{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5028831362724304, "min": 0.4934605360031128, "max": 1.4368268251419067, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15014.078125, "min": 14693.28125, "max": 43587.578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5835267901420593, "min": -0.1807340532541275, "max": 0.6015130877494812, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.55455017089844, "min": -42.83396911621094, "max": 165.4160919189453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.027452293783426285, "min": -0.027452293783426285, "max": 0.33393594622612, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.741547107696533, "min": -7.741547107696533, "max": 79.142822265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06803573890741137, "min": 0.06363366088512395, "max": 0.0737662756883543, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9525003447037592, "min": 0.506086928184357, "max": 1.0327278596369602, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015568697703359854, "min": 0.00010064681685805673, "max": 0.016595749503938436, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21796176784703797, "min": 0.0013084086191547375, "max": 0.2323404930551381, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.40264038962857e-06, "min": 7.40264038962857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010363696545479999, "min": 0.00010363696545479999, "max": 0.0035071004309666, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246751428571431, "min": 0.10246751428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345452000000003, "min": 1.3691136000000002, "max": 2.569033400000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025650467714285715, "min": 0.00025650467714285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00359106548, "min": 0.00359106548, "max": 0.11692643666000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009652777574956417, "min": 0.009652777574956417, "max": 0.4172501266002655, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1351388841867447, "min": 0.1351388841867447, "max": 2.920750856399536, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 333.01063829787233, "min": 310.03225806451616, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31303.0, "min": 15984.0, "max": 32440.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.624066651989055, "min": -1.0000000521540642, "max": 1.6370543264176534, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 151.0381986349821, "min": -32.000001668930054, "max": 151.0381986349821, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.624066651989055, "min": -1.0000000521540642, "max": 1.6370543264176534, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 151.0381986349821, "min": -32.000001668930054, "max": 151.0381986349821, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03392111031921901, "min": 0.03242105406819172, "max": 8.880287981592119, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.154663259687368, "min": 3.0151580283418298, "max": 142.0846077054739, "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": "1715168772", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715170401" }, "total": 1629.72557081, "count": 1, "self": 0.32248322599957646, "children": { "run_training.setup": { "total": 0.052455744000099, "count": 1, "self": 0.052455744000099 }, "TrainerController.start_learning": { "total": 1629.3506318400002, "count": 1, "self": 1.3465455260197814, "children": { "TrainerController._reset_env": { "total": 2.036261887000137, "count": 1, "self": 2.036261887000137 }, "TrainerController.advance": { "total": 1625.8862360679805, "count": 63737, "self": 1.2771937789618732, "children": { "env_step": { "total": 1060.855880641004, "count": 63737, "self": 940.6056499590359, "children": { "SubprocessEnvManager._take_step": { "total": 119.43753719197548, "count": 63737, "self": 4.302538014959055, "children": { "TorchPolicy.evaluate": { "total": 115.13499917701643, "count": 62560, "self": 115.13499917701643 } } }, "workers": { "total": 0.8126934899926255, "count": 63737, "self": 0.0, "children": { "worker_root": { "total": 1627.2214600270554, "count": 63737, "is_parallel": true, "self": 784.5912084411284, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021605249999083753, "count": 1, "is_parallel": true, "self": 0.0006672379997780808, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014932870001302945, "count": 8, "is_parallel": true, "self": 0.0014932870001302945 } } }, "UnityEnvironment.step": { "total": 0.03509324799983915, "count": 1, "is_parallel": true, "self": 0.0004235129999869969, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029668100000890263, "count": 1, "is_parallel": true, "self": 0.00029668100000890263 }, "communicator.exchange": { "total": 0.03326184100001228, "count": 1, "is_parallel": true, "self": 0.03326184100001228 }, "steps_from_proto": { "total": 0.0011112129998309683, "count": 1, "is_parallel": true, "self": 0.0002450449994739756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008661680003569927, "count": 8, "is_parallel": true, "self": 0.0008661680003569927 } } } } } } }, "UnityEnvironment.step": { "total": 842.630251585927, "count": 63736, "is_parallel": true, "self": 21.563971725002148, "children": { "UnityEnvironment._generate_step_input": { "total": 13.94617676195935, "count": 63736, "is_parallel": true, "self": 13.94617676195935 }, "communicator.exchange": { "total": 745.3669176319861, "count": 63736, "is_parallel": true, "self": 745.3669176319861 }, "steps_from_proto": { "total": 61.7531854669794, "count": 63736, "is_parallel": true, "self": 13.419754748951163, "children": { "_process_rank_one_or_two_observation": { "total": 48.33343071802824, "count": 509888, "is_parallel": true, "self": 48.33343071802824 } } } } } } } } } } }, "trainer_advance": { "total": 563.7531616480146, "count": 63737, "self": 2.4172667940306383, "children": { "process_trajectory": { "total": 114.50943362598332, "count": 63737, "self": 114.3222039859836, "children": { "RLTrainer._checkpoint": { "total": 0.18722963999971398, "count": 2, "self": 0.18722963999971398 } } }, "_update_policy": { "total": 446.82646122800065, "count": 442, "self": 259.99159265501135, "children": { "TorchPPOOptimizer.update": { "total": 186.8348685729893, "count": 22803, "self": 186.8348685729893 } } } } } } }, "trainer_threads": { "total": 1.0250000741507392e-06, "count": 1, "self": 1.0250000741507392e-06 }, "TrainerController._save_models": { "total": 0.08158733399977791, "count": 1, "self": 0.0013520319998860941, "children": { "RLTrainer._checkpoint": { "total": 0.08023530199989182, "count": 1, "self": 0.08023530199989182 } } } } } } }