b56021ef41e103aedb3
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3944a237d21eeae90858d40a939a8862adc0fdffc979eaaeddf5f2ce48fef6ba
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20f1dcc3b0747fc44724486ffc65a3d509939555fe925f5c49e0408360f7f70e
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ae51c34a582f6c54cd738821f9e1f2a17f0fc9350deb49f7b8db7ebeb9a32d
3
  size 3850564
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fa9dd402a0fcf3e1e53e55139b541caaa08fa05a720fa010b5c165b52523950
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d377319d166e041179661b20468e414a16a17e1f49b8ffc8dd5febcdfe4678
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f30fd81b9f5da3d6a017acf6e50cf6578d2bbe6089959057da1b552e718f4144
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6aa7915e2927788d29e681dd72720884efa093b5af6949715d43e7d70fc7cbe
3
  size 3850564
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fa9dd402a0fcf3e1e53e55139b541caaa08fa05a720fa010b5c165b52523950
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d377319d166e041179661b20468e414a16a17e1f49b8ffc8dd5febcdfe4678
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74742ba1e2de0ddca7d4aad224a4a32e6aec676c9e3930e89b17a3c838eed533
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:562b4e6928a23e4e0d954cfabe9a1a38024cde30f1f0a2d30e0c9a58ffb740e9
3
  size 3850564
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c351af9daf4f241cca36ed1b3b44de340658569b25655e7c427ebf54cb8573a4
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2fb5f34116ac1ef017ac95077ccf1ea0cccd36a8dc33a2d74305d729d524d05
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0e8f566667159da3b8ec7a3e541418ad6d579f12b6d5a3b4b5b9a64940eced1
3
  size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8263a38d4c0dd17b8943ce5fa3111366bc1257ff46dd99e71ff593ca4a8b151a
3
  size 3850487
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3e86834437ec1b433c74675a44cec3ad33de36ba4050ad8dd4b14ae39d3a848
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e602babcb7f9947ee020739c856252aa4cd198d4b0a3109a8a1c742b845d08
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa4aff4f6ea851efe8e8daef1795d7a47b84dc81be8a64feedd95143836f7ccf
3
  size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c916d182324242b0de4db43152912185cbaa2362c0f92f2ca748481ede133394
3
  size 3850487
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f48faa31a56c06c8315e3f34f043d0967d5de45a50dd6195f4c2e427c1019e8
3
  size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f85d252280147f6b47c08532350d2a1c391698bbf344d8557889e8c515334c
3
  size 3849717
SnowballTarget/events.out.tfevents.1746253412.d47b4b7ab28e.3773.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b373c36a63e6a67e9034089acf3fdcdf3b2293e12094f017919b3b711ddc0a1d
3
+ size 23575
run_logs/Player-0.log CHANGED
@@ -45,14 +45,10 @@ 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: 0.627045 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 6 worker threads for Enlighten.
52
- abort_threads: Failed aborting id: 0x7c995041c640, mono_thread_manage will ignore it
53
-
54
- abort_threads: Failed aborting id: 0x7c995021b640, mono_thread_manage will ignore it
55
-
56
  Memory Statistics:
57
  [ALLOC_TEMP_TLS] TLS Allocator
58
  StackAllocators :
@@ -223,7 +219,7 @@ Memory Statistics:
223
  Peak Allocated Bytes 0 B
224
  Overflow Count 0
225
  [ALLOC_DEFAULT] Dual Thread Allocator
226
- Peak main deferred allocation count 33
227
  [ALLOC_BUCKET]
228
  Large Block size 4.0 MB
229
  Used Block count 1
@@ -232,13 +228,13 @@ Memory Statistics:
232
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
233
  Requested Block Size 16.0 MB
234
  Peak Block count 1
235
- Peak Allocated memory 7.2 MB
236
  Peak Large allocation bytes 0 B
237
  [ALLOC_DEFAULT_THREAD]
238
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
239
  Requested Block Size 16.0 MB
240
  Peak Block count 1
241
- Peak Allocated memory 17.3 MB
242
  Peak Large allocation bytes 16.0 MB
243
  [ALLOC_TEMP_JOB_1_FRAME]
244
  Initial Block Size 2.0 MB
@@ -267,10 +263,10 @@ Memory Statistics:
267
  Used Block count 1
268
  Peak Allocated bytes 1.0 MB
269
  [ALLOC_GFX_MAIN]
270
- Peak usage frame count: [32.0 KB-64.0 KB]: 4300 frames, [64.0 KB-128.0 KB]: 1158 frames
271
  Requested Block Size 16.0 MB
272
  Peak Block count 1
273
- Peak Allocated memory 67.3 KB
274
  Peak Large allocation bytes 0 B
275
  [ALLOC_GFX_THREAD]
276
  Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
 
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: 0.676794 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 6 worker threads for Enlighten.
 
 
 
 
52
  Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
 
219
  Peak Allocated Bytes 0 B
220
  Overflow Count 0
221
  [ALLOC_DEFAULT] Dual Thread Allocator
222
+ Peak main deferred allocation count 36
223
  [ALLOC_BUCKET]
224
  Large Block size 4.0 MB
225
  Used Block count 1
 
228
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
229
  Requested Block Size 16.0 MB
230
  Peak Block count 1
231
+ Peak Allocated memory 6.9 MB
232
  Peak Large allocation bytes 0 B
233
  [ALLOC_DEFAULT_THREAD]
234
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
235
  Requested Block Size 16.0 MB
236
  Peak Block count 1
237
+ Peak Allocated memory 17.4 MB
238
  Peak Large allocation bytes 16.0 MB
239
  [ALLOC_TEMP_JOB_1_FRAME]
240
  Initial Block Size 2.0 MB
 
263
  Used Block count 1
264
  Peak Allocated bytes 1.0 MB
265
  [ALLOC_GFX_MAIN]
266
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5126 frames, [64.0 KB-128.0 KB]: 332 frames
267
  Requested Block Size 16.0 MB
268
  Peak Block count 1
269
+ Peak Allocated memory 66.8 KB
270
  Peak Large allocation bytes 0 B
271
  [ALLOC_GFX_THREAD]
272
  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": 0.8262459635734558,
6
- "min": 0.8251040577888489,
7
- "max": 2.8519904613494873,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7852.6416015625,
12
- "min": 7852.6416015625,
13
- "max": 29113.119140625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.85586929321289,
30
- "min": 0.5098223090171814,
31
- "max": 12.85586929321289,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2506.89453125,
36
- "min": 98.90552520751953,
37
- "max": 2619.080078125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06645473590355785,
42
- "min": 0.06083183358126667,
43
- "max": 0.07543379304343927,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2658189436142314,
48
- "min": 0.2620026143512423,
49
- "max": 0.37639451471434715,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.22602914880011596,
54
- "min": 0.14047086079531879,
55
- "max": 0.2800162076365714,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.9041165952004638,
60
- "min": 0.5618834431812751,
61
- "max": 1.400081038182857,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.681818181818183,
114
- "min": 4.409090909090909,
115
- "max": 25.681818181818183,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1130.0,
120
- "min": 194.0,
121
- "max": 1400.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.681818181818183,
126
- "min": 4.409090909090909,
127
- "max": 25.681818181818183,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1130.0,
132
- "min": 194.0,
133
- "max": 1400.0,
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": "1746252044",
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": "2.7.0+cu126",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1746252424"
160
  },
161
- "total": 379.7381230010001,
162
  "count": 1,
163
- "self": 0.32116179899981034,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.020881049000081475,
167
  "count": 1,
168
- "self": 0.020881049000081475
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 379.3960801530002,
172
  "count": 1,
173
- "self": 0.3653449390114929,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.2435693239999637,
177
  "count": 1,
178
- "self": 2.2435693239999637
179
  },
180
  "TrainerController.advance": {
181
- "total": 376.70518597298883,
182
  "count": 18192,
183
- "self": 0.3749867089925374,
184
  "children": {
185
  "env_step": {
186
- "total": 262.32422118398904,
187
  "count": 18192,
188
- "self": 196.65858947600782,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 65.45157259099187,
192
  "count": 18192,
193
- "self": 1.1885343719936827,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 64.26303821899819,
197
  "count": 18192,
198
- "self": 64.26303821899819
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21405911698934688,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 378.61691575099053,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 205.59795651296758,
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": 0.002275046000022485,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006509590000405296,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0016240869999819552,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0016240869999819552
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.02920877799988375,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0004074639998634666,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00032627599989609735,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00032627599989609735
244
  },
245
  "communicator.exchange": {
246
- "total": 0.027285006000056455,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.027285006000056455
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0011900320000677311,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0002462339994053764,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0009437980006623548,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0009437980006623548
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 173.01895923802294,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 6.1797012280103445,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 3.2835764420037776,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 3.2835764420037776
280
  },
281
  "communicator.exchange": {
282
- "total": 143.5031138830061,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 143.5031138830061
286
  },
287
  "steps_from_proto": {
288
- "total": 20.052567685002714,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 4.002882032948264,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 16.04968565205445,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 16.04968565205445
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 114.00597808000725,
311
  "count": 18192,
312
- "self": 0.45466583200550303,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 24.86544883700185,
316
  "count": 18192,
317
- "self": 24.500822216002007,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.364626620999843,
321
  "count": 4,
322
- "self": 0.364626620999843
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 88.6858634109999,
328
  "count": 90,
329
- "self": 35.9815088619971,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 52.7043545490028,
333
  "count": 4587,
334
- "self": 52.7043545490028
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.0019998626376037e-06,
344
  "count": 1,
345
- "self": 1.0019998626376037e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08197891500003607,
349
  "count": 1,
350
- "self": 0.0008064380001542304,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.08117247699988184,
354
  "count": 1,
355
- "self": 0.08117247699988184
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7520580291748047,
6
+ "min": 0.7520580291748047,
7
+ "max": 2.8477981090545654,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7147.5595703125,
12
+ "min": 7147.5595703125,
13
+ "max": 29070.322265625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.131010055541992,
30
+ "min": 0.33000990748405457,
31
+ "max": 13.131010055541992,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2560.546875,
36
+ "min": 64.02191925048828,
37
+ "max": 2658.736083984375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06806634380065553,
42
+ "min": 0.06173997795627014,
43
+ "max": 0.07252701081874251,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2722653752026221,
48
+ "min": 0.25974765927757665,
49
+ "max": 0.36263505409371255,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.2044831329554904,
54
+ "min": 0.11893650314852815,
55
+ "max": 0.34242405603621523,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.8179325318219616,
60
+ "min": 0.4757460125941126,
61
+ "max": 1.4576207568832473,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.045454545454547,
114
+ "min": 3.6136363636363638,
115
+ "max": 26.045454545454547,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1146.0,
120
+ "min": 159.0,
121
+ "max": 1412.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.045454545454547,
126
+ "min": 3.6136363636363638,
127
+ "max": 26.045454545454547,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1146.0,
132
+ "min": 159.0,
133
+ "max": 1412.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1746253411",
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": "2.7.0+cu126",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1746253790"
160
  },
161
+ "total": 378.6090239619999,
162
  "count": 1,
163
+ "self": 0.32138472300005105,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.020847966999895107,
167
  "count": 1,
168
+ "self": 0.020847966999895107
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 378.266791272,
172
  "count": 1,
173
+ "self": 0.3496371730049077,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.2328333740000517,
177
  "count": 1,
178
+ "self": 2.2328333740000517
179
  },
180
  "TrainerController.advance": {
181
+ "total": 375.6050460069947,
182
  "count": 18192,
183
+ "self": 0.3507884239896839,
184
  "children": {
185
  "env_step": {
186
+ "total": 260.99048199699894,
187
  "count": 18192,
188
+ "self": 195.77284246699026,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 65.00955214800649,
192
  "count": 18192,
193
+ "self": 1.1892764419942523,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 63.82027570601224,
197
  "count": 18192,
198
+ "self": 63.82027570601224
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.20808738200219068,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 377.5047654209965,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 205.13931211299086,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0026334570000017266,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007442230000833661,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0018892339999183605,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0018892339999183605
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.028327417000014066,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00039694500003406574,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00026812800001607684,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00026812800001607684
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.026448834999996507,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.026448834999996507
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0012135089999674165,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0002677590000530472,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0009457499999143693,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0009457499999143693
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 172.3654533080056,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 6.117320842987738,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 3.2777932440022823,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 3.2777932440022823
280
  },
281
  "communicator.exchange": {
282
+ "total": 143.11975104199985,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 143.11975104199985
286
  },
287
  "steps_from_proto": {
288
+ "total": 19.850588179015745,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 3.9269575080171535,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 15.923630670998591,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 15.923630670998591
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 114.26377558600609,
311
  "count": 18192,
312
+ "self": 0.4459701729927019,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 25.06161602301404,
316
  "count": 18192,
317
+ "self": 24.69135717801373,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.3702588450003077,
321
  "count": 4,
322
+ "self": 0.3702588450003077
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 88.75618938999935,
328
  "count": 90,
329
+ "self": 35.94869212899812,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 52.80749726100123,
333
  "count": 4587,
334
+ "self": 52.80749726100123
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.0160001693293452e-06,
344
  "count": 1,
345
+ "self": 1.0160001693293452e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.07927370200013684,
349
  "count": 1,
350
+ "self": 0.0007795360002091911,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.07849416599992765,
354
  "count": 1,
355
+ "self": 0.07849416599992765
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": 13.727272727272727,
8
- "creation_time": 1746252141.266143,
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": 21.09090909090909,
17
- "creation_time": 1746252236.983973,
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": 24.272727272727273,
26
- "creation_time": 1746252330.8635824,
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": 27.272727272727273,
35
- "creation_time": 1746252424.2509632,
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": 27.272727272727273,
44
- "creation_time": 1746252424.344883,
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": 27.272727272727273,
54
- "creation_time": 1746252424.344883,
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": 15.818181818181818,
8
+ "creation_time": 1746253506.356322,
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": 24.363636363636363,
17
+ "creation_time": 1746253601.7430875,
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": 24.90909090909091,
26
+ "creation_time": 1746253697.7660224,
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": 27.181818181818183,
35
+ "creation_time": 1746253790.0877354,
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": 27.181818181818183,
44
+ "creation_time": 1746253790.1784375,
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": 27.181818181818183,
54
+ "creation_time": 1746253790.1784375,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]