{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8018127083778381, "min": 0.8018127083778381, "max": 2.8752317428588867, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7655.7080078125, "min": 7655.7080078125, "max": 29476.875, "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": 12.912261962890625, "min": 0.20996831357479095, "max": 12.912261962890625, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2517.89111328125, "min": 40.73385238647461, "max": 2621.166015625, "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": 0.06110212280573786, "min": 0.06110212280573786, "max": 0.0767654090756753, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24440849122295144, "min": 0.24440849122295144, "max": 0.3736472436359298, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20481103087556274, "min": 0.08439051947675133, "max": 0.2766444039695403, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.819244123502251, "min": 0.3375620779070053, "max": 1.3832220198477017, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.106097298000005e-06, "min": 8.106097298000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.242438919200002e-05, "min": 3.242438919200002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10270200000000002, "min": 0.10270200000000002, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41080800000000006, "min": 0.41080800000000006, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014482980000000007, "min": 0.00014482980000000007, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005793192000000003, "min": 0.0005793192000000003, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.363636363636363, "min": 2.3863636363636362, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 105.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 2.3863636363636362, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 105.0, "max": 1405.0, "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": "1718885042", "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": "1718885520" }, "total": 477.68522344300004, "count": 1, "self": 0.44284610100010013, "children": { "run_training.setup": { "total": 0.058045656999979656, "count": 1, "self": 0.058045656999979656 }, "TrainerController.start_learning": { "total": 477.18433168499996, "count": 1, "self": 0.5995798739963902, "children": { "TrainerController._reset_env": { "total": 2.9844894799999793, "count": 1, "self": 2.9844894799999793 }, "TrainerController.advance": { "total": 473.50162696400366, "count": 18201, "self": 0.28672123501473834, "children": { "env_step": { "total": 473.2149057289889, "count": 18201, "self": 307.27699667399315, "children": { "SubprocessEnvManager._take_step": { "total": 165.6441674020001, "count": 18201, "self": 1.5570199299951355, "children": { "TorchPolicy.evaluate": { "total": 164.08714747200497, "count": 18201, "self": 164.08714747200497 } } }, "workers": { "total": 0.29374165299566357, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 475.9074375439899, "count": 18201, "is_parallel": true, "self": 241.28477054398445, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007964906000097471, "count": 1, "is_parallel": true, "self": 0.006195148000074369, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017697580000231028, "count": 10, "is_parallel": true, "self": 0.0017697580000231028 } } }, "UnityEnvironment.step": { "total": 0.0419054110000161, "count": 1, "is_parallel": true, "self": 0.0007316600000422113, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004371290000335648, "count": 1, "is_parallel": true, "self": 0.0004371290000335648 }, "communicator.exchange": { "total": 0.0387422640000068, "count": 1, "is_parallel": true, "self": 0.0387422640000068 }, "steps_from_proto": { "total": 0.001994357999933527, "count": 1, "is_parallel": true, "self": 0.000381039999638233, "children": { "_process_rank_one_or_two_observation": { "total": 0.001613318000295294, "count": 10, "is_parallel": true, "self": 0.001613318000295294 } } } } } } }, "UnityEnvironment.step": { "total": 234.62266700000544, "count": 18200, "is_parallel": true, "self": 10.747182185038469, "children": { "UnityEnvironment._generate_step_input": { "total": 5.727377361982917, "count": 18200, "is_parallel": true, "self": 5.727377361982917 }, "communicator.exchange": { "total": 182.35019312999611, "count": 18200, "is_parallel": true, "self": 182.35019312999611 }, "steps_from_proto": { "total": 35.797914322987936, "count": 18200, "is_parallel": true, "self": 6.840094086995919, "children": { "_process_rank_one_or_two_observation": { "total": 28.957820235992017, "count": 182000, "is_parallel": true, "self": 28.957820235992017 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022942499992950616, "count": 1, "self": 0.00022942499992950616, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 467.5247330800488, "count": 699289, "is_parallel": true, "self": 15.494626534036229, "children": { "process_trajectory": { "total": 258.39921885701233, "count": 699289, "is_parallel": true, "self": 257.45391789101234, "children": { "RLTrainer._checkpoint": { "total": 0.9453009659999907, "count": 4, "is_parallel": true, "self": 0.9453009659999907 } } }, "_update_policy": { "total": 193.63088768900025, "count": 90, "is_parallel": true, "self": 61.5901347340033, "children": { "TorchPPOOptimizer.update": { "total": 132.04075295499695, "count": 4581, "is_parallel": true, "self": 132.04075295499695 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09840594199999941, "count": 1, "self": 0.0010247200000321754, "children": { "RLTrainer._checkpoint": { "total": 0.09738122199996724, "count": 1, "self": 0.09738122199996724 } } } } } } }