Hugging Face's logo

hivex-research
/
hivex-WFC-PPO-baseline-task-1-pattern-6

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-wind-farm-control
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community
philippds commited on
Commit
1d9d8be
•
1 Parent(s): a3f8a72

Upload 17 files

Browse files
Files changed (17) hide show
  1. Agent.onnx +3 -0
  2. Agent/Agent-6498432.onnx +3 -0
  3. Agent/Agent-6498432.pt +3 -0
  4. Agent/Agent-6999096.onnx +3 -0
  5. Agent/Agent-6999096.pt +3 -0
  6. Agent/Agent-7498432.onnx +3 -0
  7. Agent/Agent-7498432.pt +3 -0
  8. Agent/Agent-7999096.onnx +3 -0
  9. Agent/Agent-7999096.pt +3 -0
  10. Agent/Agent-8016384.onnx +3 -0
  11. Agent/Agent-8016384.pt +3 -0
  12. Agent/checkpoint.pt +3 -0
  13. Agent/events.out.tfevents.1715269262.RICHARD.35156.0 +3 -0
  14. README.md +33 -0
  15. configuration.yaml +94 -0
  16. run_logs/timers.json +383 -0
  17. run_logs/training_status.json +71 -0
Agent.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7a1673c9beddcfb552612c202556f47a7b7b63dfa79ceef356ef701039c378
3
+ size 21336
Agent/Agent-6498432.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54354b34ab25b2bc0fb2942e6128ce0cbfbb1fd649654042f70e1c947598dbfa
3
+ size 21336
Agent/Agent-6498432.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e90c96d7fedd999e0f1b7261044d16965639073ece903b191a45e944008f7fa0
3
+ size 129607
Agent/Agent-6999096.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44076e4b1cbbc6e1f584f848bb8cf4d95bdcc593c11fc75b2da611fd8447723b
3
+ size 21336
Agent/Agent-6999096.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb33251a00e3e54ccac7bae96382f057ee2a8413a9a7861aa3210ac22b274c0
3
+ size 129607
Agent/Agent-7498432.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582917e9534bed4450b314398942f7d955ba4df39e6d0a236cf233a095fe15f1
3
+ size 21336
Agent/Agent-7498432.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8322329bfc845a4cb50e89773190d59ae551bab9446b8a5392338320173bf3d8
3
+ size 129607
Agent/Agent-7999096.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7959841e38eeea7023af7cae17e3a22baee5f70e3d7e52ef861a1b6aab7b22
3
+ size 21336
Agent/Agent-7999096.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec76d94680a248ba101483aec9048d4e4e850d49e281d940da3a60ff38d70b7
3
+ size 129607
Agent/Agent-8016384.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7a1673c9beddcfb552612c202556f47a7b7b63dfa79ceef356ef701039c378
3
+ size 21336
Agent/Agent-8016384.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293da803a2dd6379fd4823b54bd823c46ff3fdeefc5397fe85e39db7057fd97b
3
+ size 129607
Agent/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293da803a2dd6379fd4823b54bd823c46ff3fdeefc5397fe85e39db7057fd97b
3
+ size 129607
Agent/events.out.tfevents.1715269262.RICHARD.35156.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae3d6bb07167c0c3a5d43aa39f111e55bed845dfae1d32a78f478e82ad7a9e2
3
+ size 220108
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: hivex
3
+ original_train_name: WindFarmControl_pattern_6_task_1_run_id_1_train
4
+ tags:
5
+ - hivex
6
+ - hivex-wind-farm-control
7
+ - reinforcement-learning
8
+ - multi-agent-reinforcement-learning
9
+ model-index:
10
+ - name: hivex-WFC-PPO-baseline-task-1-pattern-6
11
+ results:
12
+ - task:
13
+ type: sub-task
14
+ name: avoid_damage
15
+ task-id: 1
16
+ pattern-id: 6
17
+ dataset:
18
+ name: hivex-wind-farm-control
19
+ type: hivex-wind-farm-control
20
+ metrics:
21
+ - type: cumulative_reward
22
+ value: 4821.655510253906 +/- 37.888594391723174
23
+ name: Cumulative Reward
24
+ verified: true
25
+ - type: avoid_damage_reward
26
+ value: 4821.617194824219 +/- 38.82408699722769
27
+ name: Avoid Damage Reward
28
+ verified: true
29
+ - type: individual_performance
30
+ value: 0.0 +/- 0.0
31
+ name: Individual Performance
32
+ verified: true
33
+ ---
configuration.yaml ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Agent:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 256
7
+ buffer_size: 2048
8
+ learning_rate: 0.0003
9
+ beta: 0.005
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 3
13
+ shared_critic: false
14
+ learning_rate_schedule: linear
15
+ beta_schedule: linear
16
+ epsilon_schedule: linear
17
+ network_settings:
18
+ normalize: false
19
+ hidden_units: 64
20
+ num_layers: 2
21
+ vis_encode_type: simple
22
+ memory: null
23
+ goal_conditioning_type: hyper
24
+ deterministic: false
25
+ reward_signals:
26
+ extrinsic:
27
+ gamma: 0.9
28
+ strength: 1.0
29
+ network_settings:
30
+ normalize: false
31
+ hidden_units: 128
32
+ num_layers: 2
33
+ vis_encode_type: simple
34
+ memory: null
35
+ goal_conditioning_type: hyper
36
+ deterministic: false
37
+ init_path: null
38
+ keep_checkpoints: 5
39
+ checkpoint_interval: 500000
40
+ max_steps: 8000000
41
+ time_horizon: 2048
42
+ summary_freq: 40000
43
+ threaded: true
44
+ self_play: null
45
+ behavioral_cloning: null
46
+ env_settings:
47
+ env_path: c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/dev_environments/Hivex_WindFarmControl_win
48
+ env_args: null
49
+ base_port: 5005
50
+ num_envs: 1
51
+ num_areas: 1
52
+ seed: 5000
53
+ max_lifetime_restarts: 10
54
+ restarts_rate_limit_n: 1
55
+ restarts_rate_limit_period_s: 60
56
+ engine_settings:
57
+ width: 84
58
+ height: 84
59
+ quality_level: 5
60
+ time_scale: 20
61
+ target_frame_rate: -1
62
+ capture_frame_rate: 60
63
+ no_graphics: true
64
+ environment_parameters:
65
+ pattern:
66
+ curriculum:
67
+ - value:
68
+ sampler_type: constant
69
+ sampler_parameters:
70
+ seed: 5000
71
+ value: 6
72
+ name: pattern
73
+ completion_criteria: null
74
+ task:
75
+ curriculum:
76
+ - value:
77
+ sampler_type: constant
78
+ sampler_parameters:
79
+ seed: 5001
80
+ value: 1
81
+ name: task
82
+ completion_criteria: null
83
+ checkpoint_settings:
84
+ run_id: WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train
85
+ initialize_from: null
86
+ load_model: false
87
+ resume: false
88
+ force: false
89
+ train_model: false
90
+ inference: false
91
+ results_dir: results
92
+ torch_settings:
93
+ device: null
94
+ debug: false
run_logs/timers.json ADDED
@@ -0,0 +1,383 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Agent.Policy.Entropy.mean": {
5
+ "value": 0.790346086025238,
6
+ "min": 0.7343851327896118,
7
+ "max": 1.096280813217163,
8
+ "count": 200
9
+ },
10
+ "Agent.Policy.Entropy.sum": {
11
+ "value": 31613.84375,
12
+ "min": 29387.15625,
13
+ "max": 43931.8515625,
14
+ "count": 200
15
+ },
16
+ "Agent.Environment.LessonNumber.pattern.mean": {
17
+ "value": 0.0,
18
+ "min": 0.0,
19
+ "max": 0.0,
20
+ "count": 200
21
+ },
22
+ "Agent.Environment.LessonNumber.pattern.sum": {
23
+ "value": 0.0,
24
+ "min": 0.0,
25
+ "max": 0.0,
26
+ "count": 200
27
+ },
28
+ "Agent.Environment.LessonNumber.task.mean": {
29
+ "value": 0.0,
30
+ "min": 0.0,
31
+ "max": 0.0,
32
+ "count": 200
33
+ },
34
+ "Agent.Environment.LessonNumber.task.sum": {
35
+ "value": 0.0,
36
+ "min": 0.0,
37
+ "max": 0.0,
38
+ "count": 200
39
+ },
40
+ "Agent.Step.mean": {
41
+ "value": 7999096.0,
42
+ "min": 39096.0,
43
+ "max": 7999096.0,
44
+ "count": 200
45
+ },
46
+ "Agent.Step.sum": {
47
+ "value": 7999096.0,
48
+ "min": 39096.0,
49
+ "max": 7999096.0,
50
+ "count": 200
51
+ },
52
+ "Agent.Policy.ExtrinsicValueEstimate.mean": {
53
+ "value": 9.780200004577637,
54
+ "min": 2.4280426502227783,
55
+ "max": 9.820754051208496,
56
+ "count": 200
57
+ },
58
+ "Agent.Policy.ExtrinsicValueEstimate.sum": {
59
+ "value": 234.72479248046875,
60
+ "min": 55.84497833251953,
61
+ "max": 235.69810485839844,
62
+ "count": 200
63
+ },
64
+ "Agent.Losses.PolicyLoss.mean": {
65
+ "value": 0.04866604715246625,
66
+ "min": 0.04545393447545986,
67
+ "max": 0.05493653173690536,
68
+ "count": 200
69
+ },
70
+ "Agent.Losses.PolicyLoss.sum": {
71
+ "value": 0.14599814145739876,
72
+ "min": 0.10218151656833166,
73
+ "max": 0.1648095952107161,
74
+ "count": 200
75
+ },
76
+ "Agent.Losses.ValueLoss.mean": {
77
+ "value": 0.003906352770591473,
78
+ "min": 0.002974676047400978,
79
+ "max": 3.8673377021526294,
80
+ "count": 200
81
+ },
82
+ "Agent.Losses.ValueLoss.sum": {
83
+ "value": 0.011719058311774418,
84
+ "min": 0.008924028142202934,
85
+ "max": 10.25289195190583,
86
+ "count": 200
87
+ },
88
+ "Agent.Policy.LearningRate.mean": {
89
+ "value": 8.856997047999973e-07,
90
+ "min": 8.856997047999973e-07,
91
+ "max": 0.00029907840030719997,
92
+ "count": 200
93
+ },
94
+ "Agent.Policy.LearningRate.sum": {
95
+ "value": 2.657099114399992e-06,
96
+ "min": 2.657099114399992e-06,
97
+ "max": 0.0008936568021144,
98
+ "count": 200
99
+ },
100
+ "Agent.Policy.Epsilon.mean": {
101
+ "value": 0.10029520000000001,
102
+ "min": 0.10029520000000001,
103
+ "max": 0.1996928,
104
+ "count": 200
105
+ },
106
+ "Agent.Policy.Epsilon.sum": {
107
+ "value": 0.30088560000000003,
108
+ "min": 0.30088560000000003,
109
+ "max": 0.5978856,
110
+ "count": 200
111
+ },
112
+ "Agent.Policy.Beta.mean": {
113
+ "value": 2.4730479999999958e-05,
114
+ "min": 2.4730479999999958e-05,
115
+ "max": 0.004984670720000001,
116
+ "count": 200
117
+ },
118
+ "Agent.Policy.Beta.sum": {
119
+ "value": 7.419143999999988e-05,
120
+ "min": 7.419143999999988e-05,
121
+ "max": 0.014894491440000001,
122
+ "count": 200
123
+ },
124
+ "Agent.Environment.EpisodeLength.mean": {
125
+ "value": 4999.0,
126
+ "min": 4999.0,
127
+ "max": 4999.0,
128
+ "count": 200
129
+ },
130
+ "Agent.Environment.EpisodeLength.sum": {
131
+ "value": 39992.0,
132
+ "min": 39992.0,
133
+ "max": 39992.0,
134
+ "count": 200
135
+ },
136
+ "Agent.WindFarmControl.IndividualPerformance.mean": {
137
+ "value": 0.0,
138
+ "min": 0.0,
139
+ "max": 0.0,
140
+ "count": 200
141
+ },
142
+ "Agent.WindFarmControl.IndividualPerformance.sum": {
143
+ "value": 0.0,
144
+ "min": 0.0,
145
+ "max": 0.0,
146
+ "count": 200
147
+ },
148
+ "Agent.WindFarmControl.AvoidDamageReward.mean": {
149
+ "value": 4875.396667480469,
150
+ "min": 1677.5268249511719,
151
+ "max": 4897.457214355469,
152
+ "count": 200
153
+ },
154
+ "Agent.WindFarmControl.AvoidDamageReward.sum": {
155
+ "value": 39003.17333984375,
156
+ "min": 13420.214599609375,
157
+ "max": 39179.65771484375,
158
+ "count": 200
159
+ },
160
+ "Agent.Environment.CumulativeReward.mean": {
161
+ "value": 4857.6708984375,
162
+ "min": 1789.2040557861328,
163
+ "max": 4891.219200134277,
164
+ "count": 200
165
+ },
166
+ "Agent.Environment.CumulativeReward.sum": {
167
+ "value": 38861.3671875,
168
+ "min": 14313.632446289062,
169
+ "max": 39129.75360107422,
170
+ "count": 200
171
+ },
172
+ "Agent.Policy.ExtrinsicReward.mean": {
173
+ "value": 4857.6708984375,
174
+ "min": 1789.2040557861328,
175
+ "max": 4891.219200134277,
176
+ "count": 200
177
+ },
178
+ "Agent.Policy.ExtrinsicReward.sum": {
179
+ "value": 38861.3671875,
180
+ "min": 14313.632446289062,
181
+ "max": 39129.75360107422,
182
+ "count": 200
183
+ },
184
+ "Agent.IsTraining.mean": {
185
+ "value": 1.0,
186
+ "min": 1.0,
187
+ "max": 1.0,
188
+ "count": 200
189
+ },
190
+ "Agent.IsTraining.sum": {
191
+ "value": 1.0,
192
+ "min": 1.0,
193
+ "max": 1.0,
194
+ "count": 200
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1715269261",
200
+ "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]",
201
+ "command_line_arguments": "C:\\Users\\pdsie\\anaconda3\\envs\\mlagents20\\Scripts\\mlagents-learn c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/configs/mlagents/tmp/train/WindFarmControl_pattern_6_task_1_run_id_1_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train",
202
+ "mlagents_version": "0.30.0",
203
+ "mlagents_envs_version": "0.30.0",
204
+ "communication_protocol_version": "1.5.0",
205
+ "pytorch_version": "1.7.1+cu110",
206
+ "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1715273193"
208
+ },
209
+ "total": 3932.1076965,
210
+ "count": 1,
211
+ "self": 0.2694571000001815,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.057912399999999975,
215
+ "count": 1,
216
+ "self": 0.057912399999999975
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 3931.780327,
220
+ "count": 1,
221
+ "self": 11.143726699908257,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 1.6015077999999998,
225
+ "count": 1,
226
+ "self": 1.6015077999999998
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 3919.008560400092,
230
+ "count": 1002053,
231
+ "self": 10.426466300008997,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 3908.582094100083,
235
+ "count": 1002053,
236
+ "self": 1664.7135692999927,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 2237.3401259001093,
240
+ "count": 1002053,
241
+ "self": 28.281610000073215,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 2209.058515900036,
245
+ "count": 1002053,
246
+ "self": 2209.058515900036
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 6.528398899980708,
252
+ "count": 1002053,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 3916.478589399937,
257
+ "count": 1002053,
258
+ "is_parallel": true,
259
+ "self": 2935.2456467999436,
260
+ "children": {
261
+ "steps_from_proto": {
262
+ "total": 0.00024140000000005823,
263
+ "count": 1,
264
+ "is_parallel": true,
265
+ "self": 0.00011190000000005362,
266
+ "children": {
267
+ "_process_rank_one_or_two_observation": {
268
+ "total": 0.0001295000000000046,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.0001295000000000046
272
+ }
273
+ }
274
+ },
275
+ "UnityEnvironment.step": {
276
+ "total": 981.2327011999935,
277
+ "count": 1002053,
278
+ "is_parallel": true,
279
+ "self": 52.88822529990375,
280
+ "children": {
281
+ "UnityEnvironment._generate_step_input": {
282
+ "total": 86.6870290998966,
283
+ "count": 1002053,
284
+ "is_parallel": true,
285
+ "self": 86.6870290998966
286
+ },
287
+ "communicator.exchange": {
288
+ "total": 696.799883800111,
289
+ "count": 1002053,
290
+ "is_parallel": true,
291
+ "self": 696.799883800111
292
+ },
293
+ "steps_from_proto": {
294
+ "total": 144.85756300008217,
295
+ "count": 1002053,
296
+ "is_parallel": true,
297
+ "self": 81.40976620002975,
298
+ "children": {
299
+ "_process_rank_one_or_two_observation": {
300
+ "total": 63.447796800052416,
301
+ "count": 2004106,
302
+ "is_parallel": true,
303
+ "self": 63.447796800052416
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "trainer_threads": {
318
+ "total": 2.189999986512703e-05,
319
+ "count": 1,
320
+ "self": 2.189999986512703e-05,
321
+ "children": {
322
+ "thread_root": {
323
+ "total": 0.0,
324
+ "count": 0,
325
+ "is_parallel": true,
326
+ "self": 0.0,
327
+ "children": {
328
+ "trainer_advance": {
329
+ "total": 3929.2400280000875,
330
+ "count": 110669,
331
+ "is_parallel": true,
332
+ "self": 4.825245700135383,
333
+ "children": {
334
+ "process_trajectory": {
335
+ "total": 1952.6322472999582,
336
+ "count": 110669,
337
+ "is_parallel": true,
338
+ "self": 1952.1611276999586,
339
+ "children": {
340
+ "RLTrainer._checkpoint": {
341
+ "total": 0.471119599999696,
342
+ "count": 16,
343
+ "is_parallel": true,
344
+ "self": 0.471119599999696
345
+ }
346
+ }
347
+ },
348
+ "_update_policy": {
349
+ "total": 1971.7825349999937,
350
+ "count": 600,
351
+ "is_parallel": true,
352
+ "self": 580.4958276999798,
353
+ "children": {
354
+ "TorchPPOOptimizer.update": {
355
+ "total": 1391.2867073000139,
356
+ "count": 93600,
357
+ "is_parallel": true,
358
+ "self": 1391.2867073000139
359
+ }
360
+ }
361
+ }
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ },
368
+ "TrainerController._save_models": {
369
+ "total": 0.026510199999847828,
370
+ "count": 1,
371
+ "self": 0.005493799999840121,
372
+ "children": {
373
+ "RLTrainer._checkpoint": {
374
+ "total": 0.021016400000007707,
375
+ "count": 1,
376
+ "self": 0.021016400000007707
377
+ }
378
+ }
379
+ }
380
+ }
381
+ }
382
+ }
383
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pattern": {
3
+ "lesson_num": 0
4
+ },
5
+ "task": {
6
+ "lesson_num": 0
7
+ },
8
+ "Agent": {
9
+ "checkpoints": [
10
+ {
11
+ "steps": 6498432,
12
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-6498432.onnx",
13
+ "reward": null,
14
+ "creation_time": 1715272454.7673135,
15
+ "auxillary_file_paths": [
16
+ "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-6498432.pt"
17
+ ]
18
+ },
19
+ {
20
+ "steps": 6999096,
21
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-6999096.onnx",
22
+ "reward": 4871.915178571428,
23
+ "creation_time": 1715272695.0572176,
24
+ "auxillary_file_paths": [
25
+ "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-6999096.pt"
26
+ ]
27
+ },
28
+ {
29
+ "steps": 7498432,
30
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-7498432.onnx",
31
+ "reward": null,
32
+ "creation_time": 1715272945.6158335,
33
+ "auxillary_file_paths": [
34
+ "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-7498432.pt"
35
+ ]
36
+ },
37
+ {
38
+ "steps": 7999096,
39
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-7999096.onnx",
40
+ "reward": 4867.69091796875,
41
+ "creation_time": 1715273186.1384902,
42
+ "auxillary_file_paths": [
43
+ "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-7999096.pt"
44
+ ]
45
+ },
46
+ {
47
+ "steps": 8016384,
48
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-8016384.onnx",
49
+ "reward": null,
50
+ "creation_time": 1715273192.9905708,
51
+ "auxillary_file_paths": [
52
+ "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-8016384.pt"
53
+ ]
54
+ }
55
+ ],
56
+ "final_checkpoint": {
57
+ "steps": 8016384,
58
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent.onnx",
59
+ "reward": null,
60
+ "creation_time": 1715273192.9905708,
61
+ "auxillary_file_paths": [
62
+ "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train\\Agent\\Agent-8016384.pt"
63
+ ]
64
+ }
65
+ },
66
+ "metadata": {
67
+ "stats_format_version": "0.3.0",
68
+ "mlagents_version": "0.30.0",
69
+ "torch_version": "1.7.1+cu110"
70
+ }
71
+ }