{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48702165484428406, "min": 0.44668611884117126, "max": 1.5974081754684448, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 7293.63623046875, "min": 6742.52392578125, "max": 25558.53125, "count": 100 }, "Pyramids.Step.mean": { "value": 1499927.0, "min": 14960.0, "max": 1499927.0, "count": 100 }, "Pyramids.Step.sum": { "value": 1499927.0, "min": 14960.0, "max": 1499927.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1931789666414261, "min": -0.08827703446149826, "max": 0.54588782787323, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 24.147371292114258, "min": -10.593244552612305, "max": 71.51130676269531, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.10692010819911957, "min": -2.319406270980835, "max": 0.5430359244346619, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.365013122558594, "min": -313.1198425292969, "max": 72.2237777709961, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.021887752918216086, "min": 0.016317666446169218, "max": 0.03001637246925384, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.06566325875464826, "min": 0.04895299933850765, "max": 0.1022449663025327, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.028128571606551606, "min": 0.0004217532914481126, "max": 0.5521492043510079, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.08438571481965482, "min": 0.0012652598743443377, "max": 2.2085968174040316, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.1040105591555517e-06, "min": 1.1040105591555517e-06, "max": 0.00019877120061440002, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.3120316774666553e-06, "min": 3.3120316774666553e-06, "max": 0.0007798576100711998, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10055195555555556, "min": 0.10055195555555556, "max": 0.1993856, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.30165586666666666, "min": 0.30165586666666666, "max": 0.7899288, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.514035999999981e-05, "min": 6.514035999999981e-05, "max": 0.00993862144, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00019542107999999945, "min": 0.00019542107999999945, "max": 0.03899388712000001, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01588110625743866, "min": 0.015369528904557228, "max": 0.8264577984809875, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.04764331877231598, "min": 0.04751599207520485, "max": 1.652915596961975, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 605.9090909090909, "min": 358.6363636363636, "max": 999.0, "count": 99 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 13330.0, "min": 7480.0, "max": 18408.0, "count": 99 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0303272245959803, "min": -1.0000000521540642, "max": 1.6413636089048602, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 22.667198941111565, "min": -15.999400839209557, "max": 72.21999879181385, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0303272245959803, "min": -1.0000000521540642, "max": 1.6413636089048602, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 22.667198941111565, "min": -15.999400839209557, "max": 72.21999879181385, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09671802150974558, "min": 0.07045210495099044, "max": 11.204274728894234, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.127796473214403, "min": 2.127796473214403, "max": 104.2868239581585, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679323052", "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 3 --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": "1679326214" }, "total": 3162.679552165, "count": 1, "self": 0.44162624799992045, "children": { "run_training.setup": { "total": 0.10628935299996556, "count": 1, "self": 0.10628935299996556 }, "TrainerController.start_learning": { "total": 3162.131636564, "count": 1, "self": 2.04367966191694, "children": { "TrainerController._reset_env": { "total": 10.231304194000018, "count": 1, "self": 10.231304194000018 }, "TrainerController.advance": { "total": 3149.743723493083, "count": 95475, "self": 2.1986011099693314, "children": { "env_step": { "total": 2213.671983656081, "count": 95475, "self": 2052.434392665081, "children": { "SubprocessEnvManager._take_step": { "total": 160.00268999499417, "count": 95475, "self": 6.980408748963498, "children": { "TorchPolicy.evaluate": { "total": 153.02228124603067, "count": 93823, "self": 153.02228124603067 } } }, "workers": { "total": 1.2349009960059334, "count": 95475, "self": 0.0, "children": { "worker_root": { "total": 3155.096824597045, "count": 95475, "is_parallel": true, "self": 1275.8812516060202, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00515687000000753, "count": 1, "is_parallel": true, "self": 0.0036788550000323994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014780149999751302, "count": 8, "is_parallel": true, "self": 0.0014780149999751302 } } }, "UnityEnvironment.step": { "total": 0.0757186139999817, "count": 1, "is_parallel": true, "self": 0.0005660490000423124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046223299995062916, "count": 1, "is_parallel": true, "self": 0.00046223299995062916 }, "communicator.exchange": { "total": 0.07301252199999908, "count": 1, "is_parallel": true, "self": 0.07301252199999908 }, "steps_from_proto": { "total": 0.0016778099999896767, "count": 1, "is_parallel": true, "self": 0.0004385029999980361, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012393069999916406, "count": 8, "is_parallel": true, "self": 0.0012393069999916406 } } } } } } }, "UnityEnvironment.step": { "total": 1879.2155729910246, "count": 95474, "is_parallel": true, "self": 46.984084795974695, "children": { "UnityEnvironment._generate_step_input": { "total": 33.91037586009372, "count": 95474, "is_parallel": true, "self": 33.91037586009372 }, "communicator.exchange": { "total": 1661.6547364499272, "count": 95474, "is_parallel": true, "self": 1661.6547364499272 }, "steps_from_proto": { "total": 136.6663758850288, "count": 95474, "is_parallel": true, "self": 28.916061298933585, "children": { "_process_rank_one_or_two_observation": { "total": 107.75031458609521, "count": 763792, "is_parallel": true, "self": 107.75031458609521 } } } } } } } } } } }, "trainer_advance": { "total": 933.8731387270326, "count": 95475, "self": 3.929698067035474, "children": { "process_trajectory": { "total": 177.41394104199668, "count": 95475, "self": 177.12017251699655, "children": { "RLTrainer._checkpoint": { "total": 0.2937685250001323, "count": 3, "self": 0.2937685250001323 } } }, "_update_policy": { "total": 752.5294996180004, "count": 353, "self": 648.6307422760165, "children": { "TorchPPOOptimizer.update": { "total": 103.89875734198398, "count": 7150, "self": 103.89875734198398 } } } } } } }, "trainer_threads": { "total": 8.530000741302501e-07, "count": 1, "self": 8.530000741302501e-07 }, "TrainerController._save_models": { "total": 0.11292836199982048, "count": 1, "self": 0.0014282719998846005, "children": { "RLTrainer._checkpoint": { "total": 0.11150008999993588, "count": 1, "self": 0.11150008999993588 } } } } } } }