{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9276803135871887, "min": 0.9129436016082764, "max": 2.866730213165283, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8816.673828125, "min": 8756.955078125, "max": 29263.58203125, "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": 13.017735481262207, "min": 0.3187365233898163, "max": 13.017735481262207, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2538.45849609375, "min": 61.83488464355469, "max": 2637.0625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0692871280811161, "min": 0.062412251373504715, "max": 0.07287029790025497, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2771485123244644, "min": 0.2570503816472517, "max": 0.36435148950127483, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1838725201201205, "min": 0.10041070651027884, "max": 0.30754461804149197, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.735490080480482, "min": 0.40164282604111534, "max": 1.5052505272860621, "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": 25.931818181818183, "min": 2.8863636363636362, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 127.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.931818181818183, "min": 2.8863636363636362, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1141.0, "min": 127.0, "max": 1407.0, "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": "1752470626", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752471049" }, "total": 423.2995706889999, "count": 1, "self": 0.5051381759998321, "children": { "run_training.setup": { "total": 0.023794581000061044, "count": 1, "self": 0.023794581000061044 }, "TrainerController.start_learning": { "total": 422.770637932, "count": 1, "self": 0.36687014200174417, "children": { "TrainerController._reset_env": { "total": 3.0066049280000016, "count": 1, "self": 3.0066049280000016 }, "TrainerController.advance": { "total": 419.3186000599982, "count": 18192, "self": 0.3775805099941181, "children": { "env_step": { "total": 301.9515442199979, "count": 18192, "self": 232.78158909000092, "children": { "SubprocessEnvManager._take_step": { "total": 68.96537286501109, "count": 18192, "self": 1.248937846014087, "children": { "TorchPolicy.evaluate": { "total": 67.716435018997, "count": 18192, "self": 67.716435018997 } } }, "workers": { "total": 0.20458226498590193, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 421.35534186897064, "count": 18192, "is_parallel": true, "self": 216.82290595597397, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0048655670000243845, "count": 1, "is_parallel": true, "self": 0.0035013420001632767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013642249998611078, "count": 10, "is_parallel": true, "self": 0.0013642249998611078 } } }, "UnityEnvironment.step": { "total": 0.037819503000037, "count": 1, "is_parallel": true, "self": 0.000597999999968124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038921800000935036, "count": 1, "is_parallel": true, "self": 0.00038921800000935036 }, "communicator.exchange": { "total": 0.03499656600001799, "count": 1, "is_parallel": true, "self": 0.03499656600001799 }, "steps_from_proto": { "total": 0.0018357190000415358, "count": 1, "is_parallel": true, "self": 0.0003685540000333276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014671650000082082, "count": 10, "is_parallel": true, "self": 0.0014671650000082082 } } } } } } }, "UnityEnvironment.step": { "total": 204.53243591299668, "count": 18191, "is_parallel": true, "self": 9.775326374017254, "children": { "UnityEnvironment._generate_step_input": { "total": 5.370413355003279, "count": 18191, "is_parallel": true, "self": 5.370413355003279 }, "communicator.exchange": { "total": 157.8817031099877, "count": 18191, "is_parallel": true, "self": 157.8817031099877 }, "steps_from_proto": { "total": 31.50499307398843, "count": 18191, "is_parallel": true, "self": 5.598081523986934, "children": { "_process_rank_one_or_two_observation": { "total": 25.906911550001496, "count": 181910, "is_parallel": true, "self": 25.906911550001496 } } } } } } } } } } }, "trainer_advance": { "total": 116.98947533000614, "count": 18192, "self": 0.4451949250025109, "children": { "process_trajectory": { "total": 26.036067014002583, "count": 18192, "self": 25.646873239002616, "children": { "RLTrainer._checkpoint": { "total": 0.389193774999967, "count": 4, "self": 0.389193774999967 } } }, "_update_policy": { "total": 90.50821339100105, "count": 90, "self": 37.352948381007195, "children": { "TorchPPOOptimizer.update": { "total": 53.155265009993855, "count": 4587, "self": 53.155265009993855 } } } } } } }, "trainer_threads": { "total": 8.720001005713129e-07, "count": 1, "self": 8.720001005713129e-07 }, "TrainerController._save_models": { "total": 0.07856192999997802, "count": 1, "self": 0.0007834079999611276, "children": { "RLTrainer._checkpoint": { "total": 0.07777852200001689, "count": 1, "self": 0.07777852200001689 } } } } } } }