{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7284655570983887, "min": 0.6516228318214417, "max": 2.8669273853302, "count": 80 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6979.42822265625, "min": 6417.11962890625, "max": 29360.203125, "count": 80 }, "SnowballTarget.Step.mean": { "value": 799944.0, "min": 9952.0, "max": 799944.0, "count": 80 }, "SnowballTarget.Step.sum": { "value": 799944.0, "min": 9952.0, "max": 799944.0, "count": 80 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.998396873474121, "min": 0.4160343408584595, "max": 14.025606155395508, "count": 80 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2715.68896484375, "min": 80.71066284179688, "max": 2869.51123046875, "count": 80 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 80 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 80 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07261805048248932, "min": 0.057942750975352654, "max": 0.07971613397510773, "count": 80 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29047220192995726, "min": 0.2417547947820733, "max": 0.37883085382682286, "count": 80 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16717612809118104, "min": 0.12457735050360069, "max": 0.2951477055310034, "count": 80 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6687045123647242, "min": 0.49830940201440277, "max": 1.377832377365991, "count": 80 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.795599401499997e-06, "min": 1.795599401499997e-06, "max": 0.0002979705006765, "count": 80 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.182397605999988e-06, "min": 7.182397605999988e-06, "max": 0.0014712900095699996, "count": 80 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10059850000000001, "min": 0.10059850000000001, "max": 0.19932350000000001, "count": 80 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40239400000000003, "min": 0.40239400000000003, "max": 0.9904299999999999, "count": 80 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.9865149999999955e-05, "min": 3.9865149999999955e-05, "max": 0.00496624265, "count": 80 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00015946059999999982, "min": 0.00015946059999999982, "max": 0.024522457, "count": 80 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.363636363636363, "min": 3.340909090909091, "max": 27.745454545454546, "count": 80 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1204.0, "min": 147.0, "max": 1526.0, "count": 80 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.363636363636363, "min": 3.340909090909091, "max": 27.745454545454546, "count": 80 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1204.0, "min": 147.0, "max": 1526.0, "count": 80 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740847055", "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 --force", "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": "1740849517" }, "total": 2462.438581792, "count": 1, "self": 1.0023434469999302, "children": { "run_training.setup": { "total": 0.030618020000019897, "count": 1, "self": 0.030618020000019897 }, "TrainerController.start_learning": { "total": 2461.405620325, "count": 1, "self": 3.7951732509268368, "children": { "TrainerController._reset_env": { "total": 2.3715797419999944, "count": 1, "self": 2.3715797419999944 }, "TrainerController.advance": { "total": 2455.1050870170734, "count": 72753, "self": 1.807663933004278, "children": { "env_step": { "total": 2453.297423084069, "count": 72753, "self": 1876.6934586979305, "children": { "SubprocessEnvManager._take_step": { "total": 574.6882944080608, "count": 72753, "self": 10.74483610409834, "children": { "TorchPolicy.evaluate": { "total": 563.9434583039624, "count": 72753, "self": 563.9434583039624 } } }, "workers": { "total": 1.915669978077858, "count": 72753, "self": 0.0, "children": { "worker_root": { "total": 2453.450717552986, "count": 72753, "is_parallel": true, "self": 1167.6127296439236, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002658848000010039, "count": 1, "is_parallel": true, "self": 0.0008381720003853843, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018206759996246547, "count": 10, "is_parallel": true, "self": 0.0018206759996246547 } } }, "UnityEnvironment.step": { "total": 0.0480035619998489, "count": 1, "is_parallel": true, "self": 0.0007002350002949242, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048061899997264845, "count": 1, "is_parallel": true, "self": 0.00048061899997264845 }, "communicator.exchange": { "total": 0.04440194199969483, "count": 1, "is_parallel": true, "self": 0.04440194199969483 }, "steps_from_proto": { "total": 0.0024207659998864983, "count": 1, "is_parallel": true, "self": 0.0005604559996754688, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018603100002110295, "count": 10, "is_parallel": true, "self": 0.0018603100002110295 } } } } } } }, "UnityEnvironment.step": { "total": 1285.8379879090626, "count": 72752, "is_parallel": true, "self": 56.30156733117792, "children": { "UnityEnvironment._generate_step_input": { "total": 30.78118091792203, "count": 72752, "is_parallel": true, "self": 30.78118091792203 }, "communicator.exchange": { "total": 1020.7059219539542, "count": 72752, "is_parallel": true, "self": 1020.7059219539542 }, "steps_from_proto": { "total": 178.04931770600842, "count": 72752, "is_parallel": true, "self": 35.31857717452067, "children": { "_process_rank_one_or_two_observation": { "total": 142.73074053148775, "count": 727520, "is_parallel": true, "self": 142.73074053148775 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018092200025421334, "count": 1, "self": 0.00018092200025421334, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2423.8794823976496, "count": 3214330, "is_parallel": true, "self": 76.69925394358233, "children": { "process_trajectory": { "total": 1293.5289633050702, "count": 3214330, "is_parallel": true, "self": 1290.0305020260703, "children": { "RLTrainer._checkpoint": { "total": 3.498461278999912, "count": 16, "is_parallel": true, "self": 3.498461278999912 } } }, "_update_policy": { "total": 1053.651265148997, "count": 363, "is_parallel": true, "self": 255.19505692296707, "children": { "TorchPPOOptimizer.update": { "total": 798.45620822603, "count": 18510, "is_parallel": true, "self": 798.45620822603 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13359939299971302, "count": 1, "self": 0.00366399700033071, "children": { "RLTrainer._checkpoint": { "total": 0.1299353959993823, "count": 1, "self": 0.1299353959993823 } } } } } } }