{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408137321472168, "min": 1.408137321472168, "max": 1.4295752048492432, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70350.5390625, "min": 68877.328125, "max": 76727.71875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.81494057724957, "min": 71.83724340175954, "max": 400.472, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49367.0, "min": 48993.0, "max": 50059.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999971.0, "min": 49881.0, "max": 1999971.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999971.0, "min": 49881.0, "max": 1999971.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.403064250946045, "min": -0.019353901967406273, "max": 2.4954190254211426, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1415.40478515625, "min": -2.39988374710083, "max": 1592.282470703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7316750276878046, "min": 1.7479259061717218, "max": 4.0719201813972115, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2197.956591308117, "min": 216.7428123652935, "max": 2507.6027538776398, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7316750276878046, "min": 1.7479259061717218, "max": 4.0719201813972115, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2197.956591308117, "min": 216.7428123652935, "max": 2507.6027538776398, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017152272209407075, "min": 0.012076169943611603, "max": 0.018925777765495394, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05145681662822123, "min": 0.024152339887223206, "max": 0.055317564110494766, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05575602360897594, "min": 0.023328392797460157, "max": 0.06379072678585848, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16726807082692782, "min": 0.046656785594920314, "max": 0.18424709724883237, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8032487322833334e-06, "min": 3.8032487322833334e-06, "max": 0.00029529517656827497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.140974619685e-05, "min": 1.140974619685e-05, "max": 0.0008442346685884501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126771666666667, "min": 0.10126771666666667, "max": 0.19843172499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30380315, "min": 0.20767510000000008, "max": 0.5814115500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.325906166666667e-05, "min": 7.325906166666667e-05, "max": 0.0049217430775, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000219777185, "min": 0.000219777185, "max": 0.014072436345000001, "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": "1686833798", "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": "1686836327" }, "total": 2528.6885320389997, "count": 1, "self": 0.43932517299981555, "children": { "run_training.setup": { "total": 0.0407373720004216, "count": 1, "self": 0.0407373720004216 }, "TrainerController.start_learning": { "total": 2528.2084694939995, "count": 1, "self": 4.51528107106833, "children": { "TrainerController._reset_env": { "total": 4.05762217199981, "count": 1, "self": 4.05762217199981 }, "TrainerController.advance": { "total": 2519.5216569309314, "count": 232659, "self": 4.700557149735232, "children": { "env_step": { "total": 1962.707438018122, "count": 232659, "self": 1651.6582173840256, "children": { "SubprocessEnvManager._take_step": { "total": 308.0769422880762, "count": 232659, "self": 17.784664236065055, "children": { "TorchPolicy.evaluate": { "total": 290.29227805201117, "count": 222960, "self": 290.29227805201117 } } }, "workers": { "total": 2.9722783460201754, "count": 232659, "self": 0.0, "children": { "worker_root": { "total": 2520.2311659110446, "count": 232659, "is_parallel": true, "self": 1174.434537297967, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009922490003191342, "count": 1, "is_parallel": true, "self": 0.00026402999992569676, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007282190003934375, "count": 2, "is_parallel": true, "self": 0.0007282190003934375 } } }, "UnityEnvironment.step": { "total": 0.03251892299977044, "count": 1, "is_parallel": true, "self": 0.0002991559995280113, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002281410002069606, "count": 1, "is_parallel": true, "self": 0.0002281410002069606 }, "communicator.exchange": { "total": 0.03124974899992594, "count": 1, "is_parallel": true, "self": 0.03124974899992594 }, "steps_from_proto": { "total": 0.0007418770001095254, "count": 1, "is_parallel": true, "self": 0.00024305500028276583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004988219998267596, "count": 2, "is_parallel": true, "self": 0.0004988219998267596 } } } } } } }, "UnityEnvironment.step": { "total": 1345.7966286130777, "count": 232658, "is_parallel": true, "self": 39.64518769221468, "children": { "UnityEnvironment._generate_step_input": { "total": 83.62367336595116, "count": 232658, "is_parallel": true, "self": 83.62367336595116 }, "communicator.exchange": { "total": 1124.9909477809788, "count": 232658, "is_parallel": true, "self": 1124.9909477809788 }, "steps_from_proto": { "total": 97.53681977393308, "count": 232658, "is_parallel": true, "self": 37.185244103196965, "children": { "_process_rank_one_or_two_observation": { "total": 60.35157567073611, "count": 465316, "is_parallel": true, "self": 60.35157567073611 } } } } } } } } } } }, "trainer_advance": { "total": 552.1136617630741, "count": 232659, "self": 6.795314277306716, "children": { "process_trajectory": { "total": 145.70325088276422, "count": 232659, "self": 144.3737127757645, "children": { "RLTrainer._checkpoint": { "total": 1.3295381069997347, "count": 10, "self": 1.3295381069997347 } } }, "_update_policy": { "total": 399.61509660300317, "count": 97, "self": 338.9937146069874, "children": { "TorchPPOOptimizer.update": { "total": 60.62138199601577, "count": 2910, "self": 60.62138199601577 } } } } } } }, "trainer_threads": { "total": 9.51999936660286e-07, "count": 1, "self": 9.51999936660286e-07 }, "TrainerController._save_models": { "total": 0.11390836800001125, "count": 1, "self": 0.001805034999961208, "children": { "RLTrainer._checkpoint": { "total": 0.11210333300005004, "count": 1, "self": 0.11210333300005004 } } } } } } }