{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1408933401107788, "min": 0.1331000030040741, "max": 1.4451422691345215, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 4211.02001953125, "min": 3978.0927734375, "max": 43839.8359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989895.0, "min": 29952.0, "max": 989895.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989895.0, "min": 29952.0, "max": 989895.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3550621569156647, "min": -0.10232432931661606, "max": 0.3550621569156647, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 94.446533203125, "min": -24.66016387939453, "max": 94.446533203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04747239872813225, "min": 0.04742880165576935, "max": 0.3632095456123352, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.627657890319824, "min": 12.568632125854492, "max": 87.53350067138672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07250438436816241, "min": 0.06603680933774757, "max": 0.07250438436816241, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0150613811542737, "min": 0.4819999701795422, "max": 1.0714611336297821, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014409513144648058, "min": 0.0008280690021465284, "max": 0.014409513144648058, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20173318402507281, "min": 0.011592966030051397, "max": 0.20173318402507281, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.554676053235717e-06, "min": 7.554676053235717e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010576546474530004, "min": 0.00010576546474530004, "max": 0.0033806834731055996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251819285714288, "min": 0.10251819285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352547000000002, "min": 1.3886848, "max": 2.5268944, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026156746642857153, "min": 0.00026156746642857153, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036619445300000012, "min": 0.0036619445300000012, "max": 0.11271675056000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.09160561859607697, "min": 0.09050997346639633, "max": 0.42307570576667786, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.2824786901474, "min": 1.2671396732330322, "max": 2.9615299701690674, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 462.1194029850746, "min": 462.1194029850746, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30962.0, "min": 15984.0, "max": 33024.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2989999716406437, "min": -1.0000000521540642, "max": 1.2989999716406437, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.03299809992313, "min": -30.697001740336418, "max": 87.03299809992313, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2989999716406437, "min": -1.0000000521540642, "max": 1.2989999716406437, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.03299809992313, "min": -30.697001740336418, "max": 87.03299809992313, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.4310333515137761, "min": 0.42429793723960524, "max": 7.520682496018708, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 28.879234551422996, "min": 26.73077004609513, "max": 120.33091993629932, "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": "1685943301", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685945032" }, "total": 1731.368692346, "count": 1, "self": 0.37283626299995376, "children": { "run_training.setup": { "total": 0.04048994999993738, "count": 1, "self": 0.04048994999993738 }, "TrainerController.start_learning": { "total": 1730.955366133, "count": 1, "self": 1.5714975868854708, "children": { "TrainerController._reset_env": { "total": 4.189904978999948, "count": 1, "self": 4.189904978999948 }, "TrainerController.advance": { "total": 1725.0886394181139, "count": 63602, "self": 1.4622982369978672, "children": { "env_step": { "total": 1124.504876991035, "count": 63602, "self": 1009.1690688160552, "children": { "SubprocessEnvManager._take_step": { "total": 114.419299357015, "count": 63602, "self": 4.760665715030427, "children": { "TorchPolicy.evaluate": { "total": 109.65863364198458, "count": 62568, "self": 109.65863364198458 } } }, "workers": { "total": 0.9165088179647682, "count": 63602, "self": 0.0, "children": { "worker_root": { "total": 1728.189728813009, "count": 63602, "is_parallel": true, "self": 823.4012033581089, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019729819996427977, "count": 1, "is_parallel": true, "self": 0.0006033620002199314, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013696199994228664, "count": 8, "is_parallel": true, "self": 0.0013696199994228664 } } }, "UnityEnvironment.step": { "total": 0.04923758300037662, "count": 1, "is_parallel": true, "self": 0.0004900820003967965, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004927489999317913, "count": 1, "is_parallel": true, "self": 0.0004927489999317913 }, "communicator.exchange": { "total": 0.046554469000057, "count": 1, "is_parallel": true, "self": 0.046554469000057 }, "steps_from_proto": { "total": 0.0017002829999910318, "count": 1, "is_parallel": true, "self": 0.0002992080007970799, "children": { "_process_rank_one_or_two_observation": { "total": 0.001401074999193952, "count": 8, "is_parallel": true, "self": 0.001401074999193952 } } } } } } }, "UnityEnvironment.step": { "total": 904.7885254549001, "count": 63601, "is_parallel": true, "self": 25.58731569983638, "children": { "UnityEnvironment._generate_step_input": { "total": 17.63401546099567, "count": 63601, "is_parallel": true, "self": 17.63401546099567 }, "communicator.exchange": { "total": 785.8385756440898, "count": 63601, "is_parallel": true, "self": 785.8385756440898 }, "steps_from_proto": { "total": 75.72861864997822, "count": 63601, "is_parallel": true, "self": 15.66387929494931, "children": { "_process_rank_one_or_two_observation": { "total": 60.064739355028905, "count": 508808, "is_parallel": true, "self": 60.064739355028905 } } } } } } } } } } }, "trainer_advance": { "total": 599.121464190081, "count": 63602, "self": 2.86412017603152, "children": { "process_trajectory": { "total": 100.37848487504925, "count": 63602, "self": 100.16790631404956, "children": { "RLTrainer._checkpoint": { "total": 0.21057856099969285, "count": 2, "self": 0.21057856099969285 } } }, "_update_policy": { "total": 495.87885913900027, "count": 448, "self": 312.8440424709511, "children": { "TorchPPOOptimizer.update": { "total": 183.0348166680492, "count": 22824, "self": 183.0348166680492 } } } } } } }, "trainer_threads": { "total": 1.13300029624952e-06, "count": 1, "self": 1.13300029624952e-06 }, "TrainerController._save_models": { "total": 0.10532301600051142, "count": 1, "self": 0.0015248780000547413, "children": { "RLTrainer._checkpoint": { "total": 0.10379813800045667, "count": 1, "self": 0.10379813800045667 } } } } } } }