{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3083731234073639, "min": 0.2819095551967621, "max": 1.5033849477767944, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9221.58984375, "min": 8407.6708984375, "max": 45606.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6321502923965454, "min": -0.20968802273273468, "max": 0.6674749255180359, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.89852905273438, "min": -49.69606018066406, "max": 185.5580291748047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.045854352414608, "min": -0.06799323111772537, "max": 0.19505244493484497, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.976781845092773, "min": -18.902118682861328, "max": 47.00764083862305, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06815691671234912, "min": 0.06625544378412979, "max": 0.07429323598567286, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9541968339728877, "min": 0.4820589693634498, "max": 1.0995228199699698, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017440044884649834, "min": 0.00035465923545834245, "max": 0.017440044884649834, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2441606283850977, "min": 0.004965229296416795, "max": 0.2441606283850977, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.317976132135718e-06, "min": 7.317976132135718e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010245166584990005, "min": 0.00010245166584990005, "max": 0.003371559176147, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243929285714289, "min": 0.10243929285714289, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341501000000003, "min": 1.3886848, "max": 2.5724587, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002536853564285715, "min": 0.0002536853564285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003551594990000001, "min": 0.003551594990000001, "max": 0.11240291470000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011477920226752758, "min": 0.011477920226752758, "max": 0.3019520342350006, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16069088876247406, "min": 0.16069088876247406, "max": 2.113664150238037, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 289.13, "min": 289.13, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28913.0, "min": 15984.0, "max": 32583.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6708559803664684, "min": -1.0000000521540642, "max": 1.6833073586225509, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 167.08559803664684, "min": -30.533001720905304, "max": 167.08559803664684, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6708559803664684, "min": -1.0000000521540642, "max": 1.6833073586225509, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 167.08559803664684, "min": -30.533001720905304, "max": 167.08559803664684, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.034490513347082016, "min": 0.034490513347082016, "max": 5.952148897573352, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4490513347082015, "min": 3.4490513347082015, "max": 95.23438236117363, "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": "1678779615", "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 ./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": "1678783313" }, "total": 3698.624179746, "count": 1, "self": 0.9841866519996074, "children": { "run_training.setup": { "total": 0.174266962000047, "count": 1, "self": 0.174266962000047 }, "TrainerController.start_learning": { "total": 3697.4657261320003, "count": 1, "self": 2.7501394329301547, "children": { "TrainerController._reset_env": { "total": 4.840658382000129, "count": 1, "self": 4.840658382000129 }, "TrainerController.advance": { "total": 3689.6861928870703, "count": 64129, "self": 2.4269271272369224, "children": { "env_step": { "total": 2445.279825059886, "count": 64129, "self": 2284.3272187569974, "children": { "SubprocessEnvManager._take_step": { "total": 159.2832908698872, "count": 64129, "self": 7.205864889854865, "children": { "TorchPolicy.evaluate": { "total": 152.07742598003233, "count": 62555, "self": 152.07742598003233 } } }, "workers": { "total": 1.6693154330016569, "count": 64129, "self": 0.0, "children": { "worker_root": { "total": 3689.624627186004, "count": 64129, "is_parallel": true, "self": 1608.202089112, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033286599998518795, "count": 1, "is_parallel": true, "self": 0.0013354189998153743, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019932410000365053, "count": 8, "is_parallel": true, "self": 0.0019932410000365053 } } }, "UnityEnvironment.step": { "total": 0.07476793099999668, "count": 1, "is_parallel": true, "self": 0.0006946879998395161, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00066309200019532, "count": 1, "is_parallel": true, "self": 0.00066309200019532 }, "communicator.exchange": { "total": 0.07094438299986905, "count": 1, "is_parallel": true, "self": 0.07094438299986905 }, "steps_from_proto": { "total": 0.002465768000092794, "count": 1, "is_parallel": true, "self": 0.0005378239998208301, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019279440002719639, "count": 8, "is_parallel": true, "self": 0.0019279440002719639 } } } } } } }, "UnityEnvironment.step": { "total": 2081.422538074004, "count": 64128, "is_parallel": true, "self": 46.93465869490865, "children": { "UnityEnvironment._generate_step_input": { "total": 31.94051156905516, "count": 64128, "is_parallel": true, "self": 31.94051156905516 }, "communicator.exchange": { "total": 1848.7325163190594, "count": 64128, "is_parallel": true, "self": 1848.7325163190594 }, "steps_from_proto": { "total": 153.8148514909808, "count": 64128, "is_parallel": true, "self": 36.54262573117899, "children": { "_process_rank_one_or_two_observation": { "total": 117.27222575980181, "count": 513024, "is_parallel": true, "self": 117.27222575980181 } } } } } } } } } } }, "trainer_advance": { "total": 1241.9794406999474, "count": 64129, "self": 4.976941886015766, "children": { "process_trajectory": { "total": 182.76708277092985, "count": 64129, "self": 182.4230888389302, "children": { "RLTrainer._checkpoint": { "total": 0.34399393199964834, "count": 2, "self": 0.34399393199964834 } } }, "_update_policy": { "total": 1054.2354160430018, "count": 450, "self": 452.7237084280264, "children": { "TorchPPOOptimizer.update": { "total": 601.5117076149754, "count": 22815, "self": 601.5117076149754 } } } } } } }, "trainer_threads": { "total": 2.6799998522619717e-06, "count": 1, "self": 2.6799998522619717e-06 }, "TrainerController._save_models": { "total": 0.18873274999987188, "count": 1, "self": 0.0029940439999336377, "children": { "RLTrainer._checkpoint": { "total": 0.18573870599993825, "count": 1, "self": 0.18573870599993825 } } } } } } }