{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36647021770477295, "min": 0.36647021770477295, "max": 1.4333029985427856, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10953.0615234375, "min": 10953.0615234375, "max": 43480.6796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5184723138809204, "min": -0.12650656700134277, "max": 0.591368556022644, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.06141662597656, "min": -30.03253746032715, "max": 165.58319091796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008220351301133633, "min": 0.0002671023830771446, "max": 0.3495032787322998, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.2523763179779053, "min": 0.07238474488258362, "max": 82.832275390625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07107717379257025, "min": 0.06360095677256072, "max": 0.07660879743250495, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9950804330959835, "min": 0.5214710641376695, "max": 1.0476803669589572, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014276639248993828, "min": 0.0005500951116110972, "max": 0.01679616637522399, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19987294948591358, "min": 0.004400760892888778, "max": 0.23514632925313583, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.643733166407144e-06, "min": 7.643733166407144e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010701226432970001, "min": 0.00010701226432970001, "max": 0.0035072891309036996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254787857142857, "min": 0.10254787857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356703, "min": 1.3691136000000002, "max": 2.5690963000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026453306928571444, "min": 0.00026453306928571444, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003703462970000002, "min": 0.003703462970000002, "max": 0.11693272037, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02067652903497219, "min": 0.02067652903497219, "max": 0.6578234434127808, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.28947141766548157, "min": 0.28947141766548157, "max": 4.604763984680176, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 364.5813953488372, "min": 301.6458333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31354.0, "min": 15984.0, "max": 34138.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5153317375218167, "min": -1.0000000521540642, "max": 1.677514567039907, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.80319768935442, "min": -32.000001668930054, "max": 161.04139843583107, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5153317375218167, "min": -1.0000000521540642, "max": 1.677514567039907, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.80319768935442, "min": -32.000001668930054, "max": 161.04139843583107, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08078804624349098, "min": 0.0744586649446622, "max": 14.769344542175531, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.866983930696733, "min": 6.339833421734511, "max": 236.3095126748085, "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": "1679577951", "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=PyramidsTraining --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": "1679580160" }, "total": 2208.871212098, "count": 1, "self": 0.8485184239998489, "children": { "run_training.setup": { "total": 0.10528656399992542, "count": 1, "self": 0.10528656399992542 }, "TrainerController.start_learning": { "total": 2207.91740711, "count": 1, "self": 1.3818655550185213, "children": { "TrainerController._reset_env": { "total": 7.41780844699997, "count": 1, "self": 7.41780844699997 }, "TrainerController.advance": { "total": 2198.972193064982, "count": 63836, "self": 1.4667232049910126, "children": { "env_step": { "total": 1577.9283232659345, "count": 63836, "self": 1469.7489583289462, "children": { "SubprocessEnvManager._take_step": { "total": 107.34195967904407, "count": 63836, "self": 4.748975744037125, "children": { "TorchPolicy.evaluate": { "total": 102.59298393500694, "count": 62566, "self": 102.59298393500694 } } }, "workers": { "total": 0.8374052579442832, "count": 63836, "self": 0.0, "children": { "worker_root": { "total": 2203.1931559489335, "count": 63836, "is_parallel": true, "self": 847.6841484380107, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020234939997862966, "count": 1, "is_parallel": true, "self": 0.0006022300003678538, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014212639994184428, "count": 8, "is_parallel": true, "self": 0.0014212639994184428 } } }, "UnityEnvironment.step": { "total": 0.0487943749999431, "count": 1, "is_parallel": true, "self": 0.0005744770001001598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045666999994864454, "count": 1, "is_parallel": true, "self": 0.00045666999994864454 }, "communicator.exchange": { "total": 0.04602199800001472, "count": 1, "is_parallel": true, "self": 0.04602199800001472 }, "steps_from_proto": { "total": 0.0017412299998795788, "count": 1, "is_parallel": true, "self": 0.0003821550003522134, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013590749995273654, "count": 8, "is_parallel": true, "self": 0.0013590749995273654 } } } } } } }, "UnityEnvironment.step": { "total": 1355.5090075109229, "count": 63835, "is_parallel": true, "self": 31.58585958495587, "children": { "UnityEnvironment._generate_step_input": { "total": 22.736510561978776, "count": 63835, "is_parallel": true, "self": 22.736510561978776 }, "communicator.exchange": { "total": 1207.3890739090466, "count": 63835, "is_parallel": true, "self": 1207.3890739090466 }, "steps_from_proto": { "total": 93.79756345494161, "count": 63835, "is_parallel": true, "self": 19.80421265876612, "children": { "_process_rank_one_or_two_observation": { "total": 73.99335079617549, "count": 510680, "is_parallel": true, "self": 73.99335079617549 } } } } } } } } } } }, "trainer_advance": { "total": 619.5771465940566, "count": 63836, "self": 2.5508085290966847, "children": { "process_trajectory": { "total": 116.77466541297235, "count": 63836, "self": 116.4626436919716, "children": { "RLTrainer._checkpoint": { "total": 0.31202172100074677, "count": 2, "self": 0.31202172100074677 } } }, "_update_policy": { "total": 500.2516726519875, "count": 443, "self": 317.94097543490807, "children": { "TorchPPOOptimizer.update": { "total": 182.31069721707945, "count": 22821, "self": 182.31069721707945 } } } } } } }, "trainer_threads": { "total": 1.4979996194597334e-06, "count": 1, "self": 1.4979996194597334e-06 }, "TrainerController._save_models": { "total": 0.14553854499990848, "count": 1, "self": 0.0019431959999565152, "children": { "RLTrainer._checkpoint": { "total": 0.14359534899995197, "count": 1, "self": 0.14359534899995197 } } } } } } }