Hugging Face's logo

arjunamate
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
arjunamate commited on
Commit
7d8c576
·
verified ·
1 Parent(s): f443eff

Second Push

Browse files
Files changed (4) hide show
  1. SnowballTarget/events.out.tfevents.1771235481.37c258d46b33.4630.0 +3 -0
  2. run_logs/Player-0.log +16 -15
  3. run_logs/timers.json +154 -161
  4. run_logs/training_status.json +0 -58
SnowballTarget/events.out.tfevents.1771235481.37c258d46b33.4630.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c2122830fb6a182f4aaf44329974ee6ab50a334e591d93813f0496e922cfb0
3
+ size 6895
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 0.180 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)
@@ -45,15 +45,16 @@ 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: 0.774475 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.
52
  Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +170,22 @@ Memory Statistics:
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
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 7.1 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 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
@@ -213,13 +214,13 @@ 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]: 4784 frames, [64.0 KB-128.0 KB]: 674 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.4 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
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +232,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +250,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5458 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
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 0.092 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: 0.689776 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
+ GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
52
  Setting up 1 worker threads for Enlighten.
53
  Memory Statistics:
54
  [ALLOC_TEMP_TLS] TLS Allocator
55
  StackAllocators :
56
  [ALLOC_TEMP_MAIN]
57
+ Peak usage frame count: [8.0 KB-16.0 KB]: 401 frames, [16.0 KB-32.0 KB]: 6 frames, [2.0 MB-4.0 MB]: 1 frames
58
  Initial Block Size 4.0 MB
59
  Current Block Size 4.0 MB
60
  Peak Allocated Bytes 2.0 MB
 
170
  Peak Allocated Bytes 0 B
171
  Overflow Count 0
172
  [ALLOC_DEFAULT] Dual Thread Allocator
173
+ Peak main deferred allocation count 33
174
  [ALLOC_BUCKET]
175
  Large Block size 4.0 MB
176
  Used Block count 1
177
  Peak Allocated bytes 1.0 MB
178
  [ALLOC_DEFAULT_MAIN]
179
+ Peak usage frame count: [4.0 MB-8.0 MB]: 408 frames
180
  Requested Block Size 16.0 MB
181
  Peak Block count 1
182
+ Peak Allocated memory 5.7 MB
183
  Peak Large allocation bytes 0 B
184
  [ALLOC_DEFAULT_THREAD]
185
+ Peak usage frame count: [16.0 MB-32.0 MB]: 408 frames
186
  Requested Block Size 16.0 MB
187
  Peak Block count 1
188
+ Peak Allocated memory 17.4 MB
189
  Peak Large allocation bytes 16.0 MB
190
  [ALLOC_TEMP_JOB_1_FRAME]
191
  Initial Block Size 2.0 MB
 
214
  Used Block count 1
215
  Peak Allocated bytes 1.0 MB
216
  [ALLOC_GFX_MAIN]
217
+ Peak usage frame count: [32.0 KB-64.0 KB]: 318 frames, [64.0 KB-128.0 KB]: 90 frames
218
  Requested Block Size 16.0 MB
219
  Peak Block count 1
220
+ Peak Allocated memory 66.8 KB
221
  Peak Large allocation bytes 0 B
222
  [ALLOC_GFX_THREAD]
223
+ Peak usage frame count: [32.0 KB-64.0 KB]: 408 frames
224
  Requested Block Size 16.0 MB
225
  Peak Block count 1
226
  Peak Allocated memory 39.6 KB
 
232
  Used Block count 1
233
  Peak Allocated bytes 1.0 MB
234
  [ALLOC_CACHEOBJECTS_MAIN]
235
+ Peak usage frame count: [0.5 MB-1.0 MB]: 408 frames
236
  Requested Block Size 4.0 MB
237
  Peak Block count 1
238
  Peak Allocated memory 0.6 MB
239
  Peak Large allocation bytes 0 B
240
  [ALLOC_CACHEOBJECTS_THREAD]
241
+ Peak usage frame count: [0.5 MB-1.0 MB]: 407 frames, [2.0 MB-4.0 MB]: 1 frames
242
  Requested Block Size 4.0 MB
243
  Peak Block count 1
244
  Peak Allocated memory 2.2 MB
 
250
  Used Block count 1
251
  Peak Allocated bytes 1.0 MB
252
  [ALLOC_TYPETREE_MAIN]
253
+ Peak usage frame count: [0-1.0 KB]: 408 frames
254
  Requested Block Size 2.0 MB
255
  Peak Block count 1
256
  Peak Allocated memory 1.0 KB
257
  Peak Large allocation bytes 0 B
258
  [ALLOC_TYPETREE_THREAD]
259
+ Peak usage frame count: [1.0 KB-2.0 KB]: 408 frames
260
  Requested Block Size 2.0 MB
261
  Peak Block count 1
262
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8372244834899902,
6
- "min": 0.8372244834899902,
7
- "max": 2.828864574432373,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7956.9814453125,
12
- "min": 7956.9814453125,
13
- "max": 28877.05078125,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
  "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
  "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.046035766601562,
30
- "min": 0.27583742141723633,
31
- "max": 13.046035766601562,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2543.97705078125,
36
- "min": 53.51245880126953,
37
- "max": 2639.50390625,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07326524078619995,
42
- "min": 0.06387048077600661,
43
- "max": 0.07365418480342259,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2930609631447998,
48
- "min": 0.25548192310402645,
49
- "max": 0.35704322218239837,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.22011773244423027,
54
- "min": 0.1163426105791301,
55
- "max": 0.3039715277213676,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8804709297769211,
60
- "min": 0.4653704423165204,
61
- "max": 1.519857638606838,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
  "max": 0.000291882002706,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
  "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
  "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
- "max": 10945.0,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.25,
114
- "min": 3.0454545454545454,
115
- "max": 25.745454545454546,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1111.0,
120
- "min": 134.0,
121
- "max": 1416.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.25,
126
- "min": 3.0454545454545454,
127
- "max": 25.745454545454546,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1111.0,
132
- "min": 134.0,
133
- "max": 1416.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1771223306",
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": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1771223741"
160
  },
161
- "total": 434.7839298990002,
162
  "count": 1,
163
- "self": 0.43570642500026224,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.024271150000004127,
167
  "count": 1,
168
- "self": 0.024271150000004127
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 434.32395232399995,
172
  "count": 1,
173
- "self": 0.3625972989541424,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.520636817999957,
177
  "count": 1,
178
- "self": 3.520636817999957
179
  },
180
  "TrainerController.advance": {
181
- "total": 430.3665687060461,
182
- "count": 18192,
183
- "self": 0.36037655209747754,
184
  "children": {
185
  "env_step": {
186
- "total": 312.457133220983,
187
- "count": 18192,
188
- "self": 243.77311697402706,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 68.47076408996054,
192
- "count": 18192,
193
- "self": 1.2302057959498143,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 67.24055829401073,
197
- "count": 18192,
198
- "self": 67.24055829401073
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21325215699539513,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 432.34245809398067,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 217.8954894159915,
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": 0.004335631000003559,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0029861050004456047,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0013495259995579545,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0013495259995579545
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.07969745200011857,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005968139998913102,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0007141490000321937,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0007141490000321937
244
  },
245
  "communicator.exchange": {
246
- "total": 0.07262094400016395,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.07262094400016395
250
  },
251
  "steps_from_proto": {
252
- "total": 0.005765545000031125,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003720190004514734,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.005393525999579651,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.005393525999579651
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 214.44696867798916,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.011888436040408,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.4268846109937385,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.4268846109937385
280
  },
281
  "communicator.exchange": {
282
- "total": 163.35985708498788,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 163.35985708498788
286
  },
287
  "steps_from_proto": {
288
- "total": 35.648338545967135,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.443929731891785,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 29.20440881407535,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 29.20440881407535
298
  }
299
  }
300
  }
@@ -307,31 +307,24 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 117.54905893296564,
311
- "count": 18192,
312
- "self": 0.44864708495015293,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 26.220148464016802,
316
- "count": 18192,
317
- "self": 25.794159323016174,
318
- "children": {
319
- "RLTrainer._checkpoint": {
320
- "total": 0.42598914100062757,
321
- "count": 4,
322
- "self": 0.42598914100062757
323
- }
324
- }
325
  },
326
  "_update_policy": {
327
- "total": 90.88026338399868,
328
- "count": 90,
329
- "self": 36.68368106398884,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 54.19658232000984,
333
- "count": 4587,
334
- "self": 54.19658232000984
335
  }
336
  }
337
  }
@@ -340,19 +333,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.989998943638057e-07,
344
  "count": 1,
345
- "self": 9.989998943638057e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.07414850199984357,
349
  "count": 1,
350
- "self": 0.0006620039998779248,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07348649799996565,
354
  "count": 1,
355
- "self": 0.07348649799996565
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.821643114089966,
6
+ "min": 2.821643114089966,
7
+ "max": 2.821643114089966,
8
+ "count": 1
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 28803.333984375,
12
+ "min": 28803.333984375,
13
+ "max": 28803.333984375,
14
+ "count": 1
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 9952.0,
18
  "min": 9952.0,
19
+ "max": 9952.0,
20
+ "count": 1
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 9952.0,
24
  "min": 9952.0,
25
+ "max": 9952.0,
26
+ "count": 1
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 0.4277043342590332,
30
+ "min": 0.4277043342590332,
31
+ "max": 0.4277043342590332,
32
+ "count": 1
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 82.97463989257812,
36
+ "min": 82.97463989257812,
37
+ "max": 82.97463989257812,
38
+ "count": 1
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06835801960489363,
42
+ "min": 0.06835801960489363,
43
+ "max": 0.06835801960489363,
44
+ "count": 1
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2734320784195745,
48
+ "min": 0.2734320784195745,
49
+ "max": 0.2734320784195745,
50
+ "count": 1
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.13539279293720885,
54
+ "min": 0.13539279293720885,
55
+ "max": 0.13539279293720885,
56
+ "count": 1
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.5415711717488354,
60
+ "min": 0.5415711717488354,
61
+ "max": 0.5415711717488354,
62
+ "count": 1
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 0.000291882002706,
66
+ "min": 0.000291882002706,
67
  "max": 0.000291882002706,
68
+ "count": 1
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 0.001167528010824,
72
+ "min": 0.001167528010824,
73
+ "max": 0.001167528010824,
74
+ "count": 1
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.19729400000000002,
78
+ "min": 0.19729400000000002,
79
  "max": 0.19729400000000002,
80
+ "count": 1
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.7891760000000001,
84
+ "min": 0.7891760000000001,
85
+ "max": 0.7891760000000001,
86
+ "count": 1
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 0.0048649706,
90
+ "min": 0.0048649706,
91
  "max": 0.0048649706,
92
+ "count": 1
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0194598824,
96
+ "min": 0.0194598824,
97
+ "max": 0.0194598824,
98
+ "count": 1
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 1
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
+ "max": 8756.0,
110
+ "count": 1
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 3.909090909090909,
114
+ "min": 3.909090909090909,
115
+ "max": 3.909090909090909,
116
+ "count": 1
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 172.0,
120
+ "min": 172.0,
121
+ "max": 172.0,
122
+ "count": 1
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 3.909090909090909,
126
+ "min": 3.909090909090909,
127
+ "max": 3.909090909090909,
128
+ "count": 1
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 172.0,
132
+ "min": 172.0,
133
+ "max": 172.0,
134
+ "count": 1
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 1
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 1
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1771235480",
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": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1771235520"
160
  },
161
+ "total": 39.646496189000004,
162
  "count": 1,
163
+ "self": 0.48182900199992673,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.026747376000002987,
167
  "count": 1,
168
+ "self": 0.026747376000002987
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 39.137919811000074,
172
  "count": 1,
173
+ "self": 0.030573536997735573,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.461824671000045,
177
  "count": 1,
178
+ "self": 3.461824671000045
179
  },
180
  "TrainerController.advance": {
181
+ "total": 35.64411465700232,
182
+ "count": 1359,
183
+ "self": 0.0323910470018518,
184
  "children": {
185
  "env_step": {
186
+ "total": 27.142750105000346,
187
+ "count": 1359,
188
+ "self": 21.171929606001868,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 5.9525552919989195,
192
+ "count": 1359,
193
+ "self": 0.1060865079988389,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 5.846468784000081,
197
+ "count": 1359,
198
+ "self": 5.846468784000081
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.01826520699955836,
204
+ "count": 1358,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 39.02059578700164,
209
+ "count": 1358,
210
  "is_parallel": true,
211
+ "self": 20.516248202002203,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005206495999914296,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003599066999754541,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016074290001597547,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0016074290001597547
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.08200166900007844,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.002381823000064287,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0015376329999980953,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0015376329999980953
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.0739739540000528,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.0739739540000528
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.004108258999963255,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004109260000859649,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0036973329998772897,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0036973329998772897
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 18.504347584999437,
271
+ "count": 1357,
272
  "is_parallel": true,
273
+ "self": 0.8520413290007127,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 0.476091859999201,
277
+ "count": 1357,
278
  "is_parallel": true,
279
+ "self": 0.476091859999201
280
  },
281
  "communicator.exchange": {
282
+ "total": 14.00623891599912,
283
+ "count": 1357,
284
  "is_parallel": true,
285
+ "self": 14.00623891599912
286
  },
287
  "steps_from_proto": {
288
+ "total": 3.169975480000403,
289
+ "count": 1357,
290
  "is_parallel": true,
291
+ "self": 0.5443843100018739,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 2.625591169998529,
295
+ "count": 13570,
296
  "is_parallel": true,
297
+ "self": 2.625591169998529
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 8.468973505000122,
311
+ "count": 1358,
312
+ "self": 0.036086341999293836,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 2.1546907510007713,
316
+ "count": 1358,
317
+ "self": 2.1546907510007713
 
 
 
 
 
 
 
318
  },
319
  "_update_policy": {
320
+ "total": 6.278196412000057,
321
+ "count": 6,
322
+ "self": 2.508112299000004,
323
  "children": {
324
  "TorchPPOOptimizer.update": {
325
+ "total": 3.7700841130000526,
326
+ "count": 303,
327
+ "self": 3.7700841130000526
328
  }
329
  }
330
  }
 
333
  }
334
  },
335
  "trainer_threads": {
336
+ "total": 1.4649999684479553e-06,
337
  "count": 1,
338
+ "self": 1.4649999684479553e-06
339
  },
340
  "TrainerController._save_models": {
341
+ "total": 0.001405481000006148,
342
  "count": 1,
343
+ "self": 2.3645000055694254e-05,
344
  "children": {
345
  "RLTrainer._checkpoint": {
346
+ "total": 0.0013818359999504537,
347
  "count": 1,
348
+ "self": 0.0013818359999504537
349
  }
350
  }
351
  }
run_logs/training_status.json CHANGED
@@ -1,62 +1,4 @@
1
  {
2
- "SnowballTarget": {
3
- "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 16.545454545454547,
8
- "creation_time": 1771223417.0644171,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
- ]
12
- },
13
- {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 22.0,
17
- "creation_time": 1771223523.647256,
18
- "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
- ]
21
- },
22
- {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.454545454545453,
26
- "creation_time": 1771223632.4642012,
27
- "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
- ]
30
- },
31
- {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 24.818181818181817,
35
- "creation_time": 1771223740.4791033,
36
- "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
- ]
39
- },
40
- {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 24.818181818181817,
44
- "creation_time": 1771223740.564207,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
- ]
48
- }
49
- ],
50
- "final_checkpoint": {
51
- "steps": 200112,
52
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 24.818181818181817,
54
- "creation_time": 1771223740.564207,
55
- "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
- ]
58
- }
59
- },
60
  "metadata": {
61
  "stats_format_version": "0.3.0",
62
  "mlagents_version": "1.2.0.dev0",
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "metadata": {
3
  "stats_format_version": "0.3.0",
4
  "mlagents_version": "1.2.0.dev0",