{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4060310125350952, "min": 1.4060310125350952, "max": 1.4262311458587646, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71714.609375, "min": 68008.671875, "max": 79639.9765625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 116.6745283018868, "min": 109.88026607538802, "max": 411.08196721311475, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49470.0, "min": 49135.0, "max": 50237.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999853.0, "min": 49678.0, "max": 1999853.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999853.0, "min": 49678.0, "max": 1999853.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.25569748878479, "min": 0.022327380254864693, "max": 2.3069632053375244, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 956.4157104492188, "min": 2.701612949371338, "max": 1040.214599609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5252030004026755, "min": 2.085416222899413, "max": 3.8160845510602934, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1494.6860721707344, "min": 252.335362970829, "max": 1644.716913163662, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5252030004026755, "min": 2.085416222899413, "max": 3.8160845510602934, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1494.6860721707344, "min": 252.335362970829, "max": 1644.716913163662, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018991019599585948, "min": 0.014110280979366507, "max": 0.01970236163663988, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.037982039199171896, "min": 0.028220561958733015, "max": 0.05841422905990233, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04425876289606094, "min": 0.023147996049374342, "max": 0.05762015080286397, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08851752579212188, "min": 0.046295992098748684, "max": 0.1728604524085919, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.458098513999995e-06, "min": 4.458098513999995e-06, "max": 0.00029534460155180003, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.91619702799999e-06, "min": 8.91619702799999e-06, "max": 0.00084396796867735, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10148599999999999, "min": 0.10148599999999999, "max": 0.19844820000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20297199999999999, "min": 0.20297199999999999, "max": 0.5813226500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.415139999999995e-05, "min": 8.415139999999995e-05, "max": 0.004922565179999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001683027999999999, "min": 0.0001683027999999999, "max": 0.014068000235, "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": "1733237056", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1733239688" }, "total": 2632.750893676, "count": 1, "self": 0.6378497380001136, "children": { "run_training.setup": { "total": 0.06180454700000837, "count": 1, "self": 0.06180454700000837 }, "TrainerController.start_learning": { "total": 2632.051239391, "count": 1, "self": 5.019401329051561, "children": { "TrainerController._reset_env": { "total": 5.941085794999992, "count": 1, "self": 5.941085794999992 }, "TrainerController.advance": { "total": 2620.8981417209484, "count": 230216, "self": 5.27325266699745, "children": { "env_step": { "total": 2099.7746296690543, "count": 230216, "self": 1648.360404667055, "children": { "SubprocessEnvManager._take_step": { "total": 448.2674117549953, "count": 230216, "self": 17.177927852035907, "children": { "TorchPolicy.evaluate": { "total": 431.0894839029594, "count": 223060, "self": 431.0894839029594 } } }, "workers": { "total": 3.1468132470040473, "count": 230216, "self": 0.0, "children": { "worker_root": { "total": 2623.7278003160277, "count": 230216, "is_parallel": true, "self": 1290.392284786041, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008316580000382601, "count": 1, "is_parallel": true, "self": 0.00023459900006628231, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005970589999719778, "count": 2, "is_parallel": true, "self": 0.0005970589999719778 } } }, "UnityEnvironment.step": { "total": 0.03061934600003724, "count": 1, "is_parallel": true, "self": 0.00039645700002211015, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001986560000091231, "count": 1, "is_parallel": true, "self": 0.0001986560000091231 }, "communicator.exchange": { "total": 0.029246960000023137, "count": 1, "is_parallel": true, "self": 0.029246960000023137 }, "steps_from_proto": { "total": 0.0007772729999828698, "count": 1, "is_parallel": true, "self": 0.00022836099992673553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005489120000561343, "count": 2, "is_parallel": true, "self": 0.0005489120000561343 } } } } } } }, "UnityEnvironment.step": { "total": 1333.3355155299867, "count": 230215, "is_parallel": true, "self": 39.52450667303265, "children": { "UnityEnvironment._generate_step_input": { "total": 88.56490875503454, "count": 230215, "is_parallel": true, "self": 88.56490875503454 }, "communicator.exchange": { "total": 1111.2023186289264, "count": 230215, "is_parallel": true, "self": 1111.2023186289264 }, "steps_from_proto": { "total": 94.04378147299303, "count": 230215, "is_parallel": true, "self": 35.085199449996196, "children": { "_process_rank_one_or_two_observation": { "total": 58.958582022996836, "count": 460430, "is_parallel": true, "self": 58.958582022996836 } } } } } } } } } } }, "trainer_advance": { "total": 515.8502593848966, "count": 230216, "self": 7.420442946894013, "children": { "process_trajectory": { "total": 165.95612243000102, "count": 230216, "self": 164.5848120090016, "children": { "RLTrainer._checkpoint": { "total": 1.3713104209994071, "count": 10, "self": 1.3713104209994071 } } }, "_update_policy": { "total": 342.4736940080016, "count": 96, "self": 275.09782007999854, "children": { "TorchPPOOptimizer.update": { "total": 67.37587392800305, "count": 2880, "self": 67.37587392800305 } } } } } } }, "trainer_threads": { "total": 1.4009997357788961e-06, "count": 1, "self": 1.4009997357788961e-06 }, "TrainerController._save_models": { "total": 0.1926091450000058, "count": 1, "self": 0.002951785999812273, "children": { "RLTrainer._checkpoint": { "total": 0.18965735900019354, "count": 1, "self": 0.18965735900019354 } } } } } } }