Hugging Face's logo

darthPanda
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
darthPanda commited on
Commit
a630532
·
verified ·
1 Parent(s): 21b3e22

First Push

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. configuration.yaml +2 -0
  3. run_logs/timers.json +20 -350
  4. run_logs/training_status.json +2 -60
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": 50000, "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": 200000, "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, "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}, "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": 50000, "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": 200000, "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}
configuration.yaml CHANGED
@@ -50,6 +50,7 @@ env_settings:
50
  base_port: 5005
51
  num_envs: 1
52
  num_areas: 1
 
53
  seed: -1
54
  max_lifetime_restarts: 10
55
  restarts_rate_limit_n: 1
@@ -62,6 +63,7 @@ engine_settings:
62
  target_frame_rate: -1
63
  capture_frame_rate: 60
64
  no_graphics: true
 
65
  environment_parameters: null
66
  checkpoint_settings:
67
  run_id: SnowballTarget1
 
50
  base_port: 5005
51
  num_envs: 1
52
  num_areas: 1
53
+ timeout_wait: 60
54
  seed: -1
55
  max_lifetime_restarts: 10
56
  restarts_rate_limit_n: 1
 
63
  target_frame_rate: -1
64
  capture_frame_rate: 60
65
  no_graphics: true
66
+ no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
  run_id: SnowballTarget1
run_logs/timers.json CHANGED
@@ -1,375 +1,45 @@
1
  {
2
  "name": "root",
3
- "gauges": {
4
- "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9262873530387878,
6
- "min": 0.9239082932472229,
7
- "max": 2.8697240352630615,
8
- "count": 20
9
- },
10
- "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8884.9482421875,
12
- "min": 8884.9482421875,
13
- "max": 29451.978515625,
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": 12.910005569458008,
30
- "min": 0.338864266872406,
31
- "max": 12.910005569458008,
32
- "count": 20
33
- },
34
- "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2517.451171875,
36
- "min": 65.73966979980469,
37
- "max": 2606.02783203125,
38
- "count": 20
39
- },
40
- "SnowballTarget.Environment.EpisodeLength.mean": {
41
- "value": 199.0,
42
- "min": 199.0,
43
- "max": 199.0,
44
- "count": 20
45
- },
46
- "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
- "min": 8756.0,
49
- "max": 10945.0,
50
- "count": 20
51
- },
52
- "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06521946081763827,
54
- "min": 0.06160413643031942,
55
- "max": 0.07541242198898294,
56
- "count": 20
57
- },
58
- "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2608778432705531,
60
- "min": 0.2464165457212777,
61
- "max": 0.3657878658222947,
62
- "count": 20
63
- },
64
- "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.21077231748723516,
66
- "min": 0.10733545933252053,
67
- "max": 0.27753121256828306,
68
- "count": 20
69
- },
70
- "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8430892699489406,
72
- "min": 0.42934183733008213,
73
- "max": 1.3876560628414154,
74
- "count": 20
75
- },
76
- "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000005e-06,
78
- "min": 8.082097306000005e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
- },
82
- "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400002e-05,
84
- "min": 3.232838922400002e-05,
85
- "max": 0.00138516003828,
86
- "count": 20
87
- },
88
- "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
- },
94
- "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.96172,
98
- "count": 20
99
- },
100
- "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.0048649706,
104
- "count": 20
105
- },
106
- "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828,
110
- "count": 20
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.863636363636363,
114
- "min": 3.090909090909091,
115
- "max": 25.863636363636363,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1138.0,
120
- "min": 136.0,
121
- "max": 1380.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.863636363636363,
126
- "min": 3.090909090909091,
127
- "max": 25.863636363636363,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1138.0,
132
- "min": 136.0,
133
- "max": 1380.0,
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": "1690710094",
152
- "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
153
- "command_line_arguments": "/home/darth/MLAI-projects/unity_ML_env_rl/envunity/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
- "mlagents_version": "0.31.0.dev0",
155
- "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
- "pytorch_version": "1.11.0+cu102",
158
- "numpy_version": "1.21.2",
159
- "end_time_seconds": "1690710395"
160
  },
161
- "total": 301.2973983959964,
162
  "count": 1,
163
- "self": 0.24279949300398584,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.012102430991944857,
167
  "count": 1,
168
- "self": 0.012102430991944857
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 301.0424964720005,
172
  "count": 1,
173
- "self": 0.4472816170891747,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.1457579050038476,
177
  "count": 1,
178
- "self": 4.1457579050038476
179
- },
180
- "TrainerController.advance": {
181
- "total": 296.32677600091847,
182
- "count": 18205,
183
- "self": 0.21726975301862694,
184
- "children": {
185
- "env_step": {
186
- "total": 296.10950624789984,
187
- "count": 18205,
188
- "self": 210.70691560591513,
189
- "children": {
190
- "SubprocessEnvManager._take_step": {
191
- "total": 85.17109143872221,
192
- "count": 18205,
193
- "self": 1.0946911648643436,
194
- "children": {
195
- "TorchPolicy.evaluate": {
196
- "total": 84.07640027385787,
197
- "count": 18205,
198
- "self": 84.07640027385787
199
- }
200
- }
201
- },
202
- "workers": {
203
- "total": 0.2314992032625014,
204
- "count": 18205,
205
- "self": 0.0,
206
- "children": {
207
- "worker_root": {
208
- "total": 300.3939307623077,
209
- "count": 18205,
210
- "is_parallel": true,
211
- "self": 167.06463586754398,
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": 0.001692421006737277,
221
- "count": 1,
222
- "is_parallel": true,
223
- "self": 0.0004321349988458678,
224
- "children": {
225
- "_process_rank_one_or_two_observation": {
226
- "total": 0.001260286007891409,
227
- "count": 10,
228
- "is_parallel": true,
229
- "self": 0.001260286007891409
230
- }
231
- }
232
- },
233
- "UnityEnvironment.step": {
234
- "total": 0.021032813005149364,
235
- "count": 1,
236
- "is_parallel": true,
237
- "self": 0.0003260369994677603,
238
- "children": {
239
- "UnityEnvironment._generate_step_input": {
240
- "total": 0.00021892199583817273,
241
- "count": 1,
242
- "is_parallel": true,
243
- "self": 0.00021892199583817273
244
- },
245
- "communicator.exchange": {
246
- "total": 0.01946014900750015,
247
- "count": 1,
248
- "is_parallel": true,
249
- "self": 0.01946014900750015
250
- },
251
- "steps_from_proto": {
252
- "total": 0.001027705002343282,
253
- "count": 1,
254
- "is_parallel": true,
255
- "self": 0.00022556701151188463,
256
- "children": {
257
- "_process_rank_one_or_two_observation": {
258
- "total": 0.0008021379908313975,
259
- "count": 10,
260
- "is_parallel": true,
261
- "self": 0.0008021379908313975
262
- }
263
- }
264
- }
265
- }
266
- }
267
- }
268
- },
269
- "UnityEnvironment.step": {
270
- "total": 133.32929489476373,
271
- "count": 18204,
272
- "is_parallel": true,
273
- "self": 5.69056420630659,
274
- "children": {
275
- "UnityEnvironment._generate_step_input": {
276
- "total": 3.2870714761229465,
277
- "count": 18204,
278
- "is_parallel": true,
279
- "self": 3.2870714761229465
280
- },
281
- "communicator.exchange": {
282
- "total": 105.69360468778177,
283
- "count": 18204,
284
- "is_parallel": true,
285
- "self": 105.69360468778177
286
- },
287
- "steps_from_proto": {
288
- "total": 18.658054524552426,
289
- "count": 18204,
290
- "is_parallel": true,
291
- "self": 3.9579579753481084,
292
- "children": {
293
- "_process_rank_one_or_two_observation": {
294
- "total": 14.700096549204318,
295
- "count": 182040,
296
- "is_parallel": true,
297
- "self": 14.700096549204318
298
- }
299
- }
300
- }
301
- }
302
- }
303
- }
304
- }
305
- }
306
- }
307
- }
308
- }
309
- }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011076898954343051,
313
  "count": 1,
314
- "self": 0.00011076898954343051,
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": 295.70782078724005,
324
- "count": 220402,
325
- "is_parallel": true,
326
- "self": 2.8024480845488142,
327
- "children": {
328
- "process_trajectory": {
329
- "total": 158.59546039077395,
330
- "count": 220402,
331
- "is_parallel": true,
332
- "self": 157.94113994776853,
333
- "children": {
334
- "RLTrainer._checkpoint": {
335
- "total": 0.6543204430054175,
336
- "count": 4,
337
- "is_parallel": true,
338
- "self": 0.6543204430054175
339
- }
340
- }
341
- },
342
- "_update_policy": {
343
- "total": 134.3099123119173,
344
- "count": 90,
345
- "is_parallel": true,
346
- "self": 40.4545891147136,
347
- "children": {
348
- "TorchPPOOptimizer.update": {
349
- "total": 93.85532319720369,
350
- "count": 4587,
351
- "is_parallel": true,
352
- "self": 93.85532319720369
353
- }
354
- }
355
- }
356
- }
357
- }
358
- }
359
- }
360
- }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.12257017999945674,
364
  "count": 1,
365
- "self": 0.0008117520046653226,
366
- "children": {
367
- "RLTrainer._checkpoint": {
368
- "total": 0.12175842799479142,
369
- "count": 1,
370
- "self": 0.12175842799479142
371
- }
372
- }
373
  }
374
  }
375
  }
 
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
+ "start_time_seconds": "1705041622",
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 --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1705041623"
14
  },
15
+ "total": 0.2293522939999093,
16
  "count": 1,
17
+ "self": 0.017557923999902414,
18
  "children": {
19
  "run_training.setup": {
20
+ "total": 0.06224575999999615,
21
  "count": 1,
22
+ "self": 0.06224575999999615
23
  },
24
  "TrainerController.start_learning": {
25
+ "total": 0.14954861000001074,
26
  "count": 1,
27
+ "self": 0.0004441789999418688,
28
  "children": {
29
  "TrainerController._reset_env": {
30
+ "total": 0.1490876269999717,
31
  "count": 1,
32
+ "self": 0.1490876269999717
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  },
34
  "trainer_threads": {
35
+ "total": 1.5450000319106039e-06,
36
  "count": 1,
37
+ "self": 1.5450000319106039e-06
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  },
39
  "TrainerController._save_models": {
40
+ "total": 1.525900006527081e-05,
41
  "count": 1,
42
+ "self": 1.525900006527081e-05
 
 
 
 
 
 
 
43
  }
44
  }
45
  }
run_logs/training_status.json CHANGED
@@ -1,65 +1,7 @@
1
  {
2
- "SnowballTarget": {
3
- "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 11.181818181818182,
8
- "creation_time": 1690710173.516804,
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": 22.272727272727273,
17
- "creation_time": 1690710247.6696513,
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": 23.454545454545453,
26
- "creation_time": 1690710321.9218476,
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": 25.727272727272727,
35
- "creation_time": 1690710395.0971208,
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": 25.727272727272727,
44
- "creation_time": 1690710395.2414272,
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": 25.727272727272727,
54
- "creation_time": 1690710395.2414272,
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": "0.31.0.dev0",
63
- "torch_version": "1.11.0+cu102"
64
  }
65
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "metadata": {
3
  "stats_format_version": "0.3.0",
4
+ "mlagents_version": "1.1.0.dev0",
5
+ "torch_version": "2.1.2+cu121"
6
  }
7
  }