{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.54569011926651, "min": 0.54569011926651, "max": 1.4677014350891113, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16353.2421875, "min": 16353.2421875, "max": 44524.19140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.30905386805534363, "min": -0.11819847673177719, "max": 0.30905386805534363, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 80.35400390625, "min": -28.60403060913086, "max": 80.35400390625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022272000089287758, "min": -0.0004950736765749753, "max": 0.7359009981155396, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.790719985961914, "min": -0.1227782666683197, "max": 174.40853881835938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06738187403936449, "min": 0.06418437235579115, "max": 0.0714533347892852, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9433462365511028, "min": 0.49151292870466157, "max": 1.0418246051704045, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013686286387729481, "min": 0.0010828965312131243, "max": 0.021374494999147193, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19160800942821274, "min": 0.007580275718491871, "max": 0.19160800942821274, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5860474713499955e-06, "min": 7.5860474713499955e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010620466459889994, "min": 0.00010620466459889994, "max": 0.0032557223147592993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252865, "min": 0.10252865, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354011, "min": 1.3691136000000002, "max": 2.4424456, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026261213499999985, "min": 0.00026261213499999985, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003676569889999998, "min": 0.003676569889999998, "max": 0.10854554592999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012461402453482151, "min": 0.012461402453482151, "max": 0.6971423029899597, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17445963621139526, "min": 0.17445963621139526, "max": 4.879996299743652, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 493.17543859649123, "min": 493.17543859649123, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28111.0, "min": 15984.0, "max": 33449.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3664420788225375, "min": -1.0000000521540642, "max": 1.3664420788225375, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.88719849288464, "min": -32.000001668930054, "max": 77.88719849288464, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3664420788225375, "min": -1.0000000521540642, "max": 1.3664420788225375, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.88719849288464, "min": -32.000001668930054, "max": 77.88719849288464, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06483707643060929, "min": 0.06483707643060929, "max": 15.14714740589261, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6957133565447293, "min": 3.6633975076838396, "max": 242.35435849428177, "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": "1690034203", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690036210" }, "total": 2007.032826513, "count": 1, "self": 0.485358240999858, "children": { "run_training.setup": { "total": 0.03127404099996056, "count": 1, "self": 0.03127404099996056 }, "TrainerController.start_learning": { "total": 2006.516194231, "count": 1, "self": 1.2611863719680514, "children": { "TrainerController._reset_env": { "total": 4.547346955999956, "count": 1, "self": 4.547346955999956 }, "TrainerController.advance": { "total": 2000.615627070032, "count": 63462, "self": 1.3964754310218268, "children": { "env_step": { "total": 1345.9879816999614, "count": 63462, "self": 1240.8439532149707, "children": { "SubprocessEnvManager._take_step": { "total": 104.38107196798319, "count": 63462, "self": 4.627059711888478, "children": { "TorchPolicy.evaluate": { "total": 99.75401225609471, "count": 62571, "self": 99.75401225609471 } } }, "workers": { "total": 0.7629565170075239, "count": 63462, "self": 0.0, "children": { "worker_root": { "total": 2001.968245582053, "count": 63462, "is_parallel": true, "self": 870.4043684270321, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017539879997912067, "count": 1, "is_parallel": true, "self": 0.0005607499997495324, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011932380000416742, "count": 8, "is_parallel": true, "self": 0.0011932380000416742 } } }, "UnityEnvironment.step": { "total": 0.0943829480002023, "count": 1, "is_parallel": true, "self": 0.0006082920003791514, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004757959998187289, "count": 1, "is_parallel": true, "self": 0.0004757959998187289 }, "communicator.exchange": { "total": 0.09148030599999402, "count": 1, "is_parallel": true, "self": 0.09148030599999402 }, "steps_from_proto": { "total": 0.0018185540000104083, "count": 1, "is_parallel": true, "self": 0.0003687610003453301, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014497929996650782, "count": 8, "is_parallel": true, "self": 0.0014497929996650782 } } } } } } }, "UnityEnvironment.step": { "total": 1131.563877155021, "count": 63461, "is_parallel": true, "self": 33.494838061964856, "children": { "UnityEnvironment._generate_step_input": { "total": 22.751428917031035, "count": 63461, "is_parallel": true, "self": 22.751428917031035 }, "communicator.exchange": { "total": 975.9871041640954, "count": 63461, "is_parallel": true, "self": 975.9871041640954 }, "steps_from_proto": { "total": 99.33050601192963, "count": 63461, "is_parallel": true, "self": 19.671052900925588, "children": { "_process_rank_one_or_two_observation": { "total": 79.65945311100404, "count": 507688, "is_parallel": true, "self": 79.65945311100404 } } } } } } } } } } }, "trainer_advance": { "total": 653.2311699390486, "count": 63462, "self": 2.3150029390328655, "children": { "process_trajectory": { "total": 107.85933384301029, "count": 63462, "self": 107.65642400500997, "children": { "RLTrainer._checkpoint": { "total": 0.20290983800032336, "count": 2, "self": 0.20290983800032336 } } }, "_update_policy": { "total": 543.0568331570055, "count": 443, "self": 355.03996223196714, "children": { "TorchPPOOptimizer.update": { "total": 188.01687092503835, "count": 22821, "self": 188.01687092503835 } } } } } } }, "trainer_threads": { "total": 1.0429998837935273e-06, "count": 1, "self": 1.0429998837935273e-06 }, "TrainerController._save_models": { "total": 0.09203279000030307, "count": 1, "self": 0.0013262900001791422, "children": { "RLTrainer._checkpoint": { "total": 0.09070650000012392, "count": 1, "self": 0.09070650000012392 } } } } } } }