Hugging Face's logo

hivex-research
/
hivex-WRM-PPO-baseline-task-2-difficulty-2

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-wildfire-resource-management
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community
philippds commited on
Commit
3e7dd1e
•
1 Parent(s): f9cf7ed

Upload 9 files

Browse files
Files changed (9) hide show
  1. Agent.onnx +3 -0
  2. Agent/Agent-454383.onnx +3 -0
  3. Agent/Agent-454383.pt +3 -0
  4. Agent/checkpoint.pt +3 -0
  5. Agent/events.out.tfevents.1716696792.RICHARD.28060.0 +3 -0
  6. README.md +41 -0
  7. configuration.yaml +107 -0
  8. run_logs/timers.json +459 -0
  9. run_logs/training_status.json +35 -0
Agent.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e65ec878226e39800c9ebaa595a2d4e3a6b7cd6abb53c64a4354f3fb216d17
3
+ size 1110764
Agent/Agent-454383.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e65ec878226e39800c9ebaa595a2d4e3a6b7cd6abb53c64a4354f3fb216d17
3
+ size 1110764
Agent/Agent-454383.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f723217cba6cb15cc82b67cc1421e864a35499572936b5be4ad4c7e4247e93e4
3
+ size 7958695
Agent/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f723217cba6cb15cc82b67cc1421e864a35499572936b5be4ad4c7e4247e93e4
3
+ size 7958695
Agent/events.out.tfevents.1716696792.RICHARD.28060.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab1952622deaf75ed3bf96ad1a038db656e446e5f03f1ea119765ded889d2c9
3
+ size 239116
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: hivex
3
+ original_train_name: WildfireResourceManagement_difficulty_2_task_2_run_id_1_train
4
+ tags:
5
+ - hivex
6
+ - hivex-wildfire-resource-management
7
+ - reinforcement-learning
8
+ - multi-agent-reinforcement-learning
9
+ model-index:
10
+ - name: hivex-WRM-PPO-baseline-task-2-difficulty-2
11
+ results:
12
+ - task:
13
+ type: sub-task
14
+ name: distribute_all
15
+ task-id: 2
16
+ difficulty-id: 2
17
+ dataset:
18
+ name: hivex-wildfire-resource-management
19
+ type: hivex-wildfire-resource-management
20
+ metrics:
21
+ - type: cumulative_reward
22
+ value: 719.8077911376953 +/- 176.60168760638808
23
+ name: Cumulative Reward
24
+ verified: true
25
+ - type: collective_performance
26
+ value: 49.83914451599121 +/- 17.927922628117184
27
+ name: Collective Performance
28
+ verified: true
29
+ - type: individual_performance
30
+ value: 26.82857608795166 +/- 10.644374836699683
31
+ name: Individual Performance
32
+ verified: true
33
+ - type: reward_for_moving_resources_to_neighbours
34
+ value: 670.3809020996093 +/- 354.66801295508003
35
+ name: Reward for Moving Resources to Neighbours
36
+ verified: true
37
+ - type: reward_for_moving_resources_to_self
38
+ value: 0.3922588244080544 +/- 0.20202251712801628
39
+ name: Reward for Moving Resources to Self
40
+ verified: true
41
+ ---
configuration.yaml ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Agent:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 128
7
+ buffer_size: 2048
8
+ learning_rate: 0.0003
9
+ beta: 0.01
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: 512
20
+ num_layers: 2
21
+ vis_encode_type: simple
22
+ memory: null
23
+ goal_conditioning_type: hyper
24
+ deterministic: false
25
+ reward_signals:
26
+ curiosity:
27
+ gamma: 0.99
28
+ strength: 0.02
29
+ network_settings:
30
+ normalize: false
31
+ hidden_units: 256
32
+ num_layers: 2
33
+ vis_encode_type: simple
34
+ memory: null
35
+ goal_conditioning_type: hyper
36
+ deterministic: false
37
+ learning_rate: 0.0003
38
+ encoding_size: 256
39
+ extrinsic:
40
+ gamma: 0.99
41
+ strength: 1.0
42
+ network_settings:
43
+ normalize: false
44
+ hidden_units: 128
45
+ num_layers: 2
46
+ vis_encode_type: simple
47
+ memory: null
48
+ goal_conditioning_type: hyper
49
+ deterministic: false
50
+ init_path: null
51
+ keep_checkpoints: 5
52
+ checkpoint_interval: 500000
53
+ max_steps: 450000
54
+ time_horizon: 2048
55
+ summary_freq: 4500
56
+ threaded: true
57
+ self_play: null
58
+ behavioral_cloning: null
59
+ env_settings:
60
+ env_path: c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/dev_environments/Hivex_WildfireResourceManagement_win
61
+ env_args: null
62
+ base_port: 5006
63
+ num_envs: 1
64
+ num_areas: 1
65
+ seed: 5000
66
+ max_lifetime_restarts: 10
67
+ restarts_rate_limit_n: 1
68
+ restarts_rate_limit_period_s: 60
69
+ engine_settings:
70
+ width: 84
71
+ height: 84
72
+ quality_level: 5
73
+ time_scale: 20
74
+ target_frame_rate: -1
75
+ capture_frame_rate: 60
76
+ no_graphics: true
77
+ environment_parameters:
78
+ difficulty:
79
+ curriculum:
80
+ - value:
81
+ sampler_type: constant
82
+ sampler_parameters:
83
+ seed: 5000
84
+ value: 2
85
+ name: difficulty
86
+ completion_criteria: null
87
+ task:
88
+ curriculum:
89
+ - value:
90
+ sampler_type: constant
91
+ sampler_parameters:
92
+ seed: 5001
93
+ value: 2
94
+ name: task
95
+ completion_criteria: null
96
+ checkpoint_settings:
97
+ run_id: WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_task_2_run_id_1_train
98
+ initialize_from: null
99
+ load_model: false
100
+ resume: false
101
+ force: false
102
+ train_model: false
103
+ inference: false
104
+ results_dir: results
105
+ torch_settings:
106
+ device: null
107
+ debug: false
run_logs/timers.json ADDED
@@ -0,0 +1,459 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Agent.Policy.Entropy.mean": {
5
+ "value": 3.9072349071502686,
6
+ "min": 3.896219253540039,
7
+ "max": 4.385494709014893,
8
+ "count": 100
9
+ },
10
+ "Agent.Policy.Entropy.sum": {
11
+ "value": 32492.56640625,
12
+ "min": 3738.46923828125,
13
+ "max": 32492.56640625,
14
+ "count": 100
15
+ },
16
+ "Agent.WildfireResourceManagement.IndividualResourceCount.mean": {
17
+ "value": 0.8833332214918401,
18
+ "min": 0.6022222694423464,
19
+ "max": 0.8999998817841212,
20
+ "count": 100
21
+ },
22
+ "Agent.WildfireResourceManagement.IndividualResourceCount.sum": {
23
+ "value": 31.799995973706245,
24
+ "min": 7.3999984562397,
25
+ "max": 40.099994622170925,
26
+ "count": 100
27
+ },
28
+ "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": {
29
+ "value": 721.4021077917682,
30
+ "min": 80.86749778323703,
31
+ "max": 2428.178514268663,
32
+ "count": 100
33
+ },
34
+ "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": {
35
+ "value": 25970.475880503654,
36
+ "min": 2353.4279419481754,
37
+ "max": 43707.21325683594,
38
+ "count": 100
39
+ },
40
+ "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": {
41
+ "value": 0.3633727075903658,
42
+ "min": 0.18966750469472674,
43
+ "max": 6.678156415207519,
44
+ "count": 100
45
+ },
46
+ "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": {
47
+ "value": 13.081417473253168,
48
+ "min": 1.7070075422525406,
49
+ "max": 169.08945786952972,
50
+ "count": 100
51
+ },
52
+ "Agent.WildfireResourceManagement.CollectivePerformance.mean": {
53
+ "value": 53.49935699833764,
54
+ "min": 22.186935265858967,
55
+ "max": 157.86320326063367,
56
+ "count": 100
57
+ },
58
+ "Agent.WildfireResourceManagement.CollectivePerformance.sum": {
59
+ "value": 1925.976851940155,
60
+ "min": 270.33209228515625,
61
+ "max": 2356.889991760254,
62
+ "count": 100
63
+ },
64
+ "Agent.WildfireResourceManagement.IndividualPerformance.mean": {
65
+ "value": 28.4905375193982,
66
+ "min": 9.365763707293404,
67
+ "max": 78.2373907632298,
68
+ "count": 100
69
+ },
70
+ "Agent.WildfireResourceManagement.IndividualPerformance.sum": {
71
+ "value": 1025.6593506983352,
72
+ "min": 119.87503230571747,
73
+ "max": 1408.2730337381363,
74
+ "count": 100
75
+ },
76
+ "Agent.Environment.LessonNumber.difficulty.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 100
81
+ },
82
+ "Agent.Environment.LessonNumber.difficulty.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 100
87
+ },
88
+ "Agent.Environment.LessonNumber.task.mean": {
89
+ "value": 0.0,
90
+ "min": 0.0,
91
+ "max": 0.0,
92
+ "count": 100
93
+ },
94
+ "Agent.Environment.LessonNumber.task.sum": {
95
+ "value": 0.0,
96
+ "min": 0.0,
97
+ "max": 0.0,
98
+ "count": 100
99
+ },
100
+ "Agent.Environment.EpisodeLength.mean": {
101
+ "value": 230.5,
102
+ "min": 89.6,
103
+ "max": 499.0,
104
+ "count": 100
105
+ },
106
+ "Agent.Environment.EpisodeLength.sum": {
107
+ "value": 8298.0,
108
+ "min": 936.0,
109
+ "max": 8298.0,
110
+ "count": 100
111
+ },
112
+ "Agent.Step.mean": {
113
+ "value": 449883.0,
114
+ "min": 4251.0,
115
+ "max": 449883.0,
116
+ "count": 100
117
+ },
118
+ "Agent.Step.sum": {
119
+ "value": 449883.0,
120
+ "min": 4251.0,
121
+ "max": 449883.0,
122
+ "count": 100
123
+ },
124
+ "Agent.Policy.CuriosityValueEstimate.mean": {
125
+ "value": 0.000553550198674202,
126
+ "min": -0.06830383092164993,
127
+ "max": 0.12467946857213974,
128
+ "count": 100
129
+ },
130
+ "Agent.Policy.CuriosityValueEstimate.sum": {
131
+ "value": 0.016052955761551857,
132
+ "min": -1.5709881782531738,
133
+ "max": 4.416498184204102,
134
+ "count": 100
135
+ },
136
+ "Agent.Policy.ExtrinsicValueEstimate.mean": {
137
+ "value": 300.3558044433594,
138
+ "min": 1.9085078239440918,
139
+ "max": 309.19232177734375,
140
+ "count": 100
141
+ },
142
+ "Agent.Policy.ExtrinsicValueEstimate.sum": {
143
+ "value": 8710.318359375,
144
+ "min": 62.98075866699219,
145
+ "max": 11249.7255859375,
146
+ "count": 100
147
+ },
148
+ "Agent.Environment.CumulativeReward.mean": {
149
+ "value": 723.2452566048195,
150
+ "min": 122.79987020203562,
151
+ "max": 2623.8573888142905,
152
+ "count": 100
153
+ },
154
+ "Agent.Environment.CumulativeReward.sum": {
155
+ "value": 20974.112441539764,
156
+ "min": 4052.3957166671753,
157
+ "max": 32908.48686981201,
158
+ "count": 100
159
+ },
160
+ "Agent.Policy.CuriosityReward.mean": {
161
+ "value": 0.01017263026281806,
162
+ "min": 0.008879438338156503,
163
+ "max": 0.17959920384667136,
164
+ "count": 100
165
+ },
166
+ "Agent.Policy.CuriosityReward.sum": {
167
+ "value": 0.2950062776217237,
168
+ "min": 0.17983429972082376,
169
+ "max": 3.7317505534738302,
170
+ "count": 100
171
+ },
172
+ "Agent.Policy.ExtrinsicReward.mean": {
173
+ "value": 723.2452566048195,
174
+ "min": 122.79987020203562,
175
+ "max": 2623.8573888142905,
176
+ "count": 100
177
+ },
178
+ "Agent.Policy.ExtrinsicReward.sum": {
179
+ "value": 20974.112441539764,
180
+ "min": 4052.3957166671753,
181
+ "max": 32908.48686981201,
182
+ "count": 100
183
+ },
184
+ "Agent.Losses.PolicyLoss.mean": {
185
+ "value": 0.06636851126569565,
186
+ "min": 0.053887202596617126,
187
+ "max": 0.08192256537056866,
188
+ "count": 99
189
+ },
190
+ "Agent.Losses.PolicyLoss.sum": {
191
+ "value": 0.1327370225313913,
192
+ "min": 0.053887202596617126,
193
+ "max": 0.16384513074113732,
194
+ "count": 99
195
+ },
196
+ "Agent.Losses.ValueLoss.mean": {
197
+ "value": 12299.918729428893,
198
+ "min": 191.80274963378906,
199
+ "max": 15915.296110026042,
200
+ "count": 99
201
+ },
202
+ "Agent.Losses.ValueLoss.sum": {
203
+ "value": 24599.837458857786,
204
+ "min": 191.80274963378906,
205
+ "max": 24599.837458857786,
206
+ "count": 99
207
+ },
208
+ "Agent.Policy.LearningRate.mean": {
209
+ "value": 1.827099390999995e-06,
210
+ "min": 1.827099390999995e-06,
211
+ "max": 0.00029819400060199984,
212
+ "count": 99
213
+ },
214
+ "Agent.Policy.LearningRate.sum": {
215
+ "value": 3.65419878199999e-06,
216
+ "min": 3.65419878199999e-06,
217
+ "max": 0.0005916540027819999,
218
+ "count": 99
219
+ },
220
+ "Agent.Policy.Epsilon.mean": {
221
+ "value": 0.100609,
222
+ "min": 0.100609,
223
+ "max": 0.19939800000000005,
224
+ "count": 99
225
+ },
226
+ "Agent.Policy.Epsilon.sum": {
227
+ "value": 0.201218,
228
+ "min": 0.10158800000000001,
229
+ "max": 0.39721799999999996,
230
+ "count": 99
231
+ },
232
+ "Agent.Policy.Beta.mean": {
233
+ "value": 7.083909999999983e-05,
234
+ "min": 7.083909999999983e-05,
235
+ "max": 0.009939860200000004,
236
+ "count": 99
237
+ },
238
+ "Agent.Policy.Beta.sum": {
239
+ "value": 0.00014167819999999967,
240
+ "min": 0.00014167819999999967,
241
+ "max": 0.0197220782,
242
+ "count": 99
243
+ },
244
+ "Agent.Losses.CuriosityForwardLoss.mean": {
245
+ "value": 0.0023117968791026484,
246
+ "min": 0.001999419695628738,
247
+ "max": 0.3829007114446352,
248
+ "count": 99
249
+ },
250
+ "Agent.Losses.CuriosityForwardLoss.sum": {
251
+ "value": 0.004623593758205297,
252
+ "min": 0.001999419695628738,
253
+ "max": 0.3829007114446352,
254
+ "count": 99
255
+ },
256
+ "Agent.Losses.CuriosityInverseLoss.mean": {
257
+ "value": 3.9139821650805295,
258
+ "min": 3.8770363981073555,
259
+ "max": 4.3893865706428645,
260
+ "count": 99
261
+ },
262
+ "Agent.Losses.CuriosityInverseLoss.sum": {
263
+ "value": 7.827964330161059,
264
+ "min": 3.8770363981073555,
265
+ "max": 8.711278208050347,
266
+ "count": 99
267
+ },
268
+ "Agent.IsTraining.mean": {
269
+ "value": 1.0,
270
+ "min": 1.0,
271
+ "max": 1.0,
272
+ "count": 100
273
+ },
274
+ "Agent.IsTraining.sum": {
275
+ "value": 1.0,
276
+ "min": 1.0,
277
+ "max": 1.0,
278
+ "count": 100
279
+ }
280
+ },
281
+ "metadata": {
282
+ "timer_format_version": "0.1.0",
283
+ "start_time_seconds": "1716696791",
284
+ "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]",
285
+ "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/WildfireResourceManagement_difficulty_2_task_2_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_task_2_run_id_1_train --base-port 5006",
286
+ "mlagents_version": "0.30.0",
287
+ "mlagents_envs_version": "0.30.0",
288
+ "communication_protocol_version": "1.5.0",
289
+ "pytorch_version": "1.7.1+cu110",
290
+ "numpy_version": "1.21.0",
291
+ "end_time_seconds": "1716698424"
292
+ },
293
+ "total": 1633.0382524,
294
+ "count": 1,
295
+ "self": 0.20053069999994477,
296
+ "children": {
297
+ "run_training.setup": {
298
+ "total": 0.05210500000000007,
299
+ "count": 1,
300
+ "self": 0.05210500000000007
301
+ },
302
+ "TrainerController.start_learning": {
303
+ "total": 1632.7856167,
304
+ "count": 1,
305
+ "self": 1.227762799991524,
306
+ "children": {
307
+ "TrainerController._reset_env": {
308
+ "total": 2.081207,
309
+ "count": 1,
310
+ "self": 2.081207
311
+ },
312
+ "TrainerController.advance": {
313
+ "total": 1629.3801854000085,
314
+ "count": 50488,
315
+ "self": 0.9495130000152585,
316
+ "children": {
317
+ "env_step": {
318
+ "total": 1628.4306723999932,
319
+ "count": 50488,
320
+ "self": 1357.1245237999951,
321
+ "children": {
322
+ "SubprocessEnvManager._take_step": {
323
+ "total": 270.8429244000024,
324
+ "count": 50488,
325
+ "self": 1.727493900040713,
326
+ "children": {
327
+ "TorchPolicy.evaluate": {
328
+ "total": 269.1154304999617,
329
+ "count": 50488,
330
+ "self": 269.1154304999617
331
+ }
332
+ }
333
+ },
334
+ "workers": {
335
+ "total": 0.463224199995818,
336
+ "count": 50488,
337
+ "self": 0.0,
338
+ "children": {
339
+ "worker_root": {
340
+ "total": 1630.2148361,
341
+ "count": 50488,
342
+ "is_parallel": true,
343
+ "self": 330.95029039997416,
344
+ "children": {
345
+ "steps_from_proto": {
346
+ "total": 0.0002427000000000401,
347
+ "count": 1,
348
+ "is_parallel": true,
349
+ "self": 0.00011300000000002974,
350
+ "children": {
351
+ "_process_rank_one_or_two_observation": {
352
+ "total": 0.00012970000000001036,
353
+ "count": 2,
354
+ "is_parallel": true,
355
+ "self": 0.00012970000000001036
356
+ }
357
+ }
358
+ },
359
+ "UnityEnvironment.step": {
360
+ "total": 1299.2643030000258,
361
+ "count": 50488,
362
+ "is_parallel": true,
363
+ "self": 3.3135401000449747,
364
+ "children": {
365
+ "UnityEnvironment._generate_step_input": {
366
+ "total": 4.033551899959847,
367
+ "count": 50488,
368
+ "is_parallel": true,
369
+ "self": 4.033551899959847
370
+ },
371
+ "communicator.exchange": {
372
+ "total": 1282.423853400033,
373
+ "count": 50488,
374
+ "is_parallel": true,
375
+ "self": 1282.423853400033
376
+ },
377
+ "steps_from_proto": {
378
+ "total": 9.493357599988132,
379
+ "count": 50488,
380
+ "is_parallel": true,
381
+ "self": 4.8367685000013,
382
+ "children": {
383
+ "_process_rank_one_or_two_observation": {
384
+ "total": 4.656589099986832,
385
+ "count": 100976,
386
+ "is_parallel": true,
387
+ "self": 4.656589099986832
388
+ }
389
+ }
390
+ }
391
+ }
392
+ }
393
+ }
394
+ }
395
+ }
396
+ }
397
+ }
398
+ }
399
+ }
400
+ },
401
+ "trainer_threads": {
402
+ "total": 2.2299999955066596e-05,
403
+ "count": 1,
404
+ "self": 2.2299999955066596e-05,
405
+ "children": {
406
+ "thread_root": {
407
+ "total": 0.0,
408
+ "count": 0,
409
+ "is_parallel": true,
410
+ "self": 0.0,
411
+ "children": {
412
+ "trainer_advance": {
413
+ "total": 1629.6933504000099,
414
+ "count": 80299,
415
+ "is_parallel": true,
416
+ "self": 2.4942578999898615,
417
+ "children": {
418
+ "process_trajectory": {
419
+ "total": 1277.753238200021,
420
+ "count": 80299,
421
+ "is_parallel": true,
422
+ "self": 1277.753238200021
423
+ },
424
+ "_update_policy": {
425
+ "total": 349.4458542999988,
426
+ "count": 147,
427
+ "is_parallel": true,
428
+ "self": 170.815070199999,
429
+ "children": {
430
+ "TorchPPOOptimizer.update": {
431
+ "total": 178.6307840999998,
432
+ "count": 10305,
433
+ "is_parallel": true,
434
+ "self": 178.6307840999998
435
+ }
436
+ }
437
+ }
438
+ }
439
+ }
440
+ }
441
+ }
442
+ }
443
+ },
444
+ "TrainerController._save_models": {
445
+ "total": 0.09643920000007711,
446
+ "count": 1,
447
+ "self": 0.004752600000074381,
448
+ "children": {
449
+ "RLTrainer._checkpoint": {
450
+ "total": 0.09168660000000273,
451
+ "count": 1,
452
+ "self": 0.09168660000000273
453
+ }
454
+ }
455
+ }
456
+ }
457
+ }
458
+ }
459
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "difficulty": {
3
+ "lesson_num": 0
4
+ },
5
+ "task": {
6
+ "lesson_num": 0
7
+ },
8
+ "Agent": {
9
+ "checkpoints": [
10
+ {
11
+ "steps": 454383,
12
+ "file_path": "results\\WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_task_2_run_id_1_train\\Agent\\Agent-454383.onnx",
13
+ "reward": 851.9820594787598,
14
+ "creation_time": 1716698423.875695,
15
+ "auxillary_file_paths": [
16
+ "results\\WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_task_2_run_id_1_train\\Agent\\Agent-454383.pt"
17
+ ]
18
+ }
19
+ ],
20
+ "final_checkpoint": {
21
+ "steps": 454383,
22
+ "file_path": "results\\WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_task_2_run_id_1_train\\Agent.onnx",
23
+ "reward": 851.9820594787598,
24
+ "creation_time": 1716698423.875695,
25
+ "auxillary_file_paths": [
26
+ "results\\WildfireResourceManagement/train/WildfireResourceManagement_difficulty_2_task_2_run_id_1_train\\Agent\\Agent-454383.pt"
27
+ ]
28
+ }
29
+ },
30
+ "metadata": {
31
+ "stats_format_version": "0.3.0",
32
+ "mlagents_version": "0.30.0",
33
+ "torch_version": "1.7.1+cu110"
34
+ }
35
+ }