{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4138602018356323, "min": 1.4138602018356323, "max": 1.428648829460144, "count": 30 }, "Huggy.Policy.Entropy.sum": { "value": 69983.25, "min": 68642.0, "max": 77568.1796875, "count": 30 }, "Huggy.Environment.EpisodeLength.mean": { "value": 111.69506726457399, "min": 98.25992063492063, "max": 398.12698412698415, "count": 30 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49816.0, "min": 48917.0, "max": 50249.0, "count": 30 }, "Huggy.Step.mean": { "value": 1499528.0, "min": 49945.0, "max": 1499528.0, "count": 30 }, "Huggy.Step.sum": { "value": 1499528.0, "min": 49945.0, "max": 1499528.0, "count": 30 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.28910493850708, "min": 0.05184249207377434, "max": 2.379892110824585, "count": 30 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1020.9407958984375, "min": 6.480311393737793, "max": 1143.705078125, "count": 30 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.455825708773104, "min": 1.8467151868343352, "max": 3.821653097132106, "count": 30 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1541.2982661128044, "min": 230.83939835429192, "max": 1857.3234052062035, "count": 30 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.455825708773104, "min": 1.8467151868343352, "max": 3.821653097132106, "count": 30 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1541.2982661128044, "min": 230.83939835429192, "max": 1857.3234052062035, "count": 30 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016487548099773146, "min": 0.014579047896161986, "max": 0.019520427004802818, "count": 30 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03297509619954629, "min": 0.029158095792323972, "max": 0.05671669813843134, "count": 30 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.045760489193101724, "min": 0.020945829742898544, "max": 0.05760226671894392, "count": 30 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09152097838620345, "min": 0.04189165948579709, "max": 0.16412415094673632, "count": 30 }, "Huggy.Policy.LearningRate.mean": { "value": 5.1657982780999936e-06, "min": 5.1657982780999936e-06, "max": 0.0002938130020623333, "count": 30 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0331596556199987e-05, "min": 1.0331596556199987e-05, "max": 0.0008257796247401331, "count": 30 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1017219, "min": 0.1017219, "max": 0.1979376666666667, "count": 30 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2034438, "min": 0.2034438, "max": 0.5752598666666666, "count": 30 }, "Huggy.Policy.Beta.mean": { "value": 9.592280999999993e-05, "min": 9.592280999999993e-05, "max": 0.004897089566666667, "count": 30 }, "Huggy.Policy.Beta.sum": { "value": 0.00019184561999999986, "min": 0.00019184561999999986, "max": 0.013765467346666668, "count": 30 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1699606685", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699608547" }, "total": 1862.722646699, "count": 1, "self": 0.43237807300033637, "children": { "run_training.setup": { "total": 0.04492787000003773, "count": 1, "self": 0.04492787000003773 }, "TrainerController.start_learning": { "total": 1862.2453407559997, "count": 1, "self": 3.4048110759495103, "children": { "TrainerController._reset_env": { "total": 8.79778748800004, "count": 1, "self": 8.79778748800004 }, "TrainerController.advance": { "total": 1849.9425069760503, "count": 173122, "self": 3.5545835291493404, "children": { "env_step": { "total": 1459.1489953528535, "count": 173122, "self": 1199.7772769097721, "children": { "SubprocessEnvManager._take_step": { "total": 257.1995147260956, "count": 173122, "self": 12.602467388097807, "children": { "TorchPolicy.evaluate": { "total": 244.59704733799776, "count": 167268, "self": 244.59704733799776 } } }, "workers": { "total": 2.1722037169857913, "count": 173122, "self": 0.0, "children": { "worker_root": { "total": 1856.3878400050285, "count": 173122, "is_parallel": true, "self": 877.3011330180723, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008638369999971474, "count": 1, "is_parallel": true, "self": 0.0002792620000491297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005845749999480176, "count": 2, "is_parallel": true, "self": 0.0005845749999480176 } } }, "UnityEnvironment.step": { "total": 0.03536804899999879, "count": 1, "is_parallel": true, "self": 0.00032038699998793163, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022249799997098307, "count": 1, "is_parallel": true, "self": 0.00022249799997098307 }, "communicator.exchange": { "total": 0.033943906999979845, "count": 1, "is_parallel": true, "self": 0.033943906999979845 }, "steps_from_proto": { "total": 0.0008812570000600317, "count": 1, "is_parallel": true, "self": 0.0003041730001314136, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005770839999286181, "count": 2, "is_parallel": true, "self": 0.0005770839999286181 } } } } } } }, "UnityEnvironment.step": { "total": 979.0867069869562, "count": 173121, "is_parallel": true, "self": 30.23582710994242, "children": { "UnityEnvironment._generate_step_input": { "total": 67.05896018800354, "count": 173121, "is_parallel": true, "self": 67.05896018800354 }, "communicator.exchange": { "total": 811.6635727549825, "count": 173121, "is_parallel": true, "self": 811.6635727549825 }, "steps_from_proto": { "total": 70.12834693402772, "count": 173121, "is_parallel": true, "self": 26.56530657983967, "children": { "_process_rank_one_or_two_observation": { "total": 43.56304035418805, "count": 346242, "is_parallel": true, "self": 43.56304035418805 } } } } } } } } } } }, "trainer_advance": { "total": 387.23892809404754, "count": 173122, "self": 5.125825124953394, "children": { "process_trajectory": { "total": 111.4173299150923, "count": 173122, "self": 110.59517093209229, "children": { "RLTrainer._checkpoint": { "total": 0.8221589830000084, "count": 7, "self": 0.8221589830000084 } } }, "_update_policy": { "total": 270.69577305400185, "count": 72, "self": 223.8045822769983, "children": { "TorchPPOOptimizer.update": { "total": 46.891190777003544, "count": 2160, "self": 46.891190777003544 } } } } } } }, "trainer_threads": { "total": 9.139998837781604e-07, "count": 1, "self": 9.139998837781604e-07 }, "TrainerController._save_models": { "total": 0.10023430199998984, "count": 1, "self": 0.0019056229998568597, "children": { "RLTrainer._checkpoint": { "total": 0.09832867900013298, "count": 1, "self": 0.09832867900013298 } } } } } } }