Hugging Face's logo

mriusero
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
mriusero commited on
Commit
fd9f4cc
·
verified ·
1 Parent(s): bbfd74a

Initial commit

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.1743004216.d6962b5a41f8.264.0 +3 -0
  14. run_logs/Player-0.log +5 -5
  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:abad88c113715cd04a85370999633185750f67df7c20b4a4fce8313f9fe5eb94
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a23d9f561b6184c44ed654daa1cd1b362593589ddb1cdac9b397f45259eaff
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b6341134e12ebf11a892a6710e9041a22a6e9c88219392b9cc1aaae15f0b67
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96dc7fc7e36391a1888cbdc39d156c52da0ac6077bf70128b142fea80e7d8204
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0506c35e7ddb877d30c9cf634685d732a8bf0c2dd7b73458eed0d00fab3695d9
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0abaf22cb65334260513c8c0c75e092942f1c1ee820c49776a5ee65c25a4a7
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abad88c113715cd04a85370999633185750f67df7c20b4a4fce8313f9fe5eb94
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a23d9f561b6184c44ed654daa1cd1b362593589ddb1cdac9b397f45259eaff
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2cc031c164a9d35f78811cebe07b5fc633e7a4eb226fc7d0a9737633d165afa
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f433ee462ab6b33c9e6d682ac882f8162478af10be1f827dc28f554db94b95
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abad88c113715cd04a85370999633185750f67df7c20b4a4fce8313f9fe5eb94
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a23d9f561b6184c44ed654daa1cd1b362593589ddb1cdac9b397f45259eaff
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52c01cb3917e0b23bdb87944b7c58a41c7a73ea0958d429997aca7dfca88048c
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d3a72a8351c723e7071faa4855a6e6fcab95e0f8acbe02b8754ab75aff7bc98
3
  size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a309580a35a34e8466508fe78e0ec8b5669cd0f9e48fd37a040124f102f5298c
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b50720b83d70a9a86f421eaf1bd98d822068739e66bde24a39a71a9b4b0d1a4
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0c02a61c9f31857a197f7d102d98cc4dde15fce5ab97cc495f4c07a20a42887
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed868d0614e44b747ddaf5ae7aaef21573919389003d03e5694755d4c445796
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b1fb759c2236f0146afff4d1d6bc9b876334250cbb6123e1e5924a781bdc189
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e39bf1aea859d357cf32bad9702806701d6f497a65483fe8238649b14c34b88
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27411b20cdc761d4b579316c7c76fb110f2753ff5269640d4a6ff3158bac1c6c
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ca3249ea7bf21a6933732b83dc6f3d56f1d4f153a44c7dc2ad7839edcd3b99
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a33cadfbf5a406abd95343de1533bd8f5f0ba9d98ccbb4f616d388466837478a
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe181f8a77df029682139e880f28c417e1e9d21eea658054af18a9659c0f81a8
3
  size 3849250
SnowballTarget/events.out.tfevents.1743004216.d6962b5a41f8.264.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f4d920c09b268ff697ac22aeacd42bbe19f66167f8a6d73565e82ed0a20101a
3
+ size 23735
run_logs/Player-0.log CHANGED
@@ -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: 0.818055 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 2 worker threads for Enlighten.
@@ -179,7 +179,7 @@ Memory Statistics:
179
  Peak Allocated Bytes 0 B
180
  Overflow Count 0
181
  [ALLOC_DEFAULT] Dual Thread Allocator
182
- Peak main deferred allocation count 41
183
  [ALLOC_BUCKET]
184
  Large Block size 4.0 MB
185
  Used Block count 1
@@ -188,7 +188,7 @@ Memory Statistics:
188
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
189
  Requested Block Size 16.0 MB
190
  Peak Block count 1
191
- Peak Allocated memory 6.8 MB
192
  Peak Large allocation bytes 0 B
193
  [ALLOC_DEFAULT_THREAD]
194
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
@@ -223,10 +223,10 @@ Memory Statistics:
223
  Used Block count 1
224
  Peak Allocated bytes 1.0 MB
225
  [ALLOC_GFX_MAIN]
226
- Peak usage frame count: [32.0 KB-64.0 KB]: 5002 frames, [64.0 KB-128.0 KB]: 456 frames
227
  Requested Block Size 16.0 MB
228
  Peak Block count 1
229
- Peak Allocated memory 66.8 KB
230
  Peak Large allocation bytes 0 B
231
  [ALLOC_GFX_THREAD]
232
  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: 0.771120 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 2 worker threads for Enlighten.
 
179
  Peak Allocated Bytes 0 B
180
  Overflow Count 0
181
  [ALLOC_DEFAULT] Dual Thread Allocator
182
+ Peak main deferred allocation count 39
183
  [ALLOC_BUCKET]
184
  Large Block size 4.0 MB
185
  Used Block count 1
 
188
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
189
  Requested Block Size 16.0 MB
190
  Peak Block count 1
191
+ Peak Allocated memory 6.7 MB
192
  Peak Large allocation bytes 0 B
193
  [ALLOC_DEFAULT_THREAD]
194
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
 
223
  Used Block count 1
224
  Peak Allocated bytes 1.0 MB
225
  [ALLOC_GFX_MAIN]
226
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4511 frames, [64.0 KB-128.0 KB]: 947 frames
227
  Requested Block Size 16.0 MB
228
  Peak Block count 1
229
+ Peak Allocated memory 67.3 KB
230
  Peak Large allocation bytes 0 B
231
  [ALLOC_GFX_THREAD]
232
  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": 0.8893842697143555,
6
- "min": 0.8893842697143555,
7
- "max": 2.841306447982788,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8452.7080078125,
12
- "min": 8452.7080078125,
13
- "max": 29004.056640625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.149178504943848,
30
- "min": 0.45256561040878296,
31
- "max": 13.149178504943848,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2564.08984375,
36
- "min": 87.7977294921875,
37
- "max": 2659.34375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06332077068595134,
42
- "min": 0.059965390889178086,
43
- "max": 0.07220724702960533,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.25328308274380534,
48
- "min": 0.23986156355671234,
49
- "max": 0.360238060028767,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.21672358575697037,
54
- "min": 0.1466608619221541,
55
- "max": 0.2961667976981285,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8668943430278815,
60
- "min": 0.5866434476886164,
61
- "max": 1.4476962659288857,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.181818181818183,
114
- "min": 4.045454545454546,
115
- "max": 26.181818181818183,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1152.0,
120
- "min": 178.0,
121
- "max": 1419.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.181818181818183,
126
- "min": 4.045454545454546,
127
- "max": 26.181818181818183,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1152.0,
132
- "min": 178.0,
133
- "max": 1419.0,
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": "1742943921",
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 /kaggle/working/content/ml-agents/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": "1742944293"
160
  },
161
- "total": 372.319937735,
162
  "count": 1,
163
- "self": 0.32860405100001344,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.02194915799998398,
167
  "count": 1,
168
- "self": 0.02194915799998398
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 371.969384526,
172
  "count": 1,
173
- "self": 0.31160565498942105,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.087073610999994,
177
  "count": 1,
178
- "self": 2.087073610999994
179
  },
180
  "TrainerController.advance": {
181
- "total": 369.48809909901064,
182
  "count": 18192,
183
- "self": 0.3054609880005046,
184
  "children": {
185
  "env_step": {
186
- "total": 262.8180598290101,
187
  "count": 18192,
188
- "self": 199.55238485702068,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 63.0818324539938,
192
  "count": 18192,
193
- "self": 1.1139356359888097,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 61.96789681800499,
197
  "count": 18192,
198
- "self": 61.96789681800499
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.1838425179956289,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 371.1737359149997,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 194.5813812989948,
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": 0.002289103000009618,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0007379660002015953,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015511369998080227,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015511369998080227
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03239387799999349,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00038166199993838745,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00028033000000959873,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00028033000000959873
244
  },
245
  "communicator.exchange": {
246
- "total": 0.030647097000041867,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.030647097000041867
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0010847890000036386,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00024667600007433066,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.000838112999929308,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.000838112999929308
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 176.5923546160049,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 7.0821402940021585,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 3.811363240000958,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 3.811363240000958
280
  },
281
  "communicator.exchange": {
282
- "total": 142.1307674710057,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 142.1307674710057
286
  },
287
  "steps_from_proto": {
288
- "total": 23.568083610996098,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 4.475859420016889,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 19.09222419097921,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 19.09222419097921
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 106.36457828200002,
311
  "count": 18192,
312
- "self": 0.37671520800142844,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 23.729053352998676,
316
  "count": 18192,
317
- "self": 23.344757081998637,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.38429627100003927,
321
  "count": 4,
322
- "self": 0.38429627100003927
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 82.25880972099992,
328
  "count": 90,
329
- "self": 32.6816853709999,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 49.57712435000002,
333
  "count": 4587,
334
- "self": 49.57712435000002
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 8.490000027450151e-07,
344
  "count": 1,
345
- "self": 8.490000027450151e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08260531199994148,
349
  "count": 1,
350
- "self": 0.0008665039999868895,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.08173880799995459,
354
  "count": 1,
355
- "self": 0.08173880799995459
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8667162656784058,
6
+ "min": 0.8667162656784058,
7
+ "max": 2.85058856010437,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8237.271484375,
12
+ "min": 8237.271484375,
13
+ "max": 29098.80859375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.921371459960938,
30
+ "min": 0.33551594614982605,
31
+ "max": 12.921371459960938,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2519.66748046875,
36
+ "min": 65.09009552001953,
37
+ "max": 2605.5908203125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06933765144141016,
42
+ "min": 0.06351135143018374,
43
+ "max": 0.07422952845974543,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.27735060576564063,
48
+ "min": 0.2586047153887978,
49
+ "max": 0.3711476422987271,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.19150231774969428,
54
+ "min": 0.12223386118078933,
55
+ "max": 0.2936645640315963,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7660092709987771,
60
+ "min": 0.4889354447231573,
61
+ "max": 1.404561409178902,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.272727272727273,
114
+ "min": 3.4318181818181817,
115
+ "max": 25.454545454545453,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1112.0,
120
+ "min": 151.0,
121
+ "max": 1400.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.272727272727273,
126
+ "min": 3.4318181818181817,
127
+ "max": 25.454545454545453,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1112.0,
132
+ "min": 151.0,
133
+ "max": 1400.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1743004215",
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 /kaggle/working/content/ml-agents/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": "1743004588"
160
  },
161
+ "total": 372.34482885500006,
162
  "count": 1,
163
+ "self": 0.2713910229999783,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.02144187100009276,
167
  "count": 1,
168
+ "self": 0.02144187100009276
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 372.051995961,
172
  "count": 1,
173
+ "self": 0.3060223089998999,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.1235057039999674,
177
  "count": 1,
178
+ "self": 2.1235057039999674
179
  },
180
  "TrainerController.advance": {
181
+ "total": 369.54107361800015,
182
  "count": 18192,
183
+ "self": 0.30952646201160405,
184
  "children": {
185
  "env_step": {
186
+ "total": 261.2339372909894,
187
  "count": 18192,
188
+ "self": 196.25138360097662,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 64.7960336640042,
192
  "count": 18192,
193
+ "self": 1.114197694010386,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 63.68183596999381,
197
  "count": 18192,
198
+ "self": 63.68183596999381
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.18652002600856576,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 371.2717601420036,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 198.03160889200342,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0023388740000882535,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008227810001244507,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015160929999638029,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015160929999638029
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.02592452900000808,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00034035900000617403,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003103100000316772,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003103100000316772
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.024023683999985224,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.024023683999985224
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0012501759999850037,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0002488169999423917,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001001359000042612,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001001359000042612
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 173.24015125000017,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 6.867786438996745,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 3.7223433530009515,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 3.7223433530009515
280
  },
281
  "communicator.exchange": {
282
+ "total": 139.4826255269976,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 139.4826255269976
286
  },
287
  "steps_from_proto": {
288
+ "total": 23.167395931004876,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 4.369721719031645,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 18.79767421197323,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 18.79767421197323
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 107.99760986499916,
311
  "count": 18192,
312
+ "self": 0.3646026189995837,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 24.18952412899955,
316
  "count": 18192,
317
+ "self": 23.811835335999604,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.3776887929999475,
321
  "count": 4,
322
+ "self": 0.3776887929999475
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 83.44348311700003,
328
  "count": 90,
329
+ "self": 32.62340321499926,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 50.82007990200077,
333
  "count": 4587,
334
+ "self": 50.82007990200077
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.0859998837986495e-06,
344
  "count": 1,
345
+ "self": 1.0859998837986495e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.08139324400008263,
349
  "count": 1,
350
+ "self": 0.0009187080001993309,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.0804745359998833,
354
  "count": 1,
355
+ "self": 0.0804745359998833
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": 16.272727272727273,
8
- "creation_time": 1742944014.2764685,
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": 23.272727272727273,
17
- "creation_time": 1742944106.4585528,
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": 25.272727272727273,
26
- "creation_time": 1742944201.1363902,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.181818181818183,
35
- "creation_time": 1742944293.0758693,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 26.181818181818183,
44
- "creation_time": 1742944293.1695852,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 26.181818181818183,
54
- "creation_time": 1742944293.1695852,
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": 14.636363636363637,
8
+ "creation_time": 1743004310.206089,
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": 20.90909090909091,
17
+ "creation_time": 1743004403.24733,
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": 23.454545454545453,
26
+ "creation_time": 1743004496.0270045,
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": 25.0,
35
+ "creation_time": 1743004587.7432957,
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": 25.0,
44
+ "creation_time": 1743004587.836509,
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": 25.0,
54
+ "creation_time": 1743004587.836509,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]