{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1079429388046265, "min": 1.1079429388046265, "max": 2.868434429168701, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10663.951171875, "min": 10663.951171875, "max": 29375.63671875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.606502532958984, "min": 0.36470717191696167, "max": 12.606502532958984, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2458.26806640625, "min": 70.75318908691406, "max": 2544.73095703125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06789379374694203, "min": 0.06217636456559001, "max": 0.07463216333274555, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2715751749877681, "min": 0.24870545826236004, "max": 0.3577391821873949, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22099246018949678, "min": 0.10595987490538106, "max": 0.2820126655347207, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8839698407579871, "min": 0.42383949962152423, "max": 1.3755452296897477, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.977272727272727, "min": 3.090909090909091, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 136.0, "max": 1362.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.090909090909091, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 136.0, "max": 1362.0, "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": "1694362602", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "0.31.0.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": "1694363064" }, "total": 462.222407961, "count": 1, "self": 0.7967849489999708, "children": { "run_training.setup": { "total": 0.058965755000031095, "count": 1, "self": 0.058965755000031095 }, "TrainerController.start_learning": { "total": 461.366657257, "count": 1, "self": 0.5091899410012957, "children": { "TrainerController._reset_env": { "total": 4.165621785000042, "count": 1, "self": 4.165621785000042 }, "TrainerController.advance": { "total": 456.45833802299876, "count": 18227, "self": 0.2475304090038435, "children": { "env_step": { "total": 456.2108076139949, "count": 18227, "self": 331.5754562199923, "children": { "SubprocessEnvManager._take_step": { "total": 124.36882407800994, "count": 18227, "self": 1.7069060690069477, "children": { "TorchPolicy.evaluate": { "total": 122.66191800900299, "count": 18227, "self": 122.66191800900299 } } }, "workers": { "total": 0.26652731599267554, "count": 18227, "self": 0.0, "children": { "worker_root": { "total": 459.66012491200166, "count": 18227, "is_parallel": true, "self": 217.22798885800051, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005747601999985363, "count": 1, "is_parallel": true, "self": 0.004301444999953219, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014461570000321444, "count": 10, "is_parallel": true, "self": 0.0014461570000321444 } } }, "UnityEnvironment.step": { "total": 0.10428959999995868, "count": 1, "is_parallel": true, "self": 0.0006366979999370415, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037285700000211364, "count": 1, "is_parallel": true, "self": 0.00037285700000211364 }, "communicator.exchange": { "total": 0.09517085100003442, "count": 1, "is_parallel": true, "self": 0.09517085100003442 }, "steps_from_proto": { "total": 0.00810919399998511, "count": 1, "is_parallel": true, "self": 0.000431706000028953, "children": { "_process_rank_one_or_two_observation": { "total": 0.007677487999956156, "count": 10, "is_parallel": true, "self": 0.007677487999956156 } } } } } } }, "UnityEnvironment.step": { "total": 242.43213605400115, "count": 18226, "is_parallel": true, "self": 10.362451905004718, "children": { "UnityEnvironment._generate_step_input": { "total": 5.187209015997041, "count": 18226, "is_parallel": true, "self": 5.187209015997041 }, "communicator.exchange": { "total": 191.79757936899887, "count": 18226, "is_parallel": true, "self": 191.79757936899887 }, "steps_from_proto": { "total": 35.08489576400052, "count": 18226, "is_parallel": true, "self": 6.276368215001526, "children": { "_process_rank_one_or_two_observation": { "total": 28.808527548998995, "count": 182260, "is_parallel": true, "self": 28.808527548998995 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016865399993548635, "count": 1, "self": 0.00016865399993548635, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 453.091895476993, "count": 420901, "is_parallel": true, "self": 9.133544548030386, "children": { "process_trajectory": { "total": 249.56743375596267, "count": 420901, "is_parallel": true, "self": 247.77290365896272, "children": { "RLTrainer._checkpoint": { "total": 1.7945300969999494, "count": 4, "is_parallel": true, "self": 1.7945300969999494 } } }, "_update_policy": { "total": 194.39091717299993, "count": 90, "is_parallel": true, "self": 73.86271111200381, "children": { "TorchPPOOptimizer.update": { "total": 120.52820606099613, "count": 4587, "is_parallel": true, "self": 120.52820606099613 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23333885399995324, "count": 1, "self": 0.0013141419999556092, "children": { "RLTrainer._checkpoint": { "total": 0.23202471199999763, "count": 1, "self": 0.23202471199999763 } } } } } } }