{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.009117841720581, "min": 1.009117841720581, "max": 2.867635488510132, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9646.1572265625, "min": 9646.1572265625, "max": 29399.0, "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": 12.358718872070312, "min": 0.48788782954216003, "max": 12.358718872070312, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2409.9501953125, "min": 94.65023803710938, "max": 2473.451171875, "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": 0.07177232639614708, "min": 0.06366998861137523, "max": 0.07403366250418555, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28708930558458834, "min": 0.2591448633134931, "max": 0.3645267212959166, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19541554824978696, "min": 0.1246390436198471, "max": 0.27740663940123483, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7816621929991479, "min": 0.4985561744793884, "max": 1.3548734740299337, "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": 25.15909090909091, "min": 3.9318181818181817, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 173.0, "max": 1316.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.9318181818181817, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 173.0, "max": 1316.0, "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": "1685216853", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1685217311" }, "total": 457.50825711499994, "count": 1, "self": 0.43543479399994567, "children": { "run_training.setup": { "total": 0.04167129299997896, "count": 1, "self": 0.04167129299997896 }, "TrainerController.start_learning": { "total": 457.031151028, "count": 1, "self": 0.5143431570030543, "children": { "TrainerController._reset_env": { "total": 3.9859077959999922, "count": 1, "self": 3.9859077959999922 }, "TrainerController.advance": { "total": 452.396958989997, "count": 18202, "self": 0.25184345999906554, "children": { "env_step": { "total": 452.14511552999795, "count": 18202, "self": 331.2447155310114, "children": { "SubprocessEnvManager._take_step": { "total": 120.65054855998926, "count": 18202, "self": 1.7917032089912936, "children": { "TorchPolicy.evaluate": { "total": 118.85884535099797, "count": 18202, "self": 118.85884535099797 } } }, "workers": { "total": 0.24985143899726836, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 455.51294525901164, "count": 18202, "is_parallel": true, "self": 215.67878910001053, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005974232000028223, "count": 1, "is_parallel": true, "self": 0.0043975059999752375, "children": { "_process_rank_one_or_two_observation": { "total": 0.001576726000052986, "count": 10, "is_parallel": true, "self": 0.001576726000052986 } } }, "UnityEnvironment.step": { "total": 0.0334762850000061, "count": 1, "is_parallel": true, "self": 0.0005536099999972066, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003262519999793767, "count": 1, "is_parallel": true, "self": 0.0003262519999793767 }, "communicator.exchange": { "total": 0.03061104500000056, "count": 1, "is_parallel": true, "self": 0.03061104500000056 }, "steps_from_proto": { "total": 0.001985378000028959, "count": 1, "is_parallel": true, "self": 0.00037229600002319785, "children": { "_process_rank_one_or_two_observation": { "total": 0.001613082000005761, "count": 10, "is_parallel": true, "self": 0.001613082000005761 } } } } } } }, "UnityEnvironment.step": { "total": 239.8341561590011, "count": 18201, "is_parallel": true, "self": 9.632536569012359, "children": { "UnityEnvironment._generate_step_input": { "total": 5.202974324994898, "count": 18201, "is_parallel": true, "self": 5.202974324994898 }, "communicator.exchange": { "total": 192.66518487799578, "count": 18201, "is_parallel": true, "self": 192.66518487799578 }, "steps_from_proto": { "total": 32.33346038699807, "count": 18201, "is_parallel": true, "self": 6.209729522026123, "children": { "_process_rank_one_or_two_observation": { "total": 26.123730864971947, "count": 182010, "is_parallel": true, "self": 26.123730864971947 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011365199998181197, "count": 1, "self": 0.00011365199998181197, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.90489199798577, "count": 420064, "is_parallel": true, "self": 9.439759439979468, "children": { "process_trajectory": { "total": 243.75432228900627, "count": 420064, "is_parallel": true, "self": 242.72959497300621, "children": { "RLTrainer._checkpoint": { "total": 1.0247273160000532, "count": 4, "is_parallel": true, "self": 1.0247273160000532 } } }, "_update_policy": { "total": 195.71081026900004, "count": 90, "is_parallel": true, "self": 77.08643197399891, "children": { "TorchPPOOptimizer.update": { "total": 118.62437829500112, "count": 4587, "is_parallel": true, "self": 118.62437829500112 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1338274329999649, "count": 1, "self": 0.0008860479999839299, "children": { "RLTrainer._checkpoint": { "total": 0.13294138499998098, "count": 1, "self": 0.13294138499998098 } } } } } } }