Hugging Face's logo

hivex-research
/
hivex-OPC-PPO-baseline-task-0

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-ocean-plastic-collection
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community
philippds commited on
Commit
5e03618
•
1 Parent(s): e9e4564

Upload 16 files

Browse files
Files changed (16) hide show
  1. Agent.onnx +3 -0
  2. Agent/Agent-1499652.onnx +3 -0
  3. Agent/Agent-1499652.pt +3 -0
  4. Agent/Agent-1999721.onnx +3 -0
  5. Agent/Agent-1999721.pt +3 -0
  6. Agent/Agent-2499831.onnx +3 -0
  7. Agent/Agent-2499831.pt +3 -0
  8. Agent/Agent-2999817.onnx +3 -0
  9. Agent/Agent-2999817.pt +3 -0
  10. Agent/Agent-3000201.onnx +3 -0
  11. Agent/Agent-3000201.pt +3 -0
  12. Agent/checkpoint.pt +3 -0
  13. Agent/events.out.tfevents.1716242424.RICHARD.29368.0 +3 -0
  14. configuration.yaml +98 -0
  15. run_logs/timers.json +447 -0
  16. run_logs/training_status.json +68 -0
Agent.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8caa3b10ae5b6140476a6d47d7cbbb75f234f5719f34c8ae01bd6d29bbf5eec1
3
+ size 608107
Agent/Agent-1499652.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71125cbb26dff7307508c24d883585bedf9fc32d9f2810e50a674b1363878ef6
3
+ size 608107
Agent/Agent-1499652.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9852b1bf8184ad492d85c7dfdfe0cc9c302880a9a4de3e88ed3d492cfe5a1b44
3
+ size 4847687
Agent/Agent-1999721.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6b54a81f979ee54f3ffc0d3c54ef6262276a681a7e72e121507930aa111ca9f
3
+ size 608107
Agent/Agent-1999721.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1cc0ffcc8d74011979f2d9f858450da1723c22c1bb44b20b60381ff030563a
3
+ size 4847687
Agent/Agent-2499831.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582850b4f8f51e6f51be9092de16b072e9d01ba88911137a5fd83be54c6e2c71
3
+ size 608107
Agent/Agent-2499831.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991fe23c83ed852570ce87b5da73d14d7d3fbb0bf51b11f3393a0dae39f0eca6
3
+ size 4847687
Agent/Agent-2999817.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8caa3b10ae5b6140476a6d47d7cbbb75f234f5719f34c8ae01bd6d29bbf5eec1
3
+ size 608107
Agent/Agent-2999817.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea492f66d84ecd47052656fb811a997479b2bc4826326508eb521e5d98abd91
3
+ size 4847687
Agent/Agent-3000201.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8caa3b10ae5b6140476a6d47d7cbbb75f234f5719f34c8ae01bd6d29bbf5eec1
3
+ size 608107
Agent/Agent-3000201.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1079ed3e7f6f4436f8a2ca13c1446d1ab7b383f3945564483eb5fa6ee6266eb
3
+ size 4847687
Agent/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1079ed3e7f6f4436f8a2ca13c1446d1ab7b383f3945564483eb5fa6ee6266eb
3
+ size 4847687
Agent/events.out.tfevents.1716242424.RICHARD.29368.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f117db158fb68d76fe92ba1742bc0e194341198cddbd7f9910e97608ce86ac60
3
+ size 2548191
configuration.yaml ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Agent:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 1024
7
+ buffer_size: 10240
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: 3000000
54
+ time_horizon: 10240
55
+ summary_freq: 15000
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_OceanPlasticCollection_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
+ task:
79
+ curriculum:
80
+ - value:
81
+ sampler_type: constant
82
+ sampler_parameters:
83
+ seed: 5000
84
+ value: 0
85
+ name: task
86
+ completion_criteria: null
87
+ checkpoint_settings:
88
+ run_id: OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train
89
+ initialize_from: null
90
+ load_model: false
91
+ resume: false
92
+ force: false
93
+ train_model: false
94
+ inference: false
95
+ results_dir: results
96
+ torch_settings:
97
+ device: null
98
+ debug: false
run_logs/timers.json ADDED
@@ -0,0 +1,447 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Agent.Policy.Entropy.mean": {
5
+ "value": 0.4797113835811615,
6
+ "min": 0.45411908626556396,
7
+ "max": 1.787257194519043,
8
+ "count": 200
9
+ },
10
+ "Agent.Policy.Entropy.sum": {
11
+ "value": 7199.98828125,
12
+ "min": 6708.490234375,
13
+ "max": 27988.41796875,
14
+ "count": 200
15
+ },
16
+ "Agent.Environment.EpisodeLength.mean": {
17
+ "value": 160.4516129032258,
18
+ "min": 35.11267605633803,
19
+ "max": 459.75,
20
+ "count": 200
21
+ },
22
+ "Agent.Environment.EpisodeLength.sum": {
23
+ "value": 14922.0,
24
+ "min": 12228.0,
25
+ "max": 17409.0,
26
+ "count": 200
27
+ },
28
+ "Agent.OceanPlasticCollector.GlobalReward.mean": {
29
+ "value": 270.95790404510785,
30
+ "min": 1.317898467965964,
31
+ "max": 604.9524826845039,
32
+ "count": 200
33
+ },
34
+ "Agent.OceanPlasticCollector.GlobalReward.sum": {
35
+ "value": 48772.42272811942,
36
+ "min": 545.6099657379091,
37
+ "max": 70420.84932395071,
38
+ "count": 200
39
+ },
40
+ "Agent.OceanPlasticCollector.LocalReward.mean": {
41
+ "value": 149.92222222222222,
42
+ "min": 17.652173913043477,
43
+ "max": 270.4691358024691,
44
+ "count": 200
45
+ },
46
+ "Agent.OceanPlasticCollector.LocalReward.sum": {
47
+ "value": 26986.0,
48
+ "min": 7308.0,
49
+ "max": 34817.0,
50
+ "count": 200
51
+ },
52
+ "Agent.Environment.LessonNumber.task.mean": {
53
+ "value": 0.0,
54
+ "min": 0.0,
55
+ "max": 0.0,
56
+ "count": 200
57
+ },
58
+ "Agent.Environment.LessonNumber.task.sum": {
59
+ "value": 0.0,
60
+ "min": 0.0,
61
+ "max": 0.0,
62
+ "count": 200
63
+ },
64
+ "Agent.Step.mean": {
65
+ "value": 2999817.0,
66
+ "min": 14967.0,
67
+ "max": 2999817.0,
68
+ "count": 200
69
+ },
70
+ "Agent.Step.sum": {
71
+ "value": 2999817.0,
72
+ "min": 14967.0,
73
+ "max": 2999817.0,
74
+ "count": 200
75
+ },
76
+ "Agent.Policy.CuriosityValueEstimate.mean": {
77
+ "value": 0.16175217926502228,
78
+ "min": 0.05323157459497452,
79
+ "max": 1.155686855316162,
80
+ "count": 200
81
+ },
82
+ "Agent.Policy.CuriosityValueEstimate.sum": {
83
+ "value": 14.881200790405273,
84
+ "min": 5.788083076477051,
85
+ "max": 144.9110107421875,
86
+ "count": 200
87
+ },
88
+ "Agent.Policy.ExtrinsicValueEstimate.mean": {
89
+ "value": 310.5462341308594,
90
+ "min": -7.7407145500183105,
91
+ "max": 342.80511474609375,
92
+ "count": 200
93
+ },
94
+ "Agent.Policy.ExtrinsicValueEstimate.sum": {
95
+ "value": 28570.25390625,
96
+ "min": -2833.1015625,
97
+ "max": 45206.015625,
98
+ "count": 200
99
+ },
100
+ "Agent.Environment.CumulativeReward.mean": {
101
+ "value": 766.547702750434,
102
+ "min": -14.746666854222616,
103
+ "max": 1526.9491478341524,
104
+ "count": 200
105
+ },
106
+ "Agent.Environment.CumulativeReward.sum": {
107
+ "value": 70522.38865303993,
108
+ "min": -5869.800079584122,
109
+ "max": 95523.3875041008,
110
+ "count": 200
111
+ },
112
+ "Agent.Policy.CuriosityReward.mean": {
113
+ "value": 0.2542370162985247,
114
+ "min": 0.049774529879150944,
115
+ "max": 3.4712647386625703,
116
+ "count": 200
117
+ },
118
+ "Agent.Policy.CuriosityReward.sum": {
119
+ "value": 23.389805499464273,
120
+ "min": 21.05462613888085,
121
+ "max": 252.74574196711183,
122
+ "count": 200
123
+ },
124
+ "Agent.Policy.ExtrinsicReward.mean": {
125
+ "value": 689.8929111607697,
126
+ "min": -13.272000325361887,
127
+ "max": 1374.2541994931269,
128
+ "count": 200
129
+ },
130
+ "Agent.Policy.ExtrinsicReward.sum": {
131
+ "value": 63470.14782679081,
132
+ "min": -5282.820174634457,
133
+ "max": 85971.04710793495,
134
+ "count": 200
135
+ },
136
+ "Agent.Losses.PolicyLoss.mean": {
137
+ "value": 0.022255855907375614,
138
+ "min": 0.017184668856983384,
139
+ "max": 0.03254731826794644,
140
+ "count": 200
141
+ },
142
+ "Agent.Losses.PolicyLoss.sum": {
143
+ "value": 0.04451171181475123,
144
+ "min": 0.017184668856983384,
145
+ "max": 0.05788607834415002,
146
+ "count": 200
147
+ },
148
+ "Agent.Losses.ValueLoss.mean": {
149
+ "value": 3797.5549438476564,
150
+ "min": 169.91888580322265,
151
+ "max": 6523.48544921875,
152
+ "count": 200
153
+ },
154
+ "Agent.Losses.ValueLoss.sum": {
155
+ "value": 7595.109887695313,
156
+ "min": 169.91888580322265,
157
+ "max": 13043.020198567709,
158
+ "count": 200
159
+ },
160
+ "Agent.Policy.LearningRate.mean": {
161
+ "value": 8.820997059999996e-07,
162
+ "min": 8.820997059999996e-07,
163
+ "max": 0.00029895630034790005,
164
+ "count": 200
165
+ },
166
+ "Agent.Policy.LearningRate.sum": {
167
+ "value": 1.7641994119999991e-06,
168
+ "min": 1.7641994119999991e-06,
169
+ "max": 0.0005927097024301001,
170
+ "count": 200
171
+ },
172
+ "Agent.Policy.Epsilon.mean": {
173
+ "value": 0.10029399999999998,
174
+ "min": 0.10029399999999998,
175
+ "max": 0.19965209999999994,
176
+ "count": 200
177
+ },
178
+ "Agent.Policy.Epsilon.sum": {
179
+ "value": 0.20058799999999996,
180
+ "min": 0.10082360000000001,
181
+ "max": 0.3975699,
182
+ "count": 200
183
+ },
184
+ "Agent.Policy.Beta.mean": {
185
+ "value": 2.4670599999999994e-05,
186
+ "min": 2.4670599999999994e-05,
187
+ "max": 0.004982639789999998,
188
+ "count": 200
189
+ },
190
+ "Agent.Policy.Beta.sum": {
191
+ "value": 4.934119999999999e-05,
192
+ "min": 4.934119999999999e-05,
193
+ "max": 0.009878738010000002,
194
+ "count": 200
195
+ },
196
+ "Agent.Losses.CuriosityForwardLoss.mean": {
197
+ "value": 0.014932409487664701,
198
+ "min": 0.01433597697565953,
199
+ "max": 0.18357288849850495,
200
+ "count": 200
201
+ },
202
+ "Agent.Losses.CuriosityForwardLoss.sum": {
203
+ "value": 0.029864818975329402,
204
+ "min": 0.01433597697565953,
205
+ "max": 0.3334345837434133,
206
+ "count": 200
207
+ },
208
+ "Agent.Losses.CuriosityInverseLoss.mean": {
209
+ "value": 0.11149372160434723,
210
+ "min": 0.10612237801154455,
211
+ "max": 1.791323435306549,
212
+ "count": 200
213
+ },
214
+ "Agent.Losses.CuriosityInverseLoss.sum": {
215
+ "value": 0.22298744320869446,
216
+ "min": 0.10612237801154455,
217
+ "max": 3.092707387606303,
218
+ "count": 200
219
+ },
220
+ "Agent.IsTraining.mean": {
221
+ "value": 1.0,
222
+ "min": 1.0,
223
+ "max": 1.0,
224
+ "count": 200
225
+ },
226
+ "Agent.IsTraining.sum": {
227
+ "value": 1.0,
228
+ "min": 1.0,
229
+ "max": 1.0,
230
+ "count": 200
231
+ }
232
+ },
233
+ "metadata": {
234
+ "timer_format_version": "0.1.0",
235
+ "start_time_seconds": "1716242423",
236
+ "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]",
237
+ "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/OceanPlasticCollection_task_0_run_id_0_train.yaml --run-id=OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train --base-port 5007",
238
+ "mlagents_version": "0.30.0",
239
+ "mlagents_envs_version": "0.30.0",
240
+ "communication_protocol_version": "1.5.0",
241
+ "pytorch_version": "1.7.1+cu110",
242
+ "numpy_version": "1.21.2",
243
+ "end_time_seconds": "1716271199"
244
+ },
245
+ "total": 28777.320956,
246
+ "count": 1,
247
+ "self": 0.7713683000001765,
248
+ "children": {
249
+ "run_training.setup": {
250
+ "total": 0.05752600000000008,
251
+ "count": 1,
252
+ "self": 0.05752600000000008
253
+ },
254
+ "TrainerController.start_learning": {
255
+ "total": 28776.4920617,
256
+ "count": 1,
257
+ "self": 26.192018400066445,
258
+ "children": {
259
+ "TrainerController._reset_env": {
260
+ "total": 2.2604235,
261
+ "count": 1,
262
+ "self": 2.2604235
263
+ },
264
+ "TrainerController.advance": {
265
+ "total": 28747.843563499933,
266
+ "count": 1005085,
267
+ "self": 23.23895510065995,
268
+ "children": {
269
+ "env_step": {
270
+ "total": 28724.604608399273,
271
+ "count": 1005085,
272
+ "self": 19329.767481399856,
273
+ "children": {
274
+ "SubprocessEnvManager._take_step": {
275
+ "total": 9380.061038300126,
276
+ "count": 1005085,
277
+ "self": 45.210927699550666,
278
+ "children": {
279
+ "TorchPolicy.evaluate": {
280
+ "total": 9334.850110600575,
281
+ "count": 1000075,
282
+ "self": 9334.850110600575
283
+ }
284
+ }
285
+ },
286
+ "workers": {
287
+ "total": 14.776088699291243,
288
+ "count": 1005085,
289
+ "self": 0.0,
290
+ "children": {
291
+ "worker_root": {
292
+ "total": 28750.051403901714,
293
+ "count": 1005085,
294
+ "is_parallel": true,
295
+ "self": 10340.105120100667,
296
+ "children": {
297
+ "steps_from_proto": {
298
+ "total": 0.0004262999999999906,
299
+ "count": 1,
300
+ "is_parallel": true,
301
+ "self": 0.00011119999999964492,
302
+ "children": {
303
+ "_process_maybe_compressed_observation": {
304
+ "total": 0.00022990000000011612,
305
+ "count": 2,
306
+ "is_parallel": true,
307
+ "self": 3.160000000046459e-05,
308
+ "children": {
309
+ "_observation_to_np_array": {
310
+ "total": 0.00019829999999965153,
311
+ "count": 3,
312
+ "is_parallel": true,
313
+ "self": 0.00019829999999965153
314
+ }
315
+ }
316
+ },
317
+ "_process_rank_one_or_two_observation": {
318
+ "total": 8.520000000022954e-05,
319
+ "count": 2,
320
+ "is_parallel": true,
321
+ "self": 8.520000000022954e-05
322
+ }
323
+ }
324
+ },
325
+ "UnityEnvironment.step": {
326
+ "total": 18409.945857501047,
327
+ "count": 1005085,
328
+ "is_parallel": true,
329
+ "self": 139.23127399751684,
330
+ "children": {
331
+ "UnityEnvironment._generate_step_input": {
332
+ "total": 66.17219810147604,
333
+ "count": 1005085,
334
+ "is_parallel": true,
335
+ "self": 66.17219810147604
336
+ },
337
+ "communicator.exchange": {
338
+ "total": 17701.456413700475,
339
+ "count": 1005085,
340
+ "is_parallel": true,
341
+ "self": 17701.456413700475
342
+ },
343
+ "steps_from_proto": {
344
+ "total": 503.08597170157975,
345
+ "count": 1005085,
346
+ "is_parallel": true,
347
+ "self": 117.22940070002039,
348
+ "children": {
349
+ "_process_maybe_compressed_observation": {
350
+ "total": 318.687236299181,
351
+ "count": 2010170,
352
+ "is_parallel": true,
353
+ "self": 42.07804160099988,
354
+ "children": {
355
+ "_observation_to_np_array": {
356
+ "total": 276.6091946981811,
357
+ "count": 3019125,
358
+ "is_parallel": true,
359
+ "self": 276.6091946981811
360
+ }
361
+ }
362
+ },
363
+ "_process_rank_one_or_two_observation": {
364
+ "total": 67.16933470237839,
365
+ "count": 2010170,
366
+ "is_parallel": true,
367
+ "self": 67.16933470237839
368
+ }
369
+ }
370
+ }
371
+ }
372
+ }
373
+ }
374
+ }
375
+ }
376
+ }
377
+ }
378
+ }
379
+ }
380
+ },
381
+ "trainer_threads": {
382
+ "total": 4.029999763588421e-05,
383
+ "count": 1,
384
+ "self": 4.029999763588421e-05,
385
+ "children": {
386
+ "thread_root": {
387
+ "total": 0.0,
388
+ "count": 0,
389
+ "is_parallel": true,
390
+ "self": 0.0,
391
+ "children": {
392
+ "trainer_advance": {
393
+ "total": 28754.307471097636,
394
+ "count": 1536324,
395
+ "is_parallel": true,
396
+ "self": 54.24060769933203,
397
+ "children": {
398
+ "process_trajectory": {
399
+ "total": 24413.15793489832,
400
+ "count": 1536324,
401
+ "is_parallel": true,
402
+ "self": 24411.518989598317,
403
+ "children": {
404
+ "RLTrainer._checkpoint": {
405
+ "total": 1.638945300004707,
406
+ "count": 6,
407
+ "is_parallel": true,
408
+ "self": 1.638945300004707
409
+ }
410
+ }
411
+ },
412
+ "_update_policy": {
413
+ "total": 4286.908928499984,
414
+ "count": 278,
415
+ "is_parallel": true,
416
+ "self": 2880.6284980001737,
417
+ "children": {
418
+ "TorchPPOOptimizer.update": {
419
+ "total": 1406.28043049981,
420
+ "count": 8481,
421
+ "is_parallel": true,
422
+ "self": 1406.28043049981
423
+ }
424
+ }
425
+ }
426
+ }
427
+ }
428
+ }
429
+ }
430
+ }
431
+ },
432
+ "TrainerController._save_models": {
433
+ "total": 0.19601600000169128,
434
+ "count": 1,
435
+ "self": 0.011950100000831299,
436
+ "children": {
437
+ "RLTrainer._checkpoint": {
438
+ "total": 0.18406590000085998,
439
+ "count": 1,
440
+ "self": 0.18406590000085998
441
+ }
442
+ }
443
+ }
444
+ }
445
+ }
446
+ }
447
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "task": {
3
+ "lesson_num": 0
4
+ },
5
+ "Agent": {
6
+ "checkpoints": [
7
+ {
8
+ "steps": 1499652,
9
+ "file_path": "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-1499652.onnx",
10
+ "reward": 518.2049991687139,
11
+ "creation_time": 1716257193.0135748,
12
+ "auxillary_file_paths": [
13
+ "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-1499652.pt"
14
+ ]
15
+ },
16
+ {
17
+ "steps": 1999721,
18
+ "file_path": "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-1999721.onnx",
19
+ "reward": 780.6013921138853,
20
+ "creation_time": 1716261951.751845,
21
+ "auxillary_file_paths": [
22
+ "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-1999721.pt"
23
+ ]
24
+ },
25
+ {
26
+ "steps": 2499831,
27
+ "file_path": "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-2499831.onnx",
28
+ "reward": 641.3812922371758,
29
+ "creation_time": 1716266607.0956502,
30
+ "auxillary_file_paths": [
31
+ "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-2499831.pt"
32
+ ]
33
+ },
34
+ {
35
+ "steps": 2999817,
36
+ "file_path": "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-2999817.onnx",
37
+ "reward": 862.8513685248115,
38
+ "creation_time": 1716271198.9095488,
39
+ "auxillary_file_paths": [
40
+ "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-2999817.pt"
41
+ ]
42
+ },
43
+ {
44
+ "steps": 3000201,
45
+ "file_path": "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-3000201.onnx",
46
+ "reward": 890.9666622976462,
47
+ "creation_time": 1716271199.1416752,
48
+ "auxillary_file_paths": [
49
+ "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-3000201.pt"
50
+ ]
51
+ }
52
+ ],
53
+ "final_checkpoint": {
54
+ "steps": 3000201,
55
+ "file_path": "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent.onnx",
56
+ "reward": 890.9666622976462,
57
+ "creation_time": 1716271199.1416752,
58
+ "auxillary_file_paths": [
59
+ "results\\OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train\\Agent\\Agent-3000201.pt"
60
+ ]
61
+ }
62
+ },
63
+ "metadata": {
64
+ "stats_format_version": "0.3.0",
65
+ "mlagents_version": "0.30.0",
66
+ "torch_version": "1.7.1+cu110"
67
+ }
68
+ }