{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4048967361450195, "min": 1.4048967361450195, "max": 1.429060459136963, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72693.5703125, "min": 67865.1953125, "max": 77436.9140625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 94.92045454545455, "min": 85.92, "max": 388.1937984496124, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50118.0, "min": 48775.0, "max": 50138.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999903.0, "min": 49560.0, "max": 1999903.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999903.0, "min": 49560.0, "max": 1999903.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.339216947555542, "min": 0.04369007423520088, "max": 2.4482500553131104, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1235.1065673828125, "min": 5.592329502105713, "max": 1336.4700927734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5913932689211587, "min": 1.913872804318089, "max": 4.006013436709778, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1896.2556459903717, "min": 244.9757189527154, "max": 2157.9680810570717, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5913932689211587, "min": 1.913872804318089, "max": 4.006013436709778, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1896.2556459903717, "min": 244.9757189527154, "max": 2157.9680810570717, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018135000365307657, "min": 0.013427448435686528, "max": 0.02110537388556016, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05440500109592297, "min": 0.026854896871373057, "max": 0.05589332471912106, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053793889284133915, "min": 0.021857031062245368, "max": 0.054500589892268185, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16138166785240174, "min": 0.043714062124490735, "max": 0.16350176967680455, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.416848861083325e-06, "min": 3.416848861083325e-06, "max": 0.000295380376539875, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0250546583249974e-05, "min": 1.0250546583249974e-05, "max": 0.0008440747686417499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113891666666668, "min": 0.10113891666666668, "max": 0.198460125, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30341675, "min": 0.2074298, "max": 0.5813582500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.683194166666652e-05, "min": 6.683194166666652e-05, "max": 0.0049231602375, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020049582499999955, "min": 0.00020049582499999955, "max": 0.014069776675000003, "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": "1714855811", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714858537" }, "total": 2726.489003942, "count": 1, "self": 0.7604395140001543, "children": { "run_training.setup": { "total": 0.0578974280000466, "count": 1, "self": 0.0578974280000466 }, "TrainerController.start_learning": { "total": 2725.670667, "count": 1, "self": 5.1054362550776204, "children": { "TrainerController._reset_env": { "total": 3.912976965999974, "count": 1, "self": 3.912976965999974 }, "TrainerController.advance": { "total": 2716.4540689529226, "count": 232298, "self": 5.362862734953069, "children": { "env_step": { "total": 2185.8820174159387, "count": 232298, "self": 1808.2215255590816, "children": { "SubprocessEnvManager._take_step": { "total": 374.17146555489, "count": 232298, "self": 18.650800382913076, "children": { "TorchPolicy.evaluate": { "total": 355.52066517197693, "count": 223122, "self": 355.52066517197693 } } }, "workers": { "total": 3.489026301967101, "count": 232298, "self": 0.0, "children": { "worker_root": { "total": 2717.313722458856, "count": 232298, "is_parallel": true, "self": 1258.8397324568805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009403859999110864, "count": 1, "is_parallel": true, "self": 0.00024575099985213456, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006946350000589518, "count": 2, "is_parallel": true, "self": 0.0006946350000589518 } } }, "UnityEnvironment.step": { "total": 0.031826648999981444, "count": 1, "is_parallel": true, "self": 0.0004374710000547566, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019714499990186596, "count": 1, "is_parallel": true, "self": 0.00019714499990186596 }, "communicator.exchange": { "total": 0.030338990000018384, "count": 1, "is_parallel": true, "self": 0.030338990000018384 }, "steps_from_proto": { "total": 0.0008530430000064371, "count": 1, "is_parallel": true, "self": 0.00021152299984805722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006415200001583798, "count": 2, "is_parallel": true, "self": 0.0006415200001583798 } } } } } } }, "UnityEnvironment.step": { "total": 1458.4739900019754, "count": 232297, "is_parallel": true, "self": 44.48864859903915, "children": { "UnityEnvironment._generate_step_input": { "total": 91.65026411394479, "count": 232297, "is_parallel": true, "self": 91.65026411394479 }, "communicator.exchange": { "total": 1217.9794519150319, "count": 232297, "is_parallel": true, "self": 1217.9794519150319 }, "steps_from_proto": { "total": 104.35562537395958, "count": 232297, "is_parallel": true, "self": 36.724299832009024, "children": { "_process_rank_one_or_two_observation": { "total": 67.63132554195056, "count": 464594, "is_parallel": true, "self": 67.63132554195056 } } } } } } } } } } }, "trainer_advance": { "total": 525.2091888020307, "count": 232298, "self": 7.85669019604461, "children": { "process_trajectory": { "total": 170.81699677098663, "count": 232298, "self": 169.1695919479871, "children": { "RLTrainer._checkpoint": { "total": 1.6474048229995333, "count": 10, "self": 1.6474048229995333 } } }, "_update_policy": { "total": 346.5355018349994, "count": 97, "self": 279.4160623089929, "children": { "TorchPPOOptimizer.update": { "total": 67.11943952600654, "count": 2910, "self": 67.11943952600654 } } } } } } }, "trainer_threads": { "total": 1.461000010749558e-06, "count": 1, "self": 1.461000010749558e-06 }, "TrainerController._save_models": { "total": 0.19818336499974976, "count": 1, "self": 0.004455560999758745, "children": { "RLTrainer._checkpoint": { "total": 0.193727803999991, "count": 1, "self": 0.193727803999991 } } } } } } }