Hugging Face's logo

Lilyislily
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Lilyislily commited on
Commit
10d30ff
·
verified ·
1 Parent(s): 2c442b5

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.1714370057.ac35ea4ce6b9.1788.0 +3 -0
  14. run_logs/Player-0.log +7 -7
  15. run_logs/timers.json +110 -110
  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 sha256:35145a0b0a774a5d81f60fd26068f24c203c3f103e6581fec9d4f5d0b5c5fa23
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ab0a3199603143eaef36cffa87ce3947d0660cb3ff1cd3ae6778d0d1119bdb
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa8f5a7387dd44f510792119a4a04ff6aa5becd98e9bff7005060d3d212eb1ab
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee22aee94b7841dfdfeccdda05a372d0a61227f1c409fc55a9b1da8d0f15be89
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f58e4c7cf3b21d365ef842e294d1b38d8c2af2325d72b60fbe3cd3fdbd4ba87
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39623a16b546fb40d10e8f92b926b6c996fadae8c35aaf5fe66e180ec62d89c8
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35145a0b0a774a5d81f60fd26068f24c203c3f103e6581fec9d4f5d0b5c5fa23
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ab0a3199603143eaef36cffa87ce3947d0660cb3ff1cd3ae6778d0d1119bdb
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:250f5c8742b6a2c42534c0f1b9049bb201ea98acdd47d631ee2662e705fff9df
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed62205f12bafed9decd3f15b9a405dbf01bbabb8e33411ba11c465d8686c69a
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35145a0b0a774a5d81f60fd26068f24c203c3f103e6581fec9d4f5d0b5c5fa23
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ab0a3199603143eaef36cffa87ce3947d0660cb3ff1cd3ae6778d0d1119bdb
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb472014ddb4680fb92f8b52c725ce4ebcda362929f5aca9240162bf40dc1415
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ecb7727580399839733c507c89245cc29bda2477ed673f00033d0c594e7414
3
  size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4bb7a0a114f350ad12b7c10d558e3a07a7b847076c667359468ec7a811ffca8
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e70c2153ac621a445f2ccde31e37f72d80a723a5ec341d4c154268d9c88afc6
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6387e51f1c6af5946416fe76f4f58825c77b892577d2d9703e91469ba0788f5f
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ccbf791eb6dc62006334606498e108e2b3d97247ced1c0c8b03f99e3307c0d
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:442eb55ee62bd2ae7c8098b61639623fb01400e7b9c2b61fa08755bb194c9869
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f07c7c979d73cd456720cfbf663d4fe1eff1ad1c6ba2d24449cf424955d468
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91a9f0ff57e38b519e683ccec40860f82bda3a8c5cca32bbd6d811e871d1b13f
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:810315db3d803538e8ba377d889740751d2af1dd968c986e24aa1fc945c2295b
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ad584074cbdd4cabefc65d8a49d9aeab0cc1af588e48bf085894c015367ef04
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3587a74bc4ec56f66144e701936d4eed52e1084355bfc23cd402bc48381f5d
3
  size 3849250
SnowballTarget/events.out.tfevents.1714370057.ac35ea4ce6b9.1788.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93488f453792b0216e702a7b9f743d8a1b2d48456de0612c641a64e339b50b2e
3
+ size 23606
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 0.091 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: 0.689559 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 36
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]: 5460 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 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]: 4800 frames, [64.0 KB-128.0 KB]: 660 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]: 5460 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 0.090 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: 0.640731 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 40
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]: 5460 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]: 5460 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]: 5076 frames, [64.0 KB-128.0 KB]: 384 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]: 5460 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.906783401966095,
6
- "min": 0.9032992720603943,
7
- "max": 2.8658666610717773,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8657.9677734375,
12
- "min": 8657.9677734375,
13
- "max": 29412.390625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.966553688049316,
30
- "min": 0.33971983194351196,
31
- "max": 12.966553688049316,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2528.47802734375,
36
- "min": 65.90564727783203,
37
- "max": 2637.31787109375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06974980618813824,
54
- "min": 0.06252513799147125,
55
- "max": 0.07387437011736135,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.27899922475255295,
60
- "min": 0.250100551965885,
61
- "max": 0.3625728493620865,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.18969896501478029,
66
- "min": 0.11654883081335393,
67
- "max": 0.2928008890035106,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7587958600591211,
72
- "min": 0.4661953232534157,
73
- "max": 1.4083491701121422,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.568181818181817,
114
- "min": 3.159090909090909,
115
- "max": 25.568181818181817,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1125.0,
120
- "min": 139.0,
121
- "max": 1394.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.568181818181817,
126
- "min": 3.159090909090909,
127
- "max": 25.568181818181817,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1125.0,
132
- "min": 139.0,
133
- "max": 1394.0,
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": "1713839917",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
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": "1.1.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1713840412"
160
  },
161
- "total": 495.0238000500003,
162
  "count": 1,
163
- "self": 0.8575595320003231,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06498869300003207,
167
  "count": 1,
168
- "self": 0.06498869300003207
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 494.10125182499996,
172
  "count": 1,
173
- "self": 0.6480190930124081,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.069072963999588,
177
  "count": 1,
178
- "self": 3.069072963999588
179
  },
180
  "TrainerController.advance": {
181
- "total": 490.2185626249875,
182
- "count": 18199,
183
- "self": 0.3156588209703841,
184
  "children": {
185
  "env_step": {
186
- "total": 489.9029038040171,
187
- "count": 18199,
188
- "self": 319.053771281026,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 170.50974593699766,
192
- "count": 18199,
193
- "self": 1.6440741190021981,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 168.86567181799546,
197
- "count": 18199,
198
- "self": 168.86567181799546
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.3393865859934522,
204
- "count": 18199,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 492.68001581095723,
209
- "count": 18199,
210
  "is_parallel": true,
211
- "self": 244.67875251492478,
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": 0.0065287659999739844,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004098490999695059,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0024302750002789253,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0024302750002789253
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.09157565099985732,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007432909997078241,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00046844999997119885,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00046844999997119885
244
  },
245
  "communicator.exchange": {
246
- "total": 0.08812622699997519,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.08812622699997519
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0022376830002031056,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004795710005964793,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0017581119996066263,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0017581119996066263
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 248.00126329603245,
271
- "count": 18198,
272
  "is_parallel": true,
273
- "self": 11.229304460036019,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.026031845987291,
277
- "count": 18198,
278
  "is_parallel": true,
279
- "self": 6.026031845987291
280
  },
281
  "communicator.exchange": {
282
- "total": 192.92658663599377,
283
- "count": 18198,
284
  "is_parallel": true,
285
- "self": 192.92658663599377
286
  },
287
  "steps_from_proto": {
288
- "total": 37.81934035401537,
289
- "count": 18198,
290
  "is_parallel": true,
291
- "self": 7.155201082969597,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 30.66413927104577,
295
- "count": 181980,
296
  "is_parallel": true,
297
- "self": 30.66413927104577
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00014970500023991917,
313
  "count": 1,
314
- "self": 0.00014970500023991917,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 483.92301335380944,
324
- "count": 734957,
325
  "is_parallel": true,
326
- "self": 16.159986082931482,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 268.6254950278799,
330
- "count": 734957,
331
  "is_parallel": true,
332
- "self": 268.0422775718798,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.5832174560000567,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.5832174560000567
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 199.13753224299808,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 58.333141100992634,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 140.80439114200544,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 140.80439114200544
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.16544743800022843,
364
  "count": 1,
365
- "self": 0.0014729300000908552,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.16397450800013758,
369
  "count": 1,
370
- "self": 0.16397450800013758
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9639486074447632,
6
+ "min": 0.9639486074447632,
7
+ "max": 2.8667469024658203,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9214.384765625,
12
+ "min": 9214.384765625,
13
+ "max": 29358.35546875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.824006080627441,
30
+ "min": 0.17293085157871246,
31
+ "max": 12.82815933227539,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2500.68115234375,
36
+ "min": 33.548583984375,
37
+ "max": 2616.944580078125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06931805435614675,
54
+ "min": 0.06275898552435227,
55
+ "max": 0.07302175748684699,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.277272217424587,
60
+ "min": 0.2510359420974091,
61
+ "max": 0.3651087874342349,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19526937282552906,
66
+ "min": 0.10630987113451257,
67
+ "max": 0.28684770118664293,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7810774913021162,
72
+ "min": 0.42523948453805027,
73
+ "max": 1.414463428890004,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.34090909090909,
114
+ "min": 3.2045454545454546,
115
+ "max": 25.34090909090909,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1115.0,
120
+ "min": 141.0,
121
+ "max": 1388.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.34090909090909,
126
+ "min": 3.2045454545454546,
127
+ "max": 25.34090909090909,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1115.0,
132
+ "min": 141.0,
133
+ "max": 1388.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1714370057",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
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": "1.1.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1714370477"
160
  },
161
+ "total": 420.63135134999993,
162
  "count": 1,
163
+ "self": 0.4407798449999518,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05502466799998729,
167
  "count": 1,
168
+ "self": 0.05502466799998729
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 420.135546837,
172
  "count": 1,
173
+ "self": 0.5143801239913159,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.1606292239999902,
177
  "count": 1,
178
+ "self": 3.1606292239999902
179
  },
180
  "TrainerController.advance": {
181
+ "total": 416.37466943800865,
182
+ "count": 18200,
183
+ "self": 0.23916113901185554,
184
  "children": {
185
  "env_step": {
186
+ "total": 416.1355082989968,
187
+ "count": 18200,
188
+ "self": 266.55700497000686,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 149.31678948999678,
192
+ "count": 18200,
193
+ "self": 1.6564380489951986,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 147.66035144100158,
197
+ "count": 18200,
198
+ "self": 147.66035144100158
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2617138389931597,
204
+ "count": 18200,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 419.02265573500057,
209
+ "count": 18200,
210
  "is_parallel": true,
211
+ "self": 210.41938324500364,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005831263000004583,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0042311600000743965,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016001029999301863,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0016001029999301863
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.06305859100001499,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007129660000373406,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004209780000223873,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004209780000223873
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.059862690999977985,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.059862690999977985
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002061955999977272,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00044250399992051825,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016194520000567536,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016194520000567536
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 208.60327248999693,
271
+ "count": 18199,
272
  "is_parallel": true,
273
+ "self": 9.837777422999466,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.302773040991553,
277
+ "count": 18199,
278
  "is_parallel": true,
279
+ "self": 5.302773040991553
280
  },
281
  "communicator.exchange": {
282
+ "total": 161.09660073200064,
283
+ "count": 18199,
284
  "is_parallel": true,
285
+ "self": 161.09660073200064
286
  },
287
  "steps_from_proto": {
288
+ "total": 32.36612129400527,
289
+ "count": 18199,
290
  "is_parallel": true,
291
+ "self": 5.905627327998559,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.46049396600671,
295
+ "count": 181990,
296
  "is_parallel": true,
297
+ "self": 26.46049396600671
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 3.607899998314679e-05,
313
  "count": 1,
314
+ "self": 3.607899998314679e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 411.0824204120379,
324
+ "count": 654319,
325
  "is_parallel": true,
326
+ "self": 13.361511769021604,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 227.23520411401614,
330
+ "count": 654319,
331
  "is_parallel": true,
332
+ "self": 226.32597546701618,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.9092286469999635,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.9092286469999635
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 170.48570452900015,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 48.32712250500384,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 122.1585820239963,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 122.1585820239963
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.08583197200005088,
364
  "count": 1,
365
+ "self": 0.0009211960000357067,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.08491077600001518,
369
  "count": 1,
370
+ "self": 0.08491077600001518
371
  }
372
  }
373
  }
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": 15.363636363636363,
8
- "creation_time": 1713840041.890303,
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": 22.181818181818183,
17
- "creation_time": 1713840165.143436,
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": 23.727272727272727,
26
- "creation_time": 1713840286.3162036,
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": 25.181818181818183,
35
- "creation_time": 1713840411.8408554,
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": 25.181818181818183,
44
- "creation_time": 1713840412.046596,
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": 25.181818181818183,
54
- "creation_time": 1713840412.046596,
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": 14.0,
8
+ "creation_time": 1714370167.2567978,
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": 21.545454545454547,
17
+ "creation_time": 1714370271.418511,
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": 1714370374.5449216,
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": 26.181818181818183,
35
+ "creation_time": 1714370477.1449125,
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": 26.181818181818183,
44
+ "creation_time": 1714370477.2586834,
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": 26.181818181818183,
54
+ "creation_time": 1714370477.2586834,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]