ckauth's picture
First Push
b60d75c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.19287021458148956,
"min": 0.1828238070011139,
"max": 1.4537782669067383,
"count": 50
},
"Pyramids.Policy.Entropy.sum": {
"value": 5758.3330078125,
"min": 5452.537109375,
"max": 44101.81640625,
"count": 50
},
"Pyramids.Step.mean": {
"value": 1499951.0,
"min": 29952.0,
"max": 1499951.0,
"count": 50
},
"Pyramids.Step.sum": {
"value": 1499951.0,
"min": 29952.0,
"max": 1499951.0,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5682003498077393,
"min": -0.12197128683328629,
"max": 0.7233222126960754,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 157.39149475097656,
"min": -29.273109436035156,
"max": 211.2100830078125,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.007365076802670956,
"min": -0.003084492404013872,
"max": 0.30119678378105164,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.040126323699951,
"min": -0.860573410987854,
"max": 72.58842468261719,
"count": 50
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06810969253969365,
"min": 0.06372665595999398,
"max": 0.07355506680459943,
"count": 50
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9535356955557112,
"min": 0.514885467632196,
"max": 1.0731237693301712,
"count": 50
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016369770410924262,
"min": 0.0009559857812957643,
"max": 0.016568470552212465,
"count": 50
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22917678575293968,
"min": 0.01041859027924216,
"max": 0.23782443558836047,
"count": 50
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.9310990230000023e-06,
"min": 2.9310990230000023e-06,
"max": 0.00029676708679192377,
"count": 50
},
"Pyramids.Policy.LearningRate.sum": {
"value": 4.1035386322000034e-05,
"min": 4.1035386322000034e-05,
"max": 0.0037383335538888657,
"count": 50
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.100977,
"min": 0.100977,
"max": 0.19892236190476195,
"count": 50
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.413678,
"min": 1.3924565333333336,
"max": 2.654837133333334,
"count": 50
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00010760230000000007,
"min": 0.00010760230000000007,
"max": 0.009892343954285714,
"count": 50
},
"Pyramids.Policy.Beta.sum": {
"value": 0.001506432200000001,
"min": 0.001506432200000001,
"max": 0.12462650221999999,
"count": 50
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009245416149497032,
"min": 0.009245416149497032,
"max": 0.4475618302822113,
"count": 50
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12943582236766815,
"min": 0.12943582236766815,
"max": 3.1329329013824463,
"count": 50
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 331.1290322580645,
"min": 262.51785714285717,
"max": 999.0,
"count": 50
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30795.0,
"min": 15984.0,
"max": 33034.0,
"count": 50
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6034369416858838,
"min": -1.0000000521540642,
"max": 1.737071414078985,
"count": 50
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 147.51619863510132,
"min": -30.600001752376556,
"max": 200.4889983087778,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6034369416858838,
"min": -1.0000000521540642,
"max": 1.737071414078985,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 147.51619863510132,
"min": -30.600001752376556,
"max": 200.4889983087778,
"count": 50
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0318603856932263,
"min": 0.02690622679787624,
"max": 8.667456647381186,
"count": 50
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.93115548377682,
"min": 2.7444351333833765,
"max": 138.67930635809898,
"count": 50
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1681739173",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1681742500"
},
"total": 3327.3545418050003,
"count": 1,
"self": 0.5310748709998734,
"children": {
"run_training.setup": {
"total": 0.10446757399995477,
"count": 1,
"self": 0.10446757399995477
},
"TrainerController.start_learning": {
"total": 3326.7189993600005,
"count": 1,
"self": 1.9937653059832883,
"children": {
"TrainerController._reset_env": {
"total": 3.7409829519999676,
"count": 1,
"self": 3.7409829519999676
},
"TrainerController.advance": {
"total": 3320.895666984017,
"count": 96599,
"self": 2.1063246418416384,
"children": {
"env_step": {
"total": 2421.0195660290974,
"count": 96599,
"self": 2268.0324325032707,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.78512672889315,
"count": 96599,
"self": 6.808880580850882,
"children": {
"TorchPolicy.evaluate": {
"total": 144.97624614804226,
"count": 93794,
"self": 144.97624614804226
}
}
},
"workers": {
"total": 1.2020067969338015,
"count": 96599,
"self": 0.0,
"children": {
"worker_root": {
"total": 3319.430935395,
"count": 96599,
"is_parallel": true,
"self": 1213.8994173188262,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017008109998641885,
"count": 1,
"is_parallel": true,
"self": 0.0005691529997875477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011316580000766407,
"count": 8,
"is_parallel": true,
"self": 0.0011316580000766407
}
}
},
"UnityEnvironment.step": {
"total": 0.05058221399985996,
"count": 1,
"is_parallel": true,
"self": 0.000558246000082363,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047936499981915404,
"count": 1,
"is_parallel": true,
"self": 0.00047936499981915404
},
"communicator.exchange": {
"total": 0.04788480199999867,
"count": 1,
"is_parallel": true,
"self": 0.04788480199999867
},
"steps_from_proto": {
"total": 0.0016598009999597707,
"count": 1,
"is_parallel": true,
"self": 0.00036188899980516,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012979120001546107,
"count": 8,
"is_parallel": true,
"self": 0.0012979120001546107
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2105.5315180761736,
"count": 96598,
"is_parallel": true,
"self": 47.938897029252075,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 33.65740127809181,
"count": 96598,
"is_parallel": true,
"self": 33.65740127809181
},
"communicator.exchange": {
"total": 1885.832562357923,
"count": 96598,
"is_parallel": true,
"self": 1885.832562357923
},
"steps_from_proto": {
"total": 138.1026574109069,
"count": 96598,
"is_parallel": true,
"self": 29.375822909102908,
"children": {
"_process_rank_one_or_two_observation": {
"total": 108.72683450180398,
"count": 772784,
"is_parallel": true,
"self": 108.72683450180398
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 897.7697763130784,
"count": 96599,
"self": 3.9002535169940984,
"children": {
"process_trajectory": {
"total": 154.79438451409646,
"count": 96599,
"self": 154.4985387270965,
"children": {
"RLTrainer._checkpoint": {
"total": 0.295845786999962,
"count": 3,
"self": 0.295845786999962
}
}
},
"_update_policy": {
"total": 739.0751382819878,
"count": 685,
"self": 475.46896247607697,
"children": {
"TorchPPOOptimizer.update": {
"total": 263.6061758059109,
"count": 34203,
"self": 263.6061758059109
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.600000001024455e-07,
"count": 1,
"self": 8.600000001024455e-07
},
"TrainerController._save_models": {
"total": 0.08858325799974409,
"count": 1,
"self": 0.0013387319995672442,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08724452600017685,
"count": 1,
"self": 0.08724452600017685
}
}
}
}
}
}
}