{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4064112901687622, "min": 1.4064112901687622, "max": 1.4282495975494385, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71029.3984375, "min": 68599.6015625, "max": 76062.0546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.58687258687259, "min": 81.03448275862068, "max": 405.8373983739837, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50032.0, "min": 48969.0, "max": 50139.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999990.0, "min": 49499.0, "max": 1999990.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999990.0, "min": 49499.0, "max": 1999990.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4214794635772705, "min": 0.06255501508712769, "max": 2.452234983444214, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1256.747802734375, "min": 7.631711959838867, "max": 1478.95703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.685045118047093, "min": 1.8096757118330626, "max": 3.930410171212675, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1912.5384162664413, "min": 220.78043684363365, "max": 2321.46478921175, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.685045118047093, "min": 1.8096757118330626, "max": 3.930410171212675, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1912.5384162664413, "min": 220.78043684363365, "max": 2321.46478921175, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015918637472592916, "min": 0.012470933316702335, "max": 0.019922619449183304, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04775591241777875, "min": 0.02494186663340467, "max": 0.059111285108762485, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05099026047521168, "min": 0.02327999689926704, "max": 0.05630706838435597, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15297078142563503, "min": 0.04655999379853408, "max": 0.1689212051530679, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4831488389833422e-06, "min": 3.4831488389833422e-06, "max": 0.00029526382657872504, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0449446516950026e-05, "min": 1.0449446516950026e-05, "max": 0.0008439352686882499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116101666666667, "min": 0.10116101666666667, "max": 0.19842127500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30348305000000003, "min": 0.20750750000000004, "max": 0.5813117499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.793473166666685e-05, "min": 6.793473166666685e-05, "max": 0.004921221622499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020380419500000055, "min": 0.00020380419500000055, "max": 0.014067456325000002, "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": "1705090037", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705092435" }, "total": 2398.404176724, "count": 1, "self": 0.44529972800000905, "children": { "run_training.setup": { "total": 0.053343823999966844, "count": 1, "self": 0.053343823999966844 }, "TrainerController.start_learning": { "total": 2397.905533172, "count": 1, "self": 4.441304227068031, "children": { "TrainerController._reset_env": { "total": 3.227870932000087, "count": 1, "self": 3.227870932000087 }, "TrainerController.advance": { "total": 2390.110913298932, "count": 232501, "self": 4.966797649981345, "children": { "env_step": { "total": 1898.7855160770544, "count": 232501, "self": 1578.321613757069, "children": { "SubprocessEnvManager._take_step": { "total": 317.55870686198375, "count": 232501, "self": 16.58108607292354, "children": { "TorchPolicy.evaluate": { "total": 300.9776207890602, "count": 222993, "self": 300.9776207890602 } } }, "workers": { "total": 2.9051954580015718, "count": 232501, "self": 0.0, "children": { "worker_root": { "total": 2390.768085991022, "count": 232501, "is_parallel": true, "self": 1110.3831648931036, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006843699999308228, "count": 1, "is_parallel": true, "self": 0.00018297199983408063, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005013980000967422, "count": 2, "is_parallel": true, "self": 0.0005013980000967422 } } }, "UnityEnvironment.step": { "total": 0.02952595699991889, "count": 1, "is_parallel": true, "self": 0.0003415439999798764, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020669299999553914, "count": 1, "is_parallel": true, "self": 0.00020669299999553914 }, "communicator.exchange": { "total": 0.02827607500000795, "count": 1, "is_parallel": true, "self": 0.02827607500000795 }, "steps_from_proto": { "total": 0.0007016449999355245, "count": 1, "is_parallel": true, "self": 0.0001890699999194112, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005125750000161133, "count": 2, "is_parallel": true, "self": 0.0005125750000161133 } } } } } } }, "UnityEnvironment.step": { "total": 1280.3849210979183, "count": 232500, "is_parallel": true, "self": 40.88764312294097, "children": { "UnityEnvironment._generate_step_input": { "total": 81.65151664888845, "count": 232500, "is_parallel": true, "self": 81.65151664888845 }, "communicator.exchange": { "total": 1067.497288617038, "count": 232500, "is_parallel": true, "self": 1067.497288617038 }, "steps_from_proto": { "total": 90.34847270905084, "count": 232500, "is_parallel": true, "self": 31.814687717011566, "children": { "_process_rank_one_or_two_observation": { "total": 58.53378499203927, "count": 465000, "is_parallel": true, "self": 58.53378499203927 } } } } } } } } } } }, "trainer_advance": { "total": 486.3585995718962, "count": 232501, "self": 6.4390678439198155, "children": { "process_trajectory": { "total": 149.7436004279781, "count": 232501, "self": 148.44170606697878, "children": { "RLTrainer._checkpoint": { "total": 1.301894360999313, "count": 10, "self": 1.301894360999313 } } }, "_update_policy": { "total": 330.1759312999983, "count": 97, "self": 266.5170430229899, "children": { "TorchPPOOptimizer.update": { "total": 63.65888827700837, "count": 2910, "self": 63.65888827700837 } } } } } } }, "trainer_threads": { "total": 9.499999578110874e-07, "count": 1, "self": 9.499999578110874e-07 }, "TrainerController._save_models": { "total": 0.12544376400001056, "count": 1, "self": 0.0021423930002129055, "children": { "RLTrainer._checkpoint": { "total": 0.12330137099979765, "count": 1, "self": 0.12330137099979765 } } } } } } }