{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14898867905139923, "min": 0.1348116099834442, "max": 1.4765374660491943, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4474.42822265625, "min": 4065.91796875, "max": 44792.2421875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999992.0, "min": 29952.0, "max": 2999992.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999992.0, "min": 29952.0, "max": 2999992.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8321928977966309, "min": -0.11885575950145721, "max": 0.872637927532196, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 249.65786743164062, "min": -28.16881561279297, "max": 269.6451110839844, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012525931000709534, "min": -0.021693062037229538, "max": 0.28372928500175476, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.757779359817505, "min": -6.074057579040527, "max": 68.09503173828125, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07028049140418362, "min": 0.06310126956236609, "max": 0.0746417120708346, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0542073710627542, "min": 0.4880685719234725, "max": 1.119625681062519, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015276967455995164, "min": 0.00045737223529152834, "max": 0.018285626009391206, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22915451183992747, "min": 0.0059458390587898684, "max": 0.2742843901408681, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.518219493960003e-06, "min": 1.518219493960003e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2773292409400045e-05, "min": 2.2773292409400045e-05, "max": 0.004027700157433333, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050604000000002, "min": 0.10050604000000002, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075906000000003, "min": 1.3962282666666668, "max": 2.842566666666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.05533960000001e-05, "min": 6.05533960000001e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009083009400000015, "min": 0.0009083009400000015, "max": 0.13427241, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005902671720832586, "min": 0.005781227257102728, "max": 0.3772849440574646, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08854007720947266, "min": 0.08093718439340591, "max": 2.6409945487976074, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 239.704, "min": 211.62773722627736, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29963.0, "min": 15984.0, "max": 32516.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6962735948562622, "min": -1.0000000521540642, "max": 1.781460924190469, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 212.03419935703278, "min": -30.519601710140705, "max": 255.22619751095772, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6962735948562622, "min": -1.0000000521540642, "max": 1.781460924190469, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 212.03419935703278, "min": -30.519601710140705, "max": 255.22619751095772, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014651354121917393, "min": 0.013288510892696491, "max": 7.494385045021772, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8314192652396741, "min": 1.7017768221121514, "max": 119.91016072034836, "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 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1778714964", "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": "1778727607" }, "total": 12643.429911407, "count": 1, "self": 1.16792820900082, "children": { "run_training.setup": { "total": 0.042181580000033136, "count": 1, "self": 0.042181580000033136 }, "TrainerController.start_learning": { "total": 12642.219801618, "count": 1, "self": 7.742949274030252, "children": { "TrainerController._reset_env": { "total": 4.3852196499992715, "count": 1, "self": 4.3852196499992715 }, "TrainerController.advance": { "total": 12629.973222049968, "count": 195079, "self": 8.488060400719405, "children": { "env_step": { "total": 9223.389509081944, "count": 195079, "self": 8706.655098813308, "children": { "SubprocessEnvManager._take_step": { "total": 511.7588692379122, "count": 195079, "self": 23.028203215693793, "children": { "TorchPolicy.evaluate": { "total": 488.73066602221843, "count": 187557, "self": 488.73066602221843 } } }, "workers": { "total": 4.975541030724344, "count": 195079, "self": 0.0, "children": { "worker_root": { "total": 12614.221586950745, "count": 195079, "is_parallel": true, "self": 4525.700824042768, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006352079999487614, "count": 1, "is_parallel": true, "self": 0.004572093001115718, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017799869983718963, "count": 8, "is_parallel": true, "self": 0.0017799869983718963 } } }, "UnityEnvironment.step": { "total": 0.07597269899997627, "count": 1, "is_parallel": true, "self": 0.0007475690017599845, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007013249996816739, "count": 1, "is_parallel": true, "self": 0.0007013249996816739 }, "communicator.exchange": { "total": 0.07206011399830459, "count": 1, "is_parallel": true, "self": 0.07206011399830459 }, "steps_from_proto": { "total": 0.0024636910002300283, "count": 1, "is_parallel": true, "self": 0.0004943030035065021, "children": { "_process_rank_one_or_two_observation": { "total": 0.001969387996723526, "count": 8, "is_parallel": true, "self": 0.001969387996723526 } } } } } } }, "UnityEnvironment.step": { "total": 8088.520762907978, "count": 195078, "is_parallel": true, "self": 159.7645359278722, "children": { "UnityEnvironment._generate_step_input": { "total": 103.5806692274291, "count": 195078, "is_parallel": true, "self": 103.5806692274291 }, "communicator.exchange": { "total": 7366.7115509381165, "count": 195078, "is_parallel": true, "self": 7366.7115509381165 }, "steps_from_proto": { "total": 458.46400681456, "count": 195078, "is_parallel": true, "self": 94.07001005900929, "children": { "_process_rank_one_or_two_observation": { "total": 364.3939967555507, "count": 1560624, "is_parallel": true, "self": 364.3939967555507 } } } } } } } } } } }, "trainer_advance": { "total": 3398.0956525673046, "count": 195079, "self": 16.76018442660279, "children": { "process_trajectory": { "total": 535.2797008438683, "count": 195079, "self": 534.30141782387, "children": { "RLTrainer._checkpoint": { "total": 0.9782830199983437, "count": 6, "self": 0.9782830199983437 } } }, "_update_policy": { "total": 2846.0557672968334, "count": 1396, "self": 1143.6400711757306, "children": { "TorchPPOOptimizer.update": { "total": 1702.4156961211029, "count": 68454, "self": 1702.4156961211029 } } } } } } }, "trainer_threads": { "total": 1.134001649916172e-06, "count": 1, "self": 1.134001649916172e-06 }, "TrainerController._save_models": { "total": 0.11840950999976485, "count": 1, "self": 0.004679335001128493, "children": { "RLTrainer._checkpoint": { "total": 0.11373017499863636, "count": 1, "self": 0.11373017499863636 } } } } } } }