{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4044312238693237, "min": 1.4044312238693237, "max": 1.4284498691558838, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70196.28125, "min": 68428.40625, "max": 77340.921875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.14528301886793, "min": 90.56146788990826, "max": 453.27027027027026, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48837.0, "min": 48837.0, "max": 50313.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999994.0, "min": 49797.0, "max": 1999994.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999994.0, "min": 49797.0, "max": 1999994.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.343609571456909, "min": 0.12583576142787933, "max": 2.4490044116973877, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1242.113037109375, "min": 13.841934204101562, "max": 1288.413818359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7916850514007066, "min": 1.7487663164734841, "max": 3.921746356931163, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2009.5930772423744, "min": 192.36429481208324, "max": 2043.2298519611359, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7916850514007066, "min": 1.7487663164734841, "max": 3.921746356931163, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2009.5930772423744, "min": 192.36429481208324, "max": 2043.2298519611359, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01583832499955962, "min": 0.014214647358555037, "max": 0.021270070795920522, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04751497499867886, "min": 0.028429294717110073, "max": 0.06188409884731906, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05649776963724031, "min": 0.02138824832315246, "max": 0.06150973103940487, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16949330891172093, "min": 0.04277649664630492, "max": 0.1845291931182146, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2360489213499986e-06, "min": 3.2360489213499986e-06, "max": 0.00029533492655502494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.708146764049995e-06, "min": 9.708146764049995e-06, "max": 0.0008441851686049498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107865000000003, "min": 0.10107865000000003, "max": 0.19844497500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032359500000001, "min": 0.20731430000000006, "max": 0.5813950499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.382463499999997e-05, "min": 6.382463499999997e-05, "max": 0.0049224042525, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019147390499999994, "min": 0.00019147390499999994, "max": 0.014071612995000003, "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": "1670364407", "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670366702" }, "total": 2295.070076139, "count": 1, "self": 0.3955309420002777, "children": { "run_training.setup": { "total": 0.10853508899998587, "count": 1, "self": 0.10853508899998587 }, "TrainerController.start_learning": { "total": 2294.566010108, "count": 1, "self": 4.1652070840541455, "children": { "TrainerController._reset_env": { "total": 10.279425678999985, "count": 1, "self": 10.279425678999985 }, "TrainerController.advance": { "total": 2279.998763702946, "count": 231642, "self": 4.68094251994853, "children": { "env_step": { "total": 1805.95798379903, "count": 231642, "self": 1509.3128303429871, "children": { "SubprocessEnvManager._take_step": { "total": 293.95327950597715, "count": 231642, "self": 15.175826899978915, "children": { "TorchPolicy.evaluate": { "total": 278.77745260599823, "count": 222932, "self": 69.99240183198475, "children": { "TorchPolicy.sample_actions": { "total": 208.78505077401348, "count": 222932, "self": 208.78505077401348 } } } } }, "workers": { "total": 2.6918739500657693, "count": 231642, "self": 0.0, "children": { "worker_root": { "total": 2286.000301800016, "count": 231642, "is_parallel": true, "self": 1050.358989754986, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022490380000022014, "count": 1, "is_parallel": true, "self": 0.0003670879999617682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018819500000404332, "count": 2, "is_parallel": true, "self": 0.0018819500000404332 } } }, "UnityEnvironment.step": { "total": 0.02841593299996248, "count": 1, "is_parallel": true, "self": 0.0002841159999888987, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020032399999081463, "count": 1, "is_parallel": true, "self": 0.00020032399999081463 }, "communicator.exchange": { "total": 0.0271831739999584, "count": 1, "is_parallel": true, "self": 0.0271831739999584 }, "steps_from_proto": { "total": 0.0007483190000243667, "count": 1, "is_parallel": true, "self": 0.00025476400003299204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004935549999913746, "count": 2, "is_parallel": true, "self": 0.0004935549999913746 } } } } } } }, "UnityEnvironment.step": { "total": 1235.6413120450302, "count": 231641, "is_parallel": true, "self": 34.922929840804045, "children": { "UnityEnvironment._generate_step_input": { "total": 80.43563251410347, "count": 231641, "is_parallel": true, "self": 80.43563251410347 }, "communicator.exchange": { "total": 1023.907480302001, "count": 231641, "is_parallel": true, "self": 1023.907480302001 }, "steps_from_proto": { "total": 96.37526938812175, "count": 231641, "is_parallel": true, "self": 41.926077487193595, "children": { "_process_rank_one_or_two_observation": { "total": 54.449191900928156, "count": 463282, "is_parallel": true, "self": 54.449191900928156 } } } } } } } } } } }, "trainer_advance": { "total": 469.35983738396703, "count": 231642, "self": 6.5211160999652975, "children": { "process_trajectory": { "total": 151.35894812900392, "count": 231642, "self": 150.84906962100342, "children": { "RLTrainer._checkpoint": { "total": 0.5098785080004973, "count": 4, "self": 0.5098785080004973 } } }, "_update_policy": { "total": 311.4797731549978, "count": 97, "self": 257.3726636950005, "children": { "TorchPPOOptimizer.update": { "total": 54.10710945999733, "count": 2910, "self": 54.10710945999733 } } } } } } }, "trainer_threads": { "total": 7.749999895168003e-07, "count": 1, "self": 7.749999895168003e-07 }, "TrainerController._save_models": { "total": 0.12261286700004348, "count": 1, "self": 0.0020302859998082567, "children": { "RLTrainer._checkpoint": { "total": 0.12058258100023522, "count": 1, "self": 0.12058258100023522 } } } } } } }