{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7544828057289124, "min": 0.7544828057289124, "max": 1.4657427072525024, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22429.265625, "min": 22429.265625, "max": 44464.76953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09641178697347641, "min": -0.08947554975748062, "max": 0.14954997599124908, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 24.006534576416016, "min": -21.633586883544922, "max": 37.68659210205078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022447288036346436, "min": -0.009583016857504845, "max": 0.23947593569755554, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.589374542236328, "min": -2.3765881061553955, "max": 57.71369934082031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07145205790678193, "min": 0.06506869113916305, "max": 0.07384279055834378, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.000328810694947, "min": 0.48994766760566644, "max": 1.1076418583751566, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0061733765324286805, "min": 7.817834828023459e-05, "max": 0.01546774264003715, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.08642727145400153, "min": 0.000938140179362815, "max": 0.11636885481372398, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.68528315255714e-06, "min": 7.68528315255714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010759396413579996, "min": 0.00010759396413579996, "max": 0.003002419399193599, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256172857142855, "min": 0.10256172857142855, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358641999999997, "min": 1.3886848, "max": 2.3170013999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026591668428571424, "min": 0.00026591668428571424, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037228335799999995, "min": 0.0037228335799999995, "max": 0.10010055936000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008749304339289665, "min": 0.008749304339289665, "max": 0.3500059247016907, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12249025702476501, "min": 0.12249025702476501, "max": 2.4500415325164795, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 739.0, "min": 710.6363636363636, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28821.0, "min": 15984.0, "max": 32696.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.254139956459403, "min": -1.0000000521540642, "max": 0.6528136025775563, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 10.165598258376122, "min": -32.000001668930054, "max": 28.723798513412476, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.254139956459403, "min": -1.0000000521540642, "max": 0.6528136025775563, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 10.165598258376122, "min": -32.000001668930054, "max": 28.723798513412476, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0668524604952836, "min": 0.0668524604952836, "max": 7.922932091169059, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6740984198113438, "min": 2.665747693798039, "max": 126.76691345870495, "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": "1701174942", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701177119" }, "total": 2176.71680411, "count": 1, "self": 0.48587471299970275, "children": { "run_training.setup": { "total": 0.0565635010002552, "count": 1, "self": 0.0565635010002552 }, "TrainerController.start_learning": { "total": 2176.174365896, "count": 1, "self": 1.4983879290380173, "children": { "TrainerController._reset_env": { "total": 3.898692736999692, "count": 1, "self": 3.898692736999692 }, "TrainerController.advance": { "total": 2170.6861797419624, "count": 63101, "self": 1.5481950689782025, "children": { "env_step": { "total": 1511.5497026149678, "count": 63101, "self": 1369.758287260026, "children": { "SubprocessEnvManager._take_step": { "total": 140.86675795399424, "count": 63101, "self": 5.210860558014701, "children": { "TorchPolicy.evaluate": { "total": 135.65589739597954, "count": 62550, "self": 135.65589739597954 } } }, "workers": { "total": 0.9246574009475808, "count": 63101, "self": 0.0, "children": { "worker_root": { "total": 2171.173678108941, "count": 63101, "is_parallel": true, "self": 928.1657944149779, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002161454999622947, "count": 1, "is_parallel": true, "self": 0.0007434089989146742, "children": { "_process_rank_one_or_two_observation": { "total": 0.001418046000708273, "count": 8, "is_parallel": true, "self": 0.001418046000708273 } } }, "UnityEnvironment.step": { "total": 0.057594596999933856, "count": 1, "is_parallel": true, "self": 0.000642665999748715, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005807359998470929, "count": 1, "is_parallel": true, "self": 0.0005807359998470929 }, "communicator.exchange": { "total": 0.05447809499992218, "count": 1, "is_parallel": true, "self": 0.05447809499992218 }, "steps_from_proto": { "total": 0.0018931000004158705, "count": 1, "is_parallel": true, "self": 0.0004163120006523968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014767879997634736, "count": 8, "is_parallel": true, "self": 0.0014767879997634736 } } } } } } }, "UnityEnvironment.step": { "total": 1243.0078836939633, "count": 63100, "is_parallel": true, "self": 35.845744946882405, "children": { "UnityEnvironment._generate_step_input": { "total": 26.32400080300431, "count": 63100, "is_parallel": true, "self": 26.32400080300431 }, "communicator.exchange": { "total": 1075.5835720800555, "count": 63100, "is_parallel": true, "self": 1075.5835720800555 }, "steps_from_proto": { "total": 105.25456586402106, "count": 63100, "is_parallel": true, "self": 21.53084334696814, "children": { "_process_rank_one_or_two_observation": { "total": 83.72372251705292, "count": 504800, "is_parallel": true, "self": 83.72372251705292 } } } } } } } } } } }, "trainer_advance": { "total": 657.5882820580164, "count": 63101, "self": 2.6789325199551968, "children": { "process_trajectory": { "total": 130.94677105806295, "count": 63101, "self": 130.75832030506308, "children": { "RLTrainer._checkpoint": { "total": 0.18845075299987002, "count": 2, "self": 0.18845075299987002 } } }, "_update_policy": { "total": 523.9625784799982, "count": 431, "self": 315.1376021039896, "children": { "TorchPPOOptimizer.update": { "total": 208.82497637600864, "count": 22830, "self": 208.82497637600864 } } } } } } }, "trainer_threads": { "total": 1.1929996617254801e-06, "count": 1, "self": 1.1929996617254801e-06 }, "TrainerController._save_models": { "total": 0.09110429500015016, "count": 1, "self": 0.0016692270000930876, "children": { "RLTrainer._checkpoint": { "total": 0.08943506800005707, "count": 1, "self": 0.08943506800005707 } } } } } } }