{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48021402955055237, "min": 0.48021402955055237, "max": 1.4902441501617432, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14360.3203125, "min": 14360.3203125, "max": 45208.046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989917.0, "min": 29952.0, "max": 989917.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989917.0, "min": 29952.0, "max": 989917.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6514550447463989, "min": -0.11386136710643768, "max": 0.6566945314407349, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.0132293701172, "min": -26.985143661499023, "max": 185.18785095214844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03425249457359314, "min": 0.0006377435056492686, "max": 0.3540770411491394, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.72770881652832, "min": 0.17984366416931152, "max": 83.916259765625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750992800100772, "min": 0.06583549466779938, "max": 0.07663817848769942, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9451389920141081, "min": 0.49660611034326796, "max": 1.0465953248386342, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015837647198904528, "min": 0.0007458813101544956, "max": 0.0165399567804776, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2217270607846634, "min": 0.00522116917108147, "max": 0.2371495314263145, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.321683273757142e-06, "min": 7.321683273757142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010250356583259999, "min": 0.00010250356583259999, "max": 0.0033823445725519, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244052857142859, "min": 0.10244052857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341674000000002, "min": 1.3691136000000002, "max": 2.5275887999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025380880428571437, "min": 0.00025380880428571437, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035533232600000013, "min": 0.0035533232600000013, "max": 0.11277206519, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00891155656427145, "min": 0.00891155656427145, "max": 0.3916129469871521, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12476179748773575, "min": 0.12476179748773575, "max": 2.74129056930542, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 284.50467289719626, "min": 278.6, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30442.0, "min": 15984.0, "max": 32398.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6383962104061864, "min": -1.0000000521540642, "max": 1.6818459878861904, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.66999830305576, "min": -32.000001668930054, "max": 176.67919790744781, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6383962104061864, "min": -1.0000000521540642, "max": 1.6818459878861904, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.66999830305576, "min": -32.000001668930054, "max": 176.67919790744781, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026440907638730866, "min": 0.026440907638730866, "max": 7.4749611197039485, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.802736209705472, "min": 2.7835747565841302, "max": 119.59937791526318, "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": "1705758082", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705762162" }, "total": 4080.1000603890006, "count": 1, "self": 0.6961320010013878, "children": { "run_training.setup": { "total": 0.07145061199935299, "count": 1, "self": 0.07145061199935299 }, "TrainerController.start_learning": { "total": 4079.332477776, "count": 1, "self": 2.9428937970124025, "children": { "TrainerController._reset_env": { "total": 3.581742211999881, "count": 1, "self": 3.581742211999881 }, "TrainerController.advance": { "total": 4072.707810036987, "count": 63959, "self": 3.1623630309577493, "children": { "env_step": { "total": 2781.168790743175, "count": 63959, "self": 2574.3643647988883, "children": { "SubprocessEnvManager._take_step": { "total": 204.98373575288406, "count": 63959, "self": 9.188517959978526, "children": { "TorchPolicy.evaluate": { "total": 195.79521779290553, "count": 62568, "self": 195.79521779290553 } } }, "workers": { "total": 1.8206901914027185, "count": 63959, "self": 0.0, "children": { "worker_root": { "total": 4070.867485893039, "count": 63959, "is_parallel": true, "self": 1715.7931527451365, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036871789998258464, "count": 1, "is_parallel": true, "self": 0.0013143840005795937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023727949992462527, "count": 8, "is_parallel": true, "self": 0.0023727949992462527 } } }, "UnityEnvironment.step": { "total": 0.10302843399949779, "count": 1, "is_parallel": true, "self": 0.0007355399993684841, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006348169999910169, "count": 1, "is_parallel": true, "self": 0.0006348169999910169 }, "communicator.exchange": { "total": 0.09930291700038651, "count": 1, "is_parallel": true, "self": 0.09930291700038651 }, "steps_from_proto": { "total": 0.002355159999751777, "count": 1, "is_parallel": true, "self": 0.0006363570018947939, "children": { "_process_rank_one_or_two_observation": { "total": 0.001718802997856983, "count": 8, "is_parallel": true, "self": 0.001718802997856983 } } } } } } }, "UnityEnvironment.step": { "total": 2355.0743331479025, "count": 63958, "is_parallel": true, "self": 53.607548110902826, "children": { "UnityEnvironment._generate_step_input": { "total": 34.610732220062346, "count": 63958, "is_parallel": true, "self": 34.610732220062346 }, "communicator.exchange": { "total": 2117.674743842882, "count": 63958, "is_parallel": true, "self": 2117.674743842882 }, "steps_from_proto": { "total": 149.18130897405536, "count": 63958, "is_parallel": true, "self": 33.514541947259204, "children": { "_process_rank_one_or_two_observation": { "total": 115.66676702679615, "count": 511664, "is_parallel": true, "self": 115.66676702679615 } } } } } } } } } } }, "trainer_advance": { "total": 1288.3766562628543, "count": 63959, "self": 6.303358605868198, "children": { "process_trajectory": { "total": 203.82565376897037, "count": 63959, "self": 203.53289062696967, "children": { "RLTrainer._checkpoint": { "total": 0.29276314200069464, "count": 2, "self": 0.29276314200069464 } } }, "_update_policy": { "total": 1078.2476438880158, "count": 441, "self": 421.8264343468536, "children": { "TorchPPOOptimizer.update": { "total": 656.4212095411622, "count": 22836, "self": 656.4212095411622 } } } } } } }, "trainer_threads": { "total": 9.640007192501798e-07, "count": 1, "self": 9.640007192501798e-07 }, "TrainerController._save_models": { "total": 0.10003076599969063, "count": 1, "self": 0.0028597869986697333, "children": { "RLTrainer._checkpoint": { "total": 0.0971709790010209, "count": 1, "self": 0.0971709790010209 } } } } } } }