{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3564576506614685, "min": 0.3564576506614685, "max": 1.440848469734192, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10779.279296875, "min": 10779.279296875, "max": 43709.578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4499568045139313, "min": -0.09666720032691956, "max": 0.47483864426612854, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 119.68850708007812, "min": -23.296794891357422, "max": 128.20643615722656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0189314316958189, "min": -0.00422308873385191, "max": 0.5015295743942261, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.035760879516602, "min": -1.1106723546981812, "max": 118.86250305175781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07170333168150614, "min": 0.06358742459102583, "max": 0.07327212807704915, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.003846643541086, "min": 0.5120189807574458, "max": 1.0800974962105245, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01532350843869305, "min": 0.000552946827005047, "max": 0.015907930755929556, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2145291181417027, "min": 0.007741255578070658, "max": 0.22271103058301378, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.463090369478569e-06, "min": 7.463090369478569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010448326517269997, "min": 0.00010448326517269997, "max": 0.0033787142737619993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248766428571429, "min": 0.10248766428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348273, "min": 1.3886848, "max": 2.526238, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025851766214285714, "min": 0.00025851766214285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036192472699999997, "min": 0.0036192472699999997, "max": 0.11265117620000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012644223868846893, "min": 0.012644223868846893, "max": 0.46277302503585815, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1770191341638565, "min": 0.1770191341638565, "max": 3.2394111156463623, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 398.4054054054054, "min": 391.49397590361446, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29482.0, "min": 15984.0, "max": 32892.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5204864566189211, "min": -1.0000000521540642, "max": 1.5251893065373103, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.51599778980017, "min": -30.73160170763731, "max": 117.50059761852026, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5204864566189211, "min": -1.0000000521540642, "max": 1.5251893065373103, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.51599778980017, "min": -30.73160170763731, "max": 117.50059761852026, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05213545481878887, "min": 0.05213545481878887, "max": 9.72693215124309, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.858023656590376, "min": 3.858023656590376, "max": 155.63091441988945, "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": "1755541383", "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=PyramidsRND1 --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": "1755543544" }, "total": 2161.4613641390006, "count": 1, "self": 0.5808187480015476, "children": { "run_training.setup": { "total": 0.02325739999923826, "count": 1, "self": 0.02325739999923826 }, "TrainerController.start_learning": { "total": 2160.857287991, "count": 1, "self": 1.374255212069329, "children": { "TrainerController._reset_env": { "total": 2.1630429030001324, "count": 1, "self": 2.1630429030001324 }, "TrainerController.advance": { "total": 2157.2395248699313, "count": 63564, "self": 1.3814006308848548, "children": { "env_step": { "total": 1508.295798496979, "count": 63564, "self": 1361.268020594951, "children": { "SubprocessEnvManager._take_step": { "total": 146.22265467000125, "count": 63564, "self": 4.641185821945328, "children": { "TorchPolicy.evaluate": { "total": 141.58146884805592, "count": 62561, "self": 141.58146884805592 } } }, "workers": { "total": 0.8051232320267445, "count": 63564, "self": 0.0, "children": { "worker_root": { "total": 2156.0259611997926, "count": 63564, "is_parallel": true, "self": 908.228539197783, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001963751999937813, "count": 1, "is_parallel": true, "self": 0.0006675029999314575, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012962490000063553, "count": 8, "is_parallel": true, "self": 0.0012962490000063553 } } }, "UnityEnvironment.step": { "total": 0.05551939599990874, "count": 1, "is_parallel": true, "self": 0.0006210649999047746, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005499519993463764, "count": 1, "is_parallel": true, "self": 0.0005499519993463764 }, "communicator.exchange": { "total": 0.052521644000080414, "count": 1, "is_parallel": true, "self": 0.052521644000080414 }, "steps_from_proto": { "total": 0.0018267350005771732, "count": 1, "is_parallel": true, "self": 0.0003916510004273732, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014350840001498, "count": 8, "is_parallel": true, "self": 0.0014350840001498 } } } } } } }, "UnityEnvironment.step": { "total": 1247.7974220020096, "count": 63563, "is_parallel": true, "self": 31.62266179505241, "children": { "UnityEnvironment._generate_step_input": { "total": 22.90894604096229, "count": 63563, "is_parallel": true, "self": 22.90894604096229 }, "communicator.exchange": { "total": 1096.029977111013, "count": 63563, "is_parallel": true, "self": 1096.029977111013 }, "steps_from_proto": { "total": 97.23583705498186, "count": 63563, "is_parallel": true, "self": 19.334190000824492, "children": { "_process_rank_one_or_two_observation": { "total": 77.90164705415737, "count": 508504, "is_parallel": true, "self": 77.90164705415737 } } } } } } } } } } }, "trainer_advance": { "total": 647.5623257420675, "count": 63564, "self": 2.592371016069592, "children": { "process_trajectory": { "total": 125.30924137600232, "count": 63564, "self": 125.10892226800206, "children": { "RLTrainer._checkpoint": { "total": 0.20031910800025798, "count": 2, "self": 0.20031910800025798 } } }, "_update_policy": { "total": 519.6607133499956, "count": 447, "self": 290.2281273630633, "children": { "TorchPPOOptimizer.update": { "total": 229.43258598693228, "count": 22806, "self": 229.43258598693228 } } } } } } }, "trainer_threads": { "total": 1.0289995771017857e-06, "count": 1, "self": 1.0289995771017857e-06 }, "TrainerController._save_models": { "total": 0.08046397699945373, "count": 1, "self": 0.0013480809993779985, "children": { "RLTrainer._checkpoint": { "total": 0.07911589600007574, "count": 1, "self": 0.07911589600007574 } } } } } } }