Hugging Face's logo

geesus
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
geesus commited on
Commit
5a62307
·
verified ·
1 Parent(s): 7a4e33c

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.1743968605.a743716e2c8b.3503.0 +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:aa956ff7d41d37d2fe6bf6c028cb7dd6596435224b0215b3376eea8e8e67d310
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd014d9a60c2c813a11f9a5046f4062bce320e30c5dab0f29a90394d4f9ba29
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:380de6673cb23a1818a8b7bce955d7c95096262d4336cd6d46809ee307859bb0
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90c59dbbc1b89c1cfc0461cb406530f9ebae874b1142872e933a79be9345839
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f06854e18ff81b07b20de28f75fdaeaf074042bbae7d2410348826b5e8f2a81b
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c47efb0405e7f5a3751a3ee1995c33c39cc3bbe07cd63b62cf673a7b167297
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa956ff7d41d37d2fe6bf6c028cb7dd6596435224b0215b3376eea8e8e67d310
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd014d9a60c2c813a11f9a5046f4062bce320e30c5dab0f29a90394d4f9ba29
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:149c5a86758368db1cbadbb21a8ba7244bcb5f5accfa5e6e32afd3ed60bf6895
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92cd8344bc14619e0a1f3324ce798e40d242380af0009d6adcd3e0dde27a8dbe
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa956ff7d41d37d2fe6bf6c028cb7dd6596435224b0215b3376eea8e8e67d310
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd014d9a60c2c813a11f9a5046f4062bce320e30c5dab0f29a90394d4f9ba29
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9dba2c25ce52959910e9df7db28979fc0ecbfe4fc472207dc9270c2e8ec0755
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce75a7489457f5834f52767765d926625b38b78193a450427b7ed826c71a8331
3
  size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eecb85343c45c33102b1ce87cfcc943515d258ebe2d2714463c0e7b964788e4
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f763c606c059a8bc4e62ad4ceecb3792723e7da26ec5cbaa4d7b700805e7e69
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e119cbdb4a48926995b3119ef085873371d015345737086fcdac3120cb54ee4a
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f11e1010796a170c8a2ead9472c60a8fe5ae25b15cdaa0c2491e47317abfd5
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53432bb204488887df7cfe83aec45e05c37c72f7251ac709b74b92140e1c4f4e
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca0f1491a7b7325e75c92875b83feb784b0926282399ce4c0096bd7c0353f6a
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c670f0ce5a3ccd2339fe8d9b92d95c627207ac180226790864583155c40d5fee
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c65c1b5e8ac05b810df5b5e39ef2dcb1e9fe1409de3d8b74f0dc585ff755c9
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0971740b9ed21270c655c2c38b8fa5d47b772bb225c47a0e17b55dfc24cbe230
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b836cdefa249b24c2adf0d79e03bcaa0b9d469fa1495f1ddc5fcb0dd19eabc7e
3
  size 3849250
SnowballTarget/events.out.tfevents.1743968605.a743716e2c8b.3503.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48b15bd0251ab5a00cd259aa92225161508d2de18cbfd9a7179e4ce28c7dfea
3
+ size 23493
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 0.140 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: 0.917117 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 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -213,10 +213,10 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4869 frames, [64.0 KB-128.0 KB]: 589 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.7 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 0.088 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: 0.668471 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 44
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
 
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4565 frames, [64.0 KB-128.0 KB]: 893 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
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8368375897407532,
6
- "min": 0.7762340903282166,
7
- "max": 2.873164176940918,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7953.3046875,
12
- "min": 7650.171875,
13
- "max": 29329.259765625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.047152519226074,
30
- "min": 0.40960603952407837,
31
- "max": 13.047152519226074,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2544.19482421875,
36
- "min": 79.46356964111328,
37
- "max": 2628.412109375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06681129691787646,
42
- "min": 0.06355366775527478,
43
- "max": 0.07579493074487853,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.26724518767150585,
48
- "min": 0.2579544949534751,
49
- "max": 0.36987566014674184,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.19739664221803346,
54
- "min": 0.12207707317714926,
55
- "max": 0.2899152242085513,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7895865688721339,
60
- "min": 0.48830829270859705,
61
- "max": 1.4495761210427567,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.772727272727273,
114
- "min": 3.3863636363636362,
115
- "max": 26.10909090909091,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1134.0,
120
- "min": 149.0,
121
- "max": 1436.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.772727272727273,
126
- "min": 3.3863636363636362,
127
- "max": 26.10909090909091,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1134.0,
132
- "min": 149.0,
133
- "max": 1436.0,
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": "1743544083",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1743544578"
160
  },
161
- "total": 495.25358993500004,
162
  "count": 1,
163
- "self": 0.5369714879998355,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.03140616700011378,
167
  "count": 1,
168
- "self": 0.03140616700011378
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 494.6852122800001,
172
  "count": 1,
173
- "self": 0.4209329649841038,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.4578933640000287,
177
  "count": 1,
178
- "self": 3.4578933640000287
179
  },
180
  "TrainerController.advance": {
181
- "total": 490.7083332670161,
182
  "count": 18192,
183
- "self": 0.43737757205963135,
184
  "children": {
185
  "env_step": {
186
- "total": 350.82622134598773,
187
  "count": 18192,
188
- "self": 265.98977462999073,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 84.59460378198855,
192
  "count": 18192,
193
- "self": 1.4516953340018972,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 83.14290844798666,
197
  "count": 18192,
198
- "self": 83.14290844798666
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2418429340084458,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 493.0528376769946,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 259.76225502099123,
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": 0.006632741999965219,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004344678999814278,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0022880630001509417,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0022880630001509417
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.0420210469999347,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006855589999759104,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00043277099985061795,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00043277099985061795
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03855947100009871,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03855947100009871
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002343246000009458,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005248140000730928,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018184319999363652,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018184319999363652
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 233.29058265600338,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 11.082698952985538,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.442816381978446,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 6.442816381978446
280
  },
281
  "communicator.exchange": {
282
- "total": 178.3559406280267,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 178.3559406280267
286
  },
287
  "steps_from_proto": {
288
- "total": 37.409126693012695,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.794077197019533,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 30.615049495993162,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 30.615049495993162
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 139.44473434896872,
311
  "count": 18192,
312
- "self": 0.5205318999803694,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 32.03747278098831,
316
  "count": 18192,
317
- "self": 31.476698697988468,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.560774082999842,
321
  "count": 4,
322
- "self": 0.560774082999842
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 106.88672966800004,
328
  "count": 90,
329
- "self": 43.36331592400143,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 63.52341374399862,
333
  "count": 4587,
334
- "self": 63.52341374399862
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.0060000477096764e-06,
344
  "count": 1,
345
- "self": 1.0060000477096764e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.09805167799981973,
349
  "count": 1,
350
- "self": 0.0009348719997888111,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.09711680600003092,
354
  "count": 1,
355
- "self": 0.09711680600003092
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.852093517780304,
6
+ "min": 0.8313882946968079,
7
+ "max": 2.8371405601501465,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8098.296875,
12
+ "min": 8098.296875,
13
+ "max": 28961.53125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.88045597076416,
30
+ "min": 0.3220067322254181,
31
+ "max": 12.977343559265137,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2511.68896484375,
36
+ "min": 62.46930694580078,
37
+ "max": 2660.35546875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.07234634406403548,
42
+ "min": 0.06324103302807392,
43
+ "max": 0.07615671012172243,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2893853762561419,
48
+ "min": 0.2549555984390763,
49
+ "max": 0.3504821424310863,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.20953501848613515,
54
+ "min": 0.14811682490421935,
55
+ "max": 0.26572960936555673,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.8381400739445406,
60
+ "min": 0.5924672996168774,
61
+ "max": 1.2591190767638825,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.022727272727273,
114
+ "min": 3.7045454545454546,
115
+ "max": 25.295454545454547,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1101.0,
120
+ "min": 163.0,
121
+ "max": 1391.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.022727272727273,
126
+ "min": 3.7045454545454546,
127
+ "max": 25.295454545454547,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1101.0,
132
+ "min": 163.0,
133
+ "max": 1391.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1743968604",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1743969045"
160
  },
161
+ "total": 440.347186009,
162
  "count": 1,
163
+ "self": 0.7879881480000677,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.023761057999990953,
167
  "count": 1,
168
+ "self": 0.023761057999990953
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 439.5354368029999,
172
  "count": 1,
173
+ "self": 0.366101315991159,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.209476676999998,
177
  "count": 1,
178
+ "self": 3.209476676999998
179
  },
180
  "TrainerController.advance": {
181
+ "total": 435.8234109080089,
182
  "count": 18192,
183
+ "self": 0.3844567800168761,
184
  "children": {
185
  "env_step": {
186
+ "total": 310.98025275498844,
187
  "count": 18192,
188
+ "self": 236.33930928800203,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 74.42871971898262,
192
  "count": 18192,
193
+ "self": 1.3132103789940857,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 73.11550933998853,
197
  "count": 18192,
198
+ "self": 73.11550933998853
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.21222374800379384,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 437.87587649700424,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 230.84684459901223,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.006355127999995602,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.004674289000263343,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016808389997322593,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0016808389997322593
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.058821697999974276,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00055536000002121,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00037637399998402543,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00037637399998402543
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.05605767899999137,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.05605767899999137
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0018322849999776736,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00034177899999576766,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001490505999981906,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001490505999981906
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 207.029031897992,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 9.96113786299145,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.503942356996731,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 5.503942356996731
280
  },
281
  "communicator.exchange": {
282
+ "total": 158.67342102499333,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 158.67342102499333
286
  },
287
  "steps_from_proto": {
288
+ "total": 32.8905306530105,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 5.944594386991412,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.94593626601909,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 26.94593626601909
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 124.45870137300358,
311
  "count": 18192,
312
+ "self": 0.4619072139820446,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 27.943587980022016,
316
  "count": 18192,
317
+ "self": 27.452052090021994,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.49153589000002285,
321
  "count": 4,
322
+ "self": 0.49153589000002285
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 96.05320617899952,
328
  "count": 90,
329
+ "self": 38.94768425200675,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 57.105521926992765,
333
  "count": 4587,
334
+ "self": 57.105521926992765
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.089000079446123e-06,
344
  "count": 1,
345
+ "self": 1.089000079446123e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.1364468129997931,
349
  "count": 1,
350
+ "self": 0.0013576329997704306,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.13508918000002268,
354
  "count": 1,
355
+ "self": 0.13508918000002268
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": 15.545454545454545,
8
- "creation_time": 1743544209.3783362,
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": 23.363636363636363,
17
- "creation_time": 1743544334.164795,
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": 24.545454545454547,
26
- "creation_time": 1743544455.9019434,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.90909090909091,
35
- "creation_time": 1743544578.3062034,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.90909090909091,
44
- "creation_time": 1743544578.4192326,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.90909090909091,
54
- "creation_time": 1743544578.4192326,
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": 13.0,
8
+ "creation_time": 1743968719.8279312,
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": 21.818181818181817,
17
+ "creation_time": 1743968828.815941,
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": 24.727272727272727,
26
+ "creation_time": 1743968936.9728653,
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": 24.454545454545453,
35
+ "creation_time": 1743969044.3092651,
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": 24.454545454545453,
44
+ "creation_time": 1743969044.4637187,
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": 24.454545454545453,
54
+ "creation_time": 1743969044.4637187,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]