{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9571115374565125, "min": 0.9571115374565125, "max": 2.8583743572235107, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9149.029296875, "min": 9149.029296875, "max": 29304.052734375, "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": 12.774584770202637, "min": 0.4499974846839905, "max": 12.774584770202637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2491.0439453125, "min": 87.29951477050781, "max": 2588.11962890625, "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": 0.07202842057720808, "min": 0.062169375877619684, "max": 0.07504403808738525, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28811368230883233, "min": 0.24867750351047874, "max": 0.3752201904369262, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17756018995800438, "min": 0.15956462102750427, "max": 0.27692129484870853, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7102407598320175, "min": 0.6382584841100171, "max": 1.342890432067946, "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": 24.886363636363637, "min": 4.340909090909091, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1095.0, "min": 191.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.886363636363637, "min": 4.340909090909091, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1095.0, "min": 191.0, "max": 1380.0, "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": "1712526742", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712527192" }, "total": 449.90739441799997, "count": 1, "self": 0.48318692199995894, "children": { "run_training.setup": { "total": 0.06190400600007706, "count": 1, "self": 0.06190400600007706 }, "TrainerController.start_learning": { "total": 449.36230348999993, "count": 1, "self": 0.5759753079951224, "children": { "TrainerController._reset_env": { "total": 3.167228049999949, "count": 1, "self": 3.167228049999949 }, "TrainerController.advance": { "total": 445.46076711300475, "count": 18206, "self": 0.27822565200131066, "children": { "env_step": { "total": 445.18254146100344, "count": 18206, "self": 288.5601880630081, "children": { "SubprocessEnvManager._take_step": { "total": 156.32424203299774, "count": 18206, "self": 1.4880209830112108, "children": { "TorchPolicy.evaluate": { "total": 154.83622104998653, "count": 18206, "self": 154.83622104998653 } } }, "workers": { "total": 0.29811136499756685, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 448.04880212500257, "count": 18206, "is_parallel": true, "self": 222.12227167599804, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006897148999996716, "count": 1, "is_parallel": true, "self": 0.004120927999338164, "children": { "_process_rank_one_or_two_observation": { "total": 0.002776221000658552, "count": 10, "is_parallel": true, "self": 0.002776221000658552 } } }, "UnityEnvironment.step": { "total": 0.06317328800014366, "count": 1, "is_parallel": true, "self": 0.0006755680003607267, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040184599993153824, "count": 1, "is_parallel": true, "self": 0.00040184599993153824 }, "communicator.exchange": { "total": 0.060034839999843825, "count": 1, "is_parallel": true, "self": 0.060034839999843825 }, "steps_from_proto": { "total": 0.0020610340000075666, "count": 1, "is_parallel": true, "self": 0.00038947799953348294, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016715560004740837, "count": 10, "is_parallel": true, "self": 0.0016715560004740837 } } } } } } }, "UnityEnvironment.step": { "total": 225.92653044900453, "count": 18205, "is_parallel": true, "self": 10.464864017996888, "children": { "UnityEnvironment._generate_step_input": { "total": 5.334448257010308, "count": 18205, "is_parallel": true, "self": 5.334448257010308 }, "communicator.exchange": { "total": 176.25755538301678, "count": 18205, "is_parallel": true, "self": 176.25755538301678 }, "steps_from_proto": { "total": 33.869662790980556, "count": 18205, "is_parallel": true, "self": 6.382984005970002, "children": { "_process_rank_one_or_two_observation": { "total": 27.486678785010554, "count": 182050, "is_parallel": true, "self": 27.486678785010554 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013264700010040542, "count": 1, "self": 0.00013264700010040542, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 439.9532341459028, "count": 698560, "is_parallel": true, "self": 14.511719167978072, "children": { "process_trajectory": { "total": 243.03765774092358, "count": 698560, "is_parallel": true, "self": 241.9297495159235, "children": { "RLTrainer._checkpoint": { "total": 1.1079082250000738, "count": 4, "is_parallel": true, "self": 1.1079082250000738 } } }, "_update_policy": { "total": 182.40385723700115, "count": 90, "is_parallel": true, "self": 50.66259193899896, "children": { "TorchPPOOptimizer.update": { "total": 131.7412652980022, "count": 4587, "is_parallel": true, "self": 131.7412652980022 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15820037200001025, "count": 1, "self": 0.0016410579999046604, "children": { "RLTrainer._checkpoint": { "total": 0.1565593140001056, "count": 1, "self": 0.1565593140001056 } } } } } } }