{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9588591456413269, "min": 0.9588591456413269, "max": 2.861081600189209, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9165.734375, "min": 9165.734375, "max": 29300.3359375, "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": 12.622570991516113, "min": 0.47253069281578064, "max": 12.785687446594238, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2461.4013671875, "min": 91.67095184326172, "max": 2596.42724609375, "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": 0.06525593624260806, "min": 0.06162248689817681, "max": 0.07651369552146278, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26102374497043224, "min": 0.24648994759270723, "max": 0.35044862595660725, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20479879455239167, "min": 0.12583700206596404, "max": 0.2718899133743024, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8191951782095667, "min": 0.5033480082638562, "max": 1.359449566871512, "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": 25.181818181818183, "min": 3.5681818181818183, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 157.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 3.5681818181818183, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 157.0, "max": 1388.0, "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": "1715770830", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715771462" }, "total": 631.824444295, "count": 1, "self": 0.60803149700007, "children": { "run_training.setup": { "total": 0.08130687700003136, "count": 1, "self": 0.08130687700003136 }, "TrainerController.start_learning": { "total": 631.135105921, "count": 1, "self": 0.9356922090142916, "children": { "TrainerController._reset_env": { "total": 3.2279529090000096, "count": 1, "self": 3.2279529090000096 }, "TrainerController.advance": { "total": 626.8588180769858, "count": 18200, "self": 0.4552603219987077, "children": { "env_step": { "total": 626.4035577549871, "count": 18200, "self": 485.2383844989616, "children": { "SubprocessEnvManager._take_step": { "total": 140.71315892000717, "count": 18200, "self": 2.7572833920066273, "children": { "TorchPolicy.evaluate": { "total": 137.95587552800055, "count": 18200, "self": 137.95587552800055 } } }, "workers": { "total": 0.45201433601835106, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 628.8350588250061, "count": 18200, "is_parallel": true, "self": 290.0869080960142, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008539799000004678, "count": 1, "is_parallel": true, "self": 0.006596746000127496, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019430529998771817, "count": 10, "is_parallel": true, "self": 0.0019430529998771817 } } }, "UnityEnvironment.step": { "total": 0.051609858999995595, "count": 1, "is_parallel": true, "self": 0.0009817709999992985, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005574159999923722, "count": 1, "is_parallel": true, "self": 0.0005574159999923722 }, "communicator.exchange": { "total": 0.04751542299999301, "count": 1, "is_parallel": true, "self": 0.04751542299999301 }, "steps_from_proto": { "total": 0.0025552490000109174, "count": 1, "is_parallel": true, "self": 0.000615981000123611, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019392679998873064, "count": 10, "is_parallel": true, "self": 0.0019392679998873064 } } } } } } }, "UnityEnvironment.step": { "total": 338.74815072899185, "count": 18199, "is_parallel": true, "self": 16.461354648018016, "children": { "UnityEnvironment._generate_step_input": { "total": 8.161687908985527, "count": 18199, "is_parallel": true, "self": 8.161687908985527 }, "communicator.exchange": { "total": 267.2559471679942, "count": 18199, "is_parallel": true, "self": 267.2559471679942 }, "steps_from_proto": { "total": 46.86916100399412, "count": 18199, "is_parallel": true, "self": 9.669391974988741, "children": { "_process_rank_one_or_two_observation": { "total": 37.19976902900538, "count": 181990, "is_parallel": true, "self": 37.19976902900538 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022013500006323738, "count": 1, "self": 0.00022013500006323738, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 619.73006950897, "count": 793529, "is_parallel": true, "self": 18.413523699957295, "children": { "process_trajectory": { "total": 345.82192560001187, "count": 793529, "is_parallel": true, "self": 345.20606185901175, "children": { "RLTrainer._checkpoint": { "total": 0.615863741000112, "count": 4, "is_parallel": true, "self": 0.615863741000112 } } }, "_update_policy": { "total": 255.4946202090009, "count": 90, "is_parallel": true, "self": 66.74412219599986, "children": { "TorchPPOOptimizer.update": { "total": 188.75049801300105, "count": 4587, "is_parallel": true, "self": 188.75049801300105 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11242259099981311, "count": 1, "self": 0.0017075109999495908, "children": { "RLTrainer._checkpoint": { "total": 0.11071507999986352, "count": 1, "self": 0.11071507999986352 } } } } } } }