{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4090067148208618, "min": 1.4090067148208618, "max": 1.4310742616653442, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70515.1484375, "min": 69309.703125, "max": 77442.7734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.47359735973598, "min": 74.67170953101362, "max": 413.1322314049587, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49373.0, "min": 48688.0, "max": 50160.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999947.0, "min": 49705.0, "max": 1999947.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999947.0, "min": 49705.0, "max": 1999947.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4941318035125732, "min": 0.138327494263649, "max": 2.5345895290374756, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1511.44384765625, "min": 16.59929847717285, "max": 1662.690673828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.955162791135681, "min": 1.7249210312962533, "max": 3.955162791135681, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2396.8286514282227, "min": 206.99052375555038, "max": 2590.0357134342194, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.955162791135681, "min": 1.7249210312962533, "max": 3.955162791135681, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2396.8286514282227, "min": 206.99052375555038, "max": 2590.0357134342194, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016851754963418997, "min": 0.013088674742671932, "max": 0.019916875237928858, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050555264890256996, "min": 0.026177349485343865, "max": 0.05975062571378657, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05833745735387008, "min": 0.021165211498737332, "max": 0.0688148890932401, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17501237206161024, "min": 0.042330422997474665, "max": 0.1902780885497729, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4864988378666675e-06, "min": 3.4864988378666675e-06, "max": 0.0002952504015832, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0459496513600002e-05, "min": 1.0459496513600002e-05, "max": 0.0008439702186765998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116213333333335, "min": 0.10116213333333335, "max": 0.1984168, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30348640000000005, "min": 0.20745904999999995, "max": 0.5813233999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.799045333333333e-05, "min": 6.799045333333333e-05, "max": 0.004920998319999998, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020397136, "min": 0.00020397136, "max": 0.014068037660000005, "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": "1686539533", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686541993" }, "total": 2460.491785571, "count": 1, "self": 0.7430846460001703, "children": { "run_training.setup": { "total": 0.045765365000022484, "count": 1, "self": 0.045765365000022484 }, "TrainerController.start_learning": { "total": 2459.70293556, "count": 1, "self": 4.668018930984545, "children": { "TrainerController._reset_env": { "total": 4.906483673999958, "count": 1, "self": 4.906483673999958 }, "TrainerController.advance": { "total": 2449.941617621015, "count": 233211, "self": 4.58529631796182, "children": { "env_step": { "total": 1901.3438501090404, "count": 233211, "self": 1601.003544171025, "children": { "SubprocessEnvManager._take_step": { "total": 297.4932788550498, "count": 233211, "self": 16.77316243803034, "children": { "TorchPolicy.evaluate": { "total": 280.7201164170195, "count": 222992, "self": 280.7201164170195 } } }, "workers": { "total": 2.847027082965667, "count": 233211, "self": 0.0, "children": { "worker_root": { "total": 2451.815356370987, "count": 233211, "is_parallel": true, "self": 1143.9001619950177, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009212560000264602, "count": 1, "is_parallel": true, "self": 0.0002654140000117877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006558420000146725, "count": 2, "is_parallel": true, "self": 0.0006558420000146725 } } }, "UnityEnvironment.step": { "total": 0.05953865300000416, "count": 1, "is_parallel": true, "self": 0.0003696129999752884, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002528530000063256, "count": 1, "is_parallel": true, "self": 0.0002528530000063256 }, "communicator.exchange": { "total": 0.05821030200002042, "count": 1, "is_parallel": true, "self": 0.05821030200002042 }, "steps_from_proto": { "total": 0.0007058850000021266, "count": 1, "is_parallel": true, "self": 0.000231051000014304, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004748339999878226, "count": 2, "is_parallel": true, "self": 0.0004748339999878226 } } } } } } }, "UnityEnvironment.step": { "total": 1307.9151943759693, "count": 233210, "is_parallel": true, "self": 39.035339541912435, "children": { "UnityEnvironment._generate_step_input": { "total": 79.03883434898347, "count": 233210, "is_parallel": true, "self": 79.03883434898347 }, "communicator.exchange": { "total": 1094.652824700054, "count": 233210, "is_parallel": true, "self": 1094.652824700054 }, "steps_from_proto": { "total": 95.18819578501933, "count": 233210, "is_parallel": true, "self": 34.462961756930724, "children": { "_process_rank_one_or_two_observation": { "total": 60.72523402808861, "count": 466420, "is_parallel": true, "self": 60.72523402808861 } } } } } } } } } } }, "trainer_advance": { "total": 544.012471194013, "count": 233211, "self": 6.608322578998582, "children": { "process_trajectory": { "total": 143.8279957230148, "count": 233211, "self": 142.37099344301515, "children": { "RLTrainer._checkpoint": { "total": 1.4570022799996423, "count": 10, "self": 1.4570022799996423 } } }, "_update_policy": { "total": 393.5761528919996, "count": 97, "self": 332.08974067099814, "children": { "TorchPPOOptimizer.update": { "total": 61.486412221001444, "count": 2910, "self": 61.486412221001444 } } } } } } }, "trainer_threads": { "total": 1.3210001270635985e-06, "count": 1, "self": 1.3210001270635985e-06 }, "TrainerController._save_models": { "total": 0.1868140130000029, "count": 1, "self": 0.002645295999627706, "children": { "RLTrainer._checkpoint": { "total": 0.18416871700037518, "count": 1, "self": 0.18416871700037518 } } } } } } }