{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3890136182308197, "min": 0.3890136182308197, "max": 1.4071271419525146, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11695.3056640625, "min": 11639.923828125, "max": 42686.609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29901.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29901.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2987157702445984, "min": -0.10624446719884872, "max": 0.3766666650772095, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 76.47123718261719, "min": -25.498672485351562, "max": 98.30999755859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0033714158926159143, "min": 0.0033714158926159143, "max": 0.4524180591106415, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8630824685096741, "min": 0.8630824685096741, "max": 107.22308349609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06829631699534316, "min": 0.0645063537910542, "max": 0.07602324458186796, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9561484379348043, "min": 0.4949141378710502, "max": 1.0321170688403072, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014736550217193547, "min": 7.531473607696014e-05, "max": 0.014736550217193547, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20631170304070967, "min": 0.0009790915690004818, "max": 0.20631170304070967, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.470311795642855e-06, "min": 7.470311795642855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010458436513899997, "min": 0.00010458436513899997, "max": 0.0033774895741702, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249007142857144, "min": 0.10249007142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348610000000002, "min": 1.3886848, "max": 2.4425820000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002587581357142856, "min": 0.0002587581357142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003622613899999999, "min": 0.003622613899999999, "max": 0.11260039701999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01530809048563242, "min": 0.014819317497313023, "max": 0.4765942692756653, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21431326866149902, "min": 0.20747044682502747, "max": 3.3361599445343018, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 500.0877192982456, "min": 465.85483870967744, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28505.0, "min": 16828.0, "max": 32599.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3244140120713335, "min": -0.9999125525355339, "max": 1.3244140120713335, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 75.491598688066, "min": -31.997201681137085, "max": 82.13279824703932, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3244140120713335, "min": -0.9999125525355339, "max": 1.3244140120713335, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 75.491598688066, "min": -31.997201681137085, "max": 82.13279824703932, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07908703552011662, "min": 0.07474298660893128, "max": 8.856880375567604, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.507961024646647, "min": 4.507961024646647, "max": 150.56696638464928, "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": "1770734744", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1770736839" }, "total": 2094.478757146, "count": 1, "self": 0.4785080320002635, "children": { "run_training.setup": { "total": 0.025947431000076904, "count": 1, "self": 0.025947431000076904 }, "TrainerController.start_learning": { "total": 2093.974301683, "count": 1, "self": 1.290506265964268, "children": { "TrainerController._reset_env": { "total": 2.1000044890001845, "count": 1, "self": 2.1000044890001845 }, "TrainerController.advance": { "total": 2090.5124970870356, "count": 63509, "self": 1.3935437221966822, "children": { "env_step": { "total": 1444.6578248568208, "count": 63509, "self": 1300.191956177784, "children": { "SubprocessEnvManager._take_step": { "total": 143.69402183003422, "count": 63509, "self": 4.384852848918399, "children": { "TorchPolicy.evaluate": { "total": 139.30916898111582, "count": 62553, "self": 139.30916898111582 } } }, "workers": { "total": 0.7718468490024861, "count": 63509, "self": 0.0, "children": { "worker_root": { "total": 2087.3452386119034, "count": 63509, "is_parallel": true, "self": 898.8763370918255, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016799299996819173, "count": 1, "is_parallel": true, "self": 0.0005313179995027895, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011486120001791278, "count": 8, "is_parallel": true, "self": 0.0011486120001791278 } } }, "UnityEnvironment.step": { "total": 0.046814751000056276, "count": 1, "is_parallel": true, "self": 0.0005446170002869621, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004593419998855097, "count": 1, "is_parallel": true, "self": 0.0004593419998855097 }, "communicator.exchange": { "total": 0.04427313599990157, "count": 1, "is_parallel": true, "self": 0.04427313599990157 }, "steps_from_proto": { "total": 0.0015376559999822348, "count": 1, "is_parallel": true, "self": 0.0003198140002496075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012178419997326273, "count": 8, "is_parallel": true, "self": 0.0012178419997326273 } } } } } } }, "UnityEnvironment.step": { "total": 1188.468901520078, "count": 63508, "is_parallel": true, "self": 32.93335502607761, "children": { "UnityEnvironment._generate_step_input": { "total": 22.015530233063146, "count": 63508, "is_parallel": true, "self": 22.015530233063146 }, "communicator.exchange": { "total": 1032.2813636419546, "count": 63508, "is_parallel": true, "self": 1032.2813636419546 }, "steps_from_proto": { "total": 101.23865261898254, "count": 63508, "is_parallel": true, "self": 21.205508582850143, "children": { "_process_rank_one_or_two_observation": { "total": 80.0331440361324, "count": 508064, "is_parallel": true, "self": 80.0331440361324 } } } } } } } } } } }, "trainer_advance": { "total": 644.4611285080182, "count": 63509, "self": 2.477593067017551, "children": { "process_trajectory": { "total": 118.75116145199672, "count": 63509, "self": 118.57635009299656, "children": { "RLTrainer._checkpoint": { "total": 0.17481135900015943, "count": 2, "self": 0.17481135900015943 } } }, "_update_policy": { "total": 523.2323739890039, "count": 450, "self": 290.26228200495507, "children": { "TorchPPOOptimizer.update": { "total": 232.97009198404885, "count": 22812, "self": 232.97009198404885 } } } } } } }, "trainer_threads": { "total": 9.729992598295212e-07, "count": 1, "self": 9.729992598295212e-07 }, "TrainerController._save_models": { "total": 0.0712928680004552, "count": 1, "self": 0.0010830400005943375, "children": { "RLTrainer._checkpoint": { "total": 0.07020982799986086, "count": 1, "self": 0.07020982799986086 } } } } } } }