{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5026673078536987, "min": 0.5026673078536987, "max": 1.4213663339614868, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15240.873046875, "min": 15141.6357421875, "max": 43118.5703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3968644440174103, "min": -0.08460992574691772, "max": 0.4203161597251892, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 103.97848510742188, "min": -20.560211181640625, "max": 113.48535919189453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002554051810875535, "min": -0.013966123573482037, "max": 0.2871896028518677, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6691615581512451, "min": -3.519463062286377, "max": 68.92550659179688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0684274860049805, "min": 0.06496953819333824, "max": 0.07457199999272146, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0264122900747075, "min": 0.5220039999490502, "max": 1.0439899231229597, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01266093011405258, "min": 0.0011667398353236765, "max": 0.01634726657669359, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1899139517107887, "min": 0.015167617859207795, "max": 0.22886173207371027, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5173574942466725e-06, "min": 7.5173574942466725e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011276036241370008, "min": 0.00011276036241370008, "max": 0.0033709153763616002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250575333333334, "min": 0.10250575333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375863, "min": 1.3886848, "max": 2.4855616, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603247580000002, "min": 0.0002603247580000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003904871370000003, "min": 0.003904871370000003, "max": 0.11238147616000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006271941587328911, "min": 0.006271941587328911, "max": 0.42677026987075806, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09407912194728851, "min": 0.09074662625789642, "max": 2.987391948699951, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 508.23809523809524, "min": 377.02597402597405, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32019.0, "min": 15984.0, "max": 33823.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3329904534750514, "min": -1.0000000521540642, "max": 1.5124025435592883, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 83.97839856892824, "min": -29.895001627504826, "max": 117.96739839762449, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3329904534750514, "min": -1.0000000521540642, "max": 1.5124025435592883, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 83.97839856892824, "min": -29.895001627504826, "max": 117.96739839762449, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03333214400354625, "min": 0.026956731584132053, "max": 8.83012308459729, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0999250722234137, "min": 1.8288108107808512, "max": 141.28196935355663, "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": "1690401020", "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": "1690403177" }, "total": 2157.1569967719997, "count": 1, "self": 0.4941038019996995, "children": { "run_training.setup": { "total": 0.03230246300017825, "count": 1, "self": 0.03230246300017825 }, "TrainerController.start_learning": { "total": 2156.630590507, "count": 1, "self": 1.3044903769482517, "children": { "TrainerController._reset_env": { "total": 4.179340397000033, "count": 1, "self": 4.179340397000033 }, "TrainerController.advance": { "total": 2151.052716798052, "count": 63570, "self": 1.305836535018443, "children": { "env_step": { "total": 1498.697630629038, "count": 63570, "self": 1392.5489555429508, "children": { "SubprocessEnvManager._take_step": { "total": 105.36112305401502, "count": 63570, "self": 4.621220430106405, "children": { "TorchPolicy.evaluate": { "total": 100.73990262390862, "count": 62566, "self": 100.73990262390862 } } }, "workers": { "total": 0.7875520320721989, "count": 63570, "self": 0.0, "children": { "worker_root": { "total": 2151.7581108810687, "count": 63570, "is_parallel": true, "self": 869.9658371270434, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018194329995822045, "count": 1, "is_parallel": true, "self": 0.000577570999666932, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012418619999152725, "count": 8, "is_parallel": true, "self": 0.0012418619999152725 } } }, "UnityEnvironment.step": { "total": 0.0825513959998716, "count": 1, "is_parallel": true, "self": 0.0006032760006746685, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004878919999100617, "count": 1, "is_parallel": true, "self": 0.0004878919999100617 }, "communicator.exchange": { "total": 0.07953648299962879, "count": 1, "is_parallel": true, "self": 0.07953648299962879 }, "steps_from_proto": { "total": 0.0019237449996580835, "count": 1, "is_parallel": true, "self": 0.0003984919999311387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015252529997269448, "count": 8, "is_parallel": true, "self": 0.0015252529997269448 } } } } } } }, "UnityEnvironment.step": { "total": 1281.7922737540252, "count": 63569, "is_parallel": true, "self": 33.81636919111179, "children": { "UnityEnvironment._generate_step_input": { "total": 22.785603239986813, "count": 63569, "is_parallel": true, "self": 22.785603239986813 }, "communicator.exchange": { "total": 1126.0086817539755, "count": 63569, "is_parallel": true, "self": 1126.0086817539755 }, "steps_from_proto": { "total": 99.18161956895119, "count": 63569, "is_parallel": true, "self": 19.638228862872893, "children": { "_process_rank_one_or_two_observation": { "total": 79.5433907060783, "count": 508552, "is_parallel": true, "self": 79.5433907060783 } } } } } } } } } } }, "trainer_advance": { "total": 651.0492496339957, "count": 63570, "self": 2.542706957000064, "children": { "process_trajectory": { "total": 107.8379601379952, "count": 63570, "self": 107.63263936499561, "children": { "RLTrainer._checkpoint": { "total": 0.20532077299958473, "count": 2, "self": 0.20532077299958473 } } }, "_update_policy": { "total": 540.6685825390005, "count": 450, "self": 352.8936613729279, "children": { "TorchPPOOptimizer.update": { "total": 187.77492116607255, "count": 22824, "self": 187.77492116607255 } } } } } } }, "trainer_threads": { "total": 1.047999830916524e-06, "count": 1, "self": 1.047999830916524e-06 }, "TrainerController._save_models": { "total": 0.0940418869995483, "count": 1, "self": 0.0014040419991943054, "children": { "RLTrainer._checkpoint": { "total": 0.09263784500035399, "count": 1, "self": 0.09263784500035399 } } } } } } }