Hugging Face's logo

hivex-research
/
hivex-AWS-PPO-baseline-task-5-difficulty-10

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-aerial-wildfire-suppression
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community
philippds commited on
Commit
c38a7f5
•
1 Parent(s): 450fd62

Upload 15 files

Browse files
Files changed (15) hide show
  1. Agent.onnx +3 -0
  2. Agent/Agent-1499935.onnx +3 -0
  3. Agent/Agent-1499935.pt +3 -0
  4. Agent/Agent-1800348.onnx +3 -0
  5. Agent/Agent-1800348.pt +3 -0
  6. Agent/Agent-499898.onnx +3 -0
  7. Agent/Agent-499898.pt +3 -0
  8. Agent/Agent-999832.onnx +3 -0
  9. Agent/Agent-999832.pt +3 -0
  10. Agent/checkpoint.pt +3 -0
  11. Agent/events.out.tfevents.1717984707.RICHARD.22900.0 +3 -0
  12. README.md +42 -0
  13. configuration.yaml +94 -0
  14. run_logs/timers.json +527 -0
  15. run_logs/training_status.json +62 -0
Agent.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b30ff438dd020a62353317c0e2ac031972fcdc13f3613ab397ab9a7dc9f76cf
3
+ size 883467
Agent/Agent-1499935.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a51590c166fa3dced6c3e98f1bbe96a6e362c0858e7ca6cbec14771dd34cd064
3
+ size 883467
Agent/Agent-1499935.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:360aebdf5e10800f381122183e43d711bf3e7dc79fee7d0a0fccb05084ddfa37
3
+ size 5302191
Agent/Agent-1800348.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b30ff438dd020a62353317c0e2ac031972fcdc13f3613ab397ab9a7dc9f76cf
3
+ size 883467
Agent/Agent-1800348.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0477c6aa7789b2d35ce43550bd0ca79905110be2f17f213f7e6d7f51763bf884
3
+ size 5302191
Agent/Agent-499898.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f034f186ba9f28597d67e4a83a5a3b7a70c3c5b32caf5bb8e5e7f939af71de5
3
+ size 883467
Agent/Agent-499898.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4dea9596445e2d23812ba02b25cfe688e0d1a3e61bbe3d3d6d48c29eb05c27e
3
+ size 5302191
Agent/Agent-999832.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72f1c76f0e8d4498f5dee57b8154e831cc18c63e587403f7f27802426bba642
3
+ size 883467
Agent/Agent-999832.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776f4300acc01972034ac582bfe36f41ddf98281ddd51297242bcc69616ae928
3
+ size 5302191
Agent/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0477c6aa7789b2d35ce43550bd0ca79905110be2f17f213f7e6d7f51763bf884
3
+ size 5302191
Agent/events.out.tfevents.1717984707.RICHARD.22900.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3914e795abc8adb3ff9dc1be83154f31ebdf1b27bfe0a5f83fee2442b236ca7e
3
+ size 361409
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: hivex
3
+ original_train_name: AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train
4
+ tags:
5
+ - hivex
6
+ - hivex-aerial-wildfire-suppression
7
+ - reinforcement-learning
8
+ - multi-agent-reinforcement-learning
9
+ model-index:
10
+ - name: hivex-AWS-PPO-baseline-task-5-difficulty-10
11
+ results:
12
+ - task:
13
+ type: sub-task
14
+ name: pick_up_water
15
+ task-id: 5
16
+ difficulty-id: 10
17
+ dataset:
18
+ name: hivex-aerial-wildfire-suppression
19
+ type: hivex-aerial-wildfire-suppression
20
+ metrics:
21
+ - type: water_pickup
22
+ value: 0.997826087474823 +/- 0.009722032366868
23
+ name: Water Pickup
24
+ verified: true
25
+ - type: cumulative_reward
26
+ value: 95.0800968170166 +/- 0.29640825374624785
27
+ name: Cumulative Reward
28
+ verified: true
29
+ ---
30
+
31
+ This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>5</code> with difficulty <code>10</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
32
+
33
+ Environment: **Aerial Wildfire Suppression**<br>
34
+ Task: <code>5</code><br>
35
+ Difficulty: <code>10</code><br>
36
+ Algorithm: <code>PPO</code><br>
37
+ Episode Length: <code>3000</code><br>
38
+ Training <code>max_steps</code>: <code>1800000</code><br>
39
+ Testing <code>max_steps</code>: <code>180000</code><br><br>
40
+
41
+ Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
42
+ Download the [Environment](https://github.com/hivex-research/hivex-environments)
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: 4096
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: 256
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: 0.995
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: 1800000
41
+ time_horizon: 4096
42
+ summary_freq: 9000
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_AerialWildfireSuppression_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
+ difficulty:
66
+ curriculum:
67
+ - value:
68
+ sampler_type: constant
69
+ sampler_parameters:
70
+ seed: 5000
71
+ value: 10
72
+ name: difficulty
73
+ completion_criteria: null
74
+ task:
75
+ curriculum:
76
+ - value:
77
+ sampler_type: constant
78
+ sampler_parameters:
79
+ seed: 5001
80
+ value: 5
81
+ name: task
82
+ completion_criteria: null
83
+ checkpoint_settings:
84
+ run_id: AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_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 +1,527 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Agent.Policy.Entropy.mean": {
5
+ "value": 1.487652063369751,
6
+ "min": 1.4351953268051147,
7
+ "max": 1.633612036705017,
8
+ "count": 200
9
+ },
10
+ "Agent.Policy.Entropy.sum": {
11
+ "value": 13683.423828125,
12
+ "min": 12472.876953125,
13
+ "max": 16162.07421875,
14
+ "count": 200
15
+ },
16
+ "Agent.AerialWildfireSuppression.WaterDrop.mean": {
17
+ "value": 0.0,
18
+ "min": 0.0,
19
+ "max": 0.0,
20
+ "count": 200
21
+ },
22
+ "Agent.AerialWildfireSuppression.WaterDrop.sum": {
23
+ "value": 0.0,
24
+ "min": 0.0,
25
+ "max": 0.0,
26
+ "count": 200
27
+ },
28
+ "Agent.AerialWildfireSuppression.WaterPickup.mean": {
29
+ "value": 1.0,
30
+ "min": 0.9298245614035088,
31
+ "max": 1.0,
32
+ "count": 200
33
+ },
34
+ "Agent.AerialWildfireSuppression.WaterPickup.sum": {
35
+ "value": 57.0,
36
+ "min": 36.0,
37
+ "max": 69.0,
38
+ "count": 200
39
+ },
40
+ "Agent.AerialWildfireSuppression.PreparingTreesReward.mean": {
41
+ "value": 0.0,
42
+ "min": 0.0,
43
+ "max": 0.0,
44
+ "count": 200
45
+ },
46
+ "Agent.AerialWildfireSuppression.PreparingTreesReward.sum": {
47
+ "value": 0.0,
48
+ "min": 0.0,
49
+ "max": 0.0,
50
+ "count": 200
51
+ },
52
+ "Agent.AerialWildfireSuppression.PreparingTrees.mean": {
53
+ "value": 0.0,
54
+ "min": 0.0,
55
+ "max": 0.0,
56
+ "count": 200
57
+ },
58
+ "Agent.AerialWildfireSuppression.PreparingTrees.sum": {
59
+ "value": 0.0,
60
+ "min": 0.0,
61
+ "max": 0.0,
62
+ "count": 200
63
+ },
64
+ "Agent.AerialWildfireSuppression.ExtinguishingTreesReward.mean": {
65
+ "value": 0.0,
66
+ "min": 0.0,
67
+ "max": 0.0,
68
+ "count": 200
69
+ },
70
+ "Agent.AerialWildfireSuppression.ExtinguishingTreesReward.sum": {
71
+ "value": 0.0,
72
+ "min": 0.0,
73
+ "max": 0.0,
74
+ "count": 200
75
+ },
76
+ "Agent.AerialWildfireSuppression.ExtinguishingTrees.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 200
81
+ },
82
+ "Agent.AerialWildfireSuppression.ExtinguishingTrees.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 200
87
+ },
88
+ "Agent.AerialWildfireSuppression.FireOut.mean": {
89
+ "value": 0.0,
90
+ "min": 0.0,
91
+ "max": 0.0,
92
+ "count": 200
93
+ },
94
+ "Agent.AerialWildfireSuppression.FireOut.sum": {
95
+ "value": 0.0,
96
+ "min": 0.0,
97
+ "max": 0.0,
98
+ "count": 200
99
+ },
100
+ "Agent.AerialWildfireSuppression.FiretooClosetoCity.mean": {
101
+ "value": 0.0,
102
+ "min": 0.0,
103
+ "max": 0.0,
104
+ "count": 200
105
+ },
106
+ "Agent.AerialWildfireSuppression.FiretooClosetoCity.sum": {
107
+ "value": 0.0,
108
+ "min": 0.0,
109
+ "max": 0.0,
110
+ "count": 200
111
+ },
112
+ "Agent.AerialWildfireSuppression.CrashCount.mean": {
113
+ "value": 0.0,
114
+ "min": 0.0,
115
+ "max": 0.018518518518518517,
116
+ "count": 200
117
+ },
118
+ "Agent.AerialWildfireSuppression.CrashCount.sum": {
119
+ "value": 0.0,
120
+ "min": 0.0,
121
+ "max": 1.0,
122
+ "count": 200
123
+ },
124
+ "Agent.Environment.LessonNumber.difficulty.mean": {
125
+ "value": 0.0,
126
+ "min": 0.0,
127
+ "max": 0.0,
128
+ "count": 200
129
+ },
130
+ "Agent.Environment.LessonNumber.difficulty.sum": {
131
+ "value": 0.0,
132
+ "min": 0.0,
133
+ "max": 0.0,
134
+ "count": 200
135
+ },
136
+ "Agent.Environment.LessonNumber.task.mean": {
137
+ "value": 0.0,
138
+ "min": 0.0,
139
+ "max": 0.0,
140
+ "count": 200
141
+ },
142
+ "Agent.Environment.LessonNumber.task.sum": {
143
+ "value": 0.0,
144
+ "min": 0.0,
145
+ "max": 0.0,
146
+ "count": 200
147
+ },
148
+ "Agent.Environment.EpisodeLength.mean": {
149
+ "value": 160.52631578947367,
150
+ "min": 129.04347826086956,
151
+ "max": 246.91666666666666,
152
+ "count": 200
153
+ },
154
+ "Agent.Environment.EpisodeLength.sum": {
155
+ "value": 9150.0,
156
+ "min": 8031.0,
157
+ "max": 10065.0,
158
+ "count": 200
159
+ },
160
+ "Agent.Step.mean": {
161
+ "value": 1799972.0,
162
+ "min": 8949.0,
163
+ "max": 1799972.0,
164
+ "count": 200
165
+ },
166
+ "Agent.Step.sum": {
167
+ "value": 1799972.0,
168
+ "min": 8949.0,
169
+ "max": 1799972.0,
170
+ "count": 200
171
+ },
172
+ "Agent.Policy.ExtrinsicValueEstimate.mean": {
173
+ "value": 47.04132080078125,
174
+ "min": 3.999141216278076,
175
+ "max": 51.93593215942383,
176
+ "count": 200
177
+ },
178
+ "Agent.Policy.ExtrinsicValueEstimate.sum": {
179
+ "value": 2634.31396484375,
180
+ "min": 203.95620727539062,
181
+ "max": 3540.715087890625,
182
+ "count": 200
183
+ },
184
+ "Agent.Environment.CumulativeReward.mean": {
185
+ "value": 94.62619318280902,
186
+ "min": 90.24183339464898,
187
+ "max": 95.71714586530413,
188
+ "count": 200
189
+ },
190
+ "Agent.Environment.CumulativeReward.sum": {
191
+ "value": 5299.066818237305,
192
+ "min": 3298.3334197998047,
193
+ "max": 6700.200210571289,
194
+ "count": 200
195
+ },
196
+ "Agent.Policy.ExtrinsicReward.mean": {
197
+ "value": 94.62619318280902,
198
+ "min": 90.24183339464898,
199
+ "max": 95.71714586530413,
200
+ "count": 200
201
+ },
202
+ "Agent.Policy.ExtrinsicReward.sum": {
203
+ "value": 5299.066818237305,
204
+ "min": 3298.3334197998047,
205
+ "max": 6700.200210571289,
206
+ "count": 200
207
+ },
208
+ "Agent.Losses.PolicyLoss.mean": {
209
+ "value": 0.049968739624555204,
210
+ "min": 0.0366371691446094,
211
+ "max": 0.06002760744156024,
212
+ "count": 200
213
+ },
214
+ "Agent.Losses.PolicyLoss.sum": {
215
+ "value": 0.09993747924911041,
216
+ "min": 0.0366371691446094,
217
+ "max": 0.15816150059439607,
218
+ "count": 200
219
+ },
220
+ "Agent.Losses.ValueLoss.mean": {
221
+ "value": 5.482779108718329,
222
+ "min": 4.274142496726093,
223
+ "max": 374.66884620101365,
224
+ "count": 200
225
+ },
226
+ "Agent.Losses.ValueLoss.sum": {
227
+ "value": 10.965558217436659,
228
+ "min": 8.548284993452185,
229
+ "max": 749.3376924020273,
230
+ "count": 200
231
+ },
232
+ "Agent.Policy.LearningRate.mean": {
233
+ "value": 7.360997546666756e-07,
234
+ "min": 7.360997546666756e-07,
235
+ "max": 0.000298905000365,
236
+ "count": 200
237
+ },
238
+ "Agent.Policy.LearningRate.sum": {
239
+ "value": 1.4721995093333512e-06,
240
+ "min": 1.4721995093333512e-06,
241
+ "max": 0.0008842865052378333,
242
+ "count": 200
243
+ },
244
+ "Agent.Policy.Epsilon.mean": {
245
+ "value": 0.10024533333333334,
246
+ "min": 0.10024533333333334,
247
+ "max": 0.19963500000000003,
248
+ "count": 200
249
+ },
250
+ "Agent.Policy.Epsilon.sum": {
251
+ "value": 0.20049066666666668,
252
+ "min": 0.1867205,
253
+ "max": 0.5947621666666666,
254
+ "count": 200
255
+ },
256
+ "Agent.Policy.Beta.mean": {
257
+ "value": 2.2242133333333484e-05,
258
+ "min": 2.2242133333333484e-05,
259
+ "max": 0.0049817865,
260
+ "count": 200
261
+ },
262
+ "Agent.Policy.Beta.sum": {
263
+ "value": 4.448426666666697e-05,
264
+ "min": 4.448426666666697e-05,
265
+ "max": 0.014738632116666666,
266
+ "count": 200
267
+ },
268
+ "Agent.IsTraining.mean": {
269
+ "value": 1.0,
270
+ "min": 1.0,
271
+ "max": 1.0,
272
+ "count": 200
273
+ },
274
+ "Agent.IsTraining.sum": {
275
+ "value": 1.0,
276
+ "min": 1.0,
277
+ "max": 1.0,
278
+ "count": 200
279
+ }
280
+ },
281
+ "metadata": {
282
+ "timer_format_version": "0.1.0",
283
+ "start_time_seconds": "1717984704",
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/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train.yaml --run-id=AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train --base-port 5009",
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": "1717988819"
292
+ },
293
+ "total": 4114.8860607999995,
294
+ "count": 1,
295
+ "self": 0.608249099999739,
296
+ "children": {
297
+ "run_training.setup": {
298
+ "total": 0.048208200000000034,
299
+ "count": 1,
300
+ "self": 0.048208200000000034
301
+ },
302
+ "TrainerController.start_learning": {
303
+ "total": 4114.2296035,
304
+ "count": 1,
305
+ "self": 6.975328899962733,
306
+ "children": {
307
+ "TrainerController._reset_env": {
308
+ "total": 3.4811213000000003,
309
+ "count": 1,
310
+ "self": 3.4811213000000003
311
+ },
312
+ "TrainerController.advance": {
313
+ "total": 4103.7074418000375,
314
+ "count": 600117,
315
+ "self": 6.6781949999876815,
316
+ "children": {
317
+ "env_step": {
318
+ "total": 4097.02924680005,
319
+ "count": 600117,
320
+ "self": 2527.1466364001517,
321
+ "children": {
322
+ "SubprocessEnvManager._take_step": {
323
+ "total": 1565.3623866999546,
324
+ "count": 600117,
325
+ "self": 14.433628500075429,
326
+ "children": {
327
+ "TorchPolicy.evaluate": {
328
+ "total": 1550.9287581998792,
329
+ "count": 600117,
330
+ "self": 1550.9287581998792
331
+ }
332
+ }
333
+ },
334
+ "workers": {
335
+ "total": 4.520223699943298,
336
+ "count": 600117,
337
+ "self": 0.0,
338
+ "children": {
339
+ "worker_root": {
340
+ "total": 4102.945331000059,
341
+ "count": 600117,
342
+ "is_parallel": true,
343
+ "self": 1956.3627205001071,
344
+ "children": {
345
+ "steps_from_proto": {
346
+ "total": 0.005825199999999864,
347
+ "count": 1,
348
+ "is_parallel": true,
349
+ "self": 0.00010339999999997573,
350
+ "children": {
351
+ "_process_maybe_compressed_observation": {
352
+ "total": 0.005636700000000161,
353
+ "count": 2,
354
+ "is_parallel": true,
355
+ "self": 3.8800000000449586e-05,
356
+ "children": {
357
+ "_observation_to_np_array": {
358
+ "total": 0.0055978999999997114,
359
+ "count": 3,
360
+ "is_parallel": true,
361
+ "self": 2.6199999999754198e-05,
362
+ "children": {
363
+ "process_pixels": {
364
+ "total": 0.005571699999999957,
365
+ "count": 3,
366
+ "is_parallel": true,
367
+ "self": 0.00017059999999968767,
368
+ "children": {
369
+ "image_decompress": {
370
+ "total": 0.00540110000000027,
371
+ "count": 3,
372
+ "is_parallel": true,
373
+ "self": 0.00540110000000027
374
+ }
375
+ }
376
+ }
377
+ }
378
+ }
379
+ }
380
+ },
381
+ "_process_rank_one_or_two_observation": {
382
+ "total": 8.509999999972706e-05,
383
+ "count": 2,
384
+ "is_parallel": true,
385
+ "self": 8.509999999972706e-05
386
+ }
387
+ }
388
+ },
389
+ "UnityEnvironment.step": {
390
+ "total": 2146.576785299952,
391
+ "count": 600117,
392
+ "is_parallel": true,
393
+ "self": 24.483022499961407,
394
+ "children": {
395
+ "UnityEnvironment._generate_step_input": {
396
+ "total": 24.70284529998681,
397
+ "count": 600117,
398
+ "is_parallel": true,
399
+ "self": 24.70284529998681
400
+ },
401
+ "communicator.exchange": {
402
+ "total": 1894.0330121000961,
403
+ "count": 600117,
404
+ "is_parallel": true,
405
+ "self": 1894.0330121000961
406
+ },
407
+ "steps_from_proto": {
408
+ "total": 203.35790539990762,
409
+ "count": 600117,
410
+ "is_parallel": true,
411
+ "self": 42.8705798995974,
412
+ "children": {
413
+ "_process_maybe_compressed_observation": {
414
+ "total": 139.7349758002655,
415
+ "count": 1200234,
416
+ "is_parallel": true,
417
+ "self": 12.342407900626242,
418
+ "children": {
419
+ "_observation_to_np_array": {
420
+ "total": 127.39256789963925,
421
+ "count": 1811409,
422
+ "is_parallel": true,
423
+ "self": 11.026397299554148,
424
+ "children": {
425
+ "process_pixels": {
426
+ "total": 116.3661706000851,
427
+ "count": 1811409,
428
+ "is_parallel": true,
429
+ "self": 42.0181005000975,
430
+ "children": {
431
+ "image_decompress": {
432
+ "total": 74.3480700999876,
433
+ "count": 1811409,
434
+ "is_parallel": true,
435
+ "self": 74.3480700999876
436
+ }
437
+ }
438
+ }
439
+ }
440
+ }
441
+ }
442
+ },
443
+ "_process_rank_one_or_two_observation": {
444
+ "total": 20.75234970004474,
445
+ "count": 1200234,
446
+ "is_parallel": true,
447
+ "self": 20.75234970004474
448
+ }
449
+ }
450
+ }
451
+ }
452
+ }
453
+ }
454
+ }
455
+ }
456
+ }
457
+ }
458
+ }
459
+ }
460
+ },
461
+ "trainer_threads": {
462
+ "total": 2.5299999833805487e-05,
463
+ "count": 1,
464
+ "self": 2.5299999833805487e-05,
465
+ "children": {
466
+ "thread_root": {
467
+ "total": 0.0,
468
+ "count": 0,
469
+ "is_parallel": true,
470
+ "self": 0.0,
471
+ "children": {
472
+ "trainer_advance": {
473
+ "total": 4108.769842000013,
474
+ "count": 224022,
475
+ "is_parallel": true,
476
+ "self": 5.889544399969964,
477
+ "children": {
478
+ "process_trajectory": {
479
+ "total": 3533.2422356000466,
480
+ "count": 224022,
481
+ "is_parallel": true,
482
+ "self": 3532.9699339000463,
483
+ "children": {
484
+ "RLTrainer._checkpoint": {
485
+ "total": 0.2723017000000709,
486
+ "count": 3,
487
+ "is_parallel": true,
488
+ "self": 0.2723017000000709
489
+ }
490
+ }
491
+ },
492
+ "_update_policy": {
493
+ "total": 569.638061999997,
494
+ "count": 412,
495
+ "is_parallel": true,
496
+ "self": 141.86442069998031,
497
+ "children": {
498
+ "TorchPPOOptimizer.update": {
499
+ "total": 427.7736413000167,
500
+ "count": 20517,
501
+ "is_parallel": true,
502
+ "self": 427.7736413000167
503
+ }
504
+ }
505
+ }
506
+ }
507
+ }
508
+ }
509
+ }
510
+ }
511
+ },
512
+ "TrainerController._save_models": {
513
+ "total": 0.06568619999961811,
514
+ "count": 1,
515
+ "self": 0.0057018999996216735,
516
+ "children": {
517
+ "RLTrainer._checkpoint": {
518
+ "total": 0.05998429999999644,
519
+ "count": 1,
520
+ "self": 0.05998429999999644
521
+ }
522
+ }
523
+ }
524
+ }
525
+ }
526
+ }
527
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "difficulty": {
3
+ "lesson_num": 0
4
+ },
5
+ "task": {
6
+ "lesson_num": 0
7
+ },
8
+ "Agent": {
9
+ "checkpoints": [
10
+ {
11
+ "steps": 499898,
12
+ "file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-499898.onnx",
13
+ "reward": 92.13333892822266,
14
+ "creation_time": 1717985809.7315648,
15
+ "auxillary_file_paths": [
16
+ "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-499898.pt"
17
+ ]
18
+ },
19
+ {
20
+ "steps": 999832,
21
+ "file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-999832.onnx",
22
+ "reward": 94.87701442323882,
23
+ "creation_time": 1717986929.2966213,
24
+ "auxillary_file_paths": [
25
+ "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-999832.pt"
26
+ ]
27
+ },
28
+ {
29
+ "steps": 1499935,
30
+ "file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-1499935.onnx",
31
+ "reward": 95.2880973815918,
32
+ "creation_time": 1717988101.302394,
33
+ "auxillary_file_paths": [
34
+ "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-1499935.pt"
35
+ ]
36
+ },
37
+ {
38
+ "steps": 1800348,
39
+ "file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-1800348.onnx",
40
+ "reward": 95.00000211927626,
41
+ "creation_time": 1717988819.1775706,
42
+ "auxillary_file_paths": [
43
+ "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-1800348.pt"
44
+ ]
45
+ }
46
+ ],
47
+ "final_checkpoint": {
48
+ "steps": 1800348,
49
+ "file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent.onnx",
50
+ "reward": 95.00000211927626,
51
+ "creation_time": 1717988819.1775706,
52
+ "auxillary_file_paths": [
53
+ "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_10_task_5_run_id_2_train\\Agent\\Agent-1800348.pt"
54
+ ]
55
+ }
56
+ },
57
+ "metadata": {
58
+ "stats_format_version": "0.3.0",
59
+ "mlagents_version": "0.30.0",
60
+ "torch_version": "1.7.1+cu110"
61
+ }
62
+ }