{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7865070104598999, "min": 0.7865070104598999, "max": 2.8543009757995605, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7769.1162109375, "min": 7769.1162109375, "max": 29199.498046875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9984.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9984.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.398533821105957, "min": 0.3704783618450165, "max": 13.429444313049316, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 4635.892578125, "min": 127.81503295898438, "max": 4740.59375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06925501085326473, "min": 0.06462926948708413, "max": 0.07390515286595259, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2770200434130589, "min": 0.2585170779483365, "max": 0.369525764329763, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17454249015187517, "min": 0.11136167208143674, "max": 0.25612713968052586, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6981699606075007, "min": 0.44544668832574696, "max": 1.2806356984026293, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000009e-06, "min": 8.082097306000009e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.2328389224000035e-05, "min": 3.2328389224000035e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999998, "min": 0.10269399999999998, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4107759999999999, "min": 0.4107759999999999, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 1.2424600000000003e-05, "min": 1.2424600000000003e-05, "max": 9.75646e-05, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 4.969840000000001e-05, "min": 4.969840000000001e-05, "max": 0.0004655480000000001, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.84090909090909, "min": 4.0227272727272725, "max": 26.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1137.0, "min": 177.0, "max": 1472.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.84090909090909, "min": 4.0227272727272725, "max": 26.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1137.0, "min": 177.0, "max": 1472.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674367240", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1674367722" }, "total": 482.114023367, "count": 1, "self": 0.3945379960000537, "children": { "run_training.setup": { "total": 0.10864515099996197, "count": 1, "self": 0.10864515099996197 }, "TrainerController.start_learning": { "total": 481.61084022, "count": 1, "self": 0.4947744110023109, "children": { "TrainerController._reset_env": { "total": 9.569358023999996, "count": 1, "self": 9.569358023999996 }, "TrainerController.advance": { "total": 471.41763386099785, "count": 18201, "self": 0.24472952500974543, "children": { "env_step": { "total": 471.1729043359881, "count": 18201, "self": 340.7220522879761, "children": { "SubprocessEnvManager._take_step": { "total": 130.20180081301356, "count": 18201, "self": 1.4236278000149127, "children": { "TorchPolicy.evaluate": { "total": 128.77817301299865, "count": 18201, "self": 28.25516861299957, "children": { "TorchPolicy.sample_actions": { "total": 100.52300439999908, "count": 18201, "self": 100.52300439999908 } } } } }, "workers": { "total": 0.24905123499843285, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 480.533377311001, "count": 18201, "is_parallel": true, "self": 267.62262661300724, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006137050999996063, "count": 1, "is_parallel": true, "self": 0.0038011359998790795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023359150001169837, "count": 10, "is_parallel": true, "self": 0.0023359150001169837 } } }, "UnityEnvironment.step": { "total": 0.04563760900003899, "count": 1, "is_parallel": true, "self": 0.0006312910000474403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003090779999865845, "count": 1, "is_parallel": true, "self": 0.0003090779999865845 }, "communicator.exchange": { "total": 0.04290082400001438, "count": 1, "is_parallel": true, "self": 0.04290082400001438 }, "steps_from_proto": { "total": 0.001796415999990586, "count": 1, "is_parallel": true, "self": 0.00043313800000532865, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013632779999852573, "count": 10, "is_parallel": true, "self": 0.0013632779999852573 } } } } } } }, "UnityEnvironment.step": { "total": 212.91075069799376, "count": 18200, "is_parallel": true, "self": 8.134772321002231, "children": { "UnityEnvironment._generate_step_input": { "total": 4.755710682993936, "count": 18200, "is_parallel": true, "self": 4.755710682993936 }, "communicator.exchange": { "total": 171.21454977799692, "count": 18200, "is_parallel": true, "self": 171.21454977799692 }, "steps_from_proto": { "total": 28.805717916000674, "count": 18200, "is_parallel": true, "self": 6.009925348025263, "children": { "_process_rank_one_or_two_observation": { "total": 22.79579256797541, "count": 182000, "is_parallel": true, "self": 22.79579256797541 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.48539999399145e-05, "count": 1, "self": 9.48539999399145e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 468.05212931998227, "count": 381675, "is_parallel": true, "self": 10.086448793023123, "children": { "process_trajectory": { "total": 283.8279526659588, "count": 381675, "is_parallel": true, "self": 282.8977578139589, "children": { "RLTrainer._checkpoint": { "total": 0.9301948519998859, "count": 4, "is_parallel": true, "self": 0.9301948519998859 } } }, "_update_policy": { "total": 174.13772786100037, "count": 90, "is_parallel": true, "self": 62.635376877001534, "children": { "TorchPPOOptimizer.update": { "total": 111.50235098399884, "count": 7645, "is_parallel": true, "self": 111.50235098399884 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12897906999990028, "count": 1, "self": 0.0014101709998612932, "children": { "RLTrainer._checkpoint": { "total": 0.12756889900003898, "count": 1, "self": 0.12756889900003898 } } } } } } }