{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9820383191108704, "min": 0.9820383191108704, "max": 2.8197500705718994, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9333.2919921875, "min": 9333.2919921875, "max": 28784.0078125, "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": 12.952753067016602, "min": 0.4450951814651489, "max": 12.952753067016602, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2525.786865234375, "min": 86.34846496582031, "max": 2628.18896484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06515374402421431, "min": 0.0631238426443922, "max": 0.07565224988901914, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26061497609685724, "min": 0.2524953705775688, "max": 0.36451163145587395, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18429796003243504, "min": 0.11905707338226813, "max": 0.3063407504529345, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7371918401297402, "min": 0.47622829352907253, "max": 1.317931867989839, "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": 25.818181818181817, "min": 3.75, "max": 26.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 165.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.75, "max": 26.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 165.0, "max": 1392.0, "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": "1741964229", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741964675" }, "total": 446.25922924400015, "count": 1, "self": 0.748686598000063, "children": { "run_training.setup": { "total": 0.026061893000019154, "count": 1, "self": 0.026061893000019154 }, "TrainerController.start_learning": { "total": 445.48448075300007, "count": 1, "self": 0.38867248701080825, "children": { "TrainerController._reset_env": { "total": 3.5161279680000916, "count": 1, "self": 3.5161279680000916 }, "TrainerController.advance": { "total": 441.4256919699892, "count": 18192, "self": 0.4058102019865828, "children": { "env_step": { "total": 316.60936716699234, "count": 18192, "self": 241.2794330009932, "children": { "SubprocessEnvManager._take_step": { "total": 75.10938071999078, "count": 18192, "self": 1.3571175159863742, "children": { "TorchPolicy.evaluate": { "total": 73.75226320400441, "count": 18192, "self": 73.75226320400441 } } }, "workers": { "total": 0.2205534460083527, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 443.73417248799785, "count": 18192, "is_parallel": true, "self": 231.89316994399542, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006064272000003257, "count": 1, "is_parallel": true, "self": 0.004003079999733927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020611920002693296, "count": 10, "is_parallel": true, "self": 0.0020611920002693296 } } }, "UnityEnvironment.step": { "total": 0.03722620700000334, "count": 1, "is_parallel": true, "self": 0.0005993820000185224, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038612299999840616, "count": 1, "is_parallel": true, "self": 0.00038612299999840616 }, "communicator.exchange": { "total": 0.03411317100005817, "count": 1, "is_parallel": true, "self": 0.03411317100005817 }, "steps_from_proto": { "total": 0.00212753099992824, "count": 1, "is_parallel": true, "self": 0.0004487029999609149, "children": { "_process_rank_one_or_two_observation": { "total": 0.001678827999967325, "count": 10, "is_parallel": true, "self": 0.001678827999967325 } } } } } } }, "UnityEnvironment.step": { "total": 211.84100254400244, "count": 18191, "is_parallel": true, "self": 9.968212448000145, "children": { "UnityEnvironment._generate_step_input": { "total": 5.708483323003861, "count": 18191, "is_parallel": true, "self": 5.708483323003861 }, "communicator.exchange": { "total": 162.76010155198867, "count": 18191, "is_parallel": true, "self": 162.76010155198867 }, "steps_from_proto": { "total": 33.40420522100976, "count": 18191, "is_parallel": true, "self": 6.119313771027464, "children": { "_process_rank_one_or_two_observation": { "total": 27.284891449982297, "count": 181910, "is_parallel": true, "self": 27.284891449982297 } } } } } } } } } } }, "trainer_advance": { "total": 124.41051460101028, "count": 18192, "self": 0.476878962007504, "children": { "process_trajectory": { "total": 27.777774584003055, "count": 18192, "self": 27.19469237400324, "children": { "RLTrainer._checkpoint": { "total": 0.5830822099998159, "count": 4, "self": 0.5830822099998159 } } }, "_update_policy": { "total": 96.15586105499972, "count": 90, "self": 38.250527502995965, "children": { "TorchPPOOptimizer.update": { "total": 57.90533355200375, "count": 4587, "self": 57.90533355200375 } } } } } } }, "trainer_threads": { "total": 2.7060000320489053e-06, "count": 1, "self": 2.7060000320489053e-06 }, "TrainerController._save_models": { "total": 0.15398562199993648, "count": 1, "self": 0.0013393340000220633, "children": { "RLTrainer._checkpoint": { "total": 0.15264628799991442, "count": 1, "self": 0.15264628799991442 } } } } } } }