{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4229440987110138, "min": 0.4189181327819824, "max": 1.523527979850769, "count": 37 }, "Pyramids.Policy.Entropy.sum": { "value": 12613.884765625, "min": 12520.625, "max": 46217.74609375, "count": 37 }, "Pyramids.Step.mean": { "value": 1109950.0, "min": 29952.0, "max": 1109950.0, "count": 37 }, "Pyramids.Step.sum": { "value": 1109950.0, "min": 29952.0, "max": 1109950.0, "count": 37 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5420405864715576, "min": -0.11092951893806458, "max": 0.5420405864715576, "count": 37 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.0611572265625, "min": -26.84494400024414, "max": 149.78140258789062, "count": 37 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005026669707149267, "min": -0.003389290999621153, "max": 0.42502084374427795, "count": 37 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3823341131210327, "min": -0.9049407243728638, "max": 100.72994232177734, "count": 37 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07108240525513113, "min": 0.06528723666985735, "max": 0.0742275493539637, "count": 37 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9951536735718357, "min": 0.47906342694260196, "max": 1.0898301629440894, "count": 37 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012519621625775799, "min": 0.00038778672072526673, "max": 0.014062284119445545, "count": 37 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17527470276086118, "min": 0.0050412273694284675, "max": 0.20037357302984066, "count": 37 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001904392293774119, "min": 0.0001904392293774119, "max": 0.00029838354339596195, "count": 37 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0026661492112837666, "min": 0.0020691136102954665, "max": 0.003759513146829, "count": 37 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16347973095238094, "min": 0.16347973095238094, "max": 0.19946118095238097, "count": 37 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.288716233333333, "min": 1.3897045333333333, "max": 2.752557733333333, "count": 37 }, "Pyramids.Policy.Beta.mean": { "value": 0.006351625122142857, "min": 0.006351625122142857, "max": 0.009946171977142856, "count": 37 }, "Pyramids.Policy.Beta.sum": { "value": 0.08892275171, "min": 0.06897148288, "max": 0.1253317829, "count": 37 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006684461142867804, "min": 0.006684461142867804, "max": 0.36375197768211365, "count": 37 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09358245879411697, "min": 0.09358245879411697, "max": 2.5462639331817627, "count": 37 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.22093023255815, "min": 329.22093023255815, "max": 999.0, "count": 37 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28313.0, "min": 15984.0, "max": 32598.0, "count": 37 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6009906757363053, "min": -1.0000000521540642, "max": 1.6009906757363053, "count": 37 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.68519811332226, "min": -32.000001668930054, "max": 137.68519811332226, "count": 37 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6009906757363053, "min": -1.0000000521540642, "max": 1.6009906757363053, "count": 37 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.68519811332226, "min": -32.000001668930054, "max": 137.68519811332226, "count": 37 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02284779747271894, "min": 0.02284779747271894, "max": 7.149970472790301, "count": 37 }, "Pyramids.Policy.RndReward.sum": { "value": 1.964910582653829, "min": 1.964910582653829, "max": 114.39952756464481, "count": 37 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679612196", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1679614488" }, "total": 2291.9120064339995, "count": 1, "self": 0.5707430259999455, "children": { "run_training.setup": { "total": 0.1858476370000517, "count": 1, "self": 0.1858476370000517 }, "TrainerController.start_learning": { "total": 2291.1554157709998, "count": 1, "self": 1.4363098690323568, "children": { "TrainerController._reset_env": { "total": 9.442500624999866, "count": 1, "self": 9.442500624999866 }, "TrainerController.advance": { "total": 2279.9776958459674, "count": 71988, "self": 1.5922970449742024, "children": { "env_step": { "total": 1583.661105826942, "count": 71988, "self": 1462.2204458579392, "children": { "SubprocessEnvManager._take_step": { "total": 120.52798532802717, "count": 71988, "self": 5.212469179051368, "children": { "TorchPolicy.evaluate": { "total": 115.3155161489758, "count": 70745, "self": 115.3155161489758 } } }, "workers": { "total": 0.9126746409756379, "count": 71987, "self": 0.0, "children": { "worker_root": { "total": 2286.1412903539226, "count": 71987, "is_parallel": true, "self": 952.1478324109278, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004751907999889227, "count": 1, "is_parallel": true, "self": 0.0033636399998613342, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013882680000278924, "count": 8, "is_parallel": true, "self": 0.0013882680000278924 } } }, "UnityEnvironment.step": { "total": 0.047330315999943195, "count": 1, "is_parallel": true, "self": 0.0005455760001495946, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004437469999629684, "count": 1, "is_parallel": true, "self": 0.0004437469999629684 }, "communicator.exchange": { "total": 0.044805161999875054, "count": 1, "is_parallel": true, "self": 0.044805161999875054 }, "steps_from_proto": { "total": 0.0015358309999555786, "count": 1, "is_parallel": true, "self": 0.00033245999998143816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012033709999741404, "count": 8, "is_parallel": true, "self": 0.0012033709999741404 } } } } } } }, "UnityEnvironment.step": { "total": 1333.9934579429948, "count": 71986, "is_parallel": true, "self": 35.36945377094594, "children": { "UnityEnvironment._generate_step_input": { "total": 25.69136506301743, "count": 71986, "is_parallel": true, "self": 25.69136506301743 }, "communicator.exchange": { "total": 1171.6244269460249, "count": 71986, "is_parallel": true, "self": 1171.6244269460249 }, "steps_from_proto": { "total": 101.3082121630066, "count": 71986, "is_parallel": true, "self": 21.470143655967604, "children": { "_process_rank_one_or_two_observation": { "total": 79.838068507039, "count": 575888, "is_parallel": true, "self": 79.838068507039 } } } } } } } } } } }, "trainer_advance": { "total": 694.7242929740512, "count": 71987, "self": 2.852848954955789, "children": { "process_trajectory": { "total": 129.29073910309467, "count": 71987, "self": 128.98020645009478, "children": { "RLTrainer._checkpoint": { "total": 0.310532652999882, "count": 2, "self": 0.310532652999882 } } }, "_update_policy": { "total": 562.5807049160007, "count": 497, "self": 356.25463191701147, "children": { "TorchPPOOptimizer.update": { "total": 206.32607299898928, "count": 25809, "self": 206.32607299898928 } } } } } } }, "trainer_threads": { "total": 1.4199999895936344e-06, "count": 1, "self": 1.4199999895936344e-06 }, "TrainerController._save_models": { "total": 0.2989080110000941, "count": 1, "self": 0.0018941320004159934, "children": { "RLTrainer._checkpoint": { "total": 0.2970138789996781, "count": 1, "self": 0.2970138789996781 } } } } } } }