{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4079071283340454, "min": 1.4079071283340454, "max": 1.429749608039856, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 67057.2109375, "min": 66857.625, "max": 78390.296875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 116.20140515222482, "min": 98.898, "max": 378.6136363636364, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49618.0, "min": 48938.0, "max": 50293.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999943.0, "min": 49313.0, "max": 1999943.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999943.0, "min": 49313.0, "max": 1999943.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.368238687515259, "min": -0.013502189889550209, "max": 2.4107162952423096, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1011.2379150390625, "min": -1.768786907196045, "max": 1178.707763671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5493644817930754, "min": 1.808668750160523, "max": 3.8401853694220174, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1515.5786337256432, "min": 236.93560627102852, "max": 1858.9464794397354, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5493644817930754, "min": 1.808668750160523, "max": 3.8401853694220174, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1515.5786337256432, "min": 236.93560627102852, "max": 1858.9464794397354, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018210697547571424, "min": 0.013036945934193984, "max": 0.02128366953305279, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03642139509514285, "min": 0.026073891868387968, "max": 0.0554343343571721, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04995003895213207, "min": 0.023105983932813007, "max": 0.06661625558303462, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09990007790426414, "min": 0.047898115279773876, "max": 0.19984876674910387, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.4985235005250015e-06, "min": 4.4985235005250015e-06, "max": 0.000295268776577075, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.997047001050003e-06, "min": 8.997047001050003e-06, "max": 0.00084346246884585, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101499475, "min": 0.101499475, "max": 0.19842292499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20299895, "min": 0.20299895, "max": 0.5811541500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.48238025e-05, "min": 8.48238025e-05, "max": 0.0049213039574999996, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000169647605, "min": 0.000169647605, "max": 0.014059592085, "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": "1698764077", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698766563" }, "total": 2485.564365162, "count": 1, "self": 0.4426695099996323, "children": { "run_training.setup": { "total": 0.04361671500009834, "count": 1, "self": 0.04361671500009834 }, "TrainerController.start_learning": { "total": 2485.078078937, "count": 1, "self": 4.784247330053859, "children": { "TrainerController._reset_env": { "total": 8.472018083999956, "count": 1, "self": 8.472018083999956 }, "TrainerController.advance": { "total": 2471.7213132189468, "count": 231013, "self": 4.986857781884737, "children": { "env_step": { "total": 1973.6201881140112, "count": 231013, "self": 1619.177184427913, "children": { "SubprocessEnvManager._take_step": { "total": 351.5425437300438, "count": 231013, "self": 17.016887907065325, "children": { "TorchPolicy.evaluate": { "total": 334.5256558229785, "count": 222889, "self": 334.5256558229785 } } }, "workers": { "total": 2.9004599560543056, "count": 231013, "self": 0.0, "children": { "worker_root": { "total": 2477.409752131052, "count": 231013, "is_parallel": true, "self": 1160.6409108140788, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008711200000561803, "count": 1, "is_parallel": true, "self": 0.00023767700008647807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006334429999697022, "count": 2, "is_parallel": true, "self": 0.0006334429999697022 } } }, "UnityEnvironment.step": { "total": 0.029420970999922247, "count": 1, "is_parallel": true, "self": 0.0002910150000161593, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001983129999416633, "count": 1, "is_parallel": true, "self": 0.0001983129999416633 }, "communicator.exchange": { "total": 0.028238617000056365, "count": 1, "is_parallel": true, "self": 0.028238617000056365 }, "steps_from_proto": { "total": 0.000693025999908059, "count": 1, "is_parallel": true, "self": 0.000176543999941714, "children": { "_process_rank_one_or_two_observation": { "total": 0.000516481999966345, "count": 2, "is_parallel": true, "self": 0.000516481999966345 } } } } } } }, "UnityEnvironment.step": { "total": 1316.768841316973, "count": 231012, "is_parallel": true, "self": 40.88165255588069, "children": { "UnityEnvironment._generate_step_input": { "total": 89.26611786402054, "count": 231012, "is_parallel": true, "self": 89.26611786402054 }, "communicator.exchange": { "total": 1094.510227517097, "count": 231012, "is_parallel": true, "self": 1094.510227517097 }, "steps_from_proto": { "total": 92.11084337997477, "count": 231012, "is_parallel": true, "self": 34.56967945704332, "children": { "_process_rank_one_or_two_observation": { "total": 57.541163922931446, "count": 462024, "is_parallel": true, "self": 57.541163922931446 } } } } } } } } } } }, "trainer_advance": { "total": 493.1142673230506, "count": 231013, "self": 6.907473783962814, "children": { "process_trajectory": { "total": 149.66864958408678, "count": 231013, "self": 148.46411389508637, "children": { "RLTrainer._checkpoint": { "total": 1.2045356890004086, "count": 10, "self": 1.2045356890004086 } } }, "_update_policy": { "total": 336.53814395500103, "count": 96, "self": 274.4874258610091, "children": { "TorchPPOOptimizer.update": { "total": 62.05071809399192, "count": 2880, "self": 62.05071809399192 } } } } } } }, "trainer_threads": { "total": 1.1269999049545731e-06, "count": 1, "self": 1.1269999049545731e-06 }, "TrainerController._save_models": { "total": 0.10049917699961952, "count": 1, "self": 0.001858933999301371, "children": { "RLTrainer._checkpoint": { "total": 0.09864024300031815, "count": 1, "self": 0.09864024300031815 } } } } } } }