{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404221534729004, "min": 1.404221534729004, "max": 1.42573881149292, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68045.765625, "min": 67881.9609375, "max": 77512.6015625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 94.34169884169884, "min": 75.95076923076923, "max": 406.258064516129, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48869.0, "min": 48869.0, "max": 50376.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999381.0, "min": 49871.0, "max": 1999381.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999381.0, "min": 49871.0, "max": 1999381.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.428128242492676, "min": 0.051901113241910934, "max": 2.4836175441741943, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1257.7703857421875, "min": 6.38383674621582, "max": 1562.49267578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6464695357447887, "min": 1.759237577275532, "max": 4.08350232919725, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1888.8712195158005, "min": 216.38622200489044, "max": 2488.009931087494, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6464695357447887, "min": 1.759237577275532, "max": 4.08350232919725, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1888.8712195158005, "min": 216.38622200489044, "max": 2488.009931087494, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016410386920647904, "min": 0.013679241765930782, "max": 0.019249920827981742, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04923116076194371, "min": 0.027358483531861565, "max": 0.05553369051000724, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051503350916836, "min": 0.023184952822824317, "max": 0.05842626721908649, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.154510052750508, "min": 0.046369905645648635, "max": 0.16728331993023554, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5703988099000042e-06, "min": 3.5703988099000042e-06, "max": 0.00029527260157579993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0711196429700013e-05, "min": 1.0711196429700013e-05, "max": 0.0008439411186862999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119009999999999, "min": 0.10119009999999999, "max": 0.19842419999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30357029999999996, "min": 0.20754520000000004, "max": 0.5813137, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.938599000000008e-05, "min": 6.938599000000008e-05, "max": 0.0049213675800000006, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020815797000000024, "min": 0.00020815797000000024, "max": 0.014067553630000002, "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": "1711286081", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/geekayman/.local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711286904" }, "total": 823.4359193570008, "count": 1, "self": 0.1669054980011424, "children": { "run_training.setup": { "total": 0.01961477199984074, "count": 1, "self": 0.01961477199984074 }, "TrainerController.start_learning": { "total": 823.2493990869998, "count": 1, "self": 2.0079502869557473, "children": { "TrainerController._reset_env": { "total": 1.1525368809998326, "count": 1, "self": 1.1525368809998326 }, "TrainerController.advance": { "total": 820.0315606810445, "count": 233118, "self": 2.0102265832292687, "children": { "env_step": { "total": 631.9284917187197, "count": 233118, "self": 509.8481061853581, "children": { "SubprocessEnvManager._take_step": { "total": 120.75648294302937, "count": 233118, "self": 7.397896769931322, "children": { "TorchPolicy.evaluate": { "total": 113.35858617309805, "count": 222982, "self": 113.35858617309805 } } }, "workers": { "total": 1.3239025903321817, "count": 233118, "self": 0.0, "children": { "worker_root": { "total": 820.6461755527371, "count": 233118, "is_parallel": true, "self": 428.3389208754061, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0003519870006130077, "count": 1, "is_parallel": true, "self": 7.950100007292349e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0002724860005400842, "count": 2, "is_parallel": true, "self": 0.0002724860005400842 } } }, "UnityEnvironment.step": { "total": 0.010617881999678502, "count": 1, "is_parallel": true, "self": 0.00010509199910302414, "children": { "UnityEnvironment._generate_step_input": { "total": 8.100800005195197e-05, "count": 1, "is_parallel": true, "self": 8.100800005195197e-05 }, "communicator.exchange": { "total": 0.01022629599992797, "count": 1, "is_parallel": true, "self": 0.01022629599992797 }, "steps_from_proto": { "total": 0.0002054860005955561, "count": 1, "is_parallel": true, "self": 5.486800000653602e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00015061800058902008, "count": 2, "is_parallel": true, "self": 0.00015061800058902008 } } } } } } }, "UnityEnvironment.step": { "total": 392.307254677331, "count": 233117, "is_parallel": true, "self": 11.996925096936138, "children": { "UnityEnvironment._generate_step_input": { "total": 21.02018417409454, "count": 233117, "is_parallel": true, "self": 21.02018417409454 }, "communicator.exchange": { "total": 332.0746694530462, "count": 233117, "is_parallel": true, "self": 332.0746694530462 }, "steps_from_proto": { "total": 27.2154759532541, "count": 233117, "is_parallel": true, "self": 9.405008086492671, "children": { "_process_rank_one_or_two_observation": { "total": 17.810467866761428, "count": 466234, "is_parallel": true, "self": 17.810467866761428 } } } } } } } } } } }, "trainer_advance": { "total": 186.0928423790956, "count": 233118, "self": 2.8273340071818893, "children": { "process_trajectory": { "total": 61.67051135391739, "count": 233118, "self": 61.124389775917734, "children": { "RLTrainer._checkpoint": { "total": 0.5461215779996564, "count": 10, "self": 0.5461215779996564 } } }, "_update_policy": { "total": 121.59499701799632, "count": 97, "self": 99.63926860499214, "children": { "TorchPPOOptimizer.update": { "total": 21.95572841300418, "count": 2910, "self": 21.95572841300418 } } } } } } }, "trainer_threads": { "total": 6.450000000768341e-07, "count": 1, "self": 6.450000000768341e-07 }, "TrainerController._save_models": { "total": 0.057350592999682704, "count": 1, "self": 0.0008189109994418686, "children": { "RLTrainer._checkpoint": { "total": 0.056531682000240835, "count": 1, "self": 0.056531682000240835 } } } } } } }