Hugging Face's logo

TitanTec
/
ppo-SpaceMan-T1

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SpaceMan
deep-reinforcement-learning
ML-Agents-SpaceMan
Model card Files Metrics Community
Marco A. Egea Moreno commited on
Commit
aee1276
·
verified ·
1 Parent(s): 66f49be

Second Model

Browse files
Files changed (17) hide show
  1. SpaceMan.onnx +1 -1
  2. SpaceMan/SpaceMan-1499974.onnx +3 -0
  3. SpaceMan/SpaceMan-1499974.pt +3 -0
  4. SpaceMan/SpaceMan-1999991.onnx +3 -0
  5. SpaceMan/SpaceMan-1999991.pt +3 -0
  6. SpaceMan/SpaceMan-2499911.onnx +3 -0
  7. SpaceMan/SpaceMan-2499911.pt +3 -0
  8. SpaceMan/SpaceMan-2999989.onnx +3 -0
  9. SpaceMan/SpaceMan-2999989.pt +3 -0
  10. SpaceMan/SpaceMan-3000019.onnx +3 -0
  11. SpaceMan/SpaceMan-3000019.pt +3 -0
  12. SpaceMan/checkpoint.pt +1 -1
  13. SpaceMan/events.out.tfevents.1708233813.DESKTOP-0JACSNF.16168.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/timers.json +152 -152
  17. run_logs/training_status.json +29 -29
SpaceMan.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c93ffbf340760c1a9b8af85e7f9853abe8f05eedccf715dac5884f616b38ab57
3
  size 3584605
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695cccf9823ba8f089039266697e79cee2ff0eefad2b7dd66f3268c3c872def1
3
  size 3584605
SpaceMan/SpaceMan-1499974.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9427bb46277e56c5a6d45c89de4057ae8027f02a8d554ed06a5e0f583b7c1e6
3
+ size 3584605
SpaceMan/SpaceMan-1499974.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749107b5c59e6078fb9d9fe89ebcacdeb83418548b9d64a97dbfc11f06d2ab09
3
+ size 21491325
SpaceMan/SpaceMan-1999991.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25160dba224dde41ac6871412964082bc9f2a32de773c6615220d4a1e12d588a
3
+ size 3584605
SpaceMan/SpaceMan-1999991.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e29df437326e43d4de02ae3ae4c59ee769976ad616e01d4b784d82cca9872b24
3
+ size 21491325
SpaceMan/SpaceMan-2499911.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd4e519e858d6ae37a6d391b295762fb9fedfc99a9758c86a9b937e40a77261
3
+ size 3584605
SpaceMan/SpaceMan-2499911.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4d9461801e5efa5be33409cdf924cf2e1ea54c52ade4f0875dbcf5fd1c66df
3
+ size 21491325
SpaceMan/SpaceMan-2999989.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36f68af654f530bea5abf371f3994c126a56d3644eb46e662a869ee9ce463b1
3
+ size 3584605
SpaceMan/SpaceMan-2999989.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e536607c87bb2531c4d5a276a3b58f088157c484573f773660f25ff447b1274
3
+ size 21491325
SpaceMan/SpaceMan-3000019.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695cccf9823ba8f089039266697e79cee2ff0eefad2b7dd66f3268c3c872def1
3
+ size 3584605
SpaceMan/SpaceMan-3000019.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6893f966253b9aa1fd1c83afb42ecc09593cf8180ffaf15bb589714195c94550
3
+ size 21491325
SpaceMan/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b964bc51369187b9d059642a9693b65cde3beec907e3a0c952bd10b4202004e
3
  size 21490731
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07b021c17286914425cd613b4e7055af6457492ce2f5344e725ce540994a0cd
3
  size 21490731
SpaceMan/events.out.tfevents.1708233813.DESKTOP-0JACSNF.16168.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0802afd6f8df7859bbee2667dada27efa10d24c1ac1f72953ed9650c23f1cc
3
+ size 283458
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SpaceMan": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 204800, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 10, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "constant", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 4, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 100, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SpaceMan", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SpaceMan": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 204800, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 10, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "constant", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 4, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 100, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SpaceMan", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -68,7 +68,7 @@ checkpoint_settings:
68
  run_id: SpaceMan
69
  initialize_from: null
70
  load_model: false
71
- resume: true
72
  force: false
73
  train_model: false
74
  inference: false
 
68
  run_id: SpaceMan
69
  initialize_from: null
70
  load_model: false
71
+ resume: false
72
  force: false
73
  train_model: false
74
  inference: false
run_logs/timers.json CHANGED
@@ -2,257 +2,257 @@
2
  "name": "root",
3
  "gauges": {
4
  "SpaceMan.Policy.Entropy.mean": {
5
- "value": 1.467922329902649,
6
- "min": 1.4460493326187134,
7
- "max": 1.4702874422073364,
8
- "count": 206
9
  },
10
  "SpaceMan.Policy.Entropy.sum": {
11
- "value": 14601.423828125,
12
- "min": 3239.151123046875,
13
- "max": 14826.1328125,
14
- "count": 206
15
  },
16
  "SpaceMan.Step.mean": {
17
- "value": 2999904.0,
18
- "min": 949987.0,
19
- "max": 2999904.0,
20
- "count": 206
21
  },
22
  "SpaceMan.Step.sum": {
23
- "value": 2999904.0,
24
- "min": 949987.0,
25
- "max": 2999904.0,
26
- "count": 206
27
  },
28
  "SpaceMan.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 8.697190284729004,
30
- "min": 1.4972530603408813,
31
- "max": 8.85627555847168,
32
- "count": 206
33
  },
34
  "SpaceMan.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 947.9937133789062,
36
- "min": 41.9230842590332,
37
- "max": 965.0084228515625,
38
- "count": 206
39
  },
40
  "SpaceMan.Environment.EpisodeLength.mean": {
41
- "value": 346.96153846153845,
42
- "min": 114.55813953488372,
43
- "max": 623.625,
44
- "count": 206
45
  },
46
  "SpaceMan.Environment.EpisodeLength.sum": {
47
- "value": 9021.0,
48
- "min": 2221.0,
49
- "max": 11278.0,
50
- "count": 206
51
  },
52
  "SpaceMan.Environment.CumulativeReward.mean": {
53
- "value": 65.88783825768365,
54
- "min": 15.583248460015586,
55
- "max": 130.89143872261047,
56
- "count": 206
57
  },
58
  "SpaceMan.Environment.CumulativeReward.sum": {
59
- "value": 1778.9716329574585,
60
- "min": 285.4216604232788,
61
- "max": 2292.114513397217,
62
- "count": 206
63
  },
64
  "SpaceMan.Policy.ExtrinsicReward.mean": {
65
- "value": 65.88783825768365,
66
- "min": 15.583248460015586,
67
- "max": 130.89143872261047,
68
- "count": 206
69
  },
70
  "SpaceMan.Policy.ExtrinsicReward.sum": {
71
- "value": 1778.9716329574585,
72
- "min": 285.4216604232788,
73
- "max": 2292.114513397217,
74
- "count": 206
75
  },
76
  "SpaceMan.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
- "count": 206
81
  },
82
  "SpaceMan.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
- "count": 206
87
  },
88
  "SpaceMan.Losses.PolicyLoss.mean": {
89
- "value": 0.017651287283864805,
90
- "min": 0.017651287283864805,
91
- "max": 0.018727625109371728,
92
- "count": 10
93
  },
94
  "SpaceMan.Losses.PolicyLoss.sum": {
95
- "value": 0.017651287283864805,
96
- "min": 0.017651287283864805,
97
- "max": 0.018727625109371728,
98
- "count": 10
99
  },
100
  "SpaceMan.Losses.ValueLoss.mean": {
101
- "value": 5.96720850276947,
102
- "min": 2.832233478307724,
103
- "max": 6.14014026260376,
104
- "count": 10
105
  },
106
  "SpaceMan.Losses.ValueLoss.sum": {
107
- "value": 5.96720850276947,
108
- "min": 2.832233478307724,
109
- "max": 6.14014026260376,
110
- "count": 10
111
  },
112
  "SpaceMan.Policy.LearningRate.mean": {
113
- "value": 3.856998714666749e-07,
114
- "min": 3.856998714666749e-07,
115
- "max": 0.00018473073842310007,
116
- "count": 10
117
  },
118
  "SpaceMan.Policy.LearningRate.sum": {
119
- "value": 3.856998714666749e-07,
120
- "min": 3.856998714666749e-07,
121
- "max": 0.00018473073842310007,
122
- "count": 10
123
  },
124
  "SpaceMan.Policy.Epsilon.mean": {
125
- "value": 0.10012853333333334,
126
- "min": 0.10012853333333334,
127
- "max": 0.16157690000000002,
128
- "count": 10
129
  },
130
  "SpaceMan.Policy.Epsilon.sum": {
131
- "value": 0.10012853333333334,
132
- "min": 0.10012853333333334,
133
- "max": 0.16157690000000002,
134
- "count": 10
135
  },
136
  "SpaceMan.Policy.Beta.mean": {
137
  "value": 0.005,
138
  "min": 0.005,
139
  "max": 0.005,
140
- "count": 10
141
  },
142
  "SpaceMan.Policy.Beta.sum": {
143
  "value": 0.005,
144
  "min": 0.005,
145
  "max": 0.005,
146
- "count": 10
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1706927152",
152
  "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]",
153
- "command_line_arguments": "C:\\Users\\marko\\Documents\\UNITY\\ML-Agents\\.venv\\Scripts\\mlagents-learn config/ppo/SpaceManConfig.yaml --run-id=SpaceMan --resume",
154
  "mlagents_version": "1.0.0",
155
  "mlagents_envs_version": "1.0.0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.13.1+cu117",
158
  "numpy_version": "1.23.4",
159
- "end_time_seconds": "1706939538"
160
  },
161
- "total": 12386.343817200046,
162
  "count": 1,
163
- "self": 0.04495599982328713,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.10608000005595386,
167
  "count": 1,
168
- "self": 0.10608000005595386
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 12386.192781200167,
172
  "count": 1,
173
- "self": 33.989122175145894,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 9.272607399849221,
177
  "count": 1,
178
- "self": 9.272607399849221
179
  },
180
  "TrainerController.advance": {
181
- "total": 12342.69078802527,
182
- "count": 2062918,
183
- "self": 31.81940820766613,
184
  "children": {
185
  "env_step": {
186
- "total": 11086.329229957424,
187
- "count": 2062918,
188
- "self": 6582.622336421395,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 4481.90155536239,
192
- "count": 2062918,
193
- "self": 95.02506078104489,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 4386.8764945813455,
197
- "count": 2052171,
198
- "self": 4386.8764945813455
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 21.80533817363903,
204
- "count": 2062918,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 12341.43987455056,
209
- "count": 2062918,
210
  "is_parallel": true,
211
- "self": 7241.6551810198,
212
  "children": {
213
  "steps_from_proto": {
214
- "total": 0.00023939996026456356,
215
  "count": 1,
216
  "is_parallel": true,
217
- "self": 9.04998742043972e-05,
218
  "children": {
219
  "_process_rank_one_or_two_observation": {
220
- "total": 0.00014890008606016636,
221
  "count": 2,
222
  "is_parallel": true,
223
- "self": 0.00014890008606016636
224
  }
225
  }
226
  },
227
  "UnityEnvironment.step": {
228
- "total": 5099.7844541308,
229
- "count": 2062918,
230
  "is_parallel": true,
231
- "self": 131.40624884841964,
232
  "children": {
233
  "UnityEnvironment._generate_step_input": {
234
- "total": 97.48038711003028,
235
- "count": 2062918,
236
  "is_parallel": true,
237
- "self": 97.48038711003028
238
  },
239
  "communicator.exchange": {
240
- "total": 4572.9238510215655,
241
- "count": 2062918,
242
  "is_parallel": true,
243
- "self": 4572.9238510215655
244
  },
245
  "steps_from_proto": {
246
- "total": 297.97396715078503,
247
- "count": 2062918,
248
  "is_parallel": true,
249
- "self": 136.89252207055688,
250
  "children": {
251
  "_process_rank_one_or_two_observation": {
252
- "total": 161.08144508022815,
253
- "count": 4125836,
254
  "is_parallel": true,
255
- "self": 161.08144508022815
256
  }
257
  }
258
  }
@@ -265,31 +265,31 @@
265
  }
266
  },
267
  "trainer_advance": {
268
- "total": 1224.542149860179,
269
- "count": 2062918,
270
- "self": 34.844188132090494,
271
  "children": {
272
  "process_trajectory": {
273
- "total": 187.2766596279107,
274
- "count": 2062918,
275
- "self": 186.30765082803555,
276
  "children": {
277
  "RLTrainer._checkpoint": {
278
- "total": 0.9690087998751551,
279
- "count": 5,
280
- "self": 0.9690087998751551
281
  }
282
  }
283
  },
284
  "_update_policy": {
285
- "total": 1002.4213021001779,
286
- "count": 10,
287
- "self": 680.5896564067807,
288
  "children": {
289
  "TorchPPOOptimizer.update": {
290
- "total": 321.83164569339715,
291
- "count": 10000,
292
- "self": 321.83164569339715
293
  }
294
  }
295
  }
@@ -298,19 +298,19 @@
298
  }
299
  },
300
  "trainer_threads": {
301
- "total": 8.998904377222061e-07,
302
  "count": 1,
303
- "self": 8.998904377222061e-07
304
  },
305
  "TrainerController._save_models": {
306
- "total": 0.2402627000119537,
307
  "count": 1,
308
- "self": 0.05970859993249178,
309
  "children": {
310
  "RLTrainer._checkpoint": {
311
- "total": 0.18055410007946193,
312
  "count": 1,
313
- "self": 0.18055410007946193
314
  }
315
  }
316
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SpaceMan.Policy.Entropy.mean": {
5
+ "value": 1.4396039247512817,
6
+ "min": 1.404689073562622,
7
+ "max": 1.449188232421875,
8
+ "count": 300
9
  },
10
  "SpaceMan.Policy.Entropy.sum": {
11
+ "value": 14423.3916015625,
12
+ "min": 13927.4931640625,
13
+ "max": 14607.111328125,
14
+ "count": 300
15
  },
16
  "SpaceMan.Step.mean": {
17
+ "value": 2999989.0,
18
+ "min": 9909.0,
19
+ "max": 2999989.0,
20
+ "count": 300
21
  },
22
  "SpaceMan.Step.sum": {
23
+ "value": 2999989.0,
24
+ "min": 9909.0,
25
+ "max": 2999989.0,
26
+ "count": 300
27
  },
28
  "SpaceMan.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 5.108259677886963,
30
+ "min": -0.0456768199801445,
31
+ "max": 5.308773517608643,
32
+ "count": 300
33
  },
34
  "SpaceMan.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 541.4755249023438,
36
+ "min": -4.933096408843994,
37
+ "max": 557.4212036132812,
38
+ "count": 300
39
  },
40
  "SpaceMan.Environment.EpisodeLength.mean": {
41
+ "value": 743.2142857142857,
42
+ "min": 239.0,
43
+ "max": 1272.4285714285713,
44
+ "count": 300
45
  },
46
  "SpaceMan.Environment.EpisodeLength.sum": {
47
+ "value": 10405.0,
48
+ "min": 8081.0,
49
+ "max": 12535.0,
50
+ "count": 300
51
  },
52
  "SpaceMan.Environment.CumulativeReward.mean": {
53
+ "value": 58.78126232440655,
54
+ "min": 10.89677467800322,
55
+ "max": 105.08675193786621,
56
+ "count": 300
57
  },
58
  "SpaceMan.Environment.CumulativeReward.sum": {
59
+ "value": 764.1564102172852,
60
+ "min": 457.66453647613525,
61
+ "max": 936.7664852142334,
62
+ "count": 300
63
  },
64
  "SpaceMan.Policy.ExtrinsicReward.mean": {
65
+ "value": 58.78126232440655,
66
+ "min": 10.89677467800322,
67
+ "max": 105.08675193786621,
68
+ "count": 300
69
  },
70
  "SpaceMan.Policy.ExtrinsicReward.sum": {
71
+ "value": 764.1564102172852,
72
+ "min": 457.66453647613525,
73
+ "max": 936.7664852142334,
74
+ "count": 300
75
  },
76
  "SpaceMan.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
+ "count": 300
81
  },
82
  "SpaceMan.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
+ "count": 300
87
  },
88
  "SpaceMan.Losses.PolicyLoss.mean": {
89
+ "value": 0.017731686183484273,
90
+ "min": 0.017370412978576496,
91
+ "max": 0.018258020761189982,
92
+ "count": 14
93
  },
94
  "SpaceMan.Losses.PolicyLoss.sum": {
95
+ "value": 0.017731686183484273,
96
+ "min": 0.017370412978576496,
97
+ "max": 0.018258020761189982,
98
+ "count": 14
99
  },
100
  "SpaceMan.Losses.ValueLoss.mean": {
101
+ "value": 1.5500787984132767,
102
+ "min": 0.6227473085820675,
103
+ "max": 1.6574717750549317,
104
+ "count": 14
105
  },
106
  "SpaceMan.Losses.ValueLoss.sum": {
107
+ "value": 1.5500787984132767,
108
+ "min": 0.6227473085820675,
109
+ "max": 1.6574717750549317,
110
+ "count": 14
111
  },
112
  "SpaceMan.Policy.LearningRate.mean": {
113
+ "value": 1.3200195599966665e-05,
114
+ "min": 1.3200195599966665e-05,
115
+ "max": 0.0002795162068279333,
116
+ "count": 14
117
  },
118
  "SpaceMan.Policy.LearningRate.sum": {
119
+ "value": 1.3200195599966665e-05,
120
+ "min": 1.3200195599966665e-05,
121
+ "max": 0.0002795162068279333,
122
+ "count": 14
123
  },
124
  "SpaceMan.Policy.Epsilon.mean": {
125
+ "value": 0.10440003333333331,
126
+ "min": 0.10440003333333331,
127
+ "max": 0.19317206666666664,
128
+ "count": 14
129
  },
130
  "SpaceMan.Policy.Epsilon.sum": {
131
+ "value": 0.10440003333333331,
132
+ "min": 0.10440003333333331,
133
+ "max": 0.19317206666666664,
134
+ "count": 14
135
  },
136
  "SpaceMan.Policy.Beta.mean": {
137
  "value": 0.005,
138
  "min": 0.005,
139
  "max": 0.005,
140
+ "count": 14
141
  },
142
  "SpaceMan.Policy.Beta.sum": {
143
  "value": 0.005,
144
  "min": 0.005,
145
  "max": 0.005,
146
+ "count": 14
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1708233795",
152
  "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]",
153
+ "command_line_arguments": "C:\\Users\\marko\\Documents\\UNITY\\ML-Agents\\.venv\\Scripts\\mlagents-learn config/ppo/SpaceManConfig.yaml --run-id=SpaceMan",
154
  "mlagents_version": "1.0.0",
155
  "mlagents_envs_version": "1.0.0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.13.1+cu117",
158
  "numpy_version": "1.23.4",
159
+ "end_time_seconds": "1708251695"
160
  },
161
+ "total": 17899.673288199992,
162
  "count": 1,
163
+ "self": 0.050844899960793555,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.094327200029511,
167
  "count": 1,
168
+ "self": 0.094327200029511
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 17899.528116100002,
172
  "count": 1,
173
+ "self": 48.87804145150585,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 20.616248000005726,
177
  "count": 1,
178
+ "self": 20.616248000005726
179
  },
180
  "TrainerController.advance": {
181
+ "total": 17829.817165548448,
182
+ "count": 3007047,
183
+ "self": 43.271958130644634,
184
  "children": {
185
  "env_step": {
186
+ "total": 15947.844941709773,
187
+ "count": 3007047,
188
+ "self": 8307.44479442708,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 7608.474235826696,
192
+ "count": 3007047,
193
+ "self": 144.90336746699177,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 7463.570868359704,
197
+ "count": 3000019,
198
+ "self": 7463.570868359704
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 31.925911455997266,
204
+ "count": 3007047,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 17826.03124869382,
209
+ "count": 3007047,
210
  "is_parallel": true,
211
+ "self": 11705.28407783201,
212
  "children": {
213
  "steps_from_proto": {
214
+ "total": 0.0030157999717630446,
215
  "count": 1,
216
  "is_parallel": true,
217
+ "self": 0.00010429997928440571,
218
  "children": {
219
  "_process_rank_one_or_two_observation": {
220
+ "total": 0.002911499992478639,
221
  "count": 2,
222
  "is_parallel": true,
223
+ "self": 0.002911499992478639
224
  }
225
  }
226
  },
227
  "UnityEnvironment.step": {
228
+ "total": 6120.744155061839,
229
+ "count": 3007047,
230
  "is_parallel": true,
231
+ "self": 185.63163686619373,
232
  "children": {
233
  "UnityEnvironment._generate_step_input": {
234
+ "total": 148.9114509843639,
235
+ "count": 3007047,
236
  "is_parallel": true,
237
+ "self": 148.9114509843639
238
  },
239
  "communicator.exchange": {
240
+ "total": 5352.722329935117,
241
+ "count": 3007047,
242
  "is_parallel": true,
243
+ "self": 5352.722329935117
244
  },
245
  "steps_from_proto": {
246
+ "total": 433.4787372761639,
247
+ "count": 3007047,
248
  "is_parallel": true,
249
+ "self": 200.26946144725662,
250
  "children": {
251
  "_process_rank_one_or_two_observation": {
252
+ "total": 233.20927582890727,
253
+ "count": 6014094,
254
  "is_parallel": true,
255
+ "self": 233.20927582890727
256
  }
257
  }
258
  }
 
265
  }
266
  },
267
  "trainer_advance": {
268
+ "total": 1838.7002657080302,
269
+ "count": 3007047,
270
+ "self": 52.23635603673756,
271
  "children": {
272
  "process_trajectory": {
273
+ "total": 292.4972032713704,
274
+ "count": 3007047,
275
+ "self": 290.8138325713808,
276
  "children": {
277
  "RLTrainer._checkpoint": {
278
+ "total": 1.6833706999896094,
279
+ "count": 6,
280
+ "self": 1.6833706999896094
281
  }
282
  }
283
  },
284
  "_update_policy": {
285
+ "total": 1493.9667063999223,
286
+ "count": 14,
287
+ "self": 1025.7034898959682,
288
  "children": {
289
  "TorchPPOOptimizer.update": {
290
+ "total": 468.263216503954,
291
+ "count": 14000,
292
+ "self": 468.263216503954
293
  }
294
  }
295
  }
 
298
  }
299
  },
300
  "trainer_threads": {
301
+ "total": 1.200009137392044e-06,
302
  "count": 1,
303
+ "self": 1.200009137392044e-06
304
  },
305
  "TrainerController._save_models": {
306
+ "total": 0.2166599000338465,
307
  "count": 1,
308
+ "self": 0.01178780006011948,
309
  "children": {
310
  "RLTrainer._checkpoint": {
311
+ "total": 0.20487209997372702,
312
  "count": 1,
313
+ "self": 0.20487209997372702
314
  }
315
  }
316
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,58 @@
2
  "SpaceMan": {
3
  "checkpoints": [
4
  {
5
- "steps": 1499918,
6
- "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-1499918.onnx",
7
- "reward": 22.2175737681628,
8
- "creation_time": 1706930344.037184,
9
  "auxillary_file_paths": [
10
- "results\\SpaceMan\\SpaceMan\\SpaceMan-1499918.pt"
11
  ]
12
  },
13
  {
14
- "steps": 1999944,
15
- "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-1999944.onnx",
16
- "reward": 36.042707537212515,
17
- "creation_time": 1706933358.131544,
18
  "auxillary_file_paths": [
19
- "results\\SpaceMan\\SpaceMan\\SpaceMan-1999944.pt"
20
  ]
21
  },
22
  {
23
- "steps": 2499990,
24
- "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-2499990.onnx",
25
- "reward": 48.623730069768115,
26
- "creation_time": 1706936559.669555,
27
  "auxillary_file_paths": [
28
- "results\\SpaceMan\\SpaceMan\\SpaceMan-2499990.pt"
29
  ]
30
  },
31
  {
32
- "steps": 2999904,
33
- "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-2999904.onnx",
34
- "reward": 112.39698941367013,
35
- "creation_time": 1706939538.5782924,
36
  "auxillary_file_paths": [
37
- "results\\SpaceMan\\SpaceMan\\SpaceMan-2999904.pt"
38
  ]
39
  },
40
  {
41
- "steps": 3000004,
42
- "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-3000004.onnx",
43
- "reward": 112.39698941367013,
44
- "creation_time": 1706939538.7678978,
45
  "auxillary_file_paths": [
46
- "results\\SpaceMan\\SpaceMan\\SpaceMan-3000004.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 3000004,
52
  "file_path": "results\\SpaceMan\\SpaceMan.onnx",
53
- "reward": 112.39698941367013,
54
- "creation_time": 1706939538.7678978,
55
  "auxillary_file_paths": [
56
- "results\\SpaceMan\\SpaceMan\\SpaceMan-3000004.pt"
57
  ]
58
  }
59
  },
 
2
  "SpaceMan": {
3
  "checkpoints": [
4
  {
5
+ "steps": 1499974,
6
+ "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-1499974.onnx",
7
+ "reward": 27.752897262573242,
8
+ "creation_time": 1708242807.421201,
9
  "auxillary_file_paths": [
10
+ "results\\SpaceMan\\SpaceMan\\SpaceMan-1499974.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 1999991,
15
+ "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-1999991.onnx",
16
+ "reward": 39.76552143840925,
17
+ "creation_time": 1708245823.740176,
18
  "auxillary_file_paths": [
19
+ "results\\SpaceMan\\SpaceMan\\SpaceMan-1999991.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 2499911,
24
+ "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-2499911.onnx",
25
+ "reward": 54.230668493679595,
26
+ "creation_time": 1708248825.2128797,
27
  "auxillary_file_paths": [
28
+ "results\\SpaceMan\\SpaceMan\\SpaceMan-2499911.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 2999989,
33
+ "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-2999989.onnx",
34
+ "reward": 57.29786591071867,
35
+ "creation_time": 1708251695.3821788,
36
  "auxillary_file_paths": [
37
+ "results\\SpaceMan\\SpaceMan\\SpaceMan-2999989.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 3000019,
42
+ "file_path": "results\\SpaceMan\\SpaceMan\\SpaceMan-3000019.onnx",
43
+ "reward": 57.18509475300821,
44
+ "creation_time": 1708251695.5943718,
45
  "auxillary_file_paths": [
46
+ "results\\SpaceMan\\SpaceMan\\SpaceMan-3000019.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 3000019,
52
  "file_path": "results\\SpaceMan\\SpaceMan.onnx",
53
+ "reward": 57.18509475300821,
54
+ "creation_time": 1708251695.5943718,
55
  "auxillary_file_paths": [
56
+ "results\\SpaceMan\\SpaceMan\\SpaceMan-3000019.pt"
57
  ]
58
  }
59
  },