{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4035062789916992, "min": 1.4035062789916992, "max": 1.4289989471435547, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 67719.1796875, "min": 66691.921875, "max": 76079.8203125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 100.08704453441295, "min": 88.98747763864043, "max": 413.8677685950413, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49443.0, "min": 48790.0, "max": 50124.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999973.0, "min": 49605.0, "max": 1999973.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999973.0, "min": 49605.0, "max": 1999973.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4089598655700684, "min": 0.027619827538728714, "max": 2.430450439453125, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1190.026123046875, "min": 3.3143792152404785, "max": 1331.3487548828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7000430348189735, "min": 1.8519162192940712, "max": 3.872819878094232, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1827.821259200573, "min": 222.22994631528854, "max": 2045.9207802414894, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7000430348189735, "min": 1.8519162192940712, "max": 3.872819878094232, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1827.821259200573, "min": 222.22994631528854, "max": 2045.9207802414894, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016787382893057333, "min": 0.013774820566807951, "max": 0.02176919259129338, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050362148679172, "min": 0.027549641133615903, "max": 0.06530757777388013, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053492317679855565, "min": 0.023601049246887364, "max": 0.0783799867456158, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1604769530395667, "min": 0.04720209849377473, "max": 0.18089022611578306, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1352489549500097e-06, "min": 3.1352489549500097e-06, "max": 0.00029532022655992486, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.405746864850029e-06, "min": 9.405746864850029e-06, "max": 0.0008439568686810499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10104505000000001, "min": 0.10104505000000001, "max": 0.19844007500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30313515, "min": 0.20731554999999996, "max": 0.5813189499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.214799500000016e-05, "min": 6.214799500000016e-05, "max": 0.0049221597425000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018644398500000046, "min": 0.00018644398500000046, "max": 0.014067815605, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1754326663", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754329087" }, "total": 2424.405482854, "count": 1, "self": 0.43550257999959285, "children": { "run_training.setup": { "total": 0.02313702700007525, "count": 1, "self": 0.02313702700007525 }, "TrainerController.start_learning": { "total": 2423.9468432470003, "count": 1, "self": 3.965223141075967, "children": { "TrainerController._reset_env": { "total": 3.603465468999957, "count": 1, "self": 3.603465468999957 }, "TrainerController.advance": { "total": 2416.2748165389244, "count": 231205, "self": 4.2875334608747835, "children": { "env_step": { "total": 1915.6521230220171, "count": 231205, "self": 1513.648666789946, "children": { "SubprocessEnvManager._take_step": { "total": 399.46815599603997, "count": 231205, "self": 15.372412338052982, "children": { "TorchPolicy.evaluate": { "total": 384.095743657987, "count": 222828, "self": 384.095743657987 } } }, "workers": { "total": 2.535300236031162, "count": 231205, "self": 0.0, "children": { "worker_root": { "total": 2416.8827195618264, "count": 231205, "is_parallel": true, "self": 1180.9933971538833, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009437280000383907, "count": 1, "is_parallel": true, "self": 0.0002443690000291099, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006993590000092809, "count": 2, "is_parallel": true, "self": 0.0006993590000092809 } } }, "UnityEnvironment.step": { "total": 0.03581223100013631, "count": 1, "is_parallel": true, "self": 0.0003459700003531907, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022161599986247893, "count": 1, "is_parallel": true, "self": 0.00022161599986247893 }, "communicator.exchange": { "total": 0.0345005179999589, "count": 1, "is_parallel": true, "self": 0.0345005179999589 }, "steps_from_proto": { "total": 0.0007441269999617361, "count": 1, "is_parallel": true, "self": 0.00022459299975707836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005195340002046578, "count": 2, "is_parallel": true, "self": 0.0005195340002046578 } } } } } } }, "UnityEnvironment.step": { "total": 1235.8893224079432, "count": 231204, "is_parallel": true, "self": 36.903373231694786, "children": { "UnityEnvironment._generate_step_input": { "total": 82.20928333803658, "count": 231204, "is_parallel": true, "self": 82.20928333803658 }, "communicator.exchange": { "total": 1029.3107863370672, "count": 231204, "is_parallel": true, "self": 1029.3107863370672 }, "steps_from_proto": { "total": 87.46587950114463, "count": 231204, "is_parallel": true, "self": 32.56181180115232, "children": { "_process_rank_one_or_two_observation": { "total": 54.90406769999231, "count": 462408, "is_parallel": true, "self": 54.90406769999231 } } } } } } } } } } }, "trainer_advance": { "total": 496.33516005603224, "count": 231205, "self": 6.138974599077073, "children": { "process_trajectory": { "total": 150.5488413839546, "count": 231205, "self": 149.3596100079542, "children": { "RLTrainer._checkpoint": { "total": 1.1892313760004072, "count": 10, "self": 1.1892313760004072 } } }, "_update_policy": { "total": 339.64734407300057, "count": 97, "self": 274.2409974470072, "children": { "TorchPPOOptimizer.update": { "total": 65.40634662599336, "count": 2910, "self": 65.40634662599336 } } } } } } }, "trainer_threads": { "total": 9.410000529896934e-07, "count": 1, "self": 9.410000529896934e-07 }, "TrainerController._save_models": { "total": 0.1033371570001691, "count": 1, "self": 0.0014958629999455297, "children": { "RLTrainer._checkpoint": { "total": 0.10184129400022357, "count": 1, "self": 0.10184129400022357 } } } } } } }