{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4077935218811035, "min": 1.4077935218811035, "max": 1.4278348684310913, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71203.3828125, "min": 69012.1796875, "max": 76776.71875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.31799163179916, "min": 90.66173752310536, "max": 430.75, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49386.0, "min": 48836.0, "max": 50179.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999964.0, "min": 49982.0, "max": 1999964.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999964.0, "min": 49982.0, "max": 1999964.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3791146278381348, "min": 0.0716727152466774, "max": 2.488510847091675, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1137.216796875, "min": 8.242362022399902, "max": 1314.04638671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6656262944432982, "min": 2.0668595902297806, "max": 3.9070236591928933, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1752.1693687438965, "min": 237.6888528764248, "max": 2083.975254178047, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6656262944432982, "min": 2.0668595902297806, "max": 3.9070236591928933, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1752.1693687438965, "min": 237.6888528764248, "max": 2083.975254178047, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016243521546089646, "min": 0.01414796813041903, "max": 0.019764423634236056, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04873056463826894, "min": 0.02829593626083806, "max": 0.05929327090270817, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04890514906081889, "min": 0.020427170923600593, "max": 0.05645419669648011, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14671544718245666, "min": 0.04085434184720119, "max": 0.16936259008944032, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.291898902733333e-06, "min": 3.291898902733333e-06, "max": 0.00029532397655867497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.875696708199999e-06, "min": 9.875696708199999e-06, "max": 0.0008441821686059499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109726666666669, "min": 0.10109726666666669, "max": 0.19844132500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30329180000000006, "min": 0.20733945000000004, "max": 0.5813940500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.475360666666669e-05, "min": 6.475360666666669e-05, "max": 0.0049222221175, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019426082000000006, "min": 0.00019426082000000006, "max": 0.014071563095, "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": "1715689120", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/sriveran/.local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy.x86_64 --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715692070" }, "total": 2950.2655096299995, "count": 1, "self": 0.32237885699942126, "children": { "run_training.setup": { "total": 0.021582869000667415, "count": 1, "self": 0.021582869000667415 }, "TrainerController.start_learning": { "total": 2949.9215479039995, "count": 1, "self": 4.93302473820313, "children": { "TrainerController._reset_env": { "total": 1.497557267999582, "count": 1, "self": 1.497557267999582 }, "TrainerController.advance": { "total": 2943.4127207917963, "count": 231837, "self": 5.041166761115164, "children": { "env_step": { "total": 2223.3692751688777, "count": 231837, "self": 1928.1065345679044, "children": { "SubprocessEnvManager._take_step": { "total": 291.5571291733622, "count": 231837, "self": 19.157622618407004, "children": { "TorchPolicy.evaluate": { "total": 272.3995065549552, "count": 223018, "self": 272.3995065549552 } } }, "workers": { "total": 3.7056114276110748, "count": 231837, "self": 0.0, "children": { "worker_root": { "total": 2934.193628595127, "count": 231837, "is_parallel": true, "self": 1322.9660912658064, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007231850004245644, "count": 1, "is_parallel": true, "self": 0.00018057800116366707, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005426069992608973, "count": 2, "is_parallel": true, "self": 0.0005426069992608973 } } }, "UnityEnvironment.step": { "total": 0.015190312999948219, "count": 1, "is_parallel": true, "self": 0.00018281899974681437, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002711970000746078, "count": 1, "is_parallel": true, "self": 0.0002711970000746078 }, "communicator.exchange": { "total": 0.014400889999706123, "count": 1, "is_parallel": true, "self": 0.014400889999706123 }, "steps_from_proto": { "total": 0.0003354070004206733, "count": 1, "is_parallel": true, "self": 0.0001444020008420921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001910049995785812, "count": 2, "is_parallel": true, "self": 0.0001910049995785812 } } } } } } }, "UnityEnvironment.step": { "total": 1611.2275373293205, "count": 231836, "is_parallel": true, "self": 33.46759520860542, "children": { "UnityEnvironment._generate_step_input": { "total": 57.543769991947556, "count": 231836, "is_parallel": true, "self": 57.543769991947556 }, "communicator.exchange": { "total": 1443.818963295278, "count": 231836, "is_parallel": true, "self": 1443.818963295278 }, "steps_from_proto": { "total": 76.39720883348946, "count": 231836, "is_parallel": true, "self": 26.73576190384847, "children": { "_process_rank_one_or_two_observation": { "total": 49.66144692964099, "count": 463672, "is_parallel": true, "self": 49.66144692964099 } } } } } } } } } } }, "trainer_advance": { "total": 715.0022788618035, "count": 231837, "self": 7.711219284919025, "children": { "process_trajectory": { "total": 122.32690083689249, "count": 231837, "self": 121.61152799489355, "children": { "RLTrainer._checkpoint": { "total": 0.715372841998942, "count": 10, "self": 0.715372841998942 } } }, "_update_policy": { "total": 584.964158739992, "count": 97, "self": 137.14350422993357, "children": { "TorchPPOOptimizer.update": { "total": 447.8206545100584, "count": 2910, "self": 447.8206545100584 } } } } } } }, "trainer_threads": { "total": 6.970003596507013e-07, "count": 1, "self": 6.970003596507013e-07 }, "TrainerController._save_models": { "total": 0.07824440900003538, "count": 1, "self": 0.0017001930009428179, "children": { "RLTrainer._checkpoint": { "total": 0.07654421599909256, "count": 1, "self": 0.07654421599909256 } } } } } } }