{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31442779302597046, "min": 0.3123376667499542, "max": 1.534143328666687, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9407.6796875, "min": 9330.150390625, "max": 46539.7734375, "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": 0.5853469967842102, "min": -0.14413048326969147, "max": 0.5853469967842102, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.48251342773438, "min": -34.1589241027832, "max": 164.48251342773438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013148565776646137, "min": -0.011968915350735188, "max": 0.2266310751438141, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.694746971130371, "min": -3.207669258117676, "max": 54.391456604003906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0696586069797853, "min": 0.06475540734323704, "max": 0.07456197600105098, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9752204977169943, "min": 0.4913975127561027, "max": 1.0583987020072527, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017598831305457724, "min": 0.0006688984915327616, "max": 0.017598831305457724, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24638363827640813, "min": 0.0053511879322620925, "max": 0.24638363827640813, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.356376119335716e-06, "min": 7.356376119335716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010298926567070002, "min": 0.00010298926567070002, "max": 0.0033772525742491997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245209285714285, "min": 0.10245209285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343293, "min": 1.3691136000000002, "max": 2.5726036, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025496407642857153, "min": 0.00025496407642857153, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003569497070000001, "min": 0.003569497070000001, "max": 0.11259250491999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013572366908192635, "min": 0.01302368100732565, "max": 0.31851300597190857, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19001314043998718, "min": 0.18233153223991394, "max": 2.229591131210327, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 327.5104166666667, "min": 327.5104166666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31441.0, "min": 15984.0, "max": 32547.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5891374801285565, "min": -1.0000000521540642, "max": 1.5891374801285565, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 152.55719809234142, "min": -32.000001668930054, "max": 152.55719809234142, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5891374801285565, "min": -1.0000000521540642, "max": 1.5891374801285565, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 152.55719809234142, "min": -32.000001668930054, "max": 152.55719809234142, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04499205905206812, "min": 0.04499205905206812, "max": 6.511798510327935, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.3192376689985394, "min": 3.9530649252410512, "max": 104.18877616524696, "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": "1742230236", "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": "1742232486" }, "total": 2249.923313907, "count": 1, "self": 0.4915456590006215, "children": { "run_training.setup": { "total": 0.02408157999997229, "count": 1, "self": 0.02408157999997229 }, "TrainerController.start_learning": { "total": 2249.4076866679998, "count": 1, "self": 1.4078617809304887, "children": { "TrainerController._reset_env": { "total": 3.2677078510000115, "count": 1, "self": 3.2677078510000115 }, "TrainerController.advance": { "total": 2244.6428152650697, "count": 63819, "self": 1.4389100100597716, "children": { "env_step": { "total": 1546.7618243660004, "count": 63819, "self": 1388.9180521210187, "children": { "SubprocessEnvManager._take_step": { "total": 157.04806541497675, "count": 63819, "self": 4.96974314699645, "children": { "TorchPolicy.evaluate": { "total": 152.0783222679803, "count": 62563, "self": 152.0783222679803 } } }, "workers": { "total": 0.7957068300049741, "count": 63819, "self": 0.0, "children": { "worker_root": { "total": 2244.089968831012, "count": 63819, "is_parallel": true, "self": 972.0192049379693, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005262808999987101, "count": 1, "is_parallel": true, "self": 0.003803491999860853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014593170001262479, "count": 8, "is_parallel": true, "self": 0.0014593170001262479 } } }, "UnityEnvironment.step": { "total": 0.04849245799999835, "count": 1, "is_parallel": true, "self": 0.0005856629999243523, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004577679999897555, "count": 1, "is_parallel": true, "self": 0.0004577679999897555 }, "communicator.exchange": { "total": 0.045342900000036934, "count": 1, "is_parallel": true, "self": 0.045342900000036934 }, "steps_from_proto": { "total": 0.0021061270000473087, "count": 1, "is_parallel": true, "self": 0.0005514270000048782, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015547000000424305, "count": 8, "is_parallel": true, "self": 0.0015547000000424305 } } } } } } }, "UnityEnvironment.step": { "total": 1272.0707638930426, "count": 63818, "is_parallel": true, "self": 33.31307958894831, "children": { "UnityEnvironment._generate_step_input": { "total": 23.756827997999665, "count": 63818, "is_parallel": true, "self": 23.756827997999665 }, "communicator.exchange": { "total": 1114.7435045790212, "count": 63818, "is_parallel": true, "self": 1114.7435045790212 }, "steps_from_proto": { "total": 100.25735172707346, "count": 63818, "is_parallel": true, "self": 20.44486040398516, "children": { "_process_rank_one_or_two_observation": { "total": 79.8124913230883, "count": 510544, "is_parallel": true, "self": 79.8124913230883 } } } } } } } } } } }, "trainer_advance": { "total": 696.4420808890093, "count": 63819, "self": 2.663018977997581, "children": { "process_trajectory": { "total": 132.87687171301485, "count": 63819, "self": 132.49886597201493, "children": { "RLTrainer._checkpoint": { "total": 0.37800574099992446, "count": 2, "self": 0.37800574099992446 } } }, "_update_policy": { "total": 560.9021901979969, "count": 442, "self": 309.22097464099596, "children": { "TorchPPOOptimizer.update": { "total": 251.68121555700094, "count": 22803, "self": 251.68121555700094 } } } } } } }, "trainer_threads": { "total": 9.749996934260707e-07, "count": 1, "self": 9.749996934260707e-07 }, "TrainerController._save_models": { "total": 0.0893007959998613, "count": 1, "self": 0.0015207619999273447, "children": { "RLTrainer._checkpoint": { "total": 0.08778003399993395, "count": 1, "self": 0.08778003399993395 } } } } } } }