{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4112773537635803, "min": 0.3793245553970337, "max": 1.4767119884490967, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12371.22265625, "min": 11319.044921875, "max": 44797.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.413862407207489, "min": -0.09325626492500305, "max": 0.5300389528274536, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.98443603515625, "min": -22.38150405883789, "max": 144.17059326171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.019866134971380234, "min": -0.034065764397382736, "max": 0.1654900461435318, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.423454761505127, "min": -9.12962532043457, "max": 39.88310241699219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07019901967474391, "min": 0.06482775716198456, "max": 0.07339843762934996, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9827862754464148, "min": 0.4811575317398402, "max": 1.0500742171031616, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017913033424563417, "min": 0.0002138310012392464, "max": 0.017913033424563417, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25078246794388787, "min": 0.00299363401734945, "max": 0.25078246794388787, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.649904592921422e-06, "min": 7.649904592921422e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001070986643008999, "min": 0.0001070986643008999, "max": 0.003507441230852999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254993571428572, "min": 0.10254993571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356991000000001, "min": 1.3886848, "max": 2.569147, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002647385778571427, "min": 0.0002647385778571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037063400899999977, "min": 0.0037063400899999977, "max": 0.1169377853, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008555079810321331, "min": 0.008555079810321331, "max": 0.339886873960495, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11977112293243408, "min": 0.11977112293243408, "max": 2.3792080879211426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 413.17105263157896, "min": 358.9759036144578, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31401.0, "min": 15984.0, "max": 33087.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5078578693302054, "min": -1.0000000521540642, "max": 1.5687060007847935, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.59719806909561, "min": -31.992001608014107, "max": 130.20259806513786, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5078578693302054, "min": -1.0000000521540642, "max": 1.5687060007847935, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.59719806909561, "min": -31.992001608014107, "max": 130.20259806513786, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03612648111486219, "min": 0.03612648111486219, "max": 7.01784941740334, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7456125647295266, "min": 2.6148466583690606, "max": 112.28559067845345, "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": "1778027310", "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1778029398" }, "total": 2088.461743668, "count": 1, "self": 0.47953521000090404, "children": { "run_training.setup": { "total": 0.025651138999819523, "count": 1, "self": 0.025651138999819523 }, "TrainerController.start_learning": { "total": 2087.9565573189993, "count": 1, "self": 1.1637133059975895, "children": { "TrainerController._reset_env": { "total": 2.278692169000351, "count": 1, "self": 2.278692169000351 }, "TrainerController.advance": { "total": 2084.428669275001, "count": 63695, "self": 1.2291995486466476, "children": { "env_step": { "total": 1441.4168532181811, "count": 63695, "self": 1300.2610185313624, "children": { "SubprocessEnvManager._take_step": { "total": 140.4202787315171, "count": 63695, "self": 4.3379366118206235, "children": { "TorchPolicy.evaluate": { "total": 136.08234211969648, "count": 62564, "self": 136.08234211969648 } } }, "workers": { "total": 0.7355559553016064, "count": 63695, "self": 0.0, "children": { "worker_root": { "total": 2081.2776962658118, "count": 63695, "is_parallel": true, "self": 888.7741476341125, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017355510008201236, "count": 1, "is_parallel": true, "self": 0.0005349800012481865, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012005709995719371, "count": 8, "is_parallel": true, "self": 0.0012005709995719371 } } }, "UnityEnvironment.step": { "total": 0.10582038100073987, "count": 1, "is_parallel": true, "self": 0.00360359300429991, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048477499876753427, "count": 1, "is_parallel": true, "self": 0.00048477499876753427 }, "communicator.exchange": { "total": 0.09692616899883433, "count": 1, "is_parallel": true, "self": 0.09692616899883433 }, "steps_from_proto": { "total": 0.0048058439988381, "count": 1, "is_parallel": true, "self": 0.0004212909989291802, "children": { "_process_rank_one_or_two_observation": { "total": 0.0043845529999089194, "count": 8, "is_parallel": true, "self": 0.0043845529999089194 } } } } } } }, "UnityEnvironment.step": { "total": 1192.5035486316992, "count": 63694, "is_parallel": true, "self": 32.17797595007505, "children": { "UnityEnvironment._generate_step_input": { "total": 21.767242313024326, "count": 63694, "is_parallel": true, "self": 21.767242313024326 }, "communicator.exchange": { "total": 1038.079693927688, "count": 63694, "is_parallel": true, "self": 1038.079693927688 }, "steps_from_proto": { "total": 100.47863644091194, "count": 63694, "is_parallel": true, "self": 20.85181085090153, "children": { "_process_rank_one_or_two_observation": { "total": 79.62682559001041, "count": 509552, "is_parallel": true, "self": 79.62682559001041 } } } } } } } } } } }, "trainer_advance": { "total": 641.7826165081733, "count": 63695, "self": 2.2479546540598676, "children": { "process_trajectory": { "total": 119.82830055307386, "count": 63695, "self": 119.64740638207513, "children": { "RLTrainer._checkpoint": { "total": 0.18089417099872662, "count": 2, "self": 0.18089417099872662 } } }, "_update_policy": { "total": 519.7063613010396, "count": 452, "self": 286.464147070119, "children": { "TorchPPOOptimizer.update": { "total": 233.24221423092058, "count": 22818, "self": 233.24221423092058 } } } } } } }, "trainer_threads": { "total": 7.569997251266614e-07, "count": 1, "self": 7.569997251266614e-07 }, "TrainerController._save_models": { "total": 0.08548181200058025, "count": 1, "self": 0.000985447999482858, "children": { "RLTrainer._checkpoint": { "total": 0.08449636400109739, "count": 1, "self": 0.08449636400109739 } } } } } } }