{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.21664220094680786, "min": 0.2135288417339325, "max": 1.5174821615219116, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 6457.6708984375, "min": 6429.7802734375, "max": 46034.33984375, "count": 66 }, "Pyramids.Step.mean": { "value": 1979936.0, "min": 29952.0, "max": 1979936.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979936.0, "min": 29952.0, "max": 1979936.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6822056174278259, "min": -0.08900834619998932, "max": 0.7794942259788513, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 197.83963012695312, "min": -21.718036651611328, "max": 233.0687713623047, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007115354295819998, "min": -0.0556795671582222, "max": 0.159385547041893, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.06345272064209, "min": -14.19828987121582, "max": 38.252532958984375, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06826755396348551, "min": 0.0645247488695591, "max": 0.07547420541094592, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.955745755488797, "min": 0.5118466482282651, "max": 1.054759598012121, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01550036242125094, "min": 0.0013864562313724493, "max": 0.018257239262770057, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21700507389751317, "min": 0.011065038944351905, "max": 0.2556013496787808, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.148355426771426e-06, "min": 5.148355426771426e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.207697597479997e-05, "min": 7.207697597479997e-05, "max": 0.0037910170363277002, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10171608571428571, "min": 0.10171608571428571, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4240252, "min": 1.3845568000000001, "max": 2.7412738000000005, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018143696285714283, "min": 0.00018143696285714283, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.0025401174799999995, "min": 0.0025401174799999995, "max": 0.12638086277, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006994408089667559, "min": 0.006768988911062479, "max": 0.32938385009765625, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0979217141866684, "min": 0.09476584196090698, "max": 2.3056869506835938, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 256.3076923076923, "min": 243.71544715447155, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29988.0, "min": 15984.0, "max": 32992.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.743387920717741, "min": -1.0000000521540642, "max": 1.757991852193344, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 202.23299880325794, "min": -32.000001668930054, "max": 217.7511980831623, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.743387920717741, "min": -1.0000000521540642, "max": 1.757991852193344, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 202.23299880325794, "min": -32.000001668930054, "max": 217.7511980831623, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018733341490838815, "min": 0.017655276548239493, "max": 6.5755441803485155, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1730676129373023, "min": 2.0108764992910437, "max": 105.20870688557625, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723986727", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723994266" }, "total": 7538.6532605130005, "count": 1, "self": 0.9598813390002761, "children": { "run_training.setup": { "total": 0.0822679990000097, "count": 1, "self": 0.0822679990000097 }, "TrainerController.start_learning": { "total": 7537.611111175001, "count": 1, "self": 4.867387490104193, "children": { "TrainerController._reset_env": { "total": 3.5093121740000015, "count": 1, "self": 3.5093121740000015 }, "TrainerController.advance": { "total": 7529.141156891897, "count": 129442, "self": 5.399431629592982, "children": { "env_step": { "total": 5196.9394897083685, "count": 129442, "self": 4844.128210476346, "children": { "SubprocessEnvManager._take_step": { "total": 349.8533874851614, "count": 129442, "self": 15.834233447209499, "children": { "TorchPolicy.evaluate": { "total": 334.0191540379519, "count": 125064, "self": 334.0191540379519 } } }, "workers": { "total": 2.957891746861378, "count": 129442, "self": 0.0, "children": { "worker_root": { "total": 7521.010941535002, "count": 129442, "is_parallel": true, "self": 3072.1814092680534, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007804433999922367, "count": 1, "is_parallel": true, "self": 0.005828322999946067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019761109999762994, "count": 8, "is_parallel": true, "self": 0.0019761109999762994 } } }, "UnityEnvironment.step": { "total": 0.06663410399994518, "count": 1, "is_parallel": true, "self": 0.0008238419999315738, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005397539999876244, "count": 1, "is_parallel": true, "self": 0.0005397539999876244 }, "communicator.exchange": { "total": 0.06306350600004862, "count": 1, "is_parallel": true, "self": 0.06306350600004862 }, "steps_from_proto": { "total": 0.002207001999977365, "count": 1, "is_parallel": true, "self": 0.0004698980000057418, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017371039999716231, "count": 8, "is_parallel": true, "self": 0.0017371039999716231 } } } } } } }, "UnityEnvironment.step": { "total": 4448.829532266948, "count": 129441, "is_parallel": true, "self": 104.50979832441499, "children": { "UnityEnvironment._generate_step_input": { "total": 62.49606410487797, "count": 129441, "is_parallel": true, "self": 62.49606410487797 }, "communicator.exchange": { "total": 4012.304781938779, "count": 129441, "is_parallel": true, "self": 4012.304781938779 }, "steps_from_proto": { "total": 269.51888789887676, "count": 129441, "is_parallel": true, "self": 57.99931565483155, "children": { "_process_rank_one_or_two_observation": { "total": 211.5195722440452, "count": 1035528, "is_parallel": true, "self": 211.5195722440452 } } } } } } } } } } }, "trainer_advance": { "total": 2326.802235553935, "count": 129442, "self": 10.11307931896772, "children": { "process_trajectory": { "total": 360.52672760196174, "count": 129442, "self": 359.9141806099624, "children": { "RLTrainer._checkpoint": { "total": 0.612546991999352, "count": 4, "self": 0.612546991999352 } } }, "_update_policy": { "total": 1956.1624286330054, "count": 919, "self": 785.3781409690191, "children": { "TorchPPOOptimizer.update": { "total": 1170.7842876639863, "count": 45546, "self": 1170.7842876639863 } } } } } } }, "trainer_threads": { "total": 1.1120009730802849e-06, "count": 1, "self": 1.1120009730802849e-06 }, "TrainerController._save_models": { "total": 0.09325350699873525, "count": 1, "self": 0.002231151998785208, "children": { "RLTrainer._checkpoint": { "total": 0.09102235499995004, "count": 1, "self": 0.09102235499995004 } } } } } } }