Hugging Face's logo

hivex-research
/
hivex-WFC-PPO-baseline-task-0-pattern-8

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-wind-farm-control
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community
philippds commited on
Commit
289888b
•
1 Parent(s): 43fef10

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.1716278151.RICHARD.27752.0 +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 sha256:29f896243696666aa728a46b529d06981f98f78ec743e5c0b616c53349b0553a
3
+ size 21336
Agent/Agent-6498432.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ccd712f943f2c9ef22abb1339ced39e78f751458d07a85bc4e878acff33e816
3
+ size 21336
Agent/Agent-6498432.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d7c312246ffe187b1dba0284d4d17d6c480f4624db79199f9b74c0534d44e1
3
+ size 129607
Agent/Agent-6999096.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7c8cd9deea0e3514c9530f1f32f1799c6ade89bdc96105078064dca976c6a1c
3
+ size 21336
Agent/Agent-6999096.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198ee14cd9e0bc606411ef6eb1c68722678dab23688a2d2734e50dd295df6ca1
3
+ size 129607
Agent/Agent-7498432.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486ac21a8094f6c4a792c3c8f0a9fb1aea55a73552d79cedba0defb36e523158
3
+ size 21336
Agent/Agent-7498432.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8948a4a76063f4c2f079a75c82599e45ffd2d48265f354a6922bf672f4eb099
3
+ size 129607
Agent/Agent-7999096.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48b53006f1b0be627ed7161c8c4655f86d5f027614ae2b44b5f3e33da0bf264
3
+ size 21336
Agent/Agent-7999096.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a99aeb95f60055e2529b829a73877271c240ecbc9affff67fb8bef0b4c332d1
3
+ size 129607
Agent/Agent-8016384.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f896243696666aa728a46b529d06981f98f78ec743e5c0b616c53349b0553a
3
+ size 21336
Agent/Agent-8016384.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e528377e67b949bf0a68a2f2b58cb0a1cfd7ec4ff55132e7dc0259f34b66b666
3
+ size 129607
Agent/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e528377e67b949bf0a68a2f2b58cb0a1cfd7ec4ff55132e7dc0259f34b66b666
3
+ size 129607
Agent/events.out.tfevents.1716278151.RICHARD.27752.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b998615dbfaf6725f85864839cd9bcc950a7c3f7561874b7cbbd6d94507a9f60
3
+ size 214920
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: hivex
3
+ original_train_name: WindFarmControl_pattern_8_task_0_run_id_0_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-8
11
+ results:
12
+ - task:
13
+ type: main-task
14
+ name: main_task
15
+ task-id: 0
16
+ pattern-id: 8
17
+ dataset:
18
+ name: hivex-wind-farm-control
19
+ type: hivex-wind-farm-control
20
+ metrics:
21
+ - type: cumulative_reward
22
+ value: 4602.325573730469 +/- 41.837472251810176
23
+ name: Cumulative Reward
24
+ verified: true
25
+ - type: individual_performance
26
+ value: 4602.3477075195315 +/- 42.725026096299715
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: 5009
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: 8
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_8_task_0_run_id_0_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": 1.0342463254928589,
6
+ "min": 0.8567436933517456,
7
+ "max": 1.0977368354797363,
8
+ "count": 200
9
+ },
10
+ "Agent.Policy.Entropy.sum": {
11
+ "value": 41378.12890625,
12
+ "min": 34276.6015625,
13
+ "max": 43979.73046875,
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": 9.325874328613281,
54
+ "min": 0.7655065655708313,
55
+ "max": 9.509753227233887,
56
+ "count": 200
57
+ },
58
+ "Agent.Policy.ExtrinsicValueEstimate.sum": {
59
+ "value": 223.82098388671875,
60
+ "min": 18.37215805053711,
61
+ "max": 228.23406982421875,
62
+ "count": 200
63
+ },
64
+ "Agent.Losses.PolicyLoss.mean": {
65
+ "value": 0.04881577084447527,
66
+ "min": 0.04492947267089409,
67
+ "max": 0.05480822551688771,
68
+ "count": 200
69
+ },
70
+ "Agent.Losses.PolicyLoss.sum": {
71
+ "value": 0.1464473125334258,
72
+ "min": 0.09814778697909787,
73
+ "max": 0.16442467655066312,
74
+ "count": 200
75
+ },
76
+ "Agent.Losses.ValueLoss.mean": {
77
+ "value": 0.29578603130103726,
78
+ "min": 0.0682248831814384,
79
+ "max": 1.462727802572772,
80
+ "count": 200
81
+ },
82
+ "Agent.Losses.ValueLoss.sum": {
83
+ "value": 0.8873580939031117,
84
+ "min": 0.20467464954431522,
85
+ "max": 2.925455605145544,
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": 4625.7371826171875,
138
+ "min": 618.1424263715744,
139
+ "max": 4678.6807861328125,
140
+ "count": 200
141
+ },
142
+ "Agent.WindFarmControl.IndividualPerformance.sum": {
143
+ "value": 37005.8974609375,
144
+ "min": 4945.139410972595,
145
+ "max": 37429.4462890625,
146
+ "count": 200
147
+ },
148
+ "Agent.Environment.CumulativeReward.mean": {
149
+ "value": 4625.749465942383,
150
+ "min": 802.4631873253398,
151
+ "max": 4682.931671142578,
152
+ "count": 200
153
+ },
154
+ "Agent.Environment.CumulativeReward.sum": {
155
+ "value": 37005.99572753906,
156
+ "min": 6419.705498602719,
157
+ "max": 37463.453369140625,
158
+ "count": 200
159
+ },
160
+ "Agent.Policy.ExtrinsicReward.mean": {
161
+ "value": 4625.749465942383,
162
+ "min": 802.4631873253398,
163
+ "max": 4682.931671142578,
164
+ "count": 200
165
+ },
166
+ "Agent.Policy.ExtrinsicReward.sum": {
167
+ "value": 37005.99572753906,
168
+ "min": 6419.705498602719,
169
+ "max": 37463.453369140625,
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": "1716278148",
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_8_task_0_run_id_0_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train --base-port 5009",
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": "1716285124"
196
+ },
197
+ "total": 6975.7818057,
198
+ "count": 1,
199
+ "self": 0.34803290000036213,
200
+ "children": {
201
+ "run_training.setup": {
202
+ "total": 0.06823010000000007,
203
+ "count": 1,
204
+ "self": 0.06823010000000007
205
+ },
206
+ "TrainerController.start_learning": {
207
+ "total": 6975.3655427,
208
+ "count": 1,
209
+ "self": 21.392211200079146,
210
+ "children": {
211
+ "TrainerController._reset_env": {
212
+ "total": 4.3076970999999995,
213
+ "count": 1,
214
+ "self": 4.3076970999999995
215
+ },
216
+ "TrainerController.advance": {
217
+ "total": 6949.629124099921,
218
+ "count": 1002051,
219
+ "self": 19.631331999895338,
220
+ "children": {
221
+ "env_step": {
222
+ "total": 6929.997792100025,
223
+ "count": 1002051,
224
+ "self": 2292.9432863998,
225
+ "children": {
226
+ "SubprocessEnvManager._take_step": {
227
+ "total": 4627.3965150002705,
228
+ "count": 1002051,
229
+ "self": 38.25333070077522,
230
+ "children": {
231
+ "TorchPolicy.evaluate": {
232
+ "total": 4589.143184299495,
233
+ "count": 1002051,
234
+ "self": 4589.143184299495
235
+ }
236
+ }
237
+ },
238
+ "workers": {
239
+ "total": 9.657990699955352,
240
+ "count": 1002051,
241
+ "self": 0.0,
242
+ "children": {
243
+ "worker_root": {
244
+ "total": 6951.450070599854,
245
+ "count": 1002051,
246
+ "is_parallel": true,
247
+ "self": 5560.053164699688,
248
+ "children": {
249
+ "steps_from_proto": {
250
+ "total": 0.00048599999999998644,
251
+ "count": 1,
252
+ "is_parallel": true,
253
+ "self": 0.00033770000000066247,
254
+ "children": {
255
+ "_process_rank_one_or_two_observation": {
256
+ "total": 0.00014829999999932397,
257
+ "count": 2,
258
+ "is_parallel": true,
259
+ "self": 0.00014829999999932397
260
+ }
261
+ }
262
+ },
263
+ "UnityEnvironment.step": {
264
+ "total": 1391.3964199001666,
265
+ "count": 1002051,
266
+ "is_parallel": true,
267
+ "self": 66.13279789980515,
268
+ "children": {
269
+ "UnityEnvironment._generate_step_input": {
270
+ "total": 96.4390646001216,
271
+ "count": 1002051,
272
+ "is_parallel": true,
273
+ "self": 96.4390646001216
274
+ },
275
+ "communicator.exchange": {
276
+ "total": 1037.158965500481,
277
+ "count": 1002051,
278
+ "is_parallel": true,
279
+ "self": 1037.158965500481
280
+ },
281
+ "steps_from_proto": {
282
+ "total": 191.66559189975908,
283
+ "count": 1002051,
284
+ "is_parallel": true,
285
+ "self": 105.45197919906975,
286
+ "children": {
287
+ "_process_rank_one_or_two_observation": {
288
+ "total": 86.21361270068932,
289
+ "count": 2004102,
290
+ "is_parallel": true,
291
+ "self": 86.21361270068932
292
+ }
293
+ }
294
+ }
295
+ }
296
+ }
297
+ }
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ },
305
+ "trainer_threads": {
306
+ "total": 4.200000057608122e-05,
307
+ "count": 1,
308
+ "self": 4.200000057608122e-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": 6968.055332399885,
318
+ "count": 224650,
319
+ "is_parallel": true,
320
+ "self": 11.720379300204513,
321
+ "children": {
322
+ "process_trajectory": {
323
+ "total": 3783.882188399685,
324
+ "count": 224650,
325
+ "is_parallel": true,
326
+ "self": 3783.2448023996863,
327
+ "children": {
328
+ "RLTrainer._checkpoint": {
329
+ "total": 0.6373859999991396,
330
+ "count": 16,
331
+ "is_parallel": true,
332
+ "self": 0.6373859999991396
333
+ }
334
+ }
335
+ },
336
+ "_update_policy": {
337
+ "total": 3172.4527646999954,
338
+ "count": 600,
339
+ "is_parallel": true,
340
+ "self": 828.331355099876,
341
+ "children": {
342
+ "TorchPPOOptimizer.update": {
343
+ "total": 2344.1214096001195,
344
+ "count": 93600,
345
+ "is_parallel": true,
346
+ "self": 2344.1214096001195
347
+ }
348
+ }
349
+ }
350
+ }
351
+ }
352
+ }
353
+ }
354
+ }
355
+ },
356
+ "TrainerController._save_models": {
357
+ "total": 0.03646829999979673,
358
+ "count": 1,
359
+ "self": 0.004892799999652198,
360
+ "children": {
361
+ "RLTrainer._checkpoint": {
362
+ "total": 0.03157550000014453,
363
+ "count": 1,
364
+ "self": 0.03157550000014453
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_8_task_0_run_id_0_train\\Agent\\Agent-6498432.onnx",
13
+ "reward": null,
14
+ "creation_time": 1716283830.8849823,
15
+ "auxillary_file_paths": [
16
+ "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-6498432.pt"
17
+ ]
18
+ },
19
+ {
20
+ "steps": 6999096,
21
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-6999096.onnx",
22
+ "reward": 4519.305097307478,
23
+ "creation_time": 1716284274.8624728,
24
+ "auxillary_file_paths": [
25
+ "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-6999096.pt"
26
+ ]
27
+ },
28
+ {
29
+ "steps": 7498432,
30
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-7498432.onnx",
31
+ "reward": null,
32
+ "creation_time": 1716284703.9904711,
33
+ "auxillary_file_paths": [
34
+ "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-7498432.pt"
35
+ ]
36
+ },
37
+ {
38
+ "steps": 7999096,
39
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-7999096.onnx",
40
+ "reward": 4620.335789271763,
41
+ "creation_time": 1716285113.3463402,
42
+ "auxillary_file_paths": [
43
+ "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-7999096.pt"
44
+ ]
45
+ },
46
+ {
47
+ "steps": 8016384,
48
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-8016384.onnx",
49
+ "reward": null,
50
+ "creation_time": 1716285123.871876,
51
+ "auxillary_file_paths": [
52
+ "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent\\Agent-8016384.pt"
53
+ ]
54
+ }
55
+ ],
56
+ "final_checkpoint": {
57
+ "steps": 8016384,
58
+ "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_train\\Agent.onnx",
59
+ "reward": null,
60
+ "creation_time": 1716285123.871876,
61
+ "auxillary_file_paths": [
62
+ "results\\WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_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
+ }