ppo-Pyramids / run_logs /timers.json
robinsk8a's picture
First Push
1aa741b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.128108412027359,
"min": 0.12237264215946198,
"max": 1.413196086883545,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 3853.5009765625,
"min": 3641.394287109375,
"max": 42870.71484375,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999924.0,
"min": 29952.0,
"max": 2999924.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999924.0,
"min": 29952.0,
"max": 2999924.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7752293348312378,
"min": -0.09120776504278183,
"max": 0.915306806564331,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 233.34402465820312,
"min": -21.98107147216797,
"max": 287.9504089355469,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.001923867384903133,
"min": -0.0313878208398819,
"max": 0.28674912452697754,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.5790840983390808,
"min": -9.322182655334473,
"max": 69.10653686523438,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07260600638290357,
"min": 0.06237018431453046,
"max": 0.07413581686711698,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.01648408936065,
"min": 0.502265318624686,
"max": 1.093403842659124,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01345248880846027,
"min": 0.0004834300600804228,
"max": 0.015874433238059284,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18833484331844377,
"min": 0.006768020841125919,
"max": 0.23811649857088926,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5603137656428577e-06,
"min": 1.5603137656428577e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.184439271900001e-05,
"min": 2.184439271900001e-05,
"max": 0.004027661457446233,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10052007142857144,
"min": 0.10052007142857144,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4072810000000002,
"min": 1.3962282666666668,
"max": 2.8425537666666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.195513571428574e-05,
"min": 6.195513571428574e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008673719000000004,
"min": 0.0008673719000000004,
"max": 0.13427112129000002,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008693576790392399,
"min": 0.0084421681240201,
"max": 0.4437733292579651,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12171006947755814,
"min": 0.11819034814834595,
"max": 3.1064133644104004,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 236.72222222222223,
"min": 198.77551020408163,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29827.0,
"min": 15984.0,
"max": 34768.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7156460200037276,
"min": -1.0000000521540642,
"max": 1.8018040421444017,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 216.17139852046967,
"min": -29.666001617908478,
"max": 274.88079726696014,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7156460200037276,
"min": -1.0000000521540642,
"max": 1.8018040421444017,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 216.17139852046967,
"min": -29.666001617908478,
"max": 274.88079726696014,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.021206499116646776,
"min": 0.018371943697369622,
"max": 8.274767864495516,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.672018888697494,
"min": 2.5798983370768838,
"max": 132.39628583192825,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675979790",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1675987904"
},
"total": 8113.687668517001,
"count": 1,
"self": 0.5238510990002396,
"children": {
"run_training.setup": {
"total": 0.10744522699997106,
"count": 1,
"self": 0.10744522699997106
},
"TrainerController.start_learning": {
"total": 8113.056372191,
"count": 1,
"self": 4.485536280960332,
"children": {
"TrainerController._reset_env": {
"total": 6.144176148000042,
"count": 1,
"self": 6.144176148000042
},
"TrainerController.advance": {
"total": 8102.34191613004,
"count": 195954,
"self": 4.669002742006342,
"children": {
"env_step": {
"total": 5736.211300077174,
"count": 195954,
"self": 5360.688740819109,
"children": {
"SubprocessEnvManager._take_step": {
"total": 372.70702605290717,
"count": 195954,
"self": 15.433793747710524,
"children": {
"TorchPolicy.evaluate": {
"total": 357.27323230519664,
"count": 187564,
"self": 120.65199123718958,
"children": {
"TorchPolicy.sample_actions": {
"total": 236.62124106800707,
"count": 187564,
"self": 236.62124106800707
}
}
}
}
},
"workers": {
"total": 2.8155332051583173,
"count": 195954,
"self": 0.0,
"children": {
"worker_root": {
"total": 8094.5762574570435,
"count": 195954,
"is_parallel": true,
"self": 3121.3414085340846,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00209629899995889,
"count": 1,
"is_parallel": true,
"self": 0.00073577200055297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00136052699940592,
"count": 8,
"is_parallel": true,
"self": 0.00136052699940592
}
}
},
"UnityEnvironment.step": {
"total": 0.06486887300002309,
"count": 1,
"is_parallel": true,
"self": 0.0005478069999753643,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048680800000511226,
"count": 1,
"is_parallel": true,
"self": 0.00048680800000511226
},
"communicator.exchange": {
"total": 0.06208263000007719,
"count": 1,
"is_parallel": true,
"self": 0.06208263000007719
},
"steps_from_proto": {
"total": 0.0017516279999654216,
"count": 1,
"is_parallel": true,
"self": 0.0004514409999956115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013001869999698101,
"count": 8,
"is_parallel": true,
"self": 0.0013001869999698101
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4973.234848922959,
"count": 195953,
"is_parallel": true,
"self": 97.23238893195048,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 72.30736664192546,
"count": 195953,
"is_parallel": true,
"self": 72.30736664192546
},
"communicator.exchange": {
"total": 4466.810293531054,
"count": 195953,
"is_parallel": true,
"self": 4466.810293531054
},
"steps_from_proto": {
"total": 336.8847998180281,
"count": 195953,
"is_parallel": true,
"self": 76.31176455953118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 260.57303525849693,
"count": 1567624,
"is_parallel": true,
"self": 260.57303525849693
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2361.4616133108593,
"count": 195954,
"self": 9.056248450894145,
"children": {
"process_trajectory": {
"total": 547.6472703099521,
"count": 195954,
"self": 547.0988608279513,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5484094820008067,
"count": 6,
"self": 0.5484094820008067
}
}
},
"_update_policy": {
"total": 1804.758094550013,
"count": 1404,
"self": 700.3058228919201,
"children": {
"TorchPPOOptimizer.update": {
"total": 1104.452271658093,
"count": 68319,
"self": 1104.452271658093
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.369996405439451e-07,
"count": 1,
"self": 9.369996405439451e-07
},
"TrainerController._save_models": {
"total": 0.08474269500038645,
"count": 1,
"self": 0.0015405670001200633,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08320212800026638,
"count": 1,
"self": 0.08320212800026638
}
}
}
}
}
}
}