{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4043697118759155, "min": 1.4043697118759155, "max": 1.4275445938110352, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69444.6796875, "min": 69155.84375, "max": 77451.4453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.221875, "min": 73.26002971768202, "max": 388.47286821705427, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48782.0, "min": 48782.0, "max": 50113.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999989.0, "min": 49515.0, "max": 1999989.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999989.0, "min": 49515.0, "max": 1999989.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4603159427642822, "min": 0.0906737744808197, "max": 2.517595052719116, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1574.6021728515625, "min": 11.606243133544922, "max": 1660.900146484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7777288171462713, "min": 1.877062070183456, "max": 4.04488940010358, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2417.7464429736137, "min": 240.26394498348236, "max": 2624.803804576397, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7777288171462713, "min": 1.877062070183456, "max": 4.04488940010358, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2417.7464429736137, "min": 240.26394498348236, "max": 2624.803804576397, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0172712624952611, "min": 0.013500980833002055, "max": 0.018682890287406433, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051813787485783296, "min": 0.02700196166600411, "max": 0.05528347512329977, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053492333284682704, "min": 0.022602520789951085, "max": 0.059987076992789906, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16047699985404812, "min": 0.04520504157990217, "max": 0.17472840460638206, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.800898733066672e-06, "min": 3.800898733066672e-06, "max": 0.00029534565155144997, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1402696199200015e-05, "min": 1.1402696199200015e-05, "max": 0.0008440633686455498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126693333333332, "min": 0.10126693333333332, "max": 0.19844855000000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3038008, "min": 0.20766025, "max": 0.5813544500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.32199733333334e-05, "min": 7.32199733333334e-05, "max": 0.004922582645, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021965992000000018, "min": 0.00021965992000000018, "max": 0.014069587054999999, "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": "1675125829", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1675128066" }, "total": 2236.9738874689997, "count": 1, "self": 0.3817336969996177, "children": { "run_training.setup": { "total": 0.1196741169999882, "count": 1, "self": 0.1196741169999882 }, "TrainerController.start_learning": { "total": 2236.472479655, "count": 1, "self": 3.8268633709649293, "children": { "TrainerController._reset_env": { "total": 10.749796591000006, "count": 1, "self": 10.749796591000006 }, "TrainerController.advance": { "total": 2221.785305631035, "count": 233144, "self": 4.233784290940093, "children": { "env_step": { "total": 1747.0585733550183, "count": 233144, "self": 1470.1871603100333, "children": { "SubprocessEnvManager._take_step": { "total": 274.32136553896106, "count": 233144, "self": 14.390594223953883, "children": { "TorchPolicy.evaluate": { "total": 259.9307713150072, "count": 222926, "self": 66.16976207897426, "children": { "TorchPolicy.sample_actions": { "total": 193.76100923603292, "count": 222926, "self": 193.76100923603292 } } } } }, "workers": { "total": 2.5500475060239864, "count": 233144, "self": 0.0, "children": { "worker_root": { "total": 2228.613939547136, "count": 233144, "is_parallel": true, "self": 1016.3875001481235, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002174168000010468, "count": 1, "is_parallel": true, "self": 0.00035496099997089914, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018192070000395688, "count": 2, "is_parallel": true, "self": 0.0018192070000395688 } } }, "UnityEnvironment.step": { "total": 0.028918850999957613, "count": 1, "is_parallel": true, "self": 0.0003215319999867461, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001917369999659968, "count": 1, "is_parallel": true, "self": 0.0001917369999659968 }, "communicator.exchange": { "total": 0.027477471999986847, "count": 1, "is_parallel": true, "self": 0.027477471999986847 }, "steps_from_proto": { "total": 0.0009281100000180231, "count": 1, "is_parallel": true, "self": 0.00042483200002152444, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005032779999964987, "count": 2, "is_parallel": true, "self": 0.0005032779999964987 } } } } } } }, "UnityEnvironment.step": { "total": 1212.2264393990124, "count": 233143, "is_parallel": true, "self": 35.497743815129525, "children": { "UnityEnvironment._generate_step_input": { "total": 75.61966908886421, "count": 233143, "is_parallel": true, "self": 75.61966908886421 }, "communicator.exchange": { "total": 1008.512776934915, "count": 233143, "is_parallel": true, "self": 1008.512776934915 }, "steps_from_proto": { "total": 92.59624956010356, "count": 233143, "is_parallel": true, "self": 38.5520223049528, "children": { "_process_rank_one_or_two_observation": { "total": 54.04422725515076, "count": 466286, "is_parallel": true, "self": 54.04422725515076 } } } } } } } } } } }, "trainer_advance": { "total": 470.49294798507685, "count": 233144, "self": 6.141550114186998, "children": { "process_trajectory": { "total": 150.93813374589138, "count": 233144, "self": 149.80174612689234, "children": { "RLTrainer._checkpoint": { "total": 1.1363876189990378, "count": 10, "self": 1.1363876189990378 } } }, "_update_policy": { "total": 313.4132641249985, "count": 97, "self": 260.0034068680093, "children": { "TorchPPOOptimizer.update": { "total": 53.4098572569892, "count": 2910, "self": 53.4098572569892 } } } } } } }, "trainer_threads": { "total": 9.599998520570807e-07, "count": 1, "self": 9.599998520570807e-07 }, "TrainerController._save_models": { "total": 0.11051310199991349, "count": 1, "self": 0.002888772999995126, "children": { "RLTrainer._checkpoint": { "total": 0.10762432899991836, "count": 1, "self": 0.10762432899991836 } } } } } } }