Hugging Face's logo

briannnyee
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
briannnyee commited on
Commit
57fef76
·
verified ·
1 Parent(s): 5e5a058

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.1724331814.8deba02a6242.1095.0 +3 -0
  14. run_logs/Player-0.log +6 -6
  15. run_logs/timers.json +99 -99
  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:d5de85905924668f3eced6f31da88ed01bf7cafac64b982648dbc7eefdb66af2
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4035e2de2a32fac3ecac1e4e9bfe735e15eb3225723ee68b2a103b6adf984b
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb0b286bdb88b5ca0a97fffaa02ad9cfc78141324ae80409acab03994d27ca3d
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87871b6b1b3361bb4ab3d961e59e589f768672e9da164c5e715f090b4b341dbf
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8132ebfd8dd323797978845d715af770c4e25c80bd4bda508fb1c3ce4f5acba4
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d4cc4c424be84d349ffce61be812947356e454acfee93a6cbbb9589516e56b
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5de85905924668f3eced6f31da88ed01bf7cafac64b982648dbc7eefdb66af2
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4035e2de2a32fac3ecac1e4e9bfe735e15eb3225723ee68b2a103b6adf984b
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99f097f6077a41e962217a4cbf7d236dc5b013b9a81480aaf284992c520098ef
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee97b112c2550e4831376dab5a9aa205eea6ec140cc6299623fb93515b05a89
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5de85905924668f3eced6f31da88ed01bf7cafac64b982648dbc7eefdb66af2
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4035e2de2a32fac3ecac1e4e9bfe735e15eb3225723ee68b2a103b6adf984b
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c42578a6331fbe1b2ca79571fb5143d19338d31748a7e306944d6e581582a893
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b0deb31948d715376bcd52a3d5900917ab8af2ee68a55c067d35d9c5dd39a4
3
  size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:844620663c3c9649bb9335b4f28bfb86a1843e51774fe9224d474d1d5a071050
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7c6ecebc1f2a9e1d00d55617365af44a8229e7efa59e21ee6b237990cde888
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be46d4e68ea55d1f667bab449fdd4f80c5b006340077f15e581c286ca98dd75c
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce63c298fb055803cb5daae4ebf41904b924f95eba38bfe2913720467ae09e8
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1483143054f4986f4f14aca83587e59539197bafe68aa260b4cfa40676f67ee
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0697808ed7db502662c03395c54770bb26007a327c0b92a266e67984a02e07c3
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:531968cce31f5450c932797c7648bad9336f455f8338b54bdef7331af28503d5
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:236423255e41751836cd3d8da0335d9bc1b2f9166ae3614f18a78c8f08a71f77
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f147c9a8120470a57167fc733448b078068e36d9a7137ba89b8ef44e87330421
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88cc42311583919b9c3eca2070a72dc4fb87bc6b74fabb3553d3757ee3110938
3
  size 3849250
SnowballTarget/events.out.tfevents.1724331814.8deba02a6242.1095.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bc125c13a2356df4a29928f280cb437ce0d3f2fc619387cf7505b7c4a64c83
3
+ size 23698
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 0.102 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: 0.750168 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -169,7 +169,7 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -178,7 +178,7 @@ Memory Statistics:
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.7 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
@@ -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]: 4961 frames, [64.0 KB-128.0 KB]: 500 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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 0.087 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: 0.630282 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
 
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 46
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
 
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 6.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
 
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]: 4028 frames, [64.0 KB-128.0 KB]: 1433 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 67.7 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8986561894416809,
6
- "min": 0.8986561894416809,
7
- "max": 2.8716650009155273,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8580.369140625,
12
- "min": 8580.369140625,
13
- "max": 29535.07421875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.974709510803223,
30
- "min": 0.2676580250263214,
31
- "max": 13.014567375183105,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2530.068359375,
36
- "min": 51.9256591796875,
37
- "max": 2654.9716796875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06809029484757761,
54
- "min": 0.061514649225921626,
55
- "max": 0.07948633022343868,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.27236117939031046,
60
- "min": 0.24609189831538542,
61
- "max": 0.39743165111719336,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20496094789282948,
66
- "min": 0.12908740417675718,
67
- "max": 0.2863588478489249,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8198437915713179,
72
- "min": 0.5163496167070287,
73
- "max": 1.3715339305938459,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.15909090909091,
114
- "min": 3.5,
115
- "max": 25.704545454545453,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1107.0,
120
- "min": 154.0,
121
- "max": 1405.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.15909090909091,
126
- "min": 3.5,
127
- "max": 25.704545454545453,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1107.0,
132
- "min": 154.0,
133
- "max": 1405.0,
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": "1723385692",
152
  "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1723386163"
160
  },
161
- "total": 471.0462902080001,
162
  "count": 1,
163
- "self": 0.48606076800001574,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.07093999400001394,
167
  "count": 1,
168
- "self": 0.07093999400001394
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 470.48928944600004,
172
  "count": 1,
173
- "self": 0.5856696610184144,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.557010267999999,
177
  "count": 1,
178
- "self": 3.557010267999999
179
  },
180
  "TrainerController.advance": {
181
- "total": 466.2405171349816,
182
  "count": 18201,
183
- "self": 0.27856394598848055,
184
  "children": {
185
  "env_step": {
186
- "total": 465.9619531889931,
187
  "count": 18201,
188
- "self": 302.28292957698136,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 163.381338550009,
192
  "count": 18201,
193
- "self": 1.565804845004891,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 161.8155337050041,
197
  "count": 18201,
198
- "self": 161.8155337050041
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.29768506200275624,
204
  "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 469.36932161200275,
209
  "count": 18201,
210
  "is_parallel": true,
211
- "self": 236.457620274997,
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": 0.006102231999989272,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0045054379999101,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015967940000791714,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015967940000791714
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03803125500007809,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006584210001392421,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00043077899999843794,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00043077899999843794
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03480987199998253,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03480987199998253
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0021321829999578767,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003942230000575364,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0017379599999003403,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0017379599999003403
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 232.91170133700575,
271
  "count": 18200,
272
  "is_parallel": true,
273
- "self": 10.663751445019443,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.507414492990392,
277
  "count": 18200,
278
  "is_parallel": true,
279
- "self": 5.507414492990392
280
  },
281
  "communicator.exchange": {
282
- "total": 182.12427844299464,
283
  "count": 18200,
284
  "is_parallel": true,
285
- "self": 182.12427844299464
286
  },
287
  "steps_from_proto": {
288
- "total": 34.61625695600128,
289
  "count": 18200,
290
  "is_parallel": true,
291
- "self": 6.4896851499994455,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 28.126571806001834,
295
  "count": 182000,
296
  "is_parallel": true,
297
- "self": 28.126571806001834
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00014498199993795424,
313
  "count": 1,
314
- "self": 0.00014498199993795424,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 460.30555150493865,
324
- "count": 706841,
325
  "is_parallel": true,
326
- "self": 15.020031112861375,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 253.76446284607778,
330
- "count": 706841,
331
  "is_parallel": true,
332
- "self": 252.6951501490778,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.0693126969999867,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.0693126969999867
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 191.5210575459995,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 61.848418140994454,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 129.67263940500504,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 129.67263940500504
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.10594740000010461,
364
  "count": 1,
365
- "self": 0.0010378630001923739,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.10490953699991223,
369
  "count": 1,
370
- "self": 0.10490953699991223
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0384373664855957,
6
+ "min": 1.0384373664855957,
7
+ "max": 2.8559584617614746,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9915.0,
12
+ "min": 9915.0,
13
+ "max": 29247.87109375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.189550399780273,
30
+ "min": 0.4255053400993347,
31
+ "max": 12.189550399780273,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2376.96240234375,
36
+ "min": 82.54803466796875,
37
+ "max": 2462.41064453125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07356240453387443,
54
+ "min": 0.05799809854990787,
55
+ "max": 0.07501606463498035,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2942496181354977,
60
+ "min": 0.23199239419963147,
61
+ "max": 0.3724369349148736,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.20118075623816134,
66
+ "min": 0.1201416079489076,
67
+ "max": 0.2702872181055592,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8047230249526454,
72
+ "min": 0.4805664317956304,
73
+ "max": 1.3514360905277962,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 24.15909090909091,
114
+ "min": 3.227272727272727,
115
+ "max": 24.15909090909091,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1063.0,
120
+ "min": 142.0,
121
+ "max": 1305.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 24.15909090909091,
126
+ "min": 3.227272727272727,
127
+ "max": 24.15909090909091,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1063.0,
132
+ "min": 142.0,
133
+ "max": 1305.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1724331813",
152
  "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1724332244"
160
  },
161
+ "total": 431.1629563629999,
162
  "count": 1,
163
+ "self": 0.43149411699988605,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.060371717999998964,
167
  "count": 1,
168
+ "self": 0.060371717999998964
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 430.67109052800004,
172
  "count": 1,
173
+ "self": 0.5330210149974164,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.919699554999994,
177
  "count": 1,
178
+ "self": 2.919699554999994
179
  },
180
  "TrainerController.advance": {
181
+ "total": 427.1275536780026,
182
  "count": 18201,
183
+ "self": 0.26221873899834236,
184
  "children": {
185
  "env_step": {
186
+ "total": 426.86533493900424,
187
  "count": 18201,
188
+ "self": 273.9763929870122,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 152.61930772300005,
192
  "count": 18201,
193
+ "self": 1.4266421900051967,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 151.19266553299485,
197
  "count": 18201,
198
+ "self": 151.19266553299485
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.26963422899200395,
204
  "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 429.4961787850019,
209
  "count": 18201,
210
  "is_parallel": true,
211
+ "self": 217.98473687199746,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005386122000004434,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0038400240000271424,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015460979999772917,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015460979999772917
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03681795800000032,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000724001999998336,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00040230100000826496,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00040230100000826496
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.033562860000017736,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.033562860000017736
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021287949999759803,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0005832719999716574,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001545523000004323,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001545523000004323
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 211.51144191300446,
271
  "count": 18200,
272
  "is_parallel": true,
273
+ "self": 9.799379372001141,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.008672770999681,
277
  "count": 18200,
278
  "is_parallel": true,
279
+ "self": 5.008672770999681
280
  },
281
  "communicator.exchange": {
282
+ "total": 164.71318103400046,
283
  "count": 18200,
284
  "is_parallel": true,
285
+ "self": 164.71318103400046
286
  },
287
  "steps_from_proto": {
288
+ "total": 31.990208736003183,
289
  "count": 18200,
290
  "is_parallel": true,
291
+ "self": 5.9835831110025595,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.006625625000623,
295
  "count": 182000,
296
  "is_parallel": true,
297
+ "self": 26.006625625000623
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00012205600000925187,
313
  "count": 1,
314
+ "self": 0.00012205600000925187,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 421.75778035101,
324
+ "count": 655406,
325
  "is_parallel": true,
326
+ "self": 13.355723570954297,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 232.79396341205518,
330
+ "count": 655406,
331
  "is_parallel": true,
332
+ "self": 232.16192724705508,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.6320361650001018,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.6320361650001018
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 175.60809336800054,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 54.41475727700225,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 121.19333609099829,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 121.19333609099829
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09069422400000349,
364
  "count": 1,
365
+ "self": 0.0009345669999447637,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.08975965700005872,
369
  "count": 1,
370
+ "self": 0.08975965700005872
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": 14.363636363636363,
8
- "creation_time": 1723385815.0056627,
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": 22.636363636363637,
17
- "creation_time": 1723385931.3767653,
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": 25.181818181818183,
26
- "creation_time": 1723386048.1102502,
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": 24.727272727272727,
35
- "creation_time": 1723386163.0625553,
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": 24.727272727272727,
44
- "creation_time": 1723386163.1984425,
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": 24.727272727272727,
54
- "creation_time": 1723386163.1984425,
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": 12.818181818181818,
8
+ "creation_time": 1724331923.2383513,
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": 19.454545454545453,
17
+ "creation_time": 1724332028.7104037,
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": 22.363636363636363,
26
+ "creation_time": 1724332135.0059924,
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": 24.818181818181817,
35
+ "creation_time": 1724332243.8135328,
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": 24.818181818181817,
44
+ "creation_time": 1724332243.931337,
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": 24.818181818181817,
54
+ "creation_time": 1724332243.931337,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]