ecrof commited on
Commit
5426f35
·
1 Parent(s): cca6464

Second Push

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. configuration.yaml +2 -2
  3. run_logs/timers.json +13 -348
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 5000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 20000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 5000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 20000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -45,7 +45,7 @@ behaviors:
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
- env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
+ env_path: null
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
 
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
run_logs/timers.json CHANGED
@@ -1,375 +1,40 @@
1
  {
2
  "name": "root",
3
- "gauges": {
4
- "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.753169059753418,
6
- "min": 2.753169059753418,
7
- "max": 2.8581490516662598,
8
- "count": 2
9
- },
10
- "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 28407.19921875,
12
- "min": 28407.19921875,
13
- "max": 29238.865234375,
14
- "count": 2
15
- },
16
- "SnowballTarget.Step.mean": {
17
- "value": 19992.0,
18
- "min": 9952.0,
19
- "max": 19992.0,
20
- "count": 2
21
- },
22
- "SnowballTarget.Step.sum": {
23
- "value": 19992.0,
24
- "min": 9952.0,
25
- "max": 19992.0,
26
- "count": 2
27
- },
28
- "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 1.2926335334777832,
30
- "min": 0.22984644770622253,
31
- "max": 1.2926335334777832,
32
- "count": 2
33
- },
34
- "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 264.9898681640625,
36
- "min": 44.5902099609375,
37
- "max": 264.9898681640625,
38
- "count": 2
39
- },
40
- "SnowballTarget.Environment.EpisodeLength.mean": {
41
- "value": 199.0,
42
- "min": 199.0,
43
- "max": 199.0,
44
- "count": 2
45
- },
46
- "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
- "min": 8756.0,
49
- "max": 10945.0,
50
- "count": 2
51
- },
52
- "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06690262798873328,
54
- "min": 0.06681513686629949,
55
- "max": 0.06690262798873328,
56
- "count": 2
57
- },
58
- "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.33451313994366644,
60
- "min": 0.26726054746519795,
61
- "max": 0.33451313994366644,
62
- "count": 2
63
- },
64
- "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.1909063190513966,
66
- "min": 0.14033411378634397,
67
- "max": 0.1909063190513966,
68
- "count": 2
69
- },
70
- "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.9545315952569831,
72
- "min": 0.5613364551453759,
73
- "max": 0.9545315952569831,
74
- "count": 2
75
- },
76
- "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 7.032007656e-05,
78
- "min": 7.032007656e-05,
79
- "max": 0.00021882002706000002,
80
- "count": 2
81
- },
82
- "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.0003516003828,
84
- "min": 0.0003516003828,
85
- "max": 0.0008752801082400001,
86
- "count": 2
87
- },
88
- "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.12344000000000002,
90
- "min": 0.12344000000000002,
91
- "max": 0.17294,
92
- "count": 2
93
- },
94
- "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.6172000000000001,
96
- "min": 0.6172000000000001,
97
- "max": 0.69176,
98
- "count": 2
99
- },
100
- "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0011796560000000003,
102
- "min": 0.0011796560000000003,
103
- "max": 0.003649706,
104
- "count": 2
105
- },
106
- "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.005898280000000001,
108
- "min": 0.005898280000000001,
109
- "max": 0.014598824,
110
- "count": 2
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 5.8,
114
- "min": 3.7045454545454546,
115
- "max": 5.8,
116
- "count": 2
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 319.0,
120
- "min": 163.0,
121
- "max": 319.0,
122
- "count": 2
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 5.8,
126
- "min": 3.7045454545454546,
127
- "max": 5.8,
128
- "count": 2
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 319.0,
132
- "min": 163.0,
133
- "max": 319.0,
134
- "count": 2
135
- },
136
- "SnowballTarget.IsTraining.mean": {
137
- "value": 1.0,
138
- "min": 1.0,
139
- "max": 1.0,
140
- "count": 2
141
- },
142
- "SnowballTarget.IsTraining.sum": {
143
- "value": 1.0,
144
- "min": 1.0,
145
- "max": 1.0,
146
- "count": 2
147
- }
148
- },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1703602852",
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",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1703602902"
160
  },
161
- "total": 50.125385297999856,
162
  "count": 1,
163
- "self": 0.697786748000226,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.050454570999818316,
167
  "count": 1,
168
- "self": 0.050454570999818316
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 49.37714397899981,
172
  "count": 1,
173
- "self": 0.0787745739996808,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.0169926449998457,
177
- "count": 1,
178
- "self": 3.0169926449998457
179
- },
180
- "TrainerController.advance": {
181
- "total": 46.19316564600035,
182
- "count": 1871,
183
- "self": 0.028356551004208086,
184
- "children": {
185
- "env_step": {
186
- "total": 46.164809094996144,
187
- "count": 1871,
188
- "self": 29.74730983299537,
189
- "children": {
190
- "SubprocessEnvManager._take_step": {
191
- "total": 16.387860807994002,
192
- "count": 1871,
193
- "self": 0.1524993139955768,
194
- "children": {
195
- "TorchPolicy.evaluate": {
196
- "total": 16.235361493998425,
197
- "count": 1871,
198
- "self": 16.235361493998425
199
- }
200
- }
201
- },
202
- "workers": {
203
- "total": 0.029638454006772008,
204
- "count": 1871,
205
- "self": 0.0,
206
- "children": {
207
- "worker_root": {
208
- "total": 49.19641676199808,
209
- "count": 1871,
210
- "is_parallel": true,
211
- "self": 26.010392564993026,
212
- "children": {
213
- "run_training.setup": {
214
- "total": 0.0,
215
- "count": 0,
216
- "is_parallel": true,
217
- "self": 0.0,
218
- "children": {
219
- "steps_from_proto": {
220
- "total": 0.004247718999977224,
221
- "count": 1,
222
- "is_parallel": true,
223
- "self": 0.002968661000522843,
224
- "children": {
225
- "_process_rank_one_or_two_observation": {
226
- "total": 0.0012790579994543805,
227
- "count": 10,
228
- "is_parallel": true,
229
- "self": 0.0012790579994543805
230
- }
231
- }
232
- },
233
- "UnityEnvironment.step": {
234
- "total": 0.038339288999850396,
235
- "count": 1,
236
- "is_parallel": true,
237
- "self": 0.0006473079999977926,
238
- "children": {
239
- "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004000009998890164,
241
- "count": 1,
242
- "is_parallel": true,
243
- "self": 0.0004000009998890164
244
- },
245
- "communicator.exchange": {
246
- "total": 0.035240495999914856,
247
- "count": 1,
248
- "is_parallel": true,
249
- "self": 0.035240495999914856
250
- },
251
- "steps_from_proto": {
252
- "total": 0.002051484000048731,
253
- "count": 1,
254
- "is_parallel": true,
255
- "self": 0.00038150400041558896,
256
- "children": {
257
- "_process_rank_one_or_two_observation": {
258
- "total": 0.0016699799996331421,
259
- "count": 10,
260
- "is_parallel": true,
261
- "self": 0.0016699799996331421
262
- }
263
- }
264
- }
265
- }
266
- }
267
- }
268
- },
269
- "UnityEnvironment.step": {
270
- "total": 23.186024197005054,
271
- "count": 1870,
272
- "is_parallel": true,
273
- "self": 1.0734497650196317,
274
- "children": {
275
- "UnityEnvironment._generate_step_input": {
276
- "total": 0.5612565489891495,
277
- "count": 1870,
278
- "is_parallel": true,
279
- "self": 0.5612565489891495
280
- },
281
- "communicator.exchange": {
282
- "total": 18.12054548700098,
283
- "count": 1870,
284
- "is_parallel": true,
285
- "self": 18.12054548700098
286
- },
287
- "steps_from_proto": {
288
- "total": 3.430772395995291,
289
- "count": 1870,
290
- "is_parallel": true,
291
- "self": 0.6510793549909977,
292
- "children": {
293
- "_process_rank_one_or_two_observation": {
294
- "total": 2.7796930410042933,
295
- "count": 18700,
296
- "is_parallel": true,
297
- "self": 2.7796930410042933
298
- }
299
- }
300
- }
301
- }
302
- }
303
- }
304
- }
305
- }
306
- }
307
- }
308
- }
309
- }
310
- },
311
- "trainer_threads": {
312
- "total": 0.00023758199995427276,
313
  "count": 1,
314
- "self": 0.00023758199995427276,
315
- "children": {
316
- "thread_root": {
317
- "total": 0.0,
318
- "count": 0,
319
- "is_parallel": true,
320
- "self": 0.0,
321
- "children": {
322
- "trainer_advance": {
323
- "total": 45.66180945898827,
324
- "count": 68162,
325
- "is_parallel": true,
326
- "self": 1.3704156789815443,
327
- "children": {
328
- "process_trajectory": {
329
- "total": 25.389689409007133,
330
- "count": 68162,
331
- "is_parallel": true,
332
- "self": 24.697163631007015,
333
- "children": {
334
- "RLTrainer._checkpoint": {
335
- "total": 0.6925257780001175,
336
- "count": 4,
337
- "is_parallel": true,
338
- "self": 0.6925257780001175
339
- }
340
- }
341
- },
342
- "_update_policy": {
343
- "total": 18.901704370999596,
344
- "count": 9,
345
- "is_parallel": true,
346
- "self": 5.487976478997325,
347
- "children": {
348
- "TorchPPOOptimizer.update": {
349
- "total": 13.413727892002271,
350
- "count": 456,
351
- "is_parallel": true,
352
- "self": 13.413727892002271
353
- }
354
- }
355
- }
356
- }
357
- }
358
- }
359
- }
360
- }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.08797353199997815,
364
  "count": 1,
365
- "self": 0.000934539000127188,
366
- "children": {
367
- "RLTrainer._checkpoint": {
368
- "total": 0.08703899299985096,
369
- "count": 1,
370
- "self": 0.08703899299985096
371
- }
372
- }
373
  }
374
  }
375
  }
 
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
+ "start_time_seconds": "1703604205",
6
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
7
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --run-id=SnowballTarget1 --resume --no-graphics",
8
  "mlagents_version": "1.1.0.dev0",
9
  "mlagents_envs_version": "1.1.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "2.1.2+cu121",
12
  "numpy_version": "1.23.5",
13
+ "end_time_seconds": "1703604266"
14
  },
15
+ "total": 60.23162244000014,
16
  "count": 1,
17
+ "self": 0.03028296800039243,
18
  "children": {
19
  "run_training.setup": {
20
+ "total": 0.051774862999991456,
21
  "count": 1,
22
+ "self": 0.051774862999991456
23
  },
24
  "TrainerController.start_learning": {
25
+ "total": 60.14956460899975,
26
  "count": 1,
27
+ "self": 0.00011823599925264716,
28
  "children": {
29
  "TrainerController._reset_env": {
30
+ "total": 60.14940587700039,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "count": 1,
32
+ "self": 60.14940587700039
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  },
34
  "TrainerController._save_models": {
35
+ "total": 4.049600011057919e-05,
36
  "count": 1,
37
+ "self": 4.049600011057919e-05
 
 
 
 
 
 
 
38
  }
39
  }
40
  }