Hugging Face's logo

hivex-research
/
hivex-WFC-PPO-baseline-task-0-pattern-3

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-wind-farm-control
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community
philippds commited on
Commit
f09e11d
•
1 Parent(s): 7b00fc7

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.1715313111.RICHARD.35628.0 +3 -0
  14. README.md +29 -0
  15. configuration.yaml +94 -0
  16. run_logs/timers.json +371 -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:b8d8c90d11829a1178b1f273112a35dd228492327e43a51a2f01caa39caf09c7
3
+ size 21336
Agent/Agent-6498432.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993bd9e468ed7f5e5f0d81efa796d44274fdbacc183173c6533c0a2137e2b38b
3
+ size 21336
Agent/Agent-6498432.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8564154394bcb129d2a19e9367dfc029a2b337b358e28d4909235758d881e618
3
+ size 129607
Agent/Agent-6999096.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca30ae733d585327f68845b00a403818d1b20833ed99db8ff2dfa8246ef72e8
3
+ size 21336
Agent/Agent-6999096.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b075e1b67ae4b55850421f5fb28b57e5b889a39ec64abb7502ff9c89e834922
3
+ size 129607
Agent/Agent-7498432.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074c4e005344cf871a6a8d456909cdeb180cf467dc7de85933199131c5b907b2
3
+ size 21336
Agent/Agent-7498432.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd669bd7e7d1359c93fdec11c710629761bc4f16c431815ec22f749c3c9fe49f
3
+ size 129607
Agent/Agent-7999096.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0f280ce56cf87c49ff78afb22883ae5727eb242b924a21ff30a45ca79e2d1c
3
+ size 21336
Agent/Agent-7999096.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4c917c029fc730abd6478b9bcf7ced2cc226151cfb801895662ce4aac71f53
3
+ size 129607
Agent/Agent-8016384.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d8c90d11829a1178b1f273112a35dd228492327e43a51a2f01caa39caf09c7
3
+ size 21336
Agent/Agent-8016384.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ded99f9add99863e371d9919a801cf912790bf241ce77ceea1a7571becbc82
3
+ size 129607
Agent/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ded99f9add99863e371d9919a801cf912790bf241ce77ceea1a7571becbc82
3
+ size 129607
Agent/events.out.tfevents.1715313111.RICHARD.35628.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c00006176af591623a512be4f90af1f0754d69c5af933087597c229eba9b5ed2
3
+ size 231447
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: hivex
3
+ original_train_name: WindFarmControl_pattern_3_task_0_run_id_2_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-0-pattern-3
11
+ results:
12
+ - task:
13
+ type: main-task
14
+ name: main_task
15
+ task-id: 0
16
+ pattern-id: 3
17
+ dataset:
18
+ name: hivex-wind-farm-control
19
+ type: hivex-wind-farm-control
20
+ metrics:
21
+ - type: cumulative_reward
22
+ value: 4601.440402832031 +/- 41.81579798428404
23
+ name: Cumulative Reward
24
+ verified: true
25
+ - type: individual_performance
26
+ value: 4601.383317871094 +/- 41.655823555724716
27
+ name: Individual Performance
28
+ verified: true
29
+ ---
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: 3
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: 0
81
+ name: task
82
+ completion_criteria: null
83
+ checkpoint_settings:
84
+ run_id: WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_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 +1,371 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Agent.Policy.Entropy.mean": {
5
+ "value": 1.0409033298492432,
6
+ "min": 0.8868308663368225,
7
+ "max": 1.0960010290145874,
8
+ "count": 200
9
+ },
10
+ "Agent.Policy.Entropy.sum": {
11
+ "value": 41619.4765625,
12
+ "min": 35473.234375,
13
+ "max": 43916.14453125,
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": 9.20212173461914,
54
+ "min": 0.31864607334136963,
55
+ "max": 9.59177303314209,
56
+ "count": 200
57
+ },
58
+ "Agent.Policy.ExtrinsicValueEstimate.sum": {
59
+ "value": 220.85092163085938,
60
+ "min": 7.647505760192871,
61
+ "max": 230.20254516601562,
62
+ "count": 200
63
+ },
64
+ "Agent.Losses.PolicyLoss.mean": {
65
+ "value": 0.048751471053586265,
66
+ "min": 0.044550919785771324,
67
+ "max": 0.05530484307174837,
68
+ "count": 200
69
+ },
70
+ "Agent.Losses.PolicyLoss.sum": {
71
+ "value": 0.1462544131607588,
72
+ "min": 0.1022773164731916,
73
+ "max": 0.1659145292152451,
74
+ "count": 200
75
+ },
76
+ "Agent.Losses.ValueLoss.mean": {
77
+ "value": 0.23453213936152187,
78
+ "min": 0.0719803709279014,
79
+ "max": 1.5479311684612185,
80
+ "count": 200
81
+ },
82
+ "Agent.Losses.ValueLoss.sum": {
83
+ "value": 0.7035964180845656,
84
+ "min": 0.2159411127837042,
85
+ "max": 3.095862336922437,
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": 4557.384582519531,
138
+ "min": 122.8925666809082,
139
+ "max": 4710.6898193359375,
140
+ "count": 200
141
+ },
142
+ "Agent.WindFarmControl.IndividualPerformance.sum": {
143
+ "value": 36459.07666015625,
144
+ "min": 983.1405334472656,
145
+ "max": 37685.5185546875,
146
+ "count": 200
147
+ },
148
+ "Agent.Environment.CumulativeReward.mean": {
149
+ "value": 4557.195991516113,
150
+ "min": 202.63095023233856,
151
+ "max": 4692.5495681762695,
152
+ "count": 200
153
+ },
154
+ "Agent.Environment.CumulativeReward.sum": {
155
+ "value": 36457.567932128906,
156
+ "min": 1621.0476018587085,
157
+ "max": 37540.396545410156,
158
+ "count": 200
159
+ },
160
+ "Agent.Policy.ExtrinsicReward.mean": {
161
+ "value": 4557.195991516113,
162
+ "min": 202.63095023233856,
163
+ "max": 4692.5495681762695,
164
+ "count": 200
165
+ },
166
+ "Agent.Policy.ExtrinsicReward.sum": {
167
+ "value": 36457.567932128906,
168
+ "min": 1621.0476018587085,
169
+ "max": 37540.396545410156,
170
+ "count": 200
171
+ },
172
+ "Agent.IsTraining.mean": {
173
+ "value": 1.0,
174
+ "min": 1.0,
175
+ "max": 1.0,
176
+ "count": 200
177
+ },
178
+ "Agent.IsTraining.sum": {
179
+ "value": 1.0,
180
+ "min": 1.0,
181
+ "max": 1.0,
182
+ "count": 200
183
+ }
184
+ },
185
+ "metadata": {
186
+ "timer_format_version": "0.1.0",
187
+ "start_time_seconds": "1715313110",
188
+ "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]",
189
+ "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_3_task_0_run_id_2_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train",
190
+ "mlagents_version": "0.30.0",
191
+ "mlagents_envs_version": "0.30.0",
192
+ "communication_protocol_version": "1.5.0",
193
+ "pytorch_version": "1.7.1+cu110",
194
+ "numpy_version": "1.21.2",
195
+ "end_time_seconds": "1715317094"
196
+ },
197
+ "total": 3983.6268083,
198
+ "count": 1,
199
+ "self": 0.16800579999971887,
200
+ "children": {
201
+ "run_training.setup": {
202
+ "total": 0.04410550000000002,
203
+ "count": 1,
204
+ "self": 0.04410550000000002
205
+ },
206
+ "TrainerController.start_learning": {
207
+ "total": 3983.414697,
208
+ "count": 1,
209
+ "self": 10.942567499989764,
210
+ "children": {
211
+ "TrainerController._reset_env": {
212
+ "total": 1.5842729999999998,
213
+ "count": 1,
214
+ "self": 1.5842729999999998
215
+ },
216
+ "TrainerController.advance": {
217
+ "total": 3970.8617668000106,
218
+ "count": 1002054,
219
+ "self": 10.15688780010123,
220
+ "children": {
221
+ "env_step": {
222
+ "total": 3960.7048789999094,
223
+ "count": 1002054,
224
+ "self": 1725.1658909998637,
225
+ "children": {
226
+ "SubprocessEnvManager._take_step": {
227
+ "total": 2229.6549187,
228
+ "count": 1002054,
229
+ "self": 26.851314100124455,
230
+ "children": {
231
+ "TorchPolicy.evaluate": {
232
+ "total": 2202.8036045998756,
233
+ "count": 1002054,
234
+ "self": 2202.8036045998756
235
+ }
236
+ }
237
+ },
238
+ "workers": {
239
+ "total": 5.884069300045666,
240
+ "count": 1002054,
241
+ "self": 0.0,
242
+ "children": {
243
+ "worker_root": {
244
+ "total": 3966.2432604999185,
245
+ "count": 1002054,
246
+ "is_parallel": true,
247
+ "self": 2928.1238765997914,
248
+ "children": {
249
+ "steps_from_proto": {
250
+ "total": 0.00024860000000004323,
251
+ "count": 1,
252
+ "is_parallel": true,
253
+ "self": 0.00011319999999992447,
254
+ "children": {
255
+ "_process_rank_one_or_two_observation": {
256
+ "total": 0.00013540000000011876,
257
+ "count": 2,
258
+ "is_parallel": true,
259
+ "self": 0.00013540000000011876
260
+ }
261
+ }
262
+ },
263
+ "UnityEnvironment.step": {
264
+ "total": 1038.1191353001273,
265
+ "count": 1002054,
266
+ "is_parallel": true,
267
+ "self": 56.099828800254954,
268
+ "children": {
269
+ "UnityEnvironment._generate_step_input": {
270
+ "total": 87.8952539999766,
271
+ "count": 1002054,
272
+ "is_parallel": true,
273
+ "self": 87.8952539999766
274
+ },
275
+ "communicator.exchange": {
276
+ "total": 740.9766173999612,
277
+ "count": 1002054,
278
+ "is_parallel": true,
279
+ "self": 740.9766173999612
280
+ },
281
+ "steps_from_proto": {
282
+ "total": 153.14743509993448,
283
+ "count": 1002054,
284
+ "is_parallel": true,
285
+ "self": 85.87956910008882,
286
+ "children": {
287
+ "_process_rank_one_or_two_observation": {
288
+ "total": 67.26786599984567,
289
+ "count": 2004108,
290
+ "is_parallel": true,
291
+ "self": 67.26786599984567
292
+ }
293
+ }
294
+ }
295
+ }
296
+ }
297
+ }
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ },
305
+ "trainer_threads": {
306
+ "total": 2.1500000002561137e-05,
307
+ "count": 1,
308
+ "self": 2.1500000002561137e-05,
309
+ "children": {
310
+ "thread_root": {
311
+ "total": 0.0,
312
+ "count": 0,
313
+ "is_parallel": true,
314
+ "self": 0.0,
315
+ "children": {
316
+ "trainer_advance": {
317
+ "total": 3980.866350599922,
318
+ "count": 118021,
319
+ "is_parallel": true,
320
+ "self": 4.689097199971911,
321
+ "children": {
322
+ "process_trajectory": {
323
+ "total": 2065.4026606999523,
324
+ "count": 118021,
325
+ "is_parallel": true,
326
+ "self": 2064.9446620999524,
327
+ "children": {
328
+ "RLTrainer._checkpoint": {
329
+ "total": 0.4579985999997689,
330
+ "count": 16,
331
+ "is_parallel": true,
332
+ "self": 0.4579985999997689
333
+ }
334
+ }
335
+ },
336
+ "_update_policy": {
337
+ "total": 1910.7745926999978,
338
+ "count": 600,
339
+ "is_parallel": true,
340
+ "self": 573.8176353000254,
341
+ "children": {
342
+ "TorchPPOOptimizer.update": {
343
+ "total": 1336.9569573999725,
344
+ "count": 93600,
345
+ "is_parallel": true,
346
+ "self": 1336.9569573999725
347
+ }
348
+ }
349
+ }
350
+ }
351
+ }
352
+ }
353
+ }
354
+ }
355
+ },
356
+ "TrainerController._save_models": {
357
+ "total": 0.026068199999826902,
358
+ "count": 1,
359
+ "self": 0.004728699999759556,
360
+ "children": {
361
+ "RLTrainer._checkpoint": {
362
+ "total": 0.021339500000067346,
363
+ "count": 1,
364
+ "self": 0.021339500000067346
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ }
371
+ }
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_3_task_0_run_id_2_train\\Agent\\Agent-6498432.onnx",
13
+ "reward": null,
14
+ "creation_time": 1715316345.1963308,
15
+ "auxillary_file_paths": [
16
+ "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-6498432.pt"
17
+ ]
18
+ },
19
+ {
20
+ "steps": 6999096,
21
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-6999096.onnx",
22
+ "reward": 4505.438816615513,
23
+ "creation_time": 1715316589.2661247,
24
+ "auxillary_file_paths": [
25
+ "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-6999096.pt"
26
+ ]
27
+ },
28
+ {
29
+ "steps": 7498432,
30
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-7498432.onnx",
31
+ "reward": null,
32
+ "creation_time": 1715316843.063557,
33
+ "auxillary_file_paths": [
34
+ "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-7498432.pt"
35
+ ]
36
+ },
37
+ {
38
+ "steps": 7999096,
39
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-7999096.onnx",
40
+ "reward": 4557.173767089844,
41
+ "creation_time": 1715317086.8121157,
42
+ "auxillary_file_paths": [
43
+ "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-7999096.pt"
44
+ ]
45
+ },
46
+ {
47
+ "steps": 8016384,
48
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-8016384.onnx",
49
+ "reward": null,
50
+ "creation_time": 1715317093.8926163,
51
+ "auxillary_file_paths": [
52
+ "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent\\Agent-8016384.pt"
53
+ ]
54
+ }
55
+ ],
56
+ "final_checkpoint": {
57
+ "steps": 8016384,
58
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_train\\Agent.onnx",
59
+ "reward": null,
60
+ "creation_time": 1715317093.8926163,
61
+ "auxillary_file_paths": [
62
+ "results\\WindFarmControl/train/WindFarmControl_pattern_3_task_0_run_id_2_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
+ }