{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8599034547805786, "min": 0.8414961099624634, "max": 2.8584775924682617, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8172.5224609375, "min": 8071.630859375, "max": 29179.33984375, "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": 12.002924919128418, "min": 0.40403759479522705, "max": 12.002924919128418, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2340.5703125, "min": 78.38329315185547, "max": 2427.610107421875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07062157324253349, "min": 0.06457476647554751, "max": 0.07331106125310921, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28248629297013395, "min": 0.25829906590219004, "max": 0.3664743368155506, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19663953317292765, "min": 0.1496253023277877, "max": 0.28000011420717424, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7865581326917106, "min": 0.5985012093111508, "max": 1.4000005710358712, "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": 23.363636363636363, "min": 4.159090909090909, "max": 23.87272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1028.0, "min": 183.0, "max": 1313.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.363636363636363, "min": 4.159090909090909, "max": 23.87272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1028.0, "min": 183.0, "max": 1313.0, "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": "1748721592", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748722055" }, "total": 462.6228980000001, "count": 1, "self": 0.43728250300046057, "children": { "run_training.setup": { "total": 0.025012512999637693, "count": 1, "self": 0.025012512999637693 }, "TrainerController.start_learning": { "total": 462.160602984, "count": 1, "self": 0.4142241919812477, "children": { "TrainerController._reset_env": { "total": 3.3923742970000603, "count": 1, "self": 3.3923742970000603 }, "TrainerController.advance": { "total": 458.2627478650188, "count": 18192, "self": 0.4378761849829971, "children": { "env_step": { "total": 330.1875496160337, "count": 18192, "self": 252.45359817804137, "children": { "SubprocessEnvManager._take_step": { "total": 77.49291266801947, "count": 18192, "self": 1.436652637991756, "children": { "TorchPolicy.evaluate": { "total": 76.05626003002772, "count": 18192, "self": 76.05626003002772 } } }, "workers": { "total": 0.24103876997287443, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 460.6915151670164, "count": 18192, "is_parallel": true, "self": 240.09384697000814, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00593135600001915, "count": 1, "is_parallel": true, "self": 0.004205098000511498, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017262579995076521, "count": 10, "is_parallel": true, "self": 0.0017262579995076521 } } }, "UnityEnvironment.step": { "total": 0.044564486000126635, "count": 1, "is_parallel": true, "self": 0.0006745690002389892, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000436152000020229, "count": 1, "is_parallel": true, "self": 0.000436152000020229 }, "communicator.exchange": { "total": 0.04128212199975678, "count": 1, "is_parallel": true, "self": 0.04128212199975678 }, "steps_from_proto": { "total": 0.0021716430001106346, "count": 1, "is_parallel": true, "self": 0.0004146729997955845, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017569700003150501, "count": 10, "is_parallel": true, "self": 0.0017569700003150501 } } } } } } }, "UnityEnvironment.step": { "total": 220.59766819700826, "count": 18191, "is_parallel": true, "self": 10.431721045064023, "children": { "UnityEnvironment._generate_step_input": { "total": 5.975209259991061, "count": 18191, "is_parallel": true, "self": 5.975209259991061 }, "communicator.exchange": { "total": 169.21125281193963, "count": 18191, "is_parallel": true, "self": 169.21125281193963 }, "steps_from_proto": { "total": 34.979485080013546, "count": 18191, "is_parallel": true, "self": 6.448991169004785, "children": { "_process_rank_one_or_two_observation": { "total": 28.53049391100876, "count": 181910, "is_parallel": true, "self": 28.53049391100876 } } } } } } } } } } }, "trainer_advance": { "total": 127.63732206400209, "count": 18192, "self": 0.5472901109665145, "children": { "process_trajectory": { "total": 29.377509345036742, "count": 18192, "self": 28.937300721037445, "children": { "RLTrainer._checkpoint": { "total": 0.44020862399929683, "count": 4, "self": 0.44020862399929683 } } }, "_update_policy": { "total": 97.71252260799884, "count": 90, "self": 39.812369002973355, "children": { "TorchPPOOptimizer.update": { "total": 57.90015360502548, "count": 4587, "self": 57.90015360502548 } } } } } } }, "trainer_threads": { "total": 1.0690000635804608e-06, "count": 1, "self": 1.0690000635804608e-06 }, "TrainerController._save_models": { "total": 0.09125556099979804, "count": 1, "self": 0.0009824569997363142, "children": { "RLTrainer._checkpoint": { "total": 0.09027310400006172, "count": 1, "self": 0.09027310400006172 } } } } } } }