{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4073644876480103, "min": 1.4073644876480103, "max": 1.4291545152664185, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68704.71875, "min": 68028.984375, "max": 78690.984375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.75249500998004, "min": 80.94590163934426, "max": 398.96031746031747, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49976.0, "min": 49249.0, "max": 50269.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999728.0, "min": 49933.0, "max": 1999728.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999728.0, "min": 49933.0, "max": 1999728.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3981082439422607, "min": 0.0832897201180458, "max": 2.469179391860962, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1201.4522705078125, "min": 10.411214828491211, "max": 1480.610595703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6237917920786464, "min": 1.7312281947135926, "max": 3.9578497986927212, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1815.5196878314018, "min": 216.40352433919907, "max": 2307.8251841664314, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6237917920786464, "min": 1.7312281947135926, "max": 3.9578497986927212, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1815.5196878314018, "min": 216.40352433919907, "max": 2307.8251841664314, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017575411732670746, "min": 0.014063283868078239, "max": 0.019822165330859006, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05272623519801224, "min": 0.028126567736156478, "max": 0.059466495992577015, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05534140256543955, "min": 0.02326234048232436, "max": 0.059627570418847926, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16602420769631865, "min": 0.04652468096464872, "max": 0.17888271125654379, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.376998874366673e-06, "min": 3.376998874366673e-06, "max": 0.00029534452655182494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0130996623100019e-05, "min": 1.0130996623100019e-05, "max": 0.0008441206686264502, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112563333333334, "min": 0.10112563333333334, "max": 0.19844817500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033769, "min": 0.20743435000000005, "max": 0.5813735500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.616910333333342e-05, "min": 6.616910333333342e-05, "max": 0.0049225639325, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019850731000000028, "min": 0.00019850731000000028, "max": 0.014070540145, "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": "1672591778", "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": "1672594074" }, "total": 2296.1772304309998, "count": 1, "self": 0.3885865339998418, "children": { "run_training.setup": { "total": 0.10969405900004858, "count": 1, "self": 0.10969405900004858 }, "TrainerController.start_learning": { "total": 2295.678949838, "count": 1, "self": 3.9576196531224923, "children": { "TrainerController._reset_env": { "total": 7.683561829999917, "count": 1, "self": 7.683561829999917 }, "TrainerController.advance": { "total": 2283.9295707308775, "count": 232131, "self": 4.301150356816834, "children": { "env_step": { "total": 1812.4034471220561, "count": 232131, "self": 1523.3133208070335, "children": { "SubprocessEnvManager._take_step": { "total": 286.41090497096525, "count": 232131, "self": 14.996496969912187, "children": { "TorchPolicy.evaluate": { "total": 271.41440800105306, "count": 222937, "self": 67.68334212597642, "children": { "TorchPolicy.sample_actions": { "total": 203.73106587507664, "count": 222937, "self": 203.73106587507664 } } } } }, "workers": { "total": 2.679221344057396, "count": 232131, "self": 0.0, "children": { "worker_root": { "total": 2287.446846788844, "count": 232131, "is_parallel": true, "self": 1036.0964529108192, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001809205999961705, "count": 1, "is_parallel": true, "self": 0.0003472239998245641, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014619820001371409, "count": 2, "is_parallel": true, "self": 0.0014619820001371409 } } }, "UnityEnvironment.step": { "total": 0.02932640500011985, "count": 1, "is_parallel": true, "self": 0.000279198000271208, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001980619999812916, "count": 1, "is_parallel": true, "self": 0.0001980619999812916 }, "communicator.exchange": { "total": 0.028109419999964302, "count": 1, "is_parallel": true, "self": 0.028109419999964302 }, "steps_from_proto": { "total": 0.0007397249999030464, "count": 1, "is_parallel": true, "self": 0.0002561490000516642, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004835759998513822, "count": 2, "is_parallel": true, "self": 0.0004835759998513822 } } } } } } }, "UnityEnvironment.step": { "total": 1251.350393878025, "count": 232130, "is_parallel": true, "self": 34.95726784796602, "children": { "UnityEnvironment._generate_step_input": { "total": 80.73679408000817, "count": 232130, "is_parallel": true, "self": 80.73679408000817 }, "communicator.exchange": { "total": 1038.2623630550597, "count": 232130, "is_parallel": true, "self": 1038.2623630550597 }, "steps_from_proto": { "total": 97.39396889499108, "count": 232130, "is_parallel": true, "self": 42.530413453934216, "children": { "_process_rank_one_or_two_observation": { "total": 54.86355544105686, "count": 464260, "is_parallel": true, "self": 54.86355544105686 } } } } } } } } } } }, "trainer_advance": { "total": 467.22497325200425, "count": 232131, "self": 6.1532901070804655, "children": { "process_trajectory": { "total": 152.72801276592463, "count": 232131, "self": 151.5410273309251, "children": { "RLTrainer._checkpoint": { "total": 1.1869854349995421, "count": 10, "self": 1.1869854349995421 } } }, "_update_policy": { "total": 308.34367037899915, "count": 97, "self": 255.00343498000666, "children": { "TorchPPOOptimizer.update": { "total": 53.34023539899249, "count": 2910, "self": 53.34023539899249 } } } } } } }, "trainer_threads": { "total": 9.359996511193458e-07, "count": 1, "self": 9.359996511193458e-07 }, "TrainerController._save_models": { "total": 0.1081966880001346, "count": 1, "self": 0.0018538869999247254, "children": { "RLTrainer._checkpoint": { "total": 0.10634280100020987, "count": 1, "self": 0.10634280100020987 } } } } } } }