{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4098023176193237, "min": 1.4098023176193237, "max": 1.4306278228759766, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69793.671875, "min": 68521.5, "max": 79133.6640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 70.10099573257467, "min": 70.10099573257467, "max": 389.015503875969, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49281.0, "min": 48821.0, "max": 50183.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999974.0, "min": 49949.0, "max": 1999974.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999974.0, "min": 49949.0, "max": 1999974.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.473656177520752, "min": -0.005858226679265499, "max": 2.552219867706299, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1738.980224609375, "min": -0.7498530149459839, "max": 1761.12939453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8364405029189705, "min": 1.8410011361120269, "max": 4.072307378947735, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2697.0176735520363, "min": 235.64814542233944, "max": 2735.8067558407784, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8364405029189705, "min": 1.8410011361120269, "max": 4.072307378947735, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2697.0176735520363, "min": 235.64814542233944, "max": 2735.8067558407784, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017240568898786376, "min": 0.013589803357050793, "max": 0.02120847846559223, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05172170669635913, "min": 0.027179606714101585, "max": 0.06362543539677669, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0662620206260019, "min": 0.023223987439026435, "max": 0.06654761934445964, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.19878606187800568, "min": 0.04644797487805287, "max": 0.19964285803337892, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.067498644199999e-06, "min": 4.067498644199999e-06, "max": 0.00029537212654262503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2202495932599997e-05, "min": 1.2202495932599997e-05, "max": 0.0008443290185569998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10135580000000001, "min": 0.10135580000000001, "max": 0.19845737500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30406740000000004, "min": 0.20784404999999997, "max": 0.581443, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.765441999999996e-05, "min": 7.765441999999996e-05, "max": 0.0049230230125, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002329632599999999, "min": 0.0002329632599999999, "max": 0.0140740057, "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": "1686858434", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686860937" }, "total": 2503.108769642, "count": 1, "self": 0.44486373399968215, "children": { "run_training.setup": { "total": 0.041586243999972794, "count": 1, "self": 0.041586243999972794 }, "TrainerController.start_learning": { "total": 2502.6223196640003, "count": 1, "self": 4.467565290951825, "children": { "TrainerController._reset_env": { "total": 4.080567631000008, "count": 1, "self": 4.080567631000008 }, "TrainerController.advance": { "total": 2493.9507778200486, "count": 233369, "self": 4.597816325137956, "children": { "env_step": { "total": 1953.7463674599417, "count": 233369, "self": 1648.5553014938794, "children": { "SubprocessEnvManager._take_step": { "total": 302.2446588100238, "count": 233369, "self": 17.16948070693934, "children": { "TorchPolicy.evaluate": { "total": 285.07517810308445, "count": 222894, "self": 285.07517810308445 } } }, "workers": { "total": 2.9464071560385037, "count": 233369, "self": 0.0, "children": { "worker_root": { "total": 2494.5542519488786, "count": 233369, "is_parallel": true, "self": 1144.9184931798059, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009812769999371085, "count": 1, "is_parallel": true, "self": 0.0002682419998336627, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007130350001034458, "count": 2, "is_parallel": true, "self": 0.0007130350001034458 } } }, "UnityEnvironment.step": { "total": 0.03293311300001278, "count": 1, "is_parallel": true, "self": 0.00034585000003062305, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022980599999300466, "count": 1, "is_parallel": true, "self": 0.00022980599999300466 }, "communicator.exchange": { "total": 0.031544120999910774, "count": 1, "is_parallel": true, "self": 0.031544120999910774 }, "steps_from_proto": { "total": 0.0008133360000783796, "count": 1, "is_parallel": true, "self": 0.0002488980001089658, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005644379999694138, "count": 2, "is_parallel": true, "self": 0.0005644379999694138 } } } } } } }, "UnityEnvironment.step": { "total": 1349.6357587690727, "count": 233368, "is_parallel": true, "self": 39.62994314595744, "children": { "UnityEnvironment._generate_step_input": { "total": 82.66763108899079, "count": 233368, "is_parallel": true, "self": 82.66763108899079 }, "communicator.exchange": { "total": 1128.9221875280746, "count": 233368, "is_parallel": true, "self": 1128.9221875280746 }, "steps_from_proto": { "total": 98.41599700605002, "count": 233368, "is_parallel": true, "self": 37.152758793922885, "children": { "_process_rank_one_or_two_observation": { "total": 61.263238212127135, "count": 466736, "is_parallel": true, "self": 61.263238212127135 } } } } } } } } } } }, "trainer_advance": { "total": 535.6065940349691, "count": 233369, "self": 6.91377650599577, "children": { "process_trajectory": { "total": 147.20203239797138, "count": 233369, "self": 145.81191882097062, "children": { "RLTrainer._checkpoint": { "total": 1.3901135770007613, "count": 10, "self": 1.3901135770007613 } } }, "_update_policy": { "total": 381.490785131002, "count": 97, "self": 322.04087394300916, "children": { "TorchPPOOptimizer.update": { "total": 59.449911187992825, "count": 2910, "self": 59.449911187992825 } } } } } } }, "trainer_threads": { "total": 8.919996616896242e-07, "count": 1, "self": 8.919996616896242e-07 }, "TrainerController._save_models": { "total": 0.12340803000006417, "count": 1, "self": 0.0020269850001568557, "children": { "RLTrainer._checkpoint": { "total": 0.12138104499990732, "count": 1, "self": 0.12138104499990732 } } } } } } }