tvnguyen's picture
Third Push
b9722d7
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.18592286109924316,
"min": 0.17794272303581238,
"max": 0.48007693886756897,
"count": 67
},
"Pyramids.Policy.Entropy.sum": {
"value": 5631.2314453125,
"min": 5363.9052734375,
"max": 14525.2080078125,
"count": 67
},
"Pyramids.Step.mean": {
"value": 2999891.0,
"min": 1019928.0,
"max": 2999891.0,
"count": 67
},
"Pyramids.Step.sum": {
"value": 2999891.0,
"min": 1019928.0,
"max": 2999891.0,
"count": 67
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8583548069000244,
"min": 0.4942023456096649,
"max": 0.8688791990280151,
"count": 67
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 265.23162841796875,
"min": 108.88697814941406,
"max": 270.221435546875,
"count": 67
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02107888273894787,
"min": -0.009596453979611397,
"max": 0.07375943660736084,
"count": 67
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.5133748054504395,
"min": -2.7253928184509277,
"max": 13.645496368408203,
"count": 67
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 196.27450980392157,
"min": 196.27450980392157,
"max": 414.6756756756757,
"count": 67
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30030.0,
"min": 15649.0,
"max": 31792.0,
"count": 67
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7904402501397318,
"min": 1.4484246693275593,
"max": 1.7904402501397318,
"count": 67
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 275.7277985215187,
"min": 92.35099902749062,
"max": 275.7277985215187,
"count": 67
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7904402501397318,
"min": 1.4484246693275593,
"max": 1.7904402501397318,
"count": 67
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 275.7277985215187,
"min": 92.35099902749062,
"max": 275.7277985215187,
"count": 67
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.017876258854387258,
"min": 0.017876258854387258,
"max": 0.06815792065321442,
"count": 67
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.752943863575638,
"min": 2.515744366814033,
"max": 5.043686128337868,
"count": 67
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07133124608296056,
"min": 0.06443350202688534,
"max": 0.07196596014220137,
"count": 67
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9986374451614477,
"min": 0.638755505462862,
"max": 1.0680313948347855,
"count": 67
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01600719058739591,
"min": 0.011874273438089791,
"max": 0.016545076395143007,
"count": 67
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22410066822354277,
"min": 0.11781841344468286,
"max": 0.2443678327562178,
"count": 67
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4816852204238088e-06,
"min": 1.4816852204238088e-06,
"max": 0.0001989477114618852,
"count": 67
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.0743593085933322e-05,
"min": 2.0743593085933322e-05,
"max": 0.0028125587624806,
"count": 67
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049386190476192,
"min": 0.10049386190476192,
"max": 0.1663158925925926,
"count": 67
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4069140666666669,
"min": 1.4069140666666669,
"max": 2.4375194000000002,
"count": 67
},
"Pyramids.Policy.Beta.mean": {
"value": 5.933680428571425e-05,
"min": 5.933680428571425e-05,
"max": 0.006634957670000001,
"count": 67
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008307152599999995,
"min": 0.0008307152599999995,
"max": 0.09380818806,
"count": 67
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008710493333637714,
"min": 0.008176642470061779,
"max": 0.016550308093428612,
"count": 67
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12194690853357315,
"min": 0.11447300016880035,
"max": 0.22358304262161255,
"count": 67
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 67
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 67
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1681650125",
"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 /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics --resume",
"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": "1681655453"
},
"total": 5327.478407201999,
"count": 1,
"self": 0.47530855699915264,
"children": {
"run_training.setup": {
"total": 0.20567490999974325,
"count": 1,
"self": 0.20567490999974325
},
"TrainerController.start_learning": {
"total": 5326.797423735001,
"count": 1,
"self": 3.591834799179196,
"children": {
"TrainerController._reset_env": {
"total": 4.933868087000064,
"count": 1,
"self": 4.933868087000064
},
"TrainerController.advance": {
"total": 5318.175934921824,
"count": 131163,
"self": 3.8776282649005225,
"children": {
"env_step": {
"total": 4059.7783762618624,
"count": 131163,
"self": 3808.3597831870793,
"children": {
"SubprocessEnvManager._take_step": {
"total": 249.27971572703837,
"count": 131163,
"self": 10.687992939127525,
"children": {
"TorchPolicy.evaluate": {
"total": 238.59172278791084,
"count": 125069,
"self": 238.59172278791084
}
}
},
"workers": {
"total": 2.1388773477447103,
"count": 131163,
"self": 0.0,
"children": {
"worker_root": {
"total": 5314.536858009837,
"count": 131163,
"is_parallel": true,
"self": 1765.9769558398916,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003035013000044273,
"count": 1,
"is_parallel": true,
"self": 0.0009488090004197147,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020862039996245585,
"count": 8,
"is_parallel": true,
"self": 0.0020862039996245585
}
}
},
"UnityEnvironment.step": {
"total": 0.05871273299999302,
"count": 1,
"is_parallel": true,
"self": 0.0005845680002494191,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000594266999996762,
"count": 1,
"is_parallel": true,
"self": 0.000594266999996762
},
"communicator.exchange": {
"total": 0.05551312199986569,
"count": 1,
"is_parallel": true,
"self": 0.05551312199986569
},
"steps_from_proto": {
"total": 0.0020207759998811525,
"count": 1,
"is_parallel": true,
"self": 0.0004644770001505094,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015562989997306431,
"count": 8,
"is_parallel": true,
"self": 0.0015562989997306431
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3548.559902169945,
"count": 131162,
"is_parallel": true,
"self": 69.79849993719927,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 52.09461211420057,
"count": 131162,
"is_parallel": true,
"self": 52.09461211420057
},
"communicator.exchange": {
"total": 3209.5752868965565,
"count": 131162,
"is_parallel": true,
"self": 3209.5752868965565
},
"steps_from_proto": {
"total": 217.09150322198866,
"count": 131162,
"is_parallel": true,
"self": 48.66155478534802,
"children": {
"_process_rank_one_or_two_observation": {
"total": 168.42994843664064,
"count": 1049296,
"is_parallel": true,
"self": 168.42994843664064
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1254.5199303950603,
"count": 131163,
"self": 6.673967917902701,
"children": {
"process_trajectory": {
"total": 236.89730079215633,
"count": 131163,
"self": 236.4198225511559,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47747824100042635,
"count": 4,
"self": 0.47747824100042635
}
}
},
"_update_policy": {
"total": 1010.9486616850013,
"count": 946,
"self": 641.6979436258766,
"children": {
"TorchPPOOptimizer.update": {
"total": 369.25071805912467,
"count": 45543,
"self": 369.25071805912467
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0539988579694182e-06,
"count": 1,
"self": 1.0539988579694182e-06
},
"TrainerController._save_models": {
"total": 0.09578487299950211,
"count": 1,
"self": 0.0017574430003151065,
"children": {
"RLTrainer._checkpoint": {
"total": 0.094027429999187,
"count": 1,
"self": 0.094027429999187
}
}
}
}
}
}
}