{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3594419062137604, "min": 0.33874088525772095, "max": 1.3726294040679932, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 10783.2568359375, "min": 10156.806640625, "max": 41640.0859375, "count": 40 }, "Pyramids.Step.mean": { "value": 1199947.0, "min": 29992.0, "max": 1199947.0, "count": 40 }, "Pyramids.Step.sum": { "value": 1199947.0, "min": 29992.0, "max": 1199947.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5975440740585327, "min": -0.10700216144323349, "max": 0.6913617849349976, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.31234741210938, "min": -25.89452362060547, "max": 201.186279296875, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.013946035876870155, "min": -0.013946035876870155, "max": 0.39505305886268616, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.9048900604248047, "min": -3.9048900604248047, "max": 94.02262878417969, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07021311305431358, "min": 0.06322995721919662, "max": 0.07175734211202887, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.98298358276039, "min": 0.5000970599366333, "max": 1.0597568627951357, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015083247922836667, "min": 0.0014075484835231412, "max": 0.01576256994061017, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21116547091971336, "min": 0.019705678769323977, "max": 0.22321363662679988, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.6157952233392853e-06, "min": 3.6157952233392853e-06, "max": 0.00029603057275171424, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.0621133126749996e-05, "min": 5.0621133126749996e-05, "max": 0.0037285031571656665, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10120523214285715, "min": 0.10120523214285715, "max": 0.19867685714285718, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.41687325, "min": 1.3907380000000003, "max": 2.6428343333333335, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.00013040269107142863, "min": 0.00013040269107142863, "max": 0.009867818028571427, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.001825637675000001, "min": 0.001825637675000001, "max": 0.12429914990000002, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007362875621765852, "min": 0.007204833440482616, "max": 0.5033412575721741, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10308025777339935, "min": 0.10308025777339935, "max": 3.5233888626098633, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.87628865979383, "min": 279.05555555555554, "max": 996.125, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31998.0, "min": 16535.0, "max": 32630.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.628868027983867, "min": -0.8719250545836985, "max": 1.7201467778431165, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.0001987144351, "min": -27.901601746678352, "max": 187.4959987848997, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.628868027983867, "min": -0.8719250545836985, "max": 1.7201467778431165, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.0001987144351, "min": -27.901601746678352, "max": 187.4959987848997, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024765063982130478, "min": 0.0227960535256222, "max": 9.795757576823235, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4022112062666565, "min": 2.22968668914109, "max": 166.527878805995, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680966965", "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 --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": "1680969656" }, "total": 2690.9771126729997, "count": 1, "self": 0.5484274509994975, "children": { "run_training.setup": { "total": 0.10547557600011714, "count": 1, "self": 0.10547557600011714 }, "TrainerController.start_learning": { "total": 2690.323209646, "count": 1, "self": 1.610423748858011, "children": { "TrainerController._reset_env": { "total": 3.790402364000329, "count": 1, "self": 3.790402364000329 }, "TrainerController.advance": { "total": 2684.824957030142, "count": 77076, "self": 1.6735931550465466, "children": { "env_step": { "total": 1956.017921579003, "count": 77076, "self": 1831.700044168861, "children": { "SubprocessEnvManager._take_step": { "total": 123.34123079318442, "count": 77076, "self": 5.647243111285661, "children": { "TorchPolicy.evaluate": { "total": 117.69398768189876, "count": 75060, "self": 117.69398768189876 } } }, "workers": { "total": 0.9766466169576233, "count": 77076, "self": 0.0, "children": { "worker_root": { "total": 2684.555830574952, "count": 77076, "is_parallel": true, "self": 983.4090756249407, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001846039000156452, "count": 1, "is_parallel": true, "self": 0.0005939290008427633, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012521099993136886, "count": 8, "is_parallel": true, "self": 0.0012521099993136886 } } }, "UnityEnvironment.step": { "total": 0.04544161699959659, "count": 1, "is_parallel": true, "self": 0.0006914179998602776, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004772449997290096, "count": 1, "is_parallel": true, "self": 0.0004772449997290096 }, "communicator.exchange": { "total": 0.042671491999954014, "count": 1, "is_parallel": true, "self": 0.042671491999954014 }, "steps_from_proto": { "total": 0.0016014620000532886, "count": 1, "is_parallel": true, "self": 0.000362218000645953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012392439994073357, "count": 8, "is_parallel": true, "self": 0.0012392439994073357 } } } } } } }, "UnityEnvironment.step": { "total": 1701.1467549500112, "count": 77075, "is_parallel": true, "self": 38.01556846393942, "children": { "UnityEnvironment._generate_step_input": { "total": 26.990359274065213, "count": 77075, "is_parallel": true, "self": 26.990359274065213 }, "communicator.exchange": { "total": 1525.4954151510647, "count": 77075, "is_parallel": true, "self": 1525.4954151510647 }, "steps_from_proto": { "total": 110.64541206094191, "count": 77075, "is_parallel": true, "self": 23.577852904130395, "children": { "_process_rank_one_or_two_observation": { "total": 87.06755915681151, "count": 616600, "is_parallel": true, "self": 87.06755915681151 } } } } } } } } } } }, "trainer_advance": { "total": 727.1334422960922, "count": 77076, "self": 3.1479520298807984, "children": { "process_trajectory": { "total": 124.60769791622806, "count": 77076, "self": 124.40277884122816, "children": { "RLTrainer._checkpoint": { "total": 0.20491907499990702, "count": 2, "self": 0.20491907499990702 } } }, "_update_policy": { "total": 599.3777923499833, "count": 552, "self": 381.6486400070353, "children": { "TorchPPOOptimizer.update": { "total": 217.72915234294805, "count": 27354, "self": 217.72915234294805 } } } } } } }, "trainer_threads": { "total": 8.170000000973232e-07, "count": 1, "self": 8.170000000973232e-07 }, "TrainerController._save_models": { "total": 0.09742568599995138, "count": 1, "self": 0.0013932100000602077, "children": { "RLTrainer._checkpoint": { "total": 0.09603247599989118, "count": 1, "self": 0.09603247599989118 } } } } } } }