{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9788797497749329, "min": 0.9746589660644531, "max": 2.8610353469848633, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9346.34375, "min": 9346.34375, "max": 29299.86328125, "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": 12.789274215698242, "min": 0.29133355617523193, "max": 12.789274215698242, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2493.908447265625, "min": 56.51871109008789, "max": 2584.111328125, "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": 0.07448592353266933, "min": 0.060471451783600694, "max": 0.0760559455780358, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29794369413067734, "min": 0.24561140692294073, "max": 0.3730940358854794, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2103489354691085, "min": 0.13067687000832795, "max": 0.28468339254750924, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.841395741876434, "min": 0.5227074800333118, "max": 1.4206506992672003, "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": 25.363636363636363, "min": 3.727272727272727, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 164.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.727272727272727, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 164.0, "max": 1392.0, "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": "1675944683", "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_kurohige.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": "1675945268" }, "total": 584.9619603660001, "count": 1, "self": 0.4890181850003046, "children": { "run_training.setup": { "total": 0.18703456699995513, "count": 1, "self": 0.18703456699995513 }, "TrainerController.start_learning": { "total": 584.2859076139998, "count": 1, "self": 0.7866650579819634, "children": { "TrainerController._reset_env": { "total": 9.686102796, "count": 1, "self": 9.686102796 }, "TrainerController.advance": { "total": 573.6695053720179, "count": 18201, "self": 0.389742928018336, "children": { "env_step": { "total": 573.2797624439995, "count": 18201, "self": 396.6827395619786, "children": { "SubprocessEnvManager._take_step": { "total": 176.19086702401762, "count": 18201, "self": 2.221441203019481, "children": { "TorchPolicy.evaluate": { "total": 173.96942582099814, "count": 18201, "self": 40.18043856998486, "children": { "TorchPolicy.sample_actions": { "total": 133.78898725101328, "count": 18201, "self": 133.78898725101328 } } } } }, "workers": { "total": 0.4061558580032738, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 582.1210751160023, "count": 18201, "is_parallel": true, "self": 269.33766195499527, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006618852000030984, "count": 1, "is_parallel": true, "self": 0.0034185320000119646, "children": { "_process_rank_one_or_two_observation": { "total": 0.003200320000019019, "count": 10, "is_parallel": true, "self": 0.003200320000019019 } } }, "UnityEnvironment.step": { "total": 0.06289126300004, "count": 1, "is_parallel": true, "self": 0.0006889630000159741, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003369670000097358, "count": 1, "is_parallel": true, "self": 0.0003369670000097358 }, "communicator.exchange": { "total": 0.05909444600001734, "count": 1, "is_parallel": true, "self": 0.05909444600001734 }, "steps_from_proto": { "total": 0.0027708869999969465, "count": 1, "is_parallel": true, "self": 0.0007955740001079903, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019753129998889563, "count": 10, "is_parallel": true, "self": 0.0019753129998889563 } } } } } } }, "UnityEnvironment.step": { "total": 312.78341316100705, "count": 18200, "is_parallel": true, "self": 11.985534325996753, "children": { "UnityEnvironment._generate_step_input": { "total": 6.782450346009568, "count": 18200, "is_parallel": true, "self": 6.782450346009568 }, "communicator.exchange": { "total": 248.7109644149968, "count": 18200, "is_parallel": true, "self": 248.7109644149968 }, "steps_from_proto": { "total": 45.30446407400393, "count": 18200, "is_parallel": true, "self": 10.160746212031597, "children": { "_process_rank_one_or_two_observation": { "total": 35.143717861972334, "count": 182000, "is_parallel": true, "self": 35.143717861972334 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001774790000581561, "count": 1, "self": 0.0001774790000581561, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 568.9400825650479, "count": 545167, "is_parallel": true, "self": 14.398098026049752, "children": { "process_trajectory": { "total": 328.32979906499776, "count": 545167, "is_parallel": true, "self": 327.5447425939978, "children": { "RLTrainer._checkpoint": { "total": 0.7850564709999617, "count": 4, "is_parallel": true, "self": 0.7850564709999617 } } }, "_update_policy": { "total": 226.21218547400042, "count": 90, "is_parallel": true, "self": 81.32864213899592, "children": { "TorchPPOOptimizer.update": { "total": 144.8835433350045, "count": 4587, "is_parallel": true, "self": 144.8835433350045 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14345690899995134, "count": 1, "self": 0.000992774999986068, "children": { "RLTrainer._checkpoint": { "total": 0.14246413399996527, "count": 1, "self": 0.14246413399996527 } } } } } } }