{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7928336262702942, "min": 0.7507674098014832, "max": 2.8537838459014893, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7569.9755859375, "min": 7569.9755859375, "max": 29225.599609375, "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": 12.791764259338379, "min": 0.4743441641330719, "max": 12.791764259338379, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2494.39404296875, "min": 92.02276611328125, "max": 2586.93310546875, "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": 0.07112650568995055, "min": 0.060804472821816016, "max": 0.07487771913007486, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2845060227598022, "min": 0.24599911733143837, "max": 0.3743885956503743, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20910304445115957, "min": 0.12892813117850538, "max": 0.28256517159296013, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8364121778046383, "min": 0.5157125247140215, "max": 1.365993419406461, "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": 25.25, "min": 3.5681818181818183, "max": 25.345454545454544, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 157.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.5681818181818183, "max": 25.345454545454544, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 157.0, "max": 1394.0, "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": "1718872556", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718873014" }, "total": 458.110457151, "count": 1, "self": 0.44297919699988597, "children": { "run_training.setup": { "total": 0.05691739300004883, "count": 1, "self": 0.05691739300004883 }, "TrainerController.start_learning": { "total": 457.61056056100006, "count": 1, "self": 0.554440277982394, "children": { "TrainerController._reset_env": { "total": 2.955578729000081, "count": 1, "self": 2.955578729000081 }, "TrainerController.advance": { "total": 454.00838315401757, "count": 18202, "self": 0.2689479120313081, "children": { "env_step": { "total": 453.73943524198626, "count": 18202, "self": 294.39929075700707, "children": { "SubprocessEnvManager._take_step": { "total": 159.0545552239762, "count": 18202, "self": 1.4971675689735093, "children": { "TorchPolicy.evaluate": { "total": 157.55738765500269, "count": 18202, "self": 157.55738765500269 } } }, "workers": { "total": 0.28558926100299686, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 456.3954297890002, "count": 18202, "is_parallel": true, "self": 232.0210603049834, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005869451999842568, "count": 1, "is_parallel": true, "self": 0.00412707699956627, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017423750002762972, "count": 10, "is_parallel": true, "self": 0.0017423750002762972 } } }, "UnityEnvironment.step": { "total": 0.03687307299992426, "count": 1, "is_parallel": true, "self": 0.0006894890000239684, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042845500001931214, "count": 1, "is_parallel": true, "self": 0.00042845500001931214 }, "communicator.exchange": { "total": 0.03377880599987293, "count": 1, "is_parallel": true, "self": 0.03377880599987293 }, "steps_from_proto": { "total": 0.001976323000008051, "count": 1, "is_parallel": true, "self": 0.00038694500040037383, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015893779996076773, "count": 10, "is_parallel": true, "self": 0.0015893779996076773 } } } } } } }, "UnityEnvironment.step": { "total": 224.37436948401682, "count": 18201, "is_parallel": true, "self": 10.165036653053448, "children": { "UnityEnvironment._generate_step_input": { "total": 5.372730075992649, "count": 18201, "is_parallel": true, "self": 5.372730075992649 }, "communicator.exchange": { "total": 174.83793942398847, "count": 18201, "is_parallel": true, "self": 174.83793942398847 }, "steps_from_proto": { "total": 33.998663330982254, "count": 18201, "is_parallel": true, "self": 6.365660693998052, "children": { "_process_rank_one_or_two_observation": { "total": 27.6330026369842, "count": 182010, "is_parallel": true, "self": 27.6330026369842 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013104899994687003, "count": 1, "self": 0.00013104899994687003, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.31438429592254, "count": 680246, "is_parallel": true, "self": 14.363728461011078, "children": { "process_trajectory": { "total": 248.26547202991196, "count": 680246, "is_parallel": true, "self": 247.58205086291173, "children": { "RLTrainer._checkpoint": { "total": 0.6834211670002333, "count": 4, "is_parallel": true, "self": 0.6834211670002333 } } }, "_update_policy": { "total": 185.6851838049995, "count": 90, "is_parallel": true, "self": 59.183091499998454, "children": { "TorchPPOOptimizer.update": { "total": 126.50209230500104, "count": 4587, "is_parallel": true, "self": 126.50209230500104 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09202735100006976, "count": 1, "self": 0.0009417609999218257, "children": { "RLTrainer._checkpoint": { "total": 0.09108559000014793, "count": 1, "self": 0.09108559000014793 } } } } } } }