habanoz's picture
1m steps
e01b682
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3050019145011902,
"min": 0.3050019145011902,
"max": 1.520557165145874,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9174.4580078125,
"min": 9174.4580078125,
"max": 46127.62109375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989934.0,
"min": 29952.0,
"max": 989934.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989934.0,
"min": 29952.0,
"max": 989934.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5421900749206543,
"min": -0.163333460688591,
"max": 0.6106760501861572,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 151.27102661132812,
"min": -38.71002960205078,
"max": 170.98928833007812,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02047632448375225,
"min": 0.0009610670967958868,
"max": 0.43508318066596985,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.712894439697266,
"min": 0.2537217140197754,
"max": 103.11471557617188,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06964872555506575,
"min": 0.06564188428941028,
"max": 0.07419865614667351,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9750821577709204,
"min": 0.49019820314257323,
"max": 1.0954490018536007,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017294767268703295,
"min": 0.0010222386044729088,
"max": 0.018580202275881585,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24212674176184615,
"min": 0.007155670231310362,
"max": 0.2716302695480408,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.760283127557144e-06,
"min": 7.760283127557144e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010864396378580002,
"min": 0.00010864396378580002,
"max": 0.0035081006306331994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10258672857142857,
"min": 0.10258672857142857,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4362142,
"min": 1.3691136000000002,
"max": 2.6623221,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026841418428571437,
"min": 0.00026841418428571437,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003757798580000001,
"min": 0.003757798580000001,
"max": 0.11695974331999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013817748986184597,
"min": 0.013817748986184597,
"max": 0.37137606739997864,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1934484839439392,
"min": 0.1934484839439392,
"max": 2.599632501602173,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 339.13953488372096,
"min": 308.17525773195877,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29166.0,
"min": 15984.0,
"max": 32844.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5910743994768275,
"min": -1.0000000521540642,
"max": 1.6940408092068167,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 136.83239835500717,
"min": -32.000001668930054,
"max": 166.01599930226803,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5910743994768275,
"min": -1.0000000521540642,
"max": 1.6940408092068167,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 136.83239835500717,
"min": -32.000001668930054,
"max": 166.01599930226803,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04819922994850691,
"min": 0.04669521435351605,
"max": 7.373856204561889,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.145133775571594,
"min": 4.145133775571594,
"max": 117.98169927299023,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673554956",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673557108"
},
"total": 2151.9308114909995,
"count": 1,
"self": 0.5267468469992309,
"children": {
"run_training.setup": {
"total": 0.10606326299966895,
"count": 1,
"self": 0.10606326299966895
},
"TrainerController.start_learning": {
"total": 2151.2980013810006,
"count": 1,
"self": 1.231852411062846,
"children": {
"TrainerController._reset_env": {
"total": 6.2107747930003825,
"count": 1,
"self": 6.2107747930003825
},
"TrainerController.advance": {
"total": 2143.763690452938,
"count": 64078,
"self": 1.3039038857091327,
"children": {
"env_step": {
"total": 1473.150445218172,
"count": 64078,
"self": 1367.4169855192486,
"children": {
"SubprocessEnvManager._take_step": {
"total": 104.93994841195354,
"count": 64078,
"self": 4.414080411882878,
"children": {
"TorchPolicy.evaluate": {
"total": 100.52586800007066,
"count": 62560,
"self": 34.10100460706917,
"children": {
"TorchPolicy.sample_actions": {
"total": 66.42486339300149,
"count": 62560,
"self": 66.42486339300149
}
}
}
}
},
"workers": {
"total": 0.7935112869699879,
"count": 64078,
"self": 0.0,
"children": {
"worker_root": {
"total": 2146.464871946004,
"count": 64078,
"is_parallel": true,
"self": 881.6132887951235,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001884191000044666,
"count": 1,
"is_parallel": true,
"self": 0.0006734050002705771,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012107859997740889,
"count": 8,
"is_parallel": true,
"self": 0.0012107859997740889
}
}
},
"UnityEnvironment.step": {
"total": 0.045211206000203674,
"count": 1,
"is_parallel": true,
"self": 0.0006666049998784729,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004333310002948565,
"count": 1,
"is_parallel": true,
"self": 0.0004333310002948565
},
"communicator.exchange": {
"total": 0.04252513600022212,
"count": 1,
"is_parallel": true,
"self": 0.04252513600022212
},
"steps_from_proto": {
"total": 0.0015861339998082258,
"count": 1,
"is_parallel": true,
"self": 0.0004146580008637102,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011714759989445156,
"count": 8,
"is_parallel": true,
"self": 0.0011714759989445156
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1264.8515831508807,
"count": 64077,
"is_parallel": true,
"self": 28.5501174288529,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.804358725002203,
"count": 64077,
"is_parallel": true,
"self": 23.804358725002203
},
"communicator.exchange": {
"total": 1105.243669686071,
"count": 64077,
"is_parallel": true,
"self": 1105.243669686071
},
"steps_from_proto": {
"total": 107.25343731095472,
"count": 64077,
"is_parallel": true,
"self": 23.567228336802145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.68620897415258,
"count": 512616,
"is_parallel": true,
"self": 83.68620897415258
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 669.3093413490569,
"count": 64078,
"self": 2.363512977990922,
"children": {
"process_trajectory": {
"total": 150.80924514907383,
"count": 64078,
"self": 150.60500423907342,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2042409100004079,
"count": 2,
"self": 0.2042409100004079
}
}
},
"_update_policy": {
"total": 516.1365832219922,
"count": 446,
"self": 200.1005464940299,
"children": {
"TorchPPOOptimizer.update": {
"total": 316.03603672796226,
"count": 22821,
"self": 316.03603672796226
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.095999323297292e-06,
"count": 1,
"self": 1.095999323297292e-06
},
"TrainerController._save_models": {
"total": 0.09168262799994409,
"count": 1,
"self": 0.0014719829996465705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09021064500029752,
"count": 1,
"self": 0.09021064500029752
}
}
}
}
}
}
}