{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8598994612693787, "min": 0.8551618456840515, "max": 2.8494315147399902, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8172.484375, "min": 8172.484375, "max": 29086.99609375, "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": 12.915642738342285, "min": 0.4292309582233429, "max": 12.915642738342285, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2518.55029296875, "min": 83.27080535888672, "max": 2606.231201171875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07054992502091016, "min": 0.05835223772994461, "max": 0.07712301022661897, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28219970008364065, "min": 0.23340895091977845, "max": 0.37628742314957303, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19764660883183574, "min": 0.1235815040212508, "max": 0.28072217667804045, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.790586435327343, "min": 0.4943260160850032, "max": 1.4036108833902021, "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.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.Environment.CumulativeReward.mean": { "value": 25.704545454545453, "min": 3.6818181818181817, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1131.0, "min": 162.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.704545454545453, "min": 3.6818181818181817, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1131.0, "min": 162.0, "max": 1395.0, "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": "1783025943", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1783026379" }, "total": 436.168201081, "count": 1, "self": 0.4310023230000297, "children": { "run_training.setup": { "total": 0.025865419999945516, "count": 1, "self": 0.025865419999945516 }, "TrainerController.start_learning": { "total": 435.71133333800003, "count": 1, "self": 0.3431382160272278, "children": { "TrainerController._reset_env": { "total": 3.0596087549999993, "count": 1, "self": 3.0596087549999993 }, "TrainerController.advance": { "total": 432.23480614597315, "count": 18192, "self": 0.3565427589742285, "children": { "env_step": { "total": 315.564686523021, "count": 18192, "self": 247.9506123770268, "children": { "SubprocessEnvManager._take_step": { "total": 67.4139402480032, "count": 18192, "self": 1.2138016069973219, "children": { "TorchPolicy.evaluate": { "total": 66.20013864100588, "count": 18192, "self": 66.20013864100588 } } }, "workers": { "total": 0.20013389799100878, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 433.47465337102244, "count": 18192, "is_parallel": true, "self": 215.32823447303508, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00471502799996415, "count": 1, "is_parallel": true, "self": 0.0033341020000534627, "children": { "_process_rank_one_or_two_observation": { "total": 0.001380925999910687, "count": 10, "is_parallel": true, "self": 0.001380925999910687 } } }, "UnityEnvironment.step": { "total": 0.08162919699998383, "count": 1, "is_parallel": true, "self": 0.0005724779998672602, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035242000012658536, "count": 1, "is_parallel": true, "self": 0.00035242000012658536 }, "communicator.exchange": { "total": 0.07690643199998703, "count": 1, "is_parallel": true, "self": 0.07690643199998703 }, "steps_from_proto": { "total": 0.0037978670000029524, "count": 1, "is_parallel": true, "self": 0.00035247399955551373, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034453930004474387, "count": 10, "is_parallel": true, "self": 0.0034453930004474387 } } } } } } }, "UnityEnvironment.step": { "total": 218.14641889798736, "count": 18191, "is_parallel": true, "self": 10.131739752986732, "children": { "UnityEnvironment._generate_step_input": { "total": 5.39940634996924, "count": 18191, "is_parallel": true, "self": 5.39940634996924 }, "communicator.exchange": { "total": 166.69067302803091, "count": 18191, "is_parallel": true, "self": 166.69067302803091 }, "steps_from_proto": { "total": 35.92459976700047, "count": 18191, "is_parallel": true, "self": 6.54915915893821, "children": { "_process_rank_one_or_two_observation": { "total": 29.375440608062263, "count": 181910, "is_parallel": true, "self": 29.375440608062263 } } } } } } } } } } }, "trainer_advance": { "total": 116.31357686397791, "count": 18192, "self": 0.41432151591493493, "children": { "process_trajectory": { "total": 23.663777476062478, "count": 18192, "self": 23.289225295061897, "children": { "RLTrainer._checkpoint": { "total": 0.3745521810005812, "count": 4, "self": 0.3745521810005812 } } }, "_update_policy": { "total": 92.2354778720005, "count": 90, "self": 37.75216583400265, "children": { "TorchPPOOptimizer.update": { "total": 54.48331203799785, "count": 4587, "self": 54.48331203799785 } } } } } } }, "trainer_threads": { "total": 8.239999260695186e-07, "count": 1, "self": 8.239999260695186e-07 }, "TrainerController._save_models": { "total": 0.07377939699972558, "count": 1, "self": 0.0006521129994325747, "children": { "RLTrainer._checkpoint": { "total": 0.073127284000293, "count": 1, "self": 0.073127284000293 } } } } } } }