{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2826092839241028, "min": 0.2826092839241028, "max": 1.5848491191864014, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 2853.223388671875, "min": 2853.223388671875, "max": 16228.8544921875, "count": 100 }, "Pyramids.Step.mean": { "value": 999910.0, "min": 9984.0, "max": 999910.0, "count": 100 }, "Pyramids.Step.sum": { "value": 999910.0, "min": 9984.0, "max": 999910.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46384334564208984, "min": -0.11391963809728622, "max": 0.5060330033302307, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 40.818214416503906, "min": -9.227490425109863, "max": 48.57917022705078, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.044039901345968246, "min": -0.05073276162147522, "max": 0.4056205749511719, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.875511407852173, "min": -4.261551856994629, "max": 31.638404846191406, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0701680085544164, "min": 0.06202874526130782, "max": 0.07954392473166585, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.35084004277208203, "min": 0.15369624383954983, "max": 0.382666702818824, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01221209843934048, "min": 0.00018120926970747553, "max": 0.016489528161279545, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0610604921967024, "min": 0.0007248370788299021, "max": 0.08244764080639773, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.6889794370399968e-06, "min": 1.6889794370399968e-06, "max": 0.0002981568006144, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 8.444897185199984e-06, "min": 8.444897185199984e-06, "max": 0.0013131567622811, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10056296, "min": 0.10056296, "max": 0.1993856, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5028148, "min": 0.39717119999999995, "max": 0.9377189000000002, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.62397039999999e-05, "min": 6.62397039999999e-05, "max": 0.00993862144, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0003311985199999995, "min": 0.0003311985199999995, "max": 0.04377811810999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008012634702026844, "min": 0.007863491773605347, "max": 0.9010456204414368, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.040063172578811646, "min": 0.03335943818092346, "max": 1.8020912408828735, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 394.9130434782609, "min": 342.85185185185185, "max": 999.0, "count": 96 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 9083.0, "min": 738.0, "max": 16404.0, "count": 96 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5132545280185612, "min": -1.0000000521540642, "max": 1.64861902878398, "count": 96 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 33.29159961640835, "min": -16.000000834465027, "max": 45.812999561429024, "count": 96 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5132545280185612, "min": -1.0000000521540642, "max": 1.64861902878398, "count": 96 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 33.29159961640835, "min": -16.000000834465027, "max": 45.812999561429024, "count": 96 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033005714289505377, "min": 0.030117059673001576, "max": 10.386672714725137, "count": 96 }, "Pyramids.Policy.RndReward.sum": { "value": 0.7261257143691182, "min": 0.5370313860476017, "max": 166.1867634356022, "count": 96 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1729877736", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729880686" }, "total": 2949.1100293450004, "count": 1, "self": 0.5989152180004567, "children": { "run_training.setup": { "total": 0.07616588799987767, "count": 1, "self": 0.07616588799987767 }, "TrainerController.start_learning": { "total": 2948.434948239, "count": 1, "self": 2.4177266030101237, "children": { "TrainerController._reset_env": { "total": 3.3604438410000057, "count": 1, "self": 3.3604438410000057 }, "TrainerController.advance": { "total": 2942.5732142239895, "count": 63726, "self": 2.4932923259989366, "children": { "env_step": { "total": 1932.3342302999954, "count": 63726, "self": 1776.7762098499572, "children": { "SubprocessEnvManager._take_step": { "total": 154.18486513401217, "count": 63726, "self": 6.335472065034992, "children": { "TorchPolicy.evaluate": { "total": 147.84939306897718, "count": 62566, "self": 147.84939306897718 } } }, "workers": { "total": 1.3731553160259864, "count": 63726, "self": 0.0, "children": { "worker_root": { "total": 2942.1410218980063, "count": 63726, "is_parallel": true, "self": 1329.9792880049602, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032032409999374067, "count": 1, "is_parallel": true, "self": 0.001028396999799952, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021748440001374547, "count": 8, "is_parallel": true, "self": 0.0021748440001374547 } } }, "UnityEnvironment.step": { "total": 0.11866920400007075, "count": 1, "is_parallel": true, "self": 0.0007112880000477162, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005160319999504281, "count": 1, "is_parallel": true, "self": 0.0005160319999504281 }, "communicator.exchange": { "total": 0.11546266599998489, "count": 1, "is_parallel": true, "self": 0.11546266599998489 }, "steps_from_proto": { "total": 0.0019792180000877124, "count": 1, "is_parallel": true, "self": 0.00042561700024634774, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015536009998413647, "count": 8, "is_parallel": true, "self": 0.0015536009998413647 } } } } } } }, "UnityEnvironment.step": { "total": 1612.1617338930462, "count": 63725, "is_parallel": true, "self": 46.450452183041534, "children": { "UnityEnvironment._generate_step_input": { "total": 29.729017089979152, "count": 63725, "is_parallel": true, "self": 29.729017089979152 }, "communicator.exchange": { "total": 1411.2137150430435, "count": 63725, "is_parallel": true, "self": 1411.2137150430435 }, "steps_from_proto": { "total": 124.76854957698197, "count": 63725, "is_parallel": true, "self": 26.73224806583562, "children": { "_process_rank_one_or_two_observation": { "total": 98.03630151114635, "count": 509800, "is_parallel": true, "self": 98.03630151114635 } } } } } } } } } } }, "trainer_advance": { "total": 1007.7456915979951, "count": 63726, "self": 4.297237278982266, "children": { "process_trajectory": { "total": 155.07915193601752, "count": 63726, "self": 154.83753895501764, "children": { "RLTrainer._checkpoint": { "total": 0.24161298099988926, "count": 2, "self": 0.24161298099988926 } } }, "_update_policy": { "total": 848.3693023829953, "count": 452, "self": 357.5349593430167, "children": { "TorchPPOOptimizer.update": { "total": 490.83434303997865, "count": 22833, "self": 490.83434303997865 } } } } } } }, "trainer_threads": { "total": 1.4600000213249587e-06, "count": 1, "self": 1.4600000213249587e-06 }, "TrainerController._save_models": { "total": 0.083562110999992, "count": 1, "self": 0.0033624179995968007, "children": { "RLTrainer._checkpoint": { "total": 0.0801996930003952, "count": 1, "self": 0.0801996930003952 } } } } } } }