{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3501512110233307, "min": 0.33211055397987366, "max": 1.3325566053390503, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10605.3798828125, "min": 9969.12890625, "max": 40424.4375, "count": 33 }, "Pyramids.Step.mean": { "value": 989905.0, "min": 29952.0, "max": 989905.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989905.0, "min": 29952.0, "max": 989905.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7288305759429932, "min": -0.07709911465644836, "max": 0.740848183631897, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 211.36087036132812, "min": -18.65798568725586, "max": 212.62342834472656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.009867994114756584, "min": -0.011822749860584736, "max": 0.40765824913978577, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.8617184162139893, "min": -2.9911556243896484, "max": 96.61500549316406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0688488850417863, "min": 0.0640230809267248, "max": 0.0739196422928879, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9638843905850081, "min": 0.5004837631919332, "max": 1.0650410116159394, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014359603087844638, "min": 0.0014472519972324755, "max": 0.016265684270322146, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20103444322982494, "min": 0.010130763980627329, "max": 0.22771957978451005, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.637861739792855e-06, "min": 7.637861739792855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010693006435709998, "min": 0.00010693006435709998, "max": 0.003508976330341299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254592142857143, "min": 0.10254592142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356429, "min": 1.3691136000000002, "max": 2.5696587, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002643375507142857, "min": 0.0002643375507142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00370072571, "min": 0.00370072571, "max": 0.11698890412999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008767274208366871, "min": 0.008767274208366871, "max": 0.374515563249588, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12274183332920074, "min": 0.12274183332920074, "max": 2.6216089725494385, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 262.3719008264463, "min": 262.3719008264463, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31747.0, "min": 15984.0, "max": 32267.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6714826380172052, "min": -1.0000000521540642, "max": 1.7351727137511426, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 202.24939920008183, "min": -32.000001668930054, "max": 202.24939920008183, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6714826380172052, "min": -1.0000000521540642, "max": 1.7351727137511426, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 202.24939920008183, "min": -32.000001668930054, "max": 202.24939920008183, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.023441952148843016, "min": 0.023441952148843016, "max": 8.2253372464329, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.836476210010005, "min": 2.6988735643972177, "max": 131.6053959429264, "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": "1784541843", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "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": "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": "1784544595" }, "total": 2752.782595838, "count": 1, "self": 0.528103414000725, "children": { "run_training.setup": { "total": 0.027646086999993713, "count": 1, "self": 0.027646086999993713 }, "TrainerController.start_learning": { "total": 2752.226846336999, "count": 1, "self": 1.713667019859713, "children": { "TrainerController._reset_env": { "total": 2.247410148999734, "count": 1, "self": 2.247410148999734 }, "TrainerController.advance": { "total": 2748.1689283751402, "count": 64315, "self": 1.781306609918829, "children": { "env_step": { "total": 2062.6223466560677, "count": 64315, "self": 1886.6379189983309, "children": { "SubprocessEnvManager._take_step": { "total": 174.92111731172918, "count": 64315, "self": 5.3885907008452705, "children": { "TorchPolicy.evaluate": { "total": 169.5325266108839, "count": 62549, "self": 169.5325266108839 } } }, "workers": { "total": 1.063310346007711, "count": 64315, "self": 0.0, "children": { "worker_root": { "total": 2745.9107308560942, "count": 64315, "is_parallel": true, "self": 998.7776048480855, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017775019996406627, "count": 1, "is_parallel": true, "self": 0.0005761600004916545, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012013419991490082, "count": 8, "is_parallel": true, "self": 0.0012013419991490082 } } }, "UnityEnvironment.step": { "total": 0.053902637999271974, "count": 1, "is_parallel": true, "self": 0.0005990769996060408, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00057317799928569, "count": 1, "is_parallel": true, "self": 0.00057317799928569 }, "communicator.exchange": { "total": 0.05094423700029438, "count": 1, "is_parallel": true, "self": 0.05094423700029438 }, "steps_from_proto": { "total": 0.0017861460000858642, "count": 1, "is_parallel": true, "self": 0.00035048700283368817, "children": { "_process_rank_one_or_two_observation": { "total": 0.001435658997252176, "count": 8, "is_parallel": true, "self": 0.001435658997252176 } } } } } } }, "UnityEnvironment.step": { "total": 1747.1331260080087, "count": 64314, "is_parallel": true, "self": 36.65351603009822, "children": { "UnityEnvironment._generate_step_input": { "total": 26.03310885281644, "count": 64314, "is_parallel": true, "self": 26.03310885281644 }, "communicator.exchange": { "total": 1560.3493709020531, "count": 64314, "is_parallel": true, "self": 1560.3493709020531 }, "steps_from_proto": { "total": 124.09713022304095, "count": 64314, "is_parallel": true, "self": 25.686523472593763, "children": { "_process_rank_one_or_two_observation": { "total": 98.41060675044719, "count": 514512, "is_parallel": true, "self": 98.41060675044719 } } } } } } } } } } }, "trainer_advance": { "total": 683.7652751091537, "count": 64315, "self": 3.3280532641347236, "children": { "process_trajectory": { "total": 125.5387294600232, "count": 64315, "self": 125.33758603602382, "children": { "RLTrainer._checkpoint": { "total": 0.20114342399938323, "count": 2, "self": 0.20114342399938323 } } }, "_update_policy": { "total": 554.8984923849957, "count": 451, "self": 298.74812579199715, "children": { "TorchPPOOptimizer.update": { "total": 256.1503665929986, "count": 22824, "self": 256.1503665929986 } } } } } } }, "trainer_threads": { "total": 1.077999513654504e-06, "count": 1, "self": 1.077999513654504e-06 }, "TrainerController._save_models": { "total": 0.09683971499998734, "count": 1, "self": 0.0010708330000852584, "children": { "RLTrainer._checkpoint": { "total": 0.09576888199990208, "count": 1, "self": 0.09576888199990208 } } } } } } }