{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4014904499053955, "min": 1.4014904499053955, "max": 1.4277653694152832, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70734.625, "min": 68627.984375, "max": 77093.34375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.98203592814372, "min": 86.84035087719299, "max": 421.99159663865544, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49590.0, "min": 48852.0, "max": 50242.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999345.0, "min": 49989.0, "max": 1999345.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999345.0, "min": 49989.0, "max": 1999345.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3980538845062256, "min": -0.00964298564940691, "max": 2.4573490619659424, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1201.425048828125, "min": -1.137872338294983, "max": 1365.904052734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.667439023653666, "min": 1.8024333730592565, "max": 3.8627371399038766, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1837.3869508504868, "min": 212.68713802099228, "max": 2136.50817579031, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.667439023653666, "min": 1.8024333730592565, "max": 3.8627371399038766, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1837.3869508504868, "min": 212.68713802099228, "max": 2136.50817579031, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01702958438092739, "min": 0.013229516060528112, "max": 0.019577306915824818, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051088753142782176, "min": 0.026459032121056224, "max": 0.05873192074747445, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052959732214609784, "min": 0.023544111972053847, "max": 0.06145080729491181, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15887919664382935, "min": 0.04708822394410769, "max": 0.18435242188473544, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.198848933750006e-06, "min": 3.198848933750006e-06, "max": 0.00029536830154390005, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.596546801250018e-06, "min": 9.596546801250018e-06, "max": 0.0008442454685848499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10106625000000001, "min": 0.10106625000000001, "max": 0.19845610000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30319875, "min": 0.20727210000000007, "max": 0.58141515, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.320587500000011e-05, "min": 6.320587500000011e-05, "max": 0.004922959390000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018961762500000032, "min": 0.00018961762500000032, "max": 0.014072615985000002, "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": "1671402480", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671404712" }, "total": 2232.062187505, "count": 1, "self": 0.39568528300014805, "children": { "run_training.setup": { "total": 0.10420680400000037, "count": 1, "self": 0.10420680400000037 }, "TrainerController.start_learning": { "total": 2231.562295418, "count": 1, "self": 3.8880631450515466, "children": { "TrainerController._reset_env": { "total": 7.667768556999988, "count": 1, "self": 7.667768556999988 }, "TrainerController.advance": { "total": 2219.8912739879484, "count": 231454, "self": 4.288404419078233, "children": { "env_step": { "total": 1758.8313431089316, "count": 231454, "self": 1479.7118371128806, "children": { "SubprocessEnvManager._take_step": { "total": 276.50134769399483, "count": 231454, "self": 14.56048641192433, "children": { "TorchPolicy.evaluate": { "total": 261.9408612820705, "count": 223019, "self": 64.62168202613628, "children": { "TorchPolicy.sample_actions": { "total": 197.31917925593422, "count": 223019, "self": 197.31917925593422 } } } } }, "workers": { "total": 2.618158302056088, "count": 231454, "self": 0.0, "children": { "worker_root": { "total": 2223.5987440729673, "count": 231454, "is_parallel": true, "self": 1007.2494400479313, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002212584999995215, "count": 1, "is_parallel": true, "self": 0.00033678500000178246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018757999999934327, "count": 2, "is_parallel": true, "self": 0.0018757999999934327 } } }, "UnityEnvironment.step": { "total": 0.027545636000013474, "count": 1, "is_parallel": true, "self": 0.00028993400007948367, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018909199997096948, "count": 1, "is_parallel": true, "self": 0.00018909199997096948 }, "communicator.exchange": { "total": 0.02635741199998165, "count": 1, "is_parallel": true, "self": 0.02635741199998165 }, "steps_from_proto": { "total": 0.0007091979999813702, "count": 1, "is_parallel": true, "self": 0.0002427570000236301, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046644099995774013, "count": 2, "is_parallel": true, "self": 0.00046644099995774013 } } } } } } }, "UnityEnvironment.step": { "total": 1216.349304025036, "count": 231453, "is_parallel": true, "self": 34.66733568118798, "children": { "UnityEnvironment._generate_step_input": { "total": 80.02373798796339, "count": 231453, "is_parallel": true, "self": 80.02373798796339 }, "communicator.exchange": { "total": 1006.9203259629376, "count": 231453, "is_parallel": true, "self": 1006.9203259629376 }, "steps_from_proto": { "total": 94.73790439294703, "count": 231453, "is_parallel": true, "self": 41.28127723794984, "children": { "_process_rank_one_or_two_observation": { "total": 53.45662715499719, "count": 462906, "is_parallel": true, "self": 53.45662715499719 } } } } } } } } } } }, "trainer_advance": { "total": 456.7715264599387, "count": 231454, "self": 6.0082554900058085, "children": { "process_trajectory": { "total": 145.4992006439332, "count": 231454, "self": 144.32953474493326, "children": { "RLTrainer._checkpoint": { "total": 1.1696658989999378, "count": 10, "self": 1.1696658989999378 } } }, "_update_policy": { "total": 305.2640703259997, "count": 97, "self": 253.38502445000745, "children": { "TorchPPOOptimizer.update": { "total": 51.87904587599223, "count": 2910, "self": 51.87904587599223 } } } } } } }, "trainer_threads": { "total": 8.289998731925152e-07, "count": 1, "self": 8.289998731925152e-07 }, "TrainerController._save_models": { "total": 0.11518889900025897, "count": 1, "self": 0.0019509270005073631, "children": { "RLTrainer._checkpoint": { "total": 0.11323797199975161, "count": 1, "self": 0.11323797199975161 } } } } } } }