{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12750717997550964, "min": 0.11631365120410919, "max": 1.4257774353027344, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3831.3359375, "min": 3483.826416015625, "max": 43252.3828125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999937.0, "min": 29952.0, "max": 2999937.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999937.0, "min": 29952.0, "max": 2999937.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8287276029586792, "min": -0.08593708276748657, "max": 0.9058842062950134, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 245.30337524414062, "min": -20.71083641052246, "max": 283.541748046875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002784587675705552, "min": -0.036354463547468185, "max": 0.3167021572589874, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8242379426956177, "min": -10.906338691711426, "max": 76.3252182006836, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07189482806799267, "min": 0.06410922272092041, "max": 0.07486844834424664, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0065275929518975, "min": 0.5240791384097264, "max": 1.112102303149489, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015080146961346534, "min": 0.0013398803707373387, "max": 0.01718154192915083, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2111220574588515, "min": 0.015331724933328622, "max": 0.25772312893726246, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.507513783242855e-06, "min": 1.507513783242855e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.110519296539997e-05, "min": 2.110519296539997e-05, "max": 0.003969209376930233, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050247142857141, "min": 0.10050247142857141, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070345999999998, "min": 1.3962282666666668, "max": 2.782542200000001, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.019689571428565e-05, "min": 6.019689571428565e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008427565399999991, "min": 0.0008427565399999991, "max": 0.13231466969000003, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0073359934613108635, "min": 0.006701712030917406, "max": 0.6192254424095154, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10270390659570694, "min": 0.09382396936416626, "max": 4.334578037261963, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 217.1865671641791, "min": 198.86274509803923, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29103.0, "min": 15984.0, "max": 32814.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7380253580301555, "min": -1.0000000521540642, "max": 1.8008873049222247, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 232.89539797604084, "min": -30.658001706004143, "max": 273.44739835709333, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7380253580301555, "min": -1.0000000521540642, "max": 1.8008873049222247, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 232.89539797604084, "min": -30.658001706004143, "max": 273.44739835709333, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016384191338690485, "min": 0.014824260548053856, "max": 13.68239908106625, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.195481639384525, "min": 2.068405654252274, "max": 218.91838529706, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690852405", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "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": "1690860081" }, "total": 7675.341482369, "count": 1, "self": 0.6874560510004812, "children": { "run_training.setup": { "total": 0.03172143999995569, "count": 1, "self": 0.03172143999995569 }, "TrainerController.start_learning": { "total": 7674.622304877999, "count": 1, "self": 4.429520535857591, "children": { "TrainerController._reset_env": { "total": 4.07166559999996, "count": 1, "self": 4.07166559999996 }, "TrainerController.advance": { "total": 7666.017228334143, "count": 195847, "self": 4.691276614812523, "children": { "env_step": { "total": 5695.15596626927, "count": 195847, "self": 5361.175351118237, "children": { "SubprocessEnvManager._take_step": { "total": 331.27436869409553, "count": 195847, "self": 14.289534352234114, "children": { "TorchPolicy.evaluate": { "total": 316.9848343418614, "count": 187554, "self": 316.9848343418614 } } }, "workers": { "total": 2.7062464569371514, "count": 195847, "self": 0.0, "children": { "worker_root": { "total": 7657.038805395903, "count": 195847, "is_parallel": true, "self": 2658.9285183700194, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017274140000154148, "count": 1, "is_parallel": true, "self": 0.0005288780002956628, "children": { "_process_rank_one_or_two_observation": { "total": 0.001198535999719752, "count": 8, "is_parallel": true, "self": 0.001198535999719752 } } }, "UnityEnvironment.step": { "total": 0.04789314999993621, "count": 1, "is_parallel": true, "self": 0.0005734299998039205, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004719040000509267, "count": 1, "is_parallel": true, "self": 0.0004719040000509267 }, "communicator.exchange": { "total": 0.04505899400010094, "count": 1, "is_parallel": true, "self": 0.04505899400010094 }, "steps_from_proto": { "total": 0.0017888219999804278, "count": 1, "is_parallel": true, "self": 0.00037117900023986294, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014176429997405648, "count": 8, "is_parallel": true, "self": 0.0014176429997405648 } } } } } } }, "UnityEnvironment.step": { "total": 4998.110287025884, "count": 195846, "is_parallel": true, "self": 106.06119666041195, "children": { "UnityEnvironment._generate_step_input": { "total": 69.7546323146953, "count": 195846, "is_parallel": true, "self": 69.7546323146953 }, "communicator.exchange": { "total": 4509.801032550017, "count": 195846, "is_parallel": true, "self": 4509.801032550017 }, "steps_from_proto": { "total": 312.4934255007597, "count": 195846, "is_parallel": true, "self": 64.17306663634054, "children": { "_process_rank_one_or_two_observation": { "total": 248.32035886441918, "count": 1566768, "is_parallel": true, "self": 248.32035886441918 } } } } } } } } } } }, "trainer_advance": { "total": 1966.1699854500605, "count": 195847, "self": 8.599785773929625, "children": { "process_trajectory": { "total": 343.59275904313427, "count": 195847, "self": 342.92548210513496, "children": { "RLTrainer._checkpoint": { "total": 0.6672769379993042, "count": 6, "self": 0.6672769379993042 } } }, "_update_policy": { "total": 1613.9774406329966, "count": 1399, "self": 1051.0212236090463, "children": { "TorchPPOOptimizer.update": { "total": 562.9562170239503, "count": 68388, "self": 562.9562170239503 } } } } } } }, "trainer_threads": { "total": 8.09999619377777e-07, "count": 1, "self": 8.09999619377777e-07 }, "TrainerController._save_models": { "total": 0.1038895980000234, "count": 1, "self": 0.0015729759998066584, "children": { "RLTrainer._checkpoint": { "total": 0.10231662200021674, "count": 1, "self": 0.10231662200021674 } } } } } } }