Hugging Face's logo

hivex-research
/
hivex-WRM-PPO-baseline-task-1-difficulty-8

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-wildfire-resource-management
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community
philippds commited on
Commit
e086ef0
•
1 Parent(s): 0f2e7f0

Upload 9 files

Browse files
Files changed (9) hide show
  1. Agent.onnx +3 -0
  2. Agent/Agent-451404.onnx +3 -0
  3. Agent/Agent-451404.pt +3 -0
  4. Agent/checkpoint.pt +3 -0
  5. Agent/events.out.tfevents.1716727900.RICHARD.20724.0 +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 sha256:30eacbd20237982d70d23a5774aed836d9bfcbdc6b4c089794a0d662e6cf1fdd
3
+ size 1110764
Agent/Agent-451404.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30eacbd20237982d70d23a5774aed836d9bfcbdc6b4c089794a0d662e6cf1fdd
3
+ size 1110764
Agent/Agent-451404.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4f355573885593ee9b84b070ccca616c05085630ea1ade67f65d46ca691381
3
+ size 7958695
Agent/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4f355573885593ee9b84b070ccca616c05085630ea1ade67f65d46ca691381
3
+ size 7958695
Agent/events.out.tfevents.1716727900.RICHARD.20724.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7dba213ec8cfe65298564e68b58d9a898d5f00852c86544b3458a5f5f4583d6
3
+ size 205354
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: hivex
3
+ original_train_name: WildfireResourceManagement_difficulty_8_task_1_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-1-difficulty-8
11
+ results:
12
+ - task:
13
+ type: sub-task
14
+ name: keep_all
15
+ task-id: 1
16
+ difficulty-id: 8
17
+ dataset:
18
+ name: hivex-wildfire-resource-management
19
+ type: hivex-wildfire-resource-management
20
+ metrics:
21
+ - type: cumulative_reward
22
+ value: 355.44918060302734 +/- 174.7116155809256
23
+ name: Cumulative Reward
24
+ verified: true
25
+ - type: collective_performance
26
+ value: 60.788882446289065 +/- 27.499079077539847
27
+ name: Collective Performance
28
+ verified: true
29
+ - type: individual_performance
30
+ value: 32.571975231170654 +/- 15.25373718413003
31
+ name: Individual Performance
32
+ verified: true
33
+ - type: reward_for_moving_resources_to_neighbours
34
+ value: 1.6818679869174957 +/- 1.4253886392289061
35
+ name: Reward for Moving Resources to Neighbours
36
+ verified: true
37
+ - type: reward_for_moving_resources_to_self
38
+ value: 280.6448547363281 +/- 131.94279504724986
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: 8
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: 1
94
+ name: task
95
+ completion_criteria: null
96
+ checkpoint_settings:
97
+ run_id: WildfireResourceManagement/train/WildfireResourceManagement_difficulty_8_task_1_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": 3.9181978702545166,
6
+ "min": 3.8353826999664307,
7
+ "max": 4.385557174682617,
8
+ "count": 100
9
+ },
10
+ "Agent.Policy.Entropy.sum": {
11
+ "value": 21651.9609375,
12
+ "min": 7004.57666015625,
13
+ "max": 27602.22265625,
14
+ "count": 100
15
+ },
16
+ "Agent.WildfireResourceManagement.IndividualResourceCount.mean": {
17
+ "value": 0.8666667496716535,
18
+ "min": 0.5777778308838606,
19
+ "max": 0.9000000953674316,
20
+ "count": 100
21
+ },
22
+ "Agent.WildfireResourceManagement.IndividualResourceCount.sum": {
23
+ "value": 23.400002241134644,
24
+ "min": 7.700000762939453,
25
+ "max": 32.20000338554382,
26
+ "count": 100
27
+ },
28
+ "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": {
29
+ "value": 2.152441685018992,
30
+ "min": 0.8010983359482553,
31
+ "max": 15.489594587573299,
32
+ "count": 100
33
+ },
34
+ "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": {
35
+ "value": 58.11592549551278,
36
+ "min": 11.439244419336319,
37
+ "max": 418.21905386447906,
38
+ "count": 100
39
+ },
40
+ "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": {
41
+ "value": 304.5739384757148,
42
+ "min": 26.05030299226443,
43
+ "max": 468.1476593017578,
44
+ "count": 100
45
+ },
46
+ "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": {
47
+ "value": 8223.4963388443,
48
+ "min": 937.8109077215195,
49
+ "max": 8394.559112548828,
50
+ "count": 100
51
+ },
52
+ "Agent.WildfireResourceManagement.CollectivePerformance.mean": {
53
+ "value": 64.0783942187274,
54
+ "min": 20.735190947850544,
55
+ "max": 117.72799767388238,
56
+ "count": 100
57
+ },
58
+ "Agent.WildfireResourceManagement.CollectivePerformance.sum": {
59
+ "value": 1730.1166439056396,
60
+ "min": 435.9099578857422,
61
+ "max": 1998.507007598877,
62
+ "count": 100
63
+ },
64
+ "Agent.WildfireResourceManagement.IndividualPerformance.mean": {
65
+ "value": 35.4022040632036,
66
+ "min": 11.265056636598375,
67
+ "max": 57.77317428588867,
68
+ "count": 100
69
+ },
70
+ "Agent.WildfireResourceManagement.IndividualPerformance.sum": {
71
+ "value": 955.8595097064972,
72
+ "min": 220.9379529953003,
73
+ "max": 1043.3600313663483,
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": 204.66666666666666,
102
+ "min": 93.75,
103
+ "max": 497.0,
104
+ "count": 100
105
+ },
106
+ "Agent.Environment.EpisodeLength.sum": {
107
+ "value": 5526.0,
108
+ "min": 1719.0,
109
+ "max": 6831.0,
110
+ "count": 100
111
+ },
112
+ "Agent.Step.mean": {
113
+ "value": 449812.0,
114
+ "min": 4398.0,
115
+ "max": 449812.0,
116
+ "count": 100
117
+ },
118
+ "Agent.Step.sum": {
119
+ "value": 449812.0,
120
+ "min": 4398.0,
121
+ "max": 449812.0,
122
+ "count": 100
123
+ },
124
+ "Agent.Policy.CuriosityValueEstimate.mean": {
125
+ "value": 0.0032545796129852533,
126
+ "min": -0.04245872423052788,
127
+ "max": 0.11642169952392578,
128
+ "count": 100
129
+ },
130
+ "Agent.Policy.CuriosityValueEstimate.sum": {
131
+ "value": 0.06834617257118225,
132
+ "min": -0.9340919256210327,
133
+ "max": 3.118682861328125,
134
+ "count": 100
135
+ },
136
+ "Agent.Policy.ExtrinsicValueEstimate.mean": {
137
+ "value": 101.64611053466797,
138
+ "min": 3.4324796199798584,
139
+ "max": 117.11848449707031,
140
+ "count": 100
141
+ },
142
+ "Agent.Policy.ExtrinsicValueEstimate.sum": {
143
+ "value": 2134.568359375,
144
+ "min": 85.8119888305664,
145
+ "max": 3188.197509765625,
146
+ "count": 100
147
+ },
148
+ "Agent.Environment.CumulativeReward.mean": {
149
+ "value": 388.0023089817592,
150
+ "min": 76.50909111022949,
151
+ "max": 603.0836317274305,
152
+ "count": 100
153
+ },
154
+ "Agent.Environment.CumulativeReward.sum": {
155
+ "value": 8148.048488616943,
156
+ "min": 1912.7272777557373,
157
+ "max": 8148.048488616943,
158
+ "count": 100
159
+ },
160
+ "Agent.Policy.CuriosityReward.mean": {
161
+ "value": 0.027668442399728866,
162
+ "min": 0.02111277556805699,
163
+ "max": 0.18603225509551438,
164
+ "count": 100
165
+ },
166
+ "Agent.Policy.CuriosityReward.sum": {
167
+ "value": 0.5810372903943062,
168
+ "min": 0.5008933562785387,
169
+ "max": 4.0927096121013165,
170
+ "count": 100
171
+ },
172
+ "Agent.Policy.ExtrinsicReward.mean": {
173
+ "value": 388.0023089817592,
174
+ "min": 76.50909111022949,
175
+ "max": 603.0836317274305,
176
+ "count": 100
177
+ },
178
+ "Agent.Policy.ExtrinsicReward.sum": {
179
+ "value": 8148.048488616943,
180
+ "min": 1912.7272777557373,
181
+ "max": 8148.048488616943,
182
+ "count": 100
183
+ },
184
+ "Agent.Losses.PolicyLoss.mean": {
185
+ "value": 0.07081948476148817,
186
+ "min": 0.051579486404856045,
187
+ "max": 0.08544279739522097,
188
+ "count": 99
189
+ },
190
+ "Agent.Losses.PolicyLoss.sum": {
191
+ "value": 0.14163896952297633,
192
+ "min": 0.051579486404856045,
193
+ "max": 0.15435190841607335,
194
+ "count": 99
195
+ },
196
+ "Agent.Losses.ValueLoss.mean": {
197
+ "value": 919.6023082684374,
198
+ "min": 36.81519386224579,
199
+ "max": 919.6023082684374,
200
+ "count": 99
201
+ },
202
+ "Agent.Losses.ValueLoss.sum": {
203
+ "value": 1839.2046165368747,
204
+ "min": 36.81519386224579,
205
+ "max": 1839.2046165368747,
206
+ "count": 99
207
+ },
208
+ "Agent.Policy.LearningRate.mean": {
209
+ "value": 1.7790994069999974e-06,
210
+ "min": 1.7790994069999974e-06,
211
+ "max": 0.00029834400055199994,
212
+ "count": 99
213
+ },
214
+ "Agent.Policy.LearningRate.sum": {
215
+ "value": 3.5581988139999947e-06,
216
+ "min": 3.5581988139999947e-06,
217
+ "max": 0.0005912520029159999,
218
+ "count": 99
219
+ },
220
+ "Agent.Policy.Epsilon.mean": {
221
+ "value": 0.100593,
222
+ "min": 0.100593,
223
+ "max": 0.19944800000000004,
224
+ "count": 99
225
+ },
226
+ "Agent.Policy.Epsilon.sum": {
227
+ "value": 0.201186,
228
+ "min": 0.10142999999999998,
229
+ "max": 0.3970840000000001,
230
+ "count": 99
231
+ },
232
+ "Agent.Policy.Beta.mean": {
233
+ "value": 6.924069999999992e-05,
234
+ "min": 6.924069999999992e-05,
235
+ "max": 0.009944855199999998,
236
+ "count": 99
237
+ },
238
+ "Agent.Policy.Beta.sum": {
239
+ "value": 0.00013848139999999984,
240
+ "min": 0.00013848139999999984,
241
+ "max": 0.019708691599999995,
242
+ "count": 99
243
+ },
244
+ "Agent.Losses.CuriosityForwardLoss.mean": {
245
+ "value": 0.005482690535463514,
246
+ "min": 0.004134121945955687,
247
+ "max": 0.3886077385722545,
248
+ "count": 99
249
+ },
250
+ "Agent.Losses.CuriosityForwardLoss.sum": {
251
+ "value": 0.010965381070927028,
252
+ "min": 0.004134121945955687,
253
+ "max": 0.3886077385722545,
254
+ "count": 99
255
+ },
256
+ "Agent.Losses.CuriosityInverseLoss.mean": {
257
+ "value": 3.85200771986676,
258
+ "min": 3.732027288467165,
259
+ "max": 4.39014532691554,
260
+ "count": 99
261
+ },
262
+ "Agent.Losses.CuriosityInverseLoss.sum": {
263
+ "value": 7.70401543973352,
264
+ "min": 3.732027288467165,
265
+ "max": 8.739337876731273,
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": "1716727898",
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_8_task_1_run_id_1_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_8_task_1_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": "1716729806"
292
+ },
293
+ "total": 1907.8616203000001,
294
+ "count": 1,
295
+ "self": 0.2091005000002042,
296
+ "children": {
297
+ "run_training.setup": {
298
+ "total": 0.05204299999999995,
299
+ "count": 1,
300
+ "self": 0.05204299999999995
301
+ },
302
+ "TrainerController.start_learning": {
303
+ "total": 1907.6004768,
304
+ "count": 1,
305
+ "self": 1.3724266000042462,
306
+ "children": {
307
+ "TrainerController._reset_env": {
308
+ "total": 2.2182755,
309
+ "count": 1,
310
+ "self": 2.2182755
311
+ },
312
+ "TrainerController.advance": {
313
+ "total": 1903.8876972999958,
314
+ "count": 50157,
315
+ "self": 1.1044949999766231,
316
+ "children": {
317
+ "env_step": {
318
+ "total": 1902.7832023000192,
319
+ "count": 50157,
320
+ "self": 1589.0755829000168,
321
+ "children": {
322
+ "SubprocessEnvManager._take_step": {
323
+ "total": 313.19396319999316,
324
+ "count": 50157,
325
+ "self": 2.029523899969149,
326
+ "children": {
327
+ "TorchPolicy.evaluate": {
328
+ "total": 311.164439300024,
329
+ "count": 50157,
330
+ "self": 311.164439300024
331
+ }
332
+ }
333
+ },
334
+ "workers": {
335
+ "total": 0.5136562000090978,
336
+ "count": 50157,
337
+ "self": 0.0,
338
+ "children": {
339
+ "worker_root": {
340
+ "total": 1904.7780526000035,
341
+ "count": 50157,
342
+ "is_parallel": true,
343
+ "self": 385.78522210001825,
344
+ "children": {
345
+ "steps_from_proto": {
346
+ "total": 0.0002884999999999138,
347
+ "count": 1,
348
+ "is_parallel": true,
349
+ "self": 0.00012699999999998823,
350
+ "children": {
351
+ "_process_rank_one_or_two_observation": {
352
+ "total": 0.0001614999999999256,
353
+ "count": 2,
354
+ "is_parallel": true,
355
+ "self": 0.0001614999999999256
356
+ }
357
+ }
358
+ },
359
+ "UnityEnvironment.step": {
360
+ "total": 1518.9925419999854,
361
+ "count": 50157,
362
+ "is_parallel": true,
363
+ "self": 4.3082015999791565,
364
+ "children": {
365
+ "UnityEnvironment._generate_step_input": {
366
+ "total": 5.646964899999924,
367
+ "count": 50157,
368
+ "is_parallel": true,
369
+ "self": 5.646964899999924
370
+ },
371
+ "communicator.exchange": {
372
+ "total": 1497.4812175999834,
373
+ "count": 50157,
374
+ "is_parallel": true,
375
+ "self": 1497.4812175999834
376
+ },
377
+ "steps_from_proto": {
378
+ "total": 11.556157900023079,
379
+ "count": 50157,
380
+ "is_parallel": true,
381
+ "self": 6.010886400029484,
382
+ "children": {
383
+ "_process_rank_one_or_two_observation": {
384
+ "total": 5.545271499993595,
385
+ "count": 100314,
386
+ "is_parallel": true,
387
+ "self": 5.545271499993595
388
+ }
389
+ }
390
+ }
391
+ }
392
+ }
393
+ }
394
+ }
395
+ }
396
+ }
397
+ }
398
+ }
399
+ }
400
+ },
401
+ "trainer_threads": {
402
+ "total": 2.7199999976801337e-05,
403
+ "count": 1,
404
+ "self": 2.7199999976801337e-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": 1904.0746734999818,
414
+ "count": 92880,
415
+ "is_parallel": true,
416
+ "self": 3.372148499981222,
417
+ "children": {
418
+ "process_trajectory": {
419
+ "total": 1474.4498105000011,
420
+ "count": 92880,
421
+ "is_parallel": true,
422
+ "self": 1474.4498105000011
423
+ },
424
+ "_update_policy": {
425
+ "total": 426.25271449999946,
426
+ "count": 148,
427
+ "is_parallel": true,
428
+ "self": 209.94881250000054,
429
+ "children": {
430
+ "TorchPPOOptimizer.update": {
431
+ "total": 216.3039019999989,
432
+ "count": 10284,
433
+ "is_parallel": true,
434
+ "self": 216.3039019999989
435
+ }
436
+ }
437
+ }
438
+ }
439
+ }
440
+ }
441
+ }
442
+ }
443
+ },
444
+ "TrainerController._save_models": {
445
+ "total": 0.12205020000010336,
446
+ "count": 1,
447
+ "self": 0.005611200000203098,
448
+ "children": {
449
+ "RLTrainer._checkpoint": {
450
+ "total": 0.11643899999990026,
451
+ "count": 1,
452
+ "self": 0.11643899999990026
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": 451404,
12
+ "file_path": "results\\WildfireResourceManagement/train/WildfireResourceManagement_difficulty_8_task_1_run_id_1_train\\Agent\\Agent-451404.onnx",
13
+ "reward": 208.67558352152506,
14
+ "creation_time": 1716729806.419927,
15
+ "auxillary_file_paths": [
16
+ "results\\WildfireResourceManagement/train/WildfireResourceManagement_difficulty_8_task_1_run_id_1_train\\Agent\\Agent-451404.pt"
17
+ ]
18
+ }
19
+ ],
20
+ "final_checkpoint": {
21
+ "steps": 451404,
22
+ "file_path": "results\\WildfireResourceManagement/train/WildfireResourceManagement_difficulty_8_task_1_run_id_1_train\\Agent.onnx",
23
+ "reward": 208.67558352152506,
24
+ "creation_time": 1716729806.419927,
25
+ "auxillary_file_paths": [
26
+ "results\\WildfireResourceManagement/train/WildfireResourceManagement_difficulty_8_task_1_run_id_1_train\\Agent\\Agent-451404.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
+ }