ppo-Pyramid / run_logs /timers.json
pasto2003's picture
First Push
6665a21
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3959891200065613,
"min": 0.3959891200065613,
"max": 1.4674885272979736,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11987.3828125,
"min": 11974.537109375,
"max": 44517.73046875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989938.0,
"min": 29983.0,
"max": 989938.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989938.0,
"min": 29983.0,
"max": 989938.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3591771423816681,
"min": -0.10072144865989685,
"max": 0.36515671014785767,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 94.46358489990234,
"min": -24.273868560791016,
"max": 97.13168334960938,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.6122244000434875,
"min": -0.17625004053115845,
"max": 0.6122244000434875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 161.0150146484375,
"min": -44.94375991821289,
"max": 161.0150146484375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06921982070309153,
"min": 0.06635365187846246,
"max": 0.07515735135588664,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9690774898432815,
"min": 0.6012588108470931,
"max": 1.0629419223211396,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.06849211643843557,
"min": 0.0005106639957872239,
"max": 0.06849211643843557,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.9588896301380979,
"min": 0.00663863194523391,
"max": 0.9588896301380979,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.614054604871426e-06,
"min": 7.614054604871426e-06,
"max": 0.00029476395174535,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010659676446819997,
"min": 0.00010659676446819997,
"max": 0.0036085332971556,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253798571428571,
"min": 0.10253798571428571,
"max": 0.19825464999999998,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355318,
"min": 1.4355318,
"max": 2.5262016000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002635447728571428,
"min": 0.0002635447728571428,
"max": 0.009825639535,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003689626819999999,
"min": 0.003689626819999999,
"max": 0.12029415556,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010262065567076206,
"min": 0.010262065567076206,
"max": 0.3446158170700073,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14366891980171204,
"min": 0.14366891980171204,
"max": 2.7569265365600586,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 469.3333333333333,
"min": 469.3333333333333,
"max": 994.46875,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29568.0,
"min": 17549.0,
"max": 32762.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2131110847232833,
"min": -0.932712550740689,
"max": 1.2957784392512761,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 76.42599833756685,
"min": -30.072401642799377,
"max": 84.22559855133295,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2131110847232833,
"min": -0.932712550740689,
"max": 1.2957784392512761,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 76.42599833756685,
"min": -30.072401642799377,
"max": 84.22559855133295,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05054542627465072,
"min": 0.05054542627465072,
"max": 6.533946255015002,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.1843618553029955,
"min": 3.1843618553029955,
"max": 117.61103259027004,
"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": "1692522678",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1692524489"
},
"total": 1810.97955189,
"count": 1,
"self": 0.37448872199956895,
"children": {
"run_training.setup": {
"total": 0.04157380800006649,
"count": 1,
"self": 0.04157380800006649
},
"TrainerController.start_learning": {
"total": 1810.5634893600004,
"count": 1,
"self": 1.7299272390127953,
"children": {
"TrainerController._reset_env": {
"total": 4.167234186999849,
"count": 1,
"self": 4.167234186999849
},
"TrainerController.advance": {
"total": 1804.5535631099879,
"count": 63562,
"self": 1.7496366879804555,
"children": {
"env_step": {
"total": 1173.1469313460143,
"count": 63562,
"self": 1047.7615446549921,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.32243597803836,
"count": 63562,
"self": 5.178887251150627,
"children": {
"TorchPolicy.evaluate": {
"total": 119.14354872688773,
"count": 62576,
"self": 119.14354872688773
}
}
},
"workers": {
"total": 1.0629507129838203,
"count": 63562,
"self": 0.0,
"children": {
"worker_root": {
"total": 1807.6050802309965,
"count": 63562,
"is_parallel": true,
"self": 872.3954598569944,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019424520000939083,
"count": 1,
"is_parallel": true,
"self": 0.0006209530010892195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013214989990046888,
"count": 8,
"is_parallel": true,
"self": 0.0013214989990046888
}
}
},
"UnityEnvironment.step": {
"total": 0.03651695700000346,
"count": 1,
"is_parallel": true,
"self": 0.00038662699989799876,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003880449999087432,
"count": 1,
"is_parallel": true,
"self": 0.0003880449999087432
},
"communicator.exchange": {
"total": 0.03430390699986674,
"count": 1,
"is_parallel": true,
"self": 0.03430390699986674
},
"steps_from_proto": {
"total": 0.0014383780003299762,
"count": 1,
"is_parallel": true,
"self": 0.0002769319994513353,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001161446000878641,
"count": 8,
"is_parallel": true,
"self": 0.001161446000878641
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 935.209620374002,
"count": 63561,
"is_parallel": true,
"self": 25.16291524300823,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 16.96744027701243,
"count": 63561,
"is_parallel": true,
"self": 16.96744027701243
},
"communicator.exchange": {
"total": 815.6605681839965,
"count": 63561,
"is_parallel": true,
"self": 815.6605681839965
},
"steps_from_proto": {
"total": 77.41869666998491,
"count": 63561,
"is_parallel": true,
"self": 16.421576785104662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.99711988488025,
"count": 508488,
"is_parallel": true,
"self": 60.99711988488025
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 629.6569950759931,
"count": 63562,
"self": 3.2443745029677302,
"children": {
"process_trajectory": {
"total": 111.62119907101942,
"count": 63562,
"self": 111.39361938301954,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22757968799987793,
"count": 2,
"self": 0.22757968799987793
}
}
},
"_update_policy": {
"total": 514.791421502006,
"count": 457,
"self": 325.8604664619975,
"children": {
"TorchPPOOptimizer.update": {
"total": 188.93095504000848,
"count": 22764,
"self": 188.93095504000848
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.247000000148546e-06,
"count": 1,
"self": 1.247000000148546e-06
},
"TrainerController._save_models": {
"total": 0.11276357699989603,
"count": 1,
"self": 0.0016012999999475142,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11116227699994852,
"count": 1,
"self": 0.11116227699994852
}
}
}
}
}
}
}