{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4043635129928589, "min": 1.4043635129928589, "max": 1.4294986724853516, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69361.515625, "min": 68625.515625, "max": 78146.6875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 101.25153374233129, "min": 89.0884476534296, "max": 396.3968253968254, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49512.0, "min": 49066.0, "max": 50098.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999972.0, "min": 49571.0, "max": 1999972.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999972.0, "min": 49571.0, "max": 1999972.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.392268180847168, "min": 0.047777943313121796, "max": 2.443894624710083, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1169.819091796875, "min": 5.972242832183838, "max": 1326.8739013671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6049658541542864, "min": 1.7745988183021546, "max": 3.8568554591650916, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1762.828302681446, "min": 221.82485228776932, "max": 2079.151320040226, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6049658541542864, "min": 1.7745988183021546, "max": 3.8568554591650916, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1762.828302681446, "min": 221.82485228776932, "max": 2079.151320040226, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.013942333716355886, "min": 0.012295889342446268, "max": 0.020648452193684837, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.02788466743271177, "min": 0.024591778684892537, "max": 0.05615773696918041, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0492437694221735, "min": 0.02357418021808068, "max": 0.06236474110434452, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.098487538844347, "min": 0.04714836043616136, "max": 0.1811325470606486, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.497173500974995e-06, "min": 4.497173500974995e-06, "max": 0.00029532360155880007, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.99434700194999e-06, "min": 8.99434700194999e-06, "max": 0.0008440809186396998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10149902500000002, "min": 0.10149902500000002, "max": 0.1984412, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20299805000000004, "min": 0.20299805000000004, "max": 0.5813603, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.480134749999994e-05, "min": 8.480134749999994e-05, "max": 0.004922215879999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016960269499999989, "min": 0.00016960269499999989, "max": 0.014069878969999996, "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": "1739347238", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739349736" }, "total": 2498.3418288969997, "count": 1, "self": 0.44184669599962945, "children": { "run_training.setup": { "total": 0.023277530999962437, "count": 1, "self": 0.023277530999962437 }, "TrainerController.start_learning": { "total": 2497.87670467, "count": 1, "self": 4.629744595122702, "children": { "TrainerController._reset_env": { "total": 2.861290026000006, "count": 1, "self": 2.861290026000006 }, "TrainerController.advance": { "total": 2490.2714341398773, "count": 231597, "self": 4.8616686908103475, "children": { "env_step": { "total": 2016.0284660070063, "count": 231597, "self": 1581.031328300697, "children": { "SubprocessEnvManager._take_step": { "total": 432.2371949691918, "count": 231597, "self": 15.82034177419564, "children": { "TorchPolicy.evaluate": { "total": 416.4168531949962, "count": 222984, "self": 416.4168531949962 } } }, "workers": { "total": 2.7599427371175125, "count": 231597, "self": 0.0, "children": { "worker_root": { "total": 2490.3633105219787, "count": 231597, "is_parallel": true, "self": 1201.2597011090713, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009081120000473675, "count": 1, "is_parallel": true, "self": 0.00023802099997283221, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006700910000745353, "count": 2, "is_parallel": true, "self": 0.0006700910000745353 } } }, "UnityEnvironment.step": { "total": 0.032905251999977736, "count": 1, "is_parallel": true, "self": 0.0002854249999018066, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001897270000199569, "count": 1, "is_parallel": true, "self": 0.0001897270000199569 }, "communicator.exchange": { "total": 0.030990765000069587, "count": 1, "is_parallel": true, "self": 0.030990765000069587 }, "steps_from_proto": { "total": 0.0014393349999863858, "count": 1, "is_parallel": true, "self": 0.0002423509998834561, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011969840001029297, "count": 2, "is_parallel": true, "self": 0.0011969840001029297 } } } } } } }, "UnityEnvironment.step": { "total": 1289.1036094129074, "count": 231596, "is_parallel": true, "self": 37.083233088056886, "children": { "UnityEnvironment._generate_step_input": { "total": 84.69702660707742, "count": 231596, "is_parallel": true, "self": 84.69702660707742 }, "communicator.exchange": { "total": 1079.5829837298581, "count": 231596, "is_parallel": true, "self": 1079.5829837298581 }, "steps_from_proto": { "total": 87.74036598791497, "count": 231596, "is_parallel": true, "self": 32.75631498588427, "children": { "_process_rank_one_or_two_observation": { "total": 54.9840510020307, "count": 463192, "is_parallel": true, "self": 54.9840510020307 } } } } } } } } } } }, "trainer_advance": { "total": 469.3812994420605, "count": 231597, "self": 6.7083586889268645, "children": { "process_trajectory": { "total": 164.88309148013536, "count": 231597, "self": 163.52634550313633, "children": { "RLTrainer._checkpoint": { "total": 1.3567459769990364, "count": 10, "self": 1.3567459769990364 } } }, "_update_policy": { "total": 297.78984927299825, "count": 96, "self": 235.3880721349982, "children": { "TorchPPOOptimizer.update": { "total": 62.40177713800006, "count": 2880, "self": 62.40177713800006 } } } } } } }, "trainer_threads": { "total": 8.699998943484388e-07, "count": 1, "self": 8.699998943484388e-07 }, "TrainerController._save_models": { "total": 0.11423503900005016, "count": 1, "self": 0.0018580910000309814, "children": { "RLTrainer._checkpoint": { "total": 0.11237694800001918, "count": 1, "self": 0.11237694800001918 } } } } } } }