{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405482530593872, "min": 1.405482530593872, "max": 1.424791932106018, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69544.6796875, "min": 68371.609375, "max": 78764.328125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 106.22698072805139, "min": 82.80737018425461, "max": 387.1085271317829, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49608.0, "min": 48957.0, "max": 50143.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999967.0, "min": 49518.0, "max": 1999967.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999967.0, "min": 49518.0, "max": 1999967.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.346294641494751, "min": 0.035635609179735184, "max": 2.49809193611145, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1095.7196044921875, "min": 4.5613579750061035, "max": 1416.075439453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.531945319834307, "min": 1.7926983578363433, "max": 3.9470971624056497, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1649.4184643626213, "min": 229.46538980305195, "max": 2234.227006793022, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.531945319834307, "min": 1.7926983578363433, "max": 3.9470971624056497, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1649.4184643626213, "min": 229.46538980305195, "max": 2234.227006793022, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017806474872567275, "min": 0.01159767320981094, "max": 0.01961268134812902, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05341942461770183, "min": 0.02319534641962188, "max": 0.05687368103826884, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04987910874187946, "min": 0.02259420972938339, "max": 0.06383788250386714, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14963732622563838, "min": 0.04518841945876678, "max": 0.19151364751160144, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.358398880566669e-06, "min": 3.358398880566669e-06, "max": 0.0002953737765420749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0075196641700006e-05, "min": 1.0075196641700006e-05, "max": 0.0008442282185906, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111943333333333, "min": 0.10111943333333333, "max": 0.19845792500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30335829999999997, "min": 0.20745544999999999, "max": 0.5814094000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.58597233333334e-05, "min": 6.58597233333334e-05, "max": 0.0049230504575, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001975791700000002, "min": 0.0001975791700000002, "max": 0.014072329060000001, "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": "1682188691", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682190994" }, "total": 2303.89492211, "count": 1, "self": 0.38532438199990793, "children": { "run_training.setup": { "total": 0.12347422300001654, "count": 1, "self": 0.12347422300001654 }, "TrainerController.start_learning": { "total": 2303.3861235050003, "count": 1, "self": 4.152042835093653, "children": { "TrainerController._reset_env": { "total": 3.8766400979999958, "count": 1, "self": 3.8766400979999958 }, "TrainerController.advance": { "total": 2295.2380288829067, "count": 232161, "self": 4.549385524023364, "children": { "env_step": { "total": 1792.8011982839705, "count": 232161, "self": 1517.3093090288648, "children": { "SubprocessEnvManager._take_step": { "total": 272.7112766570348, "count": 232161, "self": 16.317214986056342, "children": { "TorchPolicy.evaluate": { "total": 256.39406167097843, "count": 222994, "self": 256.39406167097843 } } }, "workers": { "total": 2.7806125980708885, "count": 232161, "self": 0.0, "children": { "worker_root": { "total": 2295.4051083469417, "count": 232161, "is_parallel": true, "self": 1051.7638608949317, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009856209999838939, "count": 1, "is_parallel": true, "self": 0.0003723279999690021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006132930000148917, "count": 2, "is_parallel": true, "self": 0.0006132930000148917 } } }, "UnityEnvironment.step": { "total": 0.030228788999977496, "count": 1, "is_parallel": true, "self": 0.00027429099992559713, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016516000005140086, "count": 1, "is_parallel": true, "self": 0.00016516000005140086 }, "communicator.exchange": { "total": 0.0289370859999849, "count": 1, "is_parallel": true, "self": 0.0289370859999849 }, "steps_from_proto": { "total": 0.0008522520000155964, "count": 1, "is_parallel": true, "self": 0.00020085599999219994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006513960000233965, "count": 2, "is_parallel": true, "self": 0.0006513960000233965 } } } } } } }, "UnityEnvironment.step": { "total": 1243.64124745201, "count": 232160, "is_parallel": true, "self": 37.313793435171874, "children": { "UnityEnvironment._generate_step_input": { "total": 78.64921191493625, "count": 232160, "is_parallel": true, "self": 78.64921191493625 }, "communicator.exchange": { "total": 1040.8790674769825, "count": 232160, "is_parallel": true, "self": 1040.8790674769825 }, "steps_from_proto": { "total": 86.79917462491937, "count": 232160, "is_parallel": true, "self": 32.615592934965434, "children": { "_process_rank_one_or_two_observation": { "total": 54.18358168995394, "count": 464320, "is_parallel": true, "self": 54.18358168995394 } } } } } } } } } } }, "trainer_advance": { "total": 497.8874450749128, "count": 232161, "self": 6.466265206987657, "children": { "process_trajectory": { "total": 127.89032737192605, "count": 232161, "self": 126.5452050839263, "children": { "RLTrainer._checkpoint": { "total": 1.345122287999743, "count": 10, "self": 1.345122287999743 } } }, "_update_policy": { "total": 363.5308524959991, "count": 97, "self": 305.3831644969995, "children": { "TorchPPOOptimizer.update": { "total": 58.14768799899963, "count": 2910, "self": 58.14768799899963 } } } } } } }, "trainer_threads": { "total": 9.57999873207882e-07, "count": 1, "self": 9.57999873207882e-07 }, "TrainerController._save_models": { "total": 0.11941073100024369, "count": 1, "self": 0.002000582000164286, "children": { "RLTrainer._checkpoint": { "total": 0.1174101490000794, "count": 1, "self": 0.1174101490000794 } } } } } } }