{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.659187912940979, "min": 0.6173156499862671, "max": 1.4114888906478882, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19912.748046875, "min": 18420.69921875, "max": 42818.92578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29920.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29920.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1626151204109192, "min": -0.1080414354801178, "max": 0.1626151204109192, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 41.141624450683594, "min": -26.037986755371094, "max": 41.141624450683594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.6712524890899658, "min": -0.030549194663763046, "max": 1.6712524890899658, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 422.8268737792969, "min": -7.667847633361816, "max": 422.8268737792969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06901794078392015, "min": 0.06467967473791289, "max": 0.07363861727630608, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9662511709748821, "min": 0.5891089382104486, "max": 1.0328101998870718, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.6948818891074089, "min": 0.00013090192973598186, "max": 0.6948818891074089, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 9.728346447503725, "min": 0.0018326270163037462, "max": 9.728346447503725, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.662783160057142e-06, "min": 7.662783160057142e-06, "max": 0.000294853726715425, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001072789642408, "min": 0.0001072789642408, "max": 0.00337623017459, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255422857142858, "min": 0.10255422857142858, "max": 0.19828457500000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357592000000001, "min": 1.4357592000000001, "max": 2.4441787, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026516743428571434, "min": 0.00026516743428571434, "max": 0.009828629042499998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037123440800000008, "min": 0.0037123440800000008, "max": 0.112558459, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013696732930839062, "min": 0.013696732930839062, "max": 0.42166799306869507, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1917542666196823, "min": 0.1917542666196823, "max": 3.3733439445495605, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 706.6428571428571, "min": 696.609756097561, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29679.0, "min": 16974.0, "max": 32650.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.626523764892703, "min": -0.9997750516049564, "max": 0.65857329401705, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 26.313998125493526, "min": -31.992801651358604, "max": 29.63579823076725, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.626523764892703, "min": -0.9997750516049564, "max": 0.65857329401705, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 26.313998125493526, "min": -31.992801651358604, "max": 29.63579823076725, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10075437982838291, "min": 0.10075437982838291, "max": 7.98027394256658, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.231683952792082, "min": 4.165264769690111, "max": 143.64493096619844, "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": "1703065503", "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": "1703067752" }, "total": 2248.79340017, "count": 1, "self": 0.9867051340002035, "children": { "run_training.setup": { "total": 0.047504747999937535, "count": 1, "self": 0.047504747999937535 }, "TrainerController.start_learning": { "total": 2247.759190288, "count": 1, "self": 1.6674473260336526, "children": { "TrainerController._reset_env": { "total": 2.264622074000272, "count": 1, "self": 2.264622074000272 }, "TrainerController.advance": { "total": 2243.6978821739667, "count": 63213, "self": 1.6301510930070435, "children": { "env_step": { "total": 1602.5680590609932, "count": 63213, "self": 1458.6665379571232, "children": { "SubprocessEnvManager._take_step": { "total": 142.90357641197352, "count": 63213, "self": 5.14835664994871, "children": { "TorchPolicy.evaluate": { "total": 137.7552197620248, "count": 62546, "self": 137.7552197620248 } } }, "workers": { "total": 0.9979446918964641, "count": 63213, "self": 0.0, "children": { "worker_root": { "total": 2242.175577025978, "count": 63213, "is_parallel": true, "self": 913.561316739946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017532130000290636, "count": 1, "is_parallel": true, "self": 0.0005398879993663286, "children": { "_process_rank_one_or_two_observation": { "total": 0.001213325000662735, "count": 8, "is_parallel": true, "self": 0.001213325000662735 } } }, "UnityEnvironment.step": { "total": 0.07721136999998635, "count": 1, "is_parallel": true, "self": 0.0006264830003601674, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005295699997986958, "count": 1, "is_parallel": true, "self": 0.0005295699997986958 }, "communicator.exchange": { "total": 0.07453059599993139, "count": 1, "is_parallel": true, "self": 0.07453059599993139 }, "steps_from_proto": { "total": 0.0015247209998960898, "count": 1, "is_parallel": true, "self": 0.0002969679999296204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012277529999664694, "count": 8, "is_parallel": true, "self": 0.0012277529999664694 } } } } } } }, "UnityEnvironment.step": { "total": 1328.6142602860318, "count": 63212, "is_parallel": true, "self": 36.39443299213008, "children": { "UnityEnvironment._generate_step_input": { "total": 26.39216007598725, "count": 63212, "is_parallel": true, "self": 26.39216007598725 }, "communicator.exchange": { "total": 1159.6169457130236, "count": 63212, "is_parallel": true, "self": 1159.6169457130236 }, "steps_from_proto": { "total": 106.2107215048909, "count": 63212, "is_parallel": true, "self": 22.016268685833438, "children": { "_process_rank_one_or_two_observation": { "total": 84.19445281905746, "count": 505696, "is_parallel": true, "self": 84.19445281905746 } } } } } } } } } } }, "trainer_advance": { "total": 639.4996720199665, "count": 63213, "self": 2.960547474011946, "children": { "process_trajectory": { "total": 130.12816760195255, "count": 63213, "self": 129.88963012095337, "children": { "RLTrainer._checkpoint": { "total": 0.23853748099918448, "count": 2, "self": 0.23853748099918448 } } }, "_update_policy": { "total": 506.410956944002, "count": 448, "self": 300.8513082270051, "children": { "TorchPPOOptimizer.update": { "total": 205.5596487169969, "count": 22764, "self": 205.5596487169969 } } } } } } }, "trainer_threads": { "total": 1.3439994290820323e-06, "count": 1, "self": 1.3439994290820323e-06 }, "TrainerController._save_models": { "total": 0.12923736999982793, "count": 1, "self": 0.0022860010003569187, "children": { "RLTrainer._checkpoint": { "total": 0.12695136899947101, "count": 1, "self": 0.12695136899947101 } } } } } } }