Hugging Face's logo

hivex-research
/
hivex-DBR-PPO-baseline-task-2-difficulty-1

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-drone-based-reforestation
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community
philippds commited on
Commit
365c4aa
•
1 Parent(s): 962b3d2

Upload 13 files

Browse files
Files changed (13) hide show
  1. Agent.onnx +3 -0
  2. Agent/Agent-1200192.onnx +3 -0
  3. Agent/Agent-1200192.pt +3 -0
  4. Agent/Agent-499946.onnx +3 -0
  5. Agent/Agent-499946.pt +3 -0
  6. Agent/Agent-999935.onnx +3 -0
  7. Agent/Agent-999935.pt +3 -0
  8. Agent/checkpoint.pt +3 -0
  9. Agent/events.out.tfevents.1716791689.RICHARD.43176.0 +3 -0
  10. README.md +35 -0
  11. configuration.yaml +107 -0
  12. run_logs/timers.json +575 -0
  13. run_logs/training_status.json +53 -0
Agent.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188e6582edef2f2cec7fc1a0fb223b5d4c68127808c910d2d1377a05ec7bfb74
3
+ size 562656
Agent/Agent-1200192.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188e6582edef2f2cec7fc1a0fb223b5d4c68127808c910d2d1377a05ec7bfb74
3
+ size 562656
Agent/Agent-1200192.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80695872d30f8b12881d30a3219369338585eb8b03a56f0a152ab5631c3e01af
3
+ size 4530031
Agent/Agent-499946.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e032ca9538196583173298f2f0c843731edac7675673d1aeba4a0b253bceb30
3
+ size 562656
Agent/Agent-499946.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfa0980ca8826f96f04ca6bbe14e27c92346a14b6b3b6f961323894b5941e31
3
+ size 4530031
Agent/Agent-999935.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05fe418b2d4cdf2ee0d9d0eccbd569fc013cfd20dc7cb33cbf7fe009f4a678df
3
+ size 562656
Agent/Agent-999935.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e036db8b5e14c868ae53794fa046982053ff93f8c45d0582737ddb9bd76cd7
3
+ size 4530031
Agent/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80695872d30f8b12881d30a3219369338585eb8b03a56f0a152ab5631c3e01af
3
+ size 4530031
Agent/events.out.tfevents.1716791689.RICHARD.43176.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4080ce4a0cbad80dd7d380634481daaca2577554c6c4e8304bb4a107f1c7bf0b
3
+ size 2052295
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: hivex
3
+ original_train_name: DroneBasedReforestation_difficulty_1_task_2_run_id_1_train
4
+ tags:
5
+ - hivex
6
+ - hivex-drone-based-reforestation
7
+ - reinforcement-learning
8
+ - multi-agent-reinforcement-learning
9
+ model-index:
10
+ - name: hivex-DBR-PPO-baseline-task-2-difficulty-1
11
+ results:
12
+ - task:
13
+ type: sub-task
14
+ name: pick_up_seed_at_base
15
+ task-id: 2
16
+ difficulty-id: 1
17
+ dataset:
18
+ name: hivex-drone-based-reforestation
19
+ type: hivex-drone-based-reforestation
20
+ metrics:
21
+ - type: out_of_energy_count
22
+ value: 0.5738862597942352 +/- 0.0598372330317942
23
+ name: Out of Energy Count
24
+ verified: true
25
+ - type: recharge_energy_count
26
+ value: 147.40538289248943 +/- 114.91514898456525
27
+ name: Recharge Energy Count
28
+ verified: true
29
+ - type: cumulative_reward
30
+ value: 15.073969823122024 +/- 9.872171258055769
31
+ name: Cumulative Reward
32
+ verified: true
33
+ ---
34
+
35
+ This model serves as the baseline for the **Drone-Based Reforestation** environment, trained and tested on task <code>2</code> with difficulty <code>1</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>Environment: **Drone-Based Reforestation**<br>Task: <code>2</code><br>Difficulty: <code>1</code><br>Algorithm: <code>PPO</code><br>Episode Length: <code>2000</code><br>Training <code>max_steps</code>: <code>1200000</code><br>Testing <code>max_steps</code>: <code>300000</code><br><br>Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>Download the [Environment](https://github.com/hivex-research/hivex-environments)
configuration.yaml ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Agent:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 1024
7
+ buffer_size: 8192
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: 128
20
+ num_layers: 2
21
+ vis_encode_type: resnet
22
+ memory: null
23
+ goal_conditioning_type: hyper
24
+ deterministic: false
25
+ reward_signals:
26
+ curiosity:
27
+ gamma: 0.99
28
+ strength: 0.1
29
+ network_settings:
30
+ normalize: false
31
+ hidden_units: 128
32
+ num_layers: 2
33
+ vis_encode_type: resnet
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: 0.9
42
+ network_settings:
43
+ normalize: false
44
+ hidden_units: 128
45
+ num_layers: 2
46
+ vis_encode_type: resnet
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: 1200000
54
+ time_horizon: 8192
55
+ summary_freq: 6000
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_DroneBasedReforestation_win
61
+ env_args: null
62
+ base_port: 5007
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: 1
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: DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_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 +1,575 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Agent.Policy.Entropy.mean": {
5
+ "value": 1.435887336730957,
6
+ "min": 1.4189385175704956,
7
+ "max": 1.4451199769973755,
8
+ "count": 200
9
+ },
10
+ "Agent.Policy.Entropy.sum": {
11
+ "value": 7878.7138671875,
12
+ "min": 6969.048828125,
13
+ "max": 10059.47265625,
14
+ "count": 200
15
+ },
16
+ "Agent.DroneBasedReforestation.TreeDropCount.mean": {
17
+ "value": 0.0,
18
+ "min": 0.0,
19
+ "max": 0.0,
20
+ "count": 200
21
+ },
22
+ "Agent.DroneBasedReforestation.TreeDropCount.sum": {
23
+ "value": 0.0,
24
+ "min": 0.0,
25
+ "max": 0.0,
26
+ "count": 200
27
+ },
28
+ "Agent.DroneBasedReforestation.RechargeEnergyCount.mean": {
29
+ "value": 0.06666666666666667,
30
+ "min": 0.0,
31
+ "max": 425.3888888888889,
32
+ "count": 200
33
+ },
34
+ "Agent.DroneBasedReforestation.RechargeEnergyCount.sum": {
35
+ "value": 1.0,
36
+ "min": 0.0,
37
+ "max": 7657.0,
38
+ "count": 200
39
+ },
40
+ "Agent.DroneBasedReforestation.SaveLocationCount.mean": {
41
+ "value": 0.0,
42
+ "min": 0.0,
43
+ "max": 0.0,
44
+ "count": 200
45
+ },
46
+ "Agent.DroneBasedReforestation.SaveLocationCount.sum": {
47
+ "value": 0.0,
48
+ "min": 0.0,
49
+ "max": 0.0,
50
+ "count": 200
51
+ },
52
+ "Agent.DroneBasedReforestation.OutofEnergyCount.mean": {
53
+ "value": 0.5333333333333333,
54
+ "min": 0.3888888888888889,
55
+ "max": 0.7333333333333333,
56
+ "count": 200
57
+ },
58
+ "Agent.DroneBasedReforestation.OutofEnergyCount.sum": {
59
+ "value": 8.0,
60
+ "min": 7.0,
61
+ "max": 14.0,
62
+ "count": 200
63
+ },
64
+ "Agent.DroneBasedReforestation.CumulativeDistanceUntilTreeDrop.mean": {
65
+ "value": 0.0,
66
+ "min": 0.0,
67
+ "max": 0.0,
68
+ "count": 200
69
+ },
70
+ "Agent.DroneBasedReforestation.CumulativeDistanceUntilTreeDrop.sum": {
71
+ "value": 0.0,
72
+ "min": 0.0,
73
+ "max": 0.0,
74
+ "count": 200
75
+ },
76
+ "Agent.DroneBasedReforestation.CumulativeTreeDropReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 200
81
+ },
82
+ "Agent.DroneBasedReforestation.CumulativeTreeDropReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 200
87
+ },
88
+ "Agent.DroneBasedReforestation.CumulativeDistanceReward.mean": {
89
+ "value": 0.0,
90
+ "min": 0.0,
91
+ "max": 0.0,
92
+ "count": 200
93
+ },
94
+ "Agent.DroneBasedReforestation.CumulativeDistanceReward.sum": {
95
+ "value": 0.0,
96
+ "min": 0.0,
97
+ "max": 0.0,
98
+ "count": 200
99
+ },
100
+ "Agent.DroneBasedReforestation.CumulativeNormalizedDistanceUntilTreeDrop.mean": {
101
+ "value": 0.0,
102
+ "min": 0.0,
103
+ "max": 0.0,
104
+ "count": 200
105
+ },
106
+ "Agent.DroneBasedReforestation.CumulativeNormalizedDistanceUntilTreeDrop.sum": {
107
+ "value": 0.0,
108
+ "min": 0.0,
109
+ "max": 0.0,
110
+ "count": 200
111
+ },
112
+ "Agent.DroneBasedReforestation.CumulativeDistancetoExistingTrees.mean": {
113
+ "value": 0.0,
114
+ "min": 0.0,
115
+ "max": 0.0,
116
+ "count": 200
117
+ },
118
+ "Agent.DroneBasedReforestation.CumulativeDistancetoExistingTrees.sum": {
119
+ "value": 0.0,
120
+ "min": 0.0,
121
+ "max": 0.0,
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": 337.8,
150
+ "min": 286.57142857142856,
151
+ "max": 399.0,
152
+ "count": 200
153
+ },
154
+ "Agent.Environment.EpisodeLength.sum": {
155
+ "value": 5067.0,
156
+ "min": 4839.0,
157
+ "max": 6978.0,
158
+ "count": 200
159
+ },
160
+ "Agent.Step.mean": {
161
+ "value": 1199910.0,
162
+ "min": 5600.0,
163
+ "max": 1199910.0,
164
+ "count": 200
165
+ },
166
+ "Agent.Step.sum": {
167
+ "value": 1199910.0,
168
+ "min": 5600.0,
169
+ "max": 1199910.0,
170
+ "count": 200
171
+ },
172
+ "Agent.Policy.CuriosityValueEstimate.mean": {
173
+ "value": 0.30304810404777527,
174
+ "min": 0.02929520234465599,
175
+ "max": 1.0432465076446533,
176
+ "count": 200
177
+ },
178
+ "Agent.Policy.CuriosityValueEstimate.sum": {
179
+ "value": 4.545721530914307,
180
+ "min": 0.43942803144454956,
181
+ "max": 15.648697853088379,
182
+ "count": 200
183
+ },
184
+ "Agent.Policy.ExtrinsicValueEstimate.mean": {
185
+ "value": 2.1079864501953125,
186
+ "min": -0.4214349389076233,
187
+ "max": 3.233757734298706,
188
+ "count": 200
189
+ },
190
+ "Agent.Policy.ExtrinsicValueEstimate.sum": {
191
+ "value": 31.619796752929688,
192
+ "min": -6.321524143218994,
193
+ "max": 58.207637786865234,
194
+ "count": 200
195
+ },
196
+ "Agent.Environment.CumulativeReward.mean": {
197
+ "value": -0.9993666529655456,
198
+ "min": -1.1309333046277363,
199
+ "max": 34.09010376930237,
200
+ "count": 200
201
+ },
202
+ "Agent.Environment.CumulativeReward.sum": {
203
+ "value": -14.990499794483185,
204
+ "min": -16.963999569416046,
205
+ "max": 681.8020753860474,
206
+ "count": 200
207
+ },
208
+ "Agent.Policy.CuriosityReward.mean": {
209
+ "value": 1.1821201721827188,
210
+ "min": 0.0,
211
+ "max": 14.20567144950231,
212
+ "count": 200
213
+ },
214
+ "Agent.Policy.CuriosityReward.sum": {
215
+ "value": 17.731802582740784,
216
+ "min": 0.0,
217
+ "max": 255.70208609104156,
218
+ "count": 200
219
+ },
220
+ "Agent.Policy.ExtrinsicReward.mean": {
221
+ "value": -0.8994301954905192,
222
+ "min": -1.0178401708602904,
223
+ "max": 30.681086124293508,
224
+ "count": 200
225
+ },
226
+ "Agent.Policy.ExtrinsicReward.sum": {
227
+ "value": -13.491452932357788,
228
+ "min": -15.267602562904358,
229
+ "max": 613.6217224858701,
230
+ "count": 200
231
+ },
232
+ "Agent.IsTraining.mean": {
233
+ "value": 1.0,
234
+ "min": 1.0,
235
+ "max": 1.0,
236
+ "count": 200
237
+ },
238
+ "Agent.IsTraining.sum": {
239
+ "value": 1.0,
240
+ "min": 1.0,
241
+ "max": 1.0,
242
+ "count": 200
243
+ },
244
+ "Agent.Losses.PolicyLoss.mean": {
245
+ "value": 0.02971380145754665,
246
+ "min": 0.016504992517487455,
247
+ "max": 0.031236064077044528,
248
+ "count": 140
249
+ },
250
+ "Agent.Losses.PolicyLoss.sum": {
251
+ "value": 0.02971380145754665,
252
+ "min": 0.016504992517487455,
253
+ "max": 0.031236064077044528,
254
+ "count": 140
255
+ },
256
+ "Agent.Losses.ValueLoss.mean": {
257
+ "value": 0.37336699292063713,
258
+ "min": 0.005356620560633019,
259
+ "max": 22.710176428159077,
260
+ "count": 140
261
+ },
262
+ "Agent.Losses.ValueLoss.sum": {
263
+ "value": 0.37336699292063713,
264
+ "min": 0.005356620560633019,
265
+ "max": 22.710176428159077,
266
+ "count": 140
267
+ },
268
+ "Agent.Policy.LearningRate.mean": {
269
+ "value": 2.2599992500014174e-08,
270
+ "min": 2.2599992500014174e-08,
271
+ "max": 0.0002979000007,
272
+ "count": 140
273
+ },
274
+ "Agent.Policy.LearningRate.sum": {
275
+ "value": 2.2599992500014174e-08,
276
+ "min": 2.2599992500014174e-08,
277
+ "max": 0.0002979000007,
278
+ "count": 140
279
+ },
280
+ "Agent.Policy.Epsilon.mean": {
281
+ "value": 0.10000750000000001,
282
+ "min": 0.10000750000000001,
283
+ "max": 0.1993,
284
+ "count": 140
285
+ },
286
+ "Agent.Policy.Epsilon.sum": {
287
+ "value": 0.10000750000000001,
288
+ "min": 0.10000750000000001,
289
+ "max": 0.1993,
290
+ "count": 140
291
+ },
292
+ "Agent.Policy.Beta.mean": {
293
+ "value": 1.0374250000000235e-05,
294
+ "min": 1.0374250000000235e-05,
295
+ "max": 0.00496507,
296
+ "count": 140
297
+ },
298
+ "Agent.Policy.Beta.sum": {
299
+ "value": 1.0374250000000235e-05,
300
+ "min": 1.0374250000000235e-05,
301
+ "max": 0.00496507,
302
+ "count": 140
303
+ },
304
+ "Agent.Losses.CuriosityForwardLoss.mean": {
305
+ "value": 0.029829473545153935,
306
+ "min": 0.02595311333425343,
307
+ "max": 0.5835289520521959,
308
+ "count": 140
309
+ },
310
+ "Agent.Losses.CuriosityForwardLoss.sum": {
311
+ "value": 0.029829473545153935,
312
+ "min": 0.02595311333425343,
313
+ "max": 0.5835289520521959,
314
+ "count": 140
315
+ },
316
+ "Agent.Losses.CuriosityInverseLoss.mean": {
317
+ "value": 1.7122151553630829,
318
+ "min": 1.7122151553630829,
319
+ "max": 3.310828576485316,
320
+ "count": 140
321
+ },
322
+ "Agent.Losses.CuriosityInverseLoss.sum": {
323
+ "value": 1.7122151553630829,
324
+ "min": 1.7122151553630829,
325
+ "max": 3.310828576485316,
326
+ "count": 140
327
+ }
328
+ },
329
+ "metadata": {
330
+ "timer_format_version": "0.1.0",
331
+ "start_time_seconds": "1716791688",
332
+ "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]",
333
+ "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/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train.yaml --run-id=DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train --base-port 5007",
334
+ "mlagents_version": "0.30.0",
335
+ "mlagents_envs_version": "0.30.0",
336
+ "communication_protocol_version": "1.5.0",
337
+ "pytorch_version": "1.7.1+cu110",
338
+ "numpy_version": "1.21.0",
339
+ "end_time_seconds": "1716796800"
340
+ },
341
+ "total": 5112.771583,
342
+ "count": 1,
343
+ "self": 0.5061833999998271,
344
+ "children": {
345
+ "run_training.setup": {
346
+ "total": 0.0569307,
347
+ "count": 1,
348
+ "self": 0.0569307
349
+ },
350
+ "TrainerController.start_learning": {
351
+ "total": 5112.2084689,
352
+ "count": 1,
353
+ "self": 8.794914800045262,
354
+ "children": {
355
+ "TrainerController._reset_env": {
356
+ "total": 2.3047044,
357
+ "count": 1,
358
+ "self": 2.3047044
359
+ },
360
+ "TrainerController.advance": {
361
+ "total": 5100.807544299954,
362
+ "count": 401032,
363
+ "self": 8.66736219997074,
364
+ "children": {
365
+ "env_step": {
366
+ "total": 5092.140182099984,
367
+ "count": 401032,
368
+ "self": 2073.4088428996556,
369
+ "children": {
370
+ "SubprocessEnvManager._take_step": {
371
+ "total": 3013.3889008001634,
372
+ "count": 401032,
373
+ "self": 15.15800860023137,
374
+ "children": {
375
+ "TorchPolicy.evaluate": {
376
+ "total": 2998.230892199932,
377
+ "count": 400200,
378
+ "self": 2998.230892199932
379
+ }
380
+ }
381
+ },
382
+ "workers": {
383
+ "total": 5.342438400164718,
384
+ "count": 401032,
385
+ "self": 0.0,
386
+ "children": {
387
+ "worker_root": {
388
+ "total": 5102.285246300213,
389
+ "count": 401032,
390
+ "is_parallel": true,
391
+ "self": 3314.0328470004383,
392
+ "children": {
393
+ "steps_from_proto": {
394
+ "total": 0.006262299999999943,
395
+ "count": 1,
396
+ "is_parallel": true,
397
+ "self": 0.00010449999999950776,
398
+ "children": {
399
+ "_process_maybe_compressed_observation": {
400
+ "total": 0.006111800000000223,
401
+ "count": 2,
402
+ "is_parallel": true,
403
+ "self": 3.080000000021954e-05,
404
+ "children": {
405
+ "_observation_to_np_array": {
406
+ "total": 0.006081000000000003,
407
+ "count": 3,
408
+ "is_parallel": true,
409
+ "self": 2.990000000013815e-05,
410
+ "children": {
411
+ "process_pixels": {
412
+ "total": 0.006051099999999865,
413
+ "count": 3,
414
+ "is_parallel": true,
415
+ "self": 0.00023850000000003035,
416
+ "children": {
417
+ "image_decompress": {
418
+ "total": 0.0058125999999998346,
419
+ "count": 3,
420
+ "is_parallel": true,
421
+ "self": 0.0058125999999998346
422
+ }
423
+ }
424
+ }
425
+ }
426
+ }
427
+ }
428
+ },
429
+ "_process_rank_one_or_two_observation": {
430
+ "total": 4.600000000021254e-05,
431
+ "count": 2,
432
+ "is_parallel": true,
433
+ "self": 4.600000000021254e-05
434
+ }
435
+ }
436
+ },
437
+ "UnityEnvironment.step": {
438
+ "total": 1788.2461369997745,
439
+ "count": 401032,
440
+ "is_parallel": true,
441
+ "self": 23.128167499308347,
442
+ "children": {
443
+ "UnityEnvironment._generate_step_input": {
444
+ "total": 24.404275500100383,
445
+ "count": 401032,
446
+ "is_parallel": true,
447
+ "self": 24.404275500100383
448
+ },
449
+ "communicator.exchange": {
450
+ "total": 1551.6798302003008,
451
+ "count": 401032,
452
+ "is_parallel": true,
453
+ "self": 1551.6798302003008
454
+ },
455
+ "steps_from_proto": {
456
+ "total": 189.03386380006518,
457
+ "count": 401032,
458
+ "is_parallel": true,
459
+ "self": 37.66603239976422,
460
+ "children": {
461
+ "_process_maybe_compressed_observation": {
462
+ "total": 135.37231290009942,
463
+ "count": 802064,
464
+ "is_parallel": true,
465
+ "self": 10.339008800349845,
466
+ "children": {
467
+ "_observation_to_np_array": {
468
+ "total": 125.03330409974957,
469
+ "count": 1203876,
470
+ "is_parallel": true,
471
+ "self": 9.5104148996205,
472
+ "children": {
473
+ "process_pixels": {
474
+ "total": 115.52288920012907,
475
+ "count": 1203876,
476
+ "is_parallel": true,
477
+ "self": 53.60336780038161,
478
+ "children": {
479
+ "image_decompress": {
480
+ "total": 61.91952139974746,
481
+ "count": 1203876,
482
+ "is_parallel": true,
483
+ "self": 61.91952139974746
484
+ }
485
+ }
486
+ }
487
+ }
488
+ }
489
+ }
490
+ },
491
+ "_process_rank_one_or_two_observation": {
492
+ "total": 15.995518500201548,
493
+ "count": 802064,
494
+ "is_parallel": true,
495
+ "self": 15.995518500201548
496
+ }
497
+ }
498
+ }
499
+ }
500
+ }
501
+ }
502
+ }
503
+ }
504
+ }
505
+ }
506
+ }
507
+ }
508
+ },
509
+ "trainer_threads": {
510
+ "total": 3.440000000409782e-05,
511
+ "count": 1,
512
+ "self": 3.440000000409782e-05,
513
+ "children": {
514
+ "thread_root": {
515
+ "total": 0.0,
516
+ "count": 0,
517
+ "is_parallel": true,
518
+ "self": 0.0,
519
+ "children": {
520
+ "trainer_advance": {
521
+ "total": 5106.15831670013,
522
+ "count": 249869,
523
+ "is_parallel": true,
524
+ "self": 10.651582200075609,
525
+ "children": {
526
+ "process_trajectory": {
527
+ "total": 4060.483484900052,
528
+ "count": 249869,
529
+ "is_parallel": true,
530
+ "self": 4059.937680600052,
531
+ "children": {
532
+ "RLTrainer._checkpoint": {
533
+ "total": 0.5458043000000998,
534
+ "count": 2,
535
+ "is_parallel": true,
536
+ "self": 0.5458043000000998
537
+ }
538
+ }
539
+ },
540
+ "_update_policy": {
541
+ "total": 1035.023249600002,
542
+ "count": 140,
543
+ "is_parallel": true,
544
+ "self": 683.0441157999867,
545
+ "children": {
546
+ "TorchPPOOptimizer.update": {
547
+ "total": 351.97913380001523,
548
+ "count": 3387,
549
+ "is_parallel": true,
550
+ "self": 351.97913380001523
551
+ }
552
+ }
553
+ }
554
+ }
555
+ }
556
+ }
557
+ }
558
+ }
559
+ },
560
+ "TrainerController._save_models": {
561
+ "total": 0.30127100000026985,
562
+ "count": 1,
563
+ "self": 0.004740000000310829,
564
+ "children": {
565
+ "RLTrainer._checkpoint": {
566
+ "total": 0.296530999999959,
567
+ "count": 1,
568
+ "self": 0.296530999999959
569
+ }
570
+ }
571
+ }
572
+ }
573
+ }
574
+ }
575
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "difficulty": {
3
+ "lesson_num": 0
4
+ },
5
+ "task": {
6
+ "lesson_num": 0
7
+ },
8
+ "Agent": {
9
+ "checkpoints": [
10
+ {
11
+ "steps": 499946,
12
+ "file_path": "results\\DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train\\Agent\\Agent-499946.onnx",
13
+ "reward": -0.9993636228821494,
14
+ "creation_time": 1716793647.69662,
15
+ "auxillary_file_paths": [
16
+ "results\\DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train\\Agent\\Agent-499946.pt"
17
+ ]
18
+ },
19
+ {
20
+ "steps": 999935,
21
+ "file_path": "results\\DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train\\Agent\\Agent-999935.onnx",
22
+ "reward": -0.9984999895095825,
23
+ "creation_time": 1716795884.0925207,
24
+ "auxillary_file_paths": [
25
+ "results\\DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train\\Agent\\Agent-999935.pt"
26
+ ]
27
+ },
28
+ {
29
+ "steps": 1200192,
30
+ "file_path": "results\\DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train\\Agent\\Agent-1200192.onnx",
31
+ "reward": 33.09966746966044,
32
+ "creation_time": 1716796800.4205854,
33
+ "auxillary_file_paths": [
34
+ "results\\DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train\\Agent\\Agent-1200192.pt"
35
+ ]
36
+ }
37
+ ],
38
+ "final_checkpoint": {
39
+ "steps": 1200192,
40
+ "file_path": "results\\DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train\\Agent.onnx",
41
+ "reward": 33.09966746966044,
42
+ "creation_time": 1716796800.4205854,
43
+ "auxillary_file_paths": [
44
+ "results\\DroneBasedReforestation/train/DroneBasedReforestation_difficulty_1_task_2_run_id_1_train\\Agent\\Agent-1200192.pt"
45
+ ]
46
+ }
47
+ },
48
+ "metadata": {
49
+ "stats_format_version": "0.3.0",
50
+ "mlagents_version": "0.30.0",
51
+ "torch_version": "1.7.1+cu110"
52
+ }
53
+ }