{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9914730787277222, "min": 0.9914730787277222, "max": 2.873957633972168, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9499.3037109375, "min": 9499.3037109375, "max": 29495.427734375, "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": 12.96503734588623, "min": 0.3656828999519348, "max": 12.96503734588623, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2528.182373046875, "min": 70.9424819946289, "max": 2602.71875, "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": 0.06374345075849253, "min": 0.06169963288562476, "max": 0.07582122400430415, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2549738030339701, "min": 0.24679853154249903, "max": 0.36523728684508516, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20116959263881046, "min": 0.09848128757256941, "max": 0.2898164811525859, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8046783705552418, "min": 0.39392515029027764, "max": 1.3678632022119035, "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": 25.886363636363637, "min": 2.8636363636363638, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 126.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 2.8636363636363638, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 126.0, "max": 1393.0, "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": "1707941657", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707942274" }, "total": 616.9848276049999, "count": 1, "self": 0.5305121579997376, "children": { "run_training.setup": { "total": 0.07121669399998609, "count": 1, "self": 0.07121669399998609 }, "TrainerController.start_learning": { "total": 616.3830987530001, "count": 1, "self": 0.9253966029928051, "children": { "TrainerController._reset_env": { "total": 4.86483831399994, "count": 1, "self": 4.86483831399994 }, "TrainerController.advance": { "total": 610.4914103100073, "count": 18203, "self": 0.44134618003295145, "children": { "env_step": { "total": 610.0500641299743, "count": 18203, "self": 469.4286792179771, "children": { "SubprocessEnvManager._take_step": { "total": 140.18064394098474, "count": 18203, "self": 2.7716976129713657, "children": { "TorchPolicy.evaluate": { "total": 137.40894632801337, "count": 18203, "self": 137.40894632801337 } } }, "workers": { "total": 0.4407409710124739, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 614.3191371800239, "count": 18203, "is_parallel": true, "self": 289.1690472830177, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007789372000047479, "count": 1, "is_parallel": true, "self": 0.0055618820002791836, "children": { "_process_rank_one_or_two_observation": { "total": 0.002227489999768295, "count": 10, "is_parallel": true, "self": 0.002227489999768295 } } }, "UnityEnvironment.step": { "total": 0.05753250100008245, "count": 1, "is_parallel": true, "self": 0.0026428850000002058, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005031310000731537, "count": 1, "is_parallel": true, "self": 0.0005031310000731537 }, "communicator.exchange": { "total": 0.04731931200001327, "count": 1, "is_parallel": true, "self": 0.04731931200001327 }, "steps_from_proto": { "total": 0.007067172999995819, "count": 1, "is_parallel": true, "self": 0.0005673890000252868, "children": { "_process_rank_one_or_two_observation": { "total": 0.006499783999970532, "count": 10, "is_parallel": true, "self": 0.006499783999970532 } } } } } } }, "UnityEnvironment.step": { "total": 325.1500898970062, "count": 18202, "is_parallel": true, "self": 15.278682513998433, "children": { "UnityEnvironment._generate_step_input": { "total": 7.886213973984923, "count": 18202, "is_parallel": true, "self": 7.886213973984923 }, "communicator.exchange": { "total": 255.72345804001293, "count": 18202, "is_parallel": true, "self": 255.72345804001293 }, "steps_from_proto": { "total": 46.2617353690099, "count": 18202, "is_parallel": true, "self": 9.199899673961909, "children": { "_process_rank_one_or_two_observation": { "total": 37.06183569504799, "count": 182020, "is_parallel": true, "self": 37.06183569504799 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013422500001070148, "count": 1, "self": 0.00013422500001070148, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 603.3576001671316, "count": 787096, "is_parallel": true, "self": 18.87754923110151, "children": { "process_trajectory": { "total": 321.9403706180301, "count": 787096, "is_parallel": true, "self": 321.37840758902985, "children": { "RLTrainer._checkpoint": { "total": 0.5619630290002533, "count": 4, "is_parallel": true, "self": 0.5619630290002533 } } }, "_update_policy": { "total": 262.539680318, "count": 90, "is_parallel": true, "self": 68.92569046499761, "children": { "TorchPPOOptimizer.update": { "total": 193.6139898530024, "count": 4587, "is_parallel": true, "self": 193.6139898530024 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10131930100010322, "count": 1, "self": 0.0012558180001178698, "children": { "RLTrainer._checkpoint": { "total": 0.10006348299998535, "count": 1, "self": 0.10006348299998535 } } } } } } }