{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3985103368759155, "min": 1.3985103368759155, "max": 1.4250669479370117, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70557.640625, "min": 66821.171875, "max": 76534.1875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.42495126705653, "min": 94.96353166986565, "max": 393.921875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49466.0, "min": 48852.0, "max": 50422.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999924.0, "min": 49974.0, "max": 1999924.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999924.0, "min": 49974.0, "max": 1999924.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.338472604751587, "min": -0.08609951287508011, "max": 2.402088165283203, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1199.636474609375, "min": -10.934638023376465, "max": 1224.5780029296875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5628491670299924, "min": 1.6621279321669593, "max": 3.788732764793902, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1827.741622686386, "min": 211.09024738520384, "max": 1904.0761551856995, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5628491670299924, "min": 1.6621279321669593, "max": 3.788732764793902, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1827.741622686386, "min": 211.09024738520384, "max": 1904.0761551856995, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015037462744415581, "min": 0.0143752336306837, "max": 0.0206442303257063, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.045112388233246745, "min": 0.0287504672613674, "max": 0.05868993570426634, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05703667878276772, "min": 0.026007442673047384, "max": 0.06046217121183872, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17111003634830316, "min": 0.05201488534609477, "max": 0.17111003634830316, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1656489448166735e-06, "min": 3.1656489448166735e-06, "max": 0.0002953395765534749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.49694683445002e-06, "min": 9.49694683445002e-06, "max": 0.0008441889186037001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105518333333335, "min": 0.10105518333333335, "max": 0.19844652500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30316555000000006, "min": 0.2072692, "max": 0.5813963, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.265364833333344e-05, "min": 6.265364833333344e-05, "max": 0.0049224815975, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018796094500000033, "min": 0.00018796094500000033, "max": 0.01407167537, "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": "1701078800", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701081281" }, "total": 2481.9621794739996, "count": 1, "self": 0.4520289449997108, "children": { "run_training.setup": { "total": 0.05780383299997993, "count": 1, "self": 0.05780383299997993 }, "TrainerController.start_learning": { "total": 2481.452346696, "count": 1, "self": 4.600083497960441, "children": { "TrainerController._reset_env": { "total": 3.57930366100004, "count": 1, "self": 3.57930366100004 }, "TrainerController.advance": { "total": 2473.1680338750393, "count": 230943, "self": 5.049627047960712, "children": { "env_step": { "total": 1940.7874745331287, "count": 230943, "self": 1595.1794623630853, "children": { "SubprocessEnvManager._take_step": { "total": 342.6497728890429, "count": 230943, "self": 18.052250959020512, "children": { "TorchPolicy.evaluate": { "total": 324.59752193002237, "count": 222934, "self": 324.59752193002237 } } }, "workers": { "total": 2.9582392810004876, "count": 230943, "self": 0.0, "children": { "worker_root": { "total": 2473.8038411310044, "count": 230943, "is_parallel": true, "self": 1185.917183660199, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008671000000504137, "count": 1, "is_parallel": true, "self": 0.00023444399994332343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006326560001070902, "count": 2, "is_parallel": true, "self": 0.0006326560001070902 } } }, "UnityEnvironment.step": { "total": 0.07433612199997697, "count": 1, "is_parallel": true, "self": 0.0003422030004003318, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019423199978518824, "count": 1, "is_parallel": true, "self": 0.00019423199978518824 }, "communicator.exchange": { "total": 0.07307702399998561, "count": 1, "is_parallel": true, "self": 0.07307702399998561 }, "steps_from_proto": { "total": 0.0007226629998058343, "count": 1, "is_parallel": true, "self": 0.0002250049999474868, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004976579998583475, "count": 2, "is_parallel": true, "self": 0.0004976579998583475 } } } } } } }, "UnityEnvironment.step": { "total": 1287.8866574708054, "count": 230942, "is_parallel": true, "self": 40.19474672174897, "children": { "UnityEnvironment._generate_step_input": { "total": 80.92856169199786, "count": 230942, "is_parallel": true, "self": 80.92856169199786 }, "communicator.exchange": { "total": 1078.6186263060074, "count": 230942, "is_parallel": true, "self": 1078.6186263060074 }, "steps_from_proto": { "total": 88.14472275105118, "count": 230942, "is_parallel": true, "self": 30.882735699999103, "children": { "_process_rank_one_or_two_observation": { "total": 57.261987051052074, "count": 461884, "is_parallel": true, "self": 57.261987051052074 } } } } } } } } } } }, "trainer_advance": { "total": 527.3309322939499, "count": 230943, "self": 6.9920849599884605, "children": { "process_trajectory": { "total": 151.48820026096337, "count": 230943, "self": 150.3465088259643, "children": { "RLTrainer._checkpoint": { "total": 1.1416914349990748, "count": 10, "self": 1.1416914349990748 } } }, "_update_policy": { "total": 368.8506470729981, "count": 97, "self": 301.9142974560152, "children": { "TorchPPOOptimizer.update": { "total": 66.93634961698285, "count": 2910, "self": 66.93634961698285 } } } } } } }, "trainer_threads": { "total": 9.469999895372894e-07, "count": 1, "self": 9.469999895372894e-07 }, "TrainerController._save_models": { "total": 0.10492471499992462, "count": 1, "self": 0.001820091999888973, "children": { "RLTrainer._checkpoint": { "total": 0.10310462300003564, "count": 1, "self": 0.10310462300003564 } } } } } } }