ppo-Pyramids / run_logs /timers.json
agcagc's picture
First commit
b7f5fb5
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.601695716381073,
"min": 0.601695716381073,
"max": 1.448063611984253,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17925.71875,
"min": 17925.71875,
"max": 43928.45703125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989921.0,
"min": 29889.0,
"max": 989921.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989921.0,
"min": 29889.0,
"max": 989921.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4398577809333801,
"min": -0.1056586429476738,
"max": 0.4398577809333801,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 120.0811767578125,
"min": -25.463733673095703,
"max": 120.0811767578125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.11712273955345154,
"min": -0.005557958036661148,
"max": 0.4559553563594818,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 31.97450828552246,
"min": -1.422837257385254,
"max": 108.06141662597656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06457633996769176,
"min": 0.06321272299608664,
"max": 0.07233616372903663,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9040687595476845,
"min": 0.5670989945597724,
"max": 1.0624625924198579,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017234529056021186,
"min": 0.0004235755065085514,
"max": 0.017234529056021186,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2412834067842966,
"min": 0.005506481584611168,
"max": 0.2412834067842966,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.362976117135718e-06,
"min": 7.362976117135718e-06,
"max": 0.0002948470892176375,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010308166563990005,
"min": 0.00010308166563990005,
"max": 0.0035073635308788993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245429285714287,
"min": 0.10245429285714287,
"max": 0.19828236250000003,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343601000000001,
"min": 1.4343601000000001,
"max": 2.5691211000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025518385642857153,
"min": 0.00025518385642857153,
"max": 0.009828408013749998,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003572573990000001,
"min": 0.003572573990000001,
"max": 0.11693519789,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01205852348357439,
"min": 0.01205852348357439,
"max": 0.39700034260749817,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16881932318210602,
"min": 0.16881932318210602,
"max": 3.1760027408599854,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 409.88,
"min": 409.88,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30741.0,
"min": 16432.0,
"max": 32604.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4567493055264156,
"min": -1.0000000521540642,
"max": 1.4889910195523233,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 109.25619791448116,
"min": -32.000001668930054,
"max": 109.25619791448116,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4567493055264156,
"min": -1.0000000521540642,
"max": 1.4889910195523233,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 109.25619791448116,
"min": -32.000001668930054,
"max": 109.25619791448116,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.051020004892100894,
"min": 0.051020004892100894,
"max": 7.811611454276478,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.826500366907567,
"min": 3.7378313987865113,
"max": 132.79739472270012,
"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": "1678052766",
"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 --force --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": "1.22.4",
"end_time_seconds": "1678055011"
},
"total": 2245.094542924,
"count": 1,
"self": 0.48733348099995055,
"children": {
"run_training.setup": {
"total": 0.10682315999997627,
"count": 1,
"self": 0.10682315999997627
},
"TrainerController.start_learning": {
"total": 2244.500386283,
"count": 1,
"self": 1.4997910450092604,
"children": {
"TrainerController._reset_env": {
"total": 9.875019118000182,
"count": 1,
"self": 9.875019118000182
},
"TrainerController.advance": {
"total": 2233.0238051699903,
"count": 63475,
"self": 1.5658244459641537,
"children": {
"env_step": {
"total": 1491.094272762017,
"count": 63475,
"self": 1368.062184760952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.11461451698119,
"count": 63475,
"self": 5.0142549300135215,
"children": {
"TorchPolicy.evaluate": {
"total": 117.10035958696767,
"count": 62552,
"self": 39.67912670297551,
"children": {
"TorchPolicy.sample_actions": {
"total": 77.42123288399216,
"count": 62552,
"self": 77.42123288399216
}
}
}
}
},
"workers": {
"total": 0.9174734840837573,
"count": 63475,
"self": 0.0,
"children": {
"worker_root": {
"total": 2238.955958837929,
"count": 63475,
"is_parallel": true,
"self": 995.5685950048876,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00644598799999585,
"count": 1,
"is_parallel": true,
"self": 0.003597200000058365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028487879999374854,
"count": 8,
"is_parallel": true,
"self": 0.0028487879999374854
}
}
},
"UnityEnvironment.step": {
"total": 0.054396120000092196,
"count": 1,
"is_parallel": true,
"self": 0.0005380620002597425,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004932760000428971,
"count": 1,
"is_parallel": true,
"self": 0.0004932760000428971
},
"communicator.exchange": {
"total": 0.05174202199987121,
"count": 1,
"is_parallel": true,
"self": 0.05174202199987121
},
"steps_from_proto": {
"total": 0.001622759999918344,
"count": 1,
"is_parallel": true,
"self": 0.00041057799990085186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001212182000017492,
"count": 8,
"is_parallel": true,
"self": 0.001212182000017492
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1243.3873638330413,
"count": 63474,
"is_parallel": true,
"self": 32.012791910043916,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.42559882499245,
"count": 63474,
"is_parallel": true,
"self": 24.42559882499245
},
"communicator.exchange": {
"total": 1089.377768034984,
"count": 63474,
"is_parallel": true,
"self": 1089.377768034984
},
"steps_from_proto": {
"total": 97.5712050630209,
"count": 63474,
"is_parallel": true,
"self": 24.086998475046585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.48420658797431,
"count": 507792,
"is_parallel": true,
"self": 73.48420658797431
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 740.3637079620094,
"count": 63475,
"self": 2.91434912904856,
"children": {
"process_trajectory": {
"total": 167.52942433795738,
"count": 63475,
"self": 167.3328776179576,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19654671999978746,
"count": 2,
"self": 0.19654671999978746
}
}
},
"_update_policy": {
"total": 569.9199344950034,
"count": 449,
"self": 222.49713971399046,
"children": {
"TorchPPOOptimizer.update": {
"total": 347.42279478101295,
"count": 22812,
"self": 347.42279478101295
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3320000107341912e-06,
"count": 1,
"self": 1.3320000107341912e-06
},
"TrainerController._save_models": {
"total": 0.10176961800016215,
"count": 1,
"self": 0.0015716600000814651,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10019795800008069,
"count": 1,
"self": 0.10019795800008069
}
}
}
}
}
}
}