{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33877208828926086, "min": 0.33727115392684937, "max": 1.4872770309448242, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10228.20703125, "min": 10101.9453125, "max": 45118.03515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5765272378921509, "min": -0.08277822285890579, "max": 0.6691191792488098, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.27456665039062, "min": -19.618438720703125, "max": 190.02984619140625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.022006597369909286, "min": -0.02479897439479828, "max": 0.2924167215824127, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.117834091186523, "min": -6.968511581420898, "max": 70.18001556396484, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06934189029802315, "min": 0.0645636961387936, "max": 0.07473253857217077, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9707864641723242, "min": 0.5000410186539634, "max": 1.0449825032264926, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019753128488889517, "min": 0.0012307270303317456, "max": 0.019753128488889517, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.27654379884445324, "min": 0.00861508921232222, "max": 0.27654379884445324, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.578354616771425e-06, "min": 7.578354616771425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010609696463479994, "min": 0.00010609696463479994, "max": 0.0037579675473441996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252608571428572, "min": 0.10252608571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353652000000001, "min": 1.3691136000000002, "max": 2.6526558, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002623559628571428, "min": 0.0002623559628571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003672983479999999, "min": 0.003672983479999999, "max": 0.12528031442, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007311108056455851, "min": 0.007311108056455851, "max": 0.41977185010910034, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10235550999641418, "min": 0.10235550999641418, "max": 2.9384028911590576, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 337.7529411764706, "min": 291.3942307692308, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28709.0, "min": 15984.0, "max": 33096.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6151670356883723, "min": -1.0000000521540642, "max": 1.688786389251936, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.28919803351164, "min": -32.000001668930054, "max": 173.9449980929494, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6151670356883723, "min": -1.0000000521540642, "max": 1.688786389251936, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.28919803351164, "min": -32.000001668930054, "max": 173.9449980929494, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025721214450930025, "min": 0.02461353027418898, "max": 8.937071155756712, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.186303228329052, "min": 2.186303228329052, "max": 142.9931384921074, "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": "1692234816", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 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": "1692237084" }, "total": 2268.006400372, "count": 1, "self": 0.5278051460004463, "children": { "run_training.setup": { "total": 0.04482449399984034, "count": 1, "self": 0.04482449399984034 }, "TrainerController.start_learning": { "total": 2267.4337707319996, "count": 1, "self": 1.357420555997578, "children": { "TrainerController._reset_env": { "total": 5.8853299100001095, "count": 1, "self": 5.8853299100001095 }, "TrainerController.advance": { "total": 2260.0954500450025, "count": 64055, "self": 1.4199619780042667, "children": { "env_step": { "total": 1611.9479417230202, "count": 64055, "self": 1502.0703968258042, "children": { "SubprocessEnvManager._take_step": { "total": 109.04844567911869, "count": 64055, "self": 4.755208933123413, "children": { "TorchPolicy.evaluate": { "total": 104.29323674599527, "count": 62564, "self": 104.29323674599527 } } }, "workers": { "total": 0.8290992180973262, "count": 64055, "self": 0.0, "children": { "worker_root": { "total": 2262.014207302008, "count": 64055, "is_parallel": true, "self": 876.8510251279345, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002703125999914846, "count": 1, "is_parallel": true, "self": 0.0007476870000573399, "children": { "_process_rank_one_or_two_observation": { "total": 0.001955438999857506, "count": 8, "is_parallel": true, "self": 0.001955438999857506 } } }, "UnityEnvironment.step": { "total": 0.10979249999991225, "count": 1, "is_parallel": true, "self": 0.000558400999807418, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005422369999905641, "count": 1, "is_parallel": true, "self": 0.0005422369999905641 }, "communicator.exchange": { "total": 0.1022418130000915, "count": 1, "is_parallel": true, "self": 0.1022418130000915 }, "steps_from_proto": { "total": 0.006450049000022773, "count": 1, "is_parallel": true, "self": 0.0004101039999113709, "children": { "_process_rank_one_or_two_observation": { "total": 0.006039945000111402, "count": 8, "is_parallel": true, "self": 0.006039945000111402 } } } } } } }, "UnityEnvironment.step": { "total": 1385.1631821740734, "count": 64054, "is_parallel": true, "self": 33.7912233169925, "children": { "UnityEnvironment._generate_step_input": { "total": 23.862670029966466, "count": 64054, "is_parallel": true, "self": 23.862670029966466 }, "communicator.exchange": { "total": 1219.1033712270878, "count": 64054, "is_parallel": true, "self": 1219.1033712270878 }, "steps_from_proto": { "total": 108.40591760002667, "count": 64054, "is_parallel": true, "self": 21.32374468803164, "children": { "_process_rank_one_or_two_observation": { "total": 87.08217291199503, "count": 512432, "is_parallel": true, "self": 87.08217291199503 } } } } } } } } } } }, "trainer_advance": { "total": 646.727546343978, "count": 64055, "self": 2.6087629029364052, "children": { "process_trajectory": { "total": 115.03947876304665, "count": 64055, "self": 114.77165831404636, "children": { "RLTrainer._checkpoint": { "total": 0.2678204490002827, "count": 2, "self": 0.2678204490002827 } } }, "_update_policy": { "total": 529.079304677995, "count": 452, "self": 345.36385924199703, "children": { "TorchPPOOptimizer.update": { "total": 183.71544543599794, "count": 22788, "self": 183.71544543599794 } } } } } } }, "trainer_threads": { "total": 9.870000212686136e-07, "count": 1, "self": 9.870000212686136e-07 }, "TrainerController._save_models": { "total": 0.09556923399941297, "count": 1, "self": 0.0014177879993440001, "children": { "RLTrainer._checkpoint": { "total": 0.09415144600006897, "count": 1, "self": 0.09415144600006897 } } } } } } }