File size: 14,416 Bytes
44ef782
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
{
    "name": "root",
    "gauges": {
        "3DBall.Policy.Entropy.mean": {
            "value": 1.2530262470245361,
            "min": 1.249975562095642,
            "max": 1.4189382791519165,
            "count": 41
        },
        "3DBall.Policy.Entropy.sum": {
            "value": 15036.3154296875,
            "min": 14999.70703125,
            "max": 19505.73046875,
            "count": 41
        },
        "3DBall.Environment.EpisodeLength.mean": {
            "value": 999.0,
            "min": 22.092130518234164,
            "max": 999.0,
            "count": 41
        },
        "3DBall.Environment.EpisodeLength.sum": {
            "value": 11988.0,
            "min": 11422.0,
            "max": 12761.0,
            "count": 41
        },
        "3DBall.Step.mean": {
            "value": 491224.0,
            "min": 11989.0,
            "max": 491224.0,
            "count": 41
        },
        "3DBall.Step.sum": {
            "value": 491224.0,
            "min": 11989.0,
            "max": 491224.0,
            "count": 41
        },
        "3DBall.Policy.ExtrinsicValueEstimate.mean": {
            "value": 9.998326301574707,
            "min": -0.21952161192893982,
            "max": 10.004788398742676,
            "count": 41
        },
        "3DBall.Policy.ExtrinsicValueEstimate.sum": {
            "value": 119.97991180419922,
            "min": -114.15123748779297,
            "max": 221.3089599609375,
            "count": 41
        },
        "3DBall.Environment.CumulativeReward.mean": {
            "value": 100.00001525878906,
            "min": 1.205576880161579,
            "max": 100.00001525878906,
            "count": 41
        },
        "3DBall.Environment.CumulativeReward.sum": {
            "value": 1200.0001831054688,
            "min": 626.899977684021,
            "max": 1243.4001913070679,
            "count": 41
        },
        "3DBall.Policy.ExtrinsicReward.mean": {
            "value": 100.00001525878906,
            "min": 1.205576880161579,
            "max": 100.00001525878906,
            "count": 41
        },
        "3DBall.Policy.ExtrinsicReward.sum": {
            "value": 1200.0001831054688,
            "min": 626.899977684021,
            "max": 1243.4001913070679,
            "count": 41
        },
        "3DBall.IsTraining.mean": {
            "value": 1.0,
            "min": 1.0,
            "max": 1.0,
            "count": 41
        },
        "3DBall.IsTraining.sum": {
            "value": 1.0,
            "min": 1.0,
            "max": 1.0,
            "count": 41
        },
        "3DBall.Losses.PolicyLoss.mean": {
            "value": 0.0875553363431031,
            "min": 0.0853438666777715,
            "max": 0.10285655303845986,
            "count": 38
        },
        "3DBall.Losses.PolicyLoss.sum": {
            "value": 0.0875553363431031,
            "min": 0.0853438666777715,
            "max": 0.10285655303845986,
            "count": 38
        },
        "3DBall.Losses.ValueLoss.mean": {
            "value": 0.003986369480576965,
            "min": 0.0011322325467241375,
            "max": 3.11412584240732,
            "count": 38
        },
        "3DBall.Losses.ValueLoss.sum": {
            "value": 0.003986369480576965,
            "min": 0.0011322325467241375,
            "max": 3.11412584240732,
            "count": 38
        },
        "3DBall.Policy.LearningRate.mean": {
            "value": 1.006569664480001e-05,
            "min": 1.006569664480001e-05,
            "max": 0.0002927814024062,
            "count": 38
        },
        "3DBall.Policy.LearningRate.sum": {
            "value": 1.006569664480001e-05,
            "min": 1.006569664480001e-05,
            "max": 0.0002927814024062,
            "count": 38
        },
        "3DBall.Policy.Epsilon.mean": {
            "value": 0.10335519999999998,
            "min": 0.10335519999999998,
            "max": 0.19759379999999996,
            "count": 38
        },
        "3DBall.Policy.Epsilon.sum": {
            "value": 0.10335519999999998,
            "min": 0.10335519999999998,
            "max": 0.19759379999999996,
            "count": 38
        },
        "3DBall.Policy.Beta.mean": {
            "value": 4.321648000000003e-05,
            "min": 4.321648000000003e-05,
            "max": 0.0009761786200000003,
            "count": 38
        },
        "3DBall.Policy.Beta.sum": {
            "value": 4.321648000000003e-05,
            "min": 4.321648000000003e-05,
            "max": 0.0009761786200000003,
            "count": 38
        }
    },
    "metadata": {
        "timer_format_version": "0.1.0",
        "start_time_seconds": "1657904946",
        "python_version": "3.8.13 (default, Mar 28 2022, 06:16:26) \n[Clang 12.0.0 ]",
        "command_line_arguments": "/usr/local/Caskroom/miniconda/base/envs/ml-agents/bin/mlagents-learn ./config/ppo/3DBall.yaml --run-id=first3DBallRun3 --force --env=./trained-envs-executables/macos/3d_ball/3d ball --no-graphics",
        "mlagents_version": "0.29.0.dev0",
        "mlagents_envs_version": "0.29.0.dev0",
        "communication_protocol_version": "1.5.0",
        "pytorch_version": "1.8.1",
        "numpy_version": "1.22.3",
        "end_time_seconds": "1657905343"
    },
    "total": 397.450924047,
    "count": 1,
    "self": 0.34027323800000886,
    "children": {
        "run_training.setup": {
            "total": 0.04273055499999989,
            "count": 1,
            "self": 0.04273055499999989
        },
        "TrainerController.start_learning": {
            "total": 397.067920254,
            "count": 1,
            "self": 0.7700594520004529,
            "children": {
                "TrainerController._reset_env": {
                    "total": 2.5437515289999997,
                    "count": 1,
                    "self": 2.5437515289999997
                },
                "TrainerController.advance": {
                    "total": 393.69847658399954,
                    "count": 43985,
                    "self": 0.7830804549955701,
                    "children": {
                        "env_step": {
                            "total": 230.3137608409983,
                            "count": 43985,
                            "self": 202.2693348190025,
                            "children": {
                                "SubprocessEnvManager._take_step": {
                                    "total": 27.511717070997804,
                                    "count": 43985,
                                    "self": 2.4751557829968895,
                                    "children": {
                                        "TorchPolicy.evaluate": {
                                            "total": 25.036561288000915,
                                            "count": 42155,
                                            "self": 4.847578280001574,
                                            "children": {
                                                "TorchPolicy.sample_actions": {
                                                    "total": 20.18898300799934,
                                                    "count": 42155,
                                                    "self": 20.18898300799934
                                                }
                                            }
                                        }
                                    }
                                },
                                "workers": {
                                    "total": 0.532708950998015,
                                    "count": 43985,
                                    "self": 0.0,
                                    "children": {
                                        "worker_root": {
                                            "total": 393.1404451730054,
                                            "count": 43985,
                                            "is_parallel": true,
                                            "self": 237.20454446299738,
                                            "children": {
                                                "steps_from_proto": {
                                                    "total": 0.000473571000000117,
                                                    "count": 1,
                                                    "is_parallel": true,
                                                    "self": 0.00017897400000022046,
                                                    "children": {
                                                        "_process_rank_one_or_two_observation": {
                                                            "total": 0.0002945969999998965,
                                                            "count": 2,
                                                            "is_parallel": true,
                                                            "self": 0.0002945969999998965
                                                        }
                                                    }
                                                },
                                                "UnityEnvironment.step": {
                                                    "total": 155.93542713900803,
                                                    "count": 43985,
                                                    "is_parallel": true,
                                                    "self": 5.6048235150036305,
                                                    "children": {
                                                        "UnityEnvironment._generate_step_input": {
                                                            "total": 7.386330972004274,
                                                            "count": 43985,
                                                            "is_parallel": true,
                                                            "self": 7.386330972004274
                                                        },
                                                        "communicator.exchange": {
                                                            "total": 132.06233277000166,
                                                            "count": 43985,
                                                            "is_parallel": true,
                                                            "self": 132.06233277000166
                                                        },
                                                        "steps_from_proto": {
                                                            "total": 10.88193988199847,
                                                            "count": 43985,
                                                            "is_parallel": true,
                                                            "self": 5.169313770000414,
                                                            "children": {
                                                                "_process_rank_one_or_two_observation": {
                                                                    "total": 5.7126261119980555,
                                                                    "count": 87970,
                                                                    "is_parallel": true,
                                                                    "self": 5.7126261119980555
                                                                }
                                                            }
                                                        }
                                                    }
                                                }
                                            }
                                        }
                                    }
                                }
                            }
                        },
                        "trainer_advance": {
                            "total": 162.60163528800567,
                            "count": 43985,
                            "self": 1.2461401930077045,
                            "children": {
                                "process_trajectory": {
                                    "total": 22.86444937999798,
                                    "count": 43985,
                                    "self": 22.749369502998007,
                                    "children": {
                                        "RLTrainer._checkpoint": {
                                            "total": 0.11507987699997102,
                                            "count": 1,
                                            "self": 0.11507987699997102
                                        }
                                    }
                                },
                                "_update_policy": {
                                    "total": 138.49104571499998,
                                    "count": 39,
                                    "self": 67.82378533699823,
                                    "children": {
                                        "TorchPPOOptimizer.update": {
                                            "total": 70.66726037800176,
                                            "count": 23229,
                                            "self": 70.66726037800176
                                        }
                                    }
                                }
                            }
                        }
                    }
                },
                "trainer_threads": {
                    "total": 1.0870000437535055e-06,
                    "count": 1,
                    "self": 1.0870000437535055e-06
                },
                "TrainerController._save_models": {
                    "total": 0.05563160199994854,
                    "count": 1,
                    "self": 0.0015699369999424562,
                    "children": {
                        "RLTrainer._checkpoint": {
                            "total": 0.05406166500000609,
                            "count": 1,
                            "self": 0.05406166500000609
                        }
                    }
                }
            }
        }
    }
}