{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48379194736480713, "min": 0.48379194736480713, "max": 1.4188684225082397, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14436.3515625, "min": 14436.3515625, "max": 43042.79296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989885.0, "min": 29952.0, "max": 989885.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989885.0, "min": 29952.0, "max": 989885.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2871297299861908, "min": -0.1082937940955162, "max": 0.2871297299861908, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 73.79234313964844, "min": -26.098804473876953, "max": 74.86961364746094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012709363363683224, "min": -0.015038547106087208, "max": 0.305647075176239, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2663064002990723, "min": -3.819791078567505, "max": 73.35530090332031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0704256998031356, "min": 0.0650896433937244, "max": 0.07321692797761468, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9859597972438983, "min": 0.507143614908022, "max": 1.0747438535521117, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015386342804482585, "min": 0.00015941712284968967, "max": 0.016267696638923464, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2154087992627562, "min": 0.001913005474196276, "max": 0.2154087992627562, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.46328322655714e-06, "min": 7.46328322655714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010448596517179996, "min": 0.00010448596517179996, "max": 0.0034929307356897994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248772857142859, "min": 0.10248772857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348282, "min": 1.3691136000000002, "max": 2.5275118, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002585240842857142, "min": 0.0002585240842857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003619337179999999, "min": 0.003619337179999999, "max": 0.11644458897999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01102800015360117, "min": 0.01102800015360117, "max": 0.5263792276382446, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15439200401306152, "min": 0.15439200401306152, "max": 3.684654474258423, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 525.1090909090909, "min": 525.1090909090909, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28881.0, "min": 15984.0, "max": 32526.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1838945181532339, "min": -1.0000000521540642, "max": 1.1838945181532339, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 65.11419849842787, "min": -32.000001668930054, "max": 65.7153983861208, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1838945181532339, "min": -1.0000000521540642, "max": 1.1838945181532339, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 65.11419849842787, "min": -32.000001668930054, "max": 65.7153983861208, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0596144320062277, "min": 0.0596144320062277, "max": 10.240615317597985, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2787937603425235, "min": 3.1664377196575515, "max": 163.84984508156776, "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": "1744707272", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744709416" }, "total": 2144.453138808, "count": 1, "self": 0.4761590659995818, "children": { "run_training.setup": { "total": 0.02058423399989806, "count": 1, "self": 0.02058423399989806 }, "TrainerController.start_learning": { "total": 2143.9563955080002, "count": 1, "self": 1.4712903360054952, "children": { "TrainerController._reset_env": { "total": 2.103301040000133, "count": 1, "self": 2.103301040000133 }, "TrainerController.advance": { "total": 2140.295352301994, "count": 63360, "self": 1.5650157579984807, "children": { "env_step": { "total": 1455.1577125119986, "count": 63360, "self": 1295.0736453200282, "children": { "SubprocessEnvManager._take_step": { "total": 159.2363002579998, "count": 63360, "self": 4.795404632996224, "children": { "TorchPolicy.evaluate": { "total": 154.44089562500358, "count": 62561, "self": 154.44089562500358 } } }, "workers": { "total": 0.8477669339706608, "count": 63360, "self": 0.0, "children": { "worker_root": { "total": 2139.1640401640398, "count": 63360, "is_parallel": true, "self": 957.8612570309672, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020115160000386823, "count": 1, "is_parallel": true, "self": 0.0006671319997622049, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013443840002764773, "count": 8, "is_parallel": true, "self": 0.0013443840002764773 } } }, "UnityEnvironment.step": { "total": 0.04637463199992453, "count": 1, "is_parallel": true, "self": 0.0005450900000596448, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004684909999923548, "count": 1, "is_parallel": true, "self": 0.0004684909999923548 }, "communicator.exchange": { "total": 0.04379681799991886, "count": 1, "is_parallel": true, "self": 0.04379681799991886 }, "steps_from_proto": { "total": 0.0015642329999536742, "count": 1, "is_parallel": true, "self": 0.0003316960001029656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012325369998507085, "count": 8, "is_parallel": true, "self": 0.0012325369998507085 } } } } } } }, "UnityEnvironment.step": { "total": 1181.3027831330726, "count": 63359, "is_parallel": true, "self": 31.905697707952868, "children": { "UnityEnvironment._generate_step_input": { "total": 23.023310856005537, "count": 63359, "is_parallel": true, "self": 23.023310856005537 }, "communicator.exchange": { "total": 1029.1221493700637, "count": 63359, "is_parallel": true, "self": 1029.1221493700637 }, "steps_from_proto": { "total": 97.25162519905052, "count": 63359, "is_parallel": true, "self": 19.951814660913442, "children": { "_process_rank_one_or_two_observation": { "total": 77.29981053813708, "count": 506872, "is_parallel": true, "self": 77.29981053813708 } } } } } } } } } } }, "trainer_advance": { "total": 683.5726240319973, "count": 63360, "self": 2.744036913961054, "children": { "process_trajectory": { "total": 128.95145754004307, "count": 63360, "self": 128.7410575250433, "children": { "RLTrainer._checkpoint": { "total": 0.21040001499977734, "count": 2, "self": 0.21040001499977734 } } }, "_update_policy": { "total": 551.8771295779932, "count": 445, "self": 302.57382373997984, "children": { "TorchPPOOptimizer.update": { "total": 249.30330583801333, "count": 22824, "self": 249.30330583801333 } } } } } } }, "trainer_threads": { "total": 8.090000847005285e-07, "count": 1, "self": 8.090000847005285e-07 }, "TrainerController._save_models": { "total": 0.08645102100035729, "count": 1, "self": 0.001533769000616303, "children": { "RLTrainer._checkpoint": { "total": 0.08491725199974098, "count": 1, "self": 0.08491725199974098 } } } } } } }