{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0957657098770142, "min": 1.0952751636505127, "max": 2.886594295501709, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10522.638671875, "min": 10522.638671875, "max": 29561.61328125, "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": 11.972090721130371, "min": 0.33043214678764343, "max": 11.972090721130371, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2334.5576171875, "min": 64.10383605957031, "max": 2401.071044921875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0679930879650159, "min": 0.063102822146189, "max": 0.07577781814581933, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2719723518600636, "min": 0.252411288584756, "max": 0.3693665283276727, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.217367370265956, "min": 0.10154086819338594, "max": 0.2803473631540935, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.869469481063824, "min": 0.40616347277354375, "max": 1.4017368157704673, "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": 24.136363636363637, "min": 2.9318181818181817, "max": 24.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1062.0, "min": 129.0, "max": 1291.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.136363636363637, "min": 2.9318181818181817, "max": 24.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1062.0, "min": 129.0, "max": 1291.0, "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": "1702843236", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702843694" }, "total": 458.71762326600003, "count": 1, "self": 0.4848353159999874, "children": { "run_training.setup": { "total": 0.05130980100000215, "count": 1, "self": 0.05130980100000215 }, "TrainerController.start_learning": { "total": 458.18147814900004, "count": 1, "self": 0.568367198001738, "children": { "TrainerController._reset_env": { "total": 2.8879297090000478, "count": 1, "self": 2.8879297090000478 }, "TrainerController.advance": { "total": 454.59770647799826, "count": 18214, "self": 0.2795517560043095, "children": { "env_step": { "total": 454.31815472199395, "count": 18214, "self": 298.0845978029893, "children": { "SubprocessEnvManager._take_step": { "total": 155.9490529979933, "count": 18214, "self": 1.4953364680027903, "children": { "TorchPolicy.evaluate": { "total": 154.45371652999052, "count": 18214, "self": 154.45371652999052 } } }, "workers": { "total": 0.2845039210113214, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 456.83343330099785, "count": 18214, "is_parallel": true, "self": 227.33657575500308, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0052049470000383735, "count": 1, "is_parallel": true, "self": 0.0037597770001411845, "children": { "_process_rank_one_or_two_observation": { "total": 0.001445169999897189, "count": 10, "is_parallel": true, "self": 0.001445169999897189 } } }, "UnityEnvironment.step": { "total": 0.03848810200003072, "count": 1, "is_parallel": true, "self": 0.000642226000024948, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042978900000889553, "count": 1, "is_parallel": true, "self": 0.00042978900000889553 }, "communicator.exchange": { "total": 0.03535815300000422, "count": 1, "is_parallel": true, "self": 0.03535815300000422 }, "steps_from_proto": { "total": 0.002057933999992656, "count": 1, "is_parallel": true, "self": 0.00044716000013522716, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016107739998574289, "count": 10, "is_parallel": true, "self": 0.0016107739998574289 } } } } } } }, "UnityEnvironment.step": { "total": 229.49685754599477, "count": 18213, "is_parallel": true, "self": 10.930229734989268, "children": { "UnityEnvironment._generate_step_input": { "total": 5.680930469003329, "count": 18213, "is_parallel": true, "self": 5.680930469003329 }, "communicator.exchange": { "total": 177.63684563999385, "count": 18213, "is_parallel": true, "self": 177.63684563999385 }, "steps_from_proto": { "total": 35.248851702008324, "count": 18213, "is_parallel": true, "self": 6.609905587051799, "children": { "_process_rank_one_or_two_observation": { "total": 28.638946114956525, "count": 182130, "is_parallel": true, "self": 28.638946114956525 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016437800002222502, "count": 1, "self": 0.00016437800002222502, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 449.0342942039619, "count": 682579, "is_parallel": true, "self": 14.35614216901564, "children": { "process_trajectory": { "total": 248.26918857594677, "count": 682579, "is_parallel": true, "self": 247.09509125194683, "children": { "RLTrainer._checkpoint": { "total": 1.1740973239999448, "count": 4, "is_parallel": true, "self": 1.1740973239999448 } } }, "_update_policy": { "total": 186.4089634589995, "count": 90, "is_parallel": true, "self": 57.66485585899096, "children": { "TorchPPOOptimizer.update": { "total": 128.74410760000853, "count": 4584, "is_parallel": true, "self": 128.74410760000853 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12731038599997646, "count": 1, "self": 0.0007997659998864037, "children": { "RLTrainer._checkpoint": { "total": 0.12651062000009006, "count": 1, "self": 0.12651062000009006 } } } } } } }