{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4656467139720917, "min": 0.4614233076572418, "max": 1.390609622001648, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14088.607421875, "min": 13835.31640625, "max": 42185.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989977.0, "min": 29979.0, "max": 989977.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989977.0, "min": 29979.0, "max": 989977.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46047669649124146, "min": -0.0860719233751297, "max": 0.47979408502578735, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 123.86823272705078, "min": -20.74333381652832, "max": 129.06460571289062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01200780738145113, "min": 0.0019785829354077578, "max": 0.5048832893371582, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.230100154876709, "min": 0.5302602052688599, "max": 120.16222381591797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0653951852251818, "min": 0.06315744226178692, "max": 0.07420338835620714, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9155325931525452, "min": 0.5825113436784461, "max": 1.0388474369869, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014776291066036543, "min": 0.00013257642899025817, "max": 0.016161584308267467, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2068680749245116, "min": 0.0018560700058636143, "max": 0.242423764624012, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.624468887114291e-06, "min": 7.624468887114291e-06, "max": 0.0002948454392181875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010674256441960008, "min": 0.00010674256441960008, "max": 0.0037245246584918005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254145714285715, "min": 0.10254145714285715, "max": 0.1982818125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355804, "min": 1.4355804, "max": 2.610880800000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026389156857142875, "min": 0.00026389156857142875, "max": 0.00982835306875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036944819600000026, "min": 0.0036944819600000026, "max": 0.12415666918000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011301355436444283, "min": 0.011301355436444283, "max": 0.53420490026474, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15821897983551025, "min": 0.15821897983551025, "max": 4.27363920211792, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 381.94805194805195, "min": 381.94805194805195, "max": 998.5806451612904, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29410.0, "min": 17033.0, "max": 34008.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5401064697411153, "min": -0.9349742462077448, "max": 1.5782136723195037, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.58819817006588, "min": -30.70760168135166, "max": 118.58819817006588, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5401064697411153, "min": -0.9349742462077448, "max": 1.5782136723195037, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.58819817006588, "min": -30.70760168135166, "max": 118.58819817006588, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04381303910117645, "min": 0.04381303910117645, "max": 11.415239632957512, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3736040107905865, "min": 3.329382886062376, "max": 205.4743133932352, "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": "1776527893", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1776530192" }, "total": 2299.0374366200003, "count": 1, "self": 0.7324784170014027, "children": { "run_training.setup": { "total": 0.023984575000213226, "count": 1, "self": 0.023984575000213226 }, "TrainerController.start_learning": { "total": 2298.2809736279987, "count": 1, "self": 1.4231368309901882, "children": { "TrainerController._reset_env": { "total": 2.183353630000056, "count": 1, "self": 2.183353630000056 }, "TrainerController.advance": { "total": 2294.5908992470095, "count": 63654, "self": 1.5163710445094694, "children": { "env_step": { "total": 1597.2094434376686, "count": 63654, "self": 1433.721294855558, "children": { "SubprocessEnvManager._take_step": { "total": 162.62268812107231, "count": 63654, "self": 5.0771338158347135, "children": { "TorchPolicy.evaluate": { "total": 157.5455543052376, "count": 62564, "self": 157.5455543052376 } } }, "workers": { "total": 0.8654604610383103, "count": 63654, "self": 0.0, "children": { "worker_root": { "total": 2291.466371287889, "count": 63654, "is_parallel": true, "self": 982.9223168741028, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020732140001200605, "count": 1, "is_parallel": true, "self": 0.0007346429993049242, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013385710008151364, "count": 8, "is_parallel": true, "self": 0.0013385710008151364 } } }, "UnityEnvironment.step": { "total": 0.052863576999698125, "count": 1, "is_parallel": true, "self": 0.0006159069998830091, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005485539995788713, "count": 1, "is_parallel": true, "self": 0.0005485539995788713 }, "communicator.exchange": { "total": 0.05006372200023179, "count": 1, "is_parallel": true, "self": 0.05006372200023179 }, "steps_from_proto": { "total": 0.0016353940000044531, "count": 1, "is_parallel": true, "self": 0.000365658998816798, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012697350011876551, "count": 8, "is_parallel": true, "self": 0.0012697350011876551 } } } } } } }, "UnityEnvironment.step": { "total": 1308.5440544137864, "count": 63653, "is_parallel": true, "self": 36.05224892680144, "children": { "UnityEnvironment._generate_step_input": { "total": 24.955949950214745, "count": 63653, "is_parallel": true, "self": 24.955949950214745 }, "communicator.exchange": { "total": 1129.188865558066, "count": 63653, "is_parallel": true, "self": 1129.188865558066 }, "steps_from_proto": { "total": 118.34698997870419, "count": 63653, "is_parallel": true, "self": 24.460046167809196, "children": { "_process_rank_one_or_two_observation": { "total": 93.88694381089499, "count": 509224, "is_parallel": true, "self": 93.88694381089499 } } } } } } } } } } }, "trainer_advance": { "total": 695.8650847648314, "count": 63654, "self": 2.8481785927679084, "children": { "process_trajectory": { "total": 131.40946985102346, "count": 63654, "self": 131.1642120120232, "children": { "RLTrainer._checkpoint": { "total": 0.24525783900026, "count": 2, "self": 0.24525783900026 } } }, "_update_policy": { "total": 561.60743632104, "count": 458, "self": 311.4060259849484, "children": { "TorchPPOOptimizer.update": { "total": 250.2014103360916, "count": 22827, "self": 250.2014103360916 } } } } } } }, "trainer_threads": { "total": 1.0709991329349577e-06, "count": 1, "self": 1.0709991329349577e-06 }, "TrainerController._save_models": { "total": 0.08358284899986756, "count": 1, "self": 0.001159835999715142, "children": { "RLTrainer._checkpoint": { "total": 0.08242301300015242, "count": 1, "self": 0.08242301300015242 } } } } } } }