{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.932853639125824, "min": 0.932853639125824, "max": 2.857147693634033, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8865.8408203125, "min": 8865.8408203125, "max": 29165.763671875, "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": 13.005616188049316, "min": 0.36463937163352966, "max": 13.005616188049316, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2536.09521484375, "min": 70.74003601074219, "max": 2650.220947265625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06126830381639165, "min": 0.06126830381639165, "max": 0.07127213167145337, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2450732152655666, "min": 0.2450732152655666, "max": 0.3563606583572668, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16774891411849097, "min": 0.1320860469964899, "max": 0.2969515254976703, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6709956564739639, "min": 0.5283441879859596, "max": 1.4442447093771953, "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": 25.545454545454547, "min": 3.8181818181818183, "max": 25.672727272727272, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1124.0, "min": 168.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.545454545454547, "min": 3.8181818181818183, "max": 25.672727272727272, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1124.0, "min": 168.0, "max": 1412.0, "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": "1756653445", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/py310/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756653905" }, "total": 460.7951734440003, "count": 1, "self": 0.443730938000499, "children": { "run_training.setup": { "total": 0.02797632400006478, "count": 1, "self": 0.02797632400006478 }, "TrainerController.start_learning": { "total": 460.3234661819997, "count": 1, "self": 0.3682626139743661, "children": { "TrainerController._reset_env": { "total": 3.522773720999794, "count": 1, "self": 3.522773720999794 }, "TrainerController.advance": { "total": 456.34293409902557, "count": 18192, "self": 0.39212621205024334, "children": { "env_step": { "total": 329.9581281559708, "count": 18192, "self": 254.56071195699724, "children": { "SubprocessEnvManager._take_step": { "total": 75.16086941198091, "count": 18192, "self": 1.3374976829913976, "children": { "TorchPolicy.evaluate": { "total": 73.82337172898951, "count": 18192, "self": 73.82337172898951 } } }, "workers": { "total": 0.23654678699267606, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 458.668531715005, "count": 18192, "is_parallel": true, "self": 234.98839607100808, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006622440999763057, "count": 1, "is_parallel": true, "self": 0.004219573998852866, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024028670009101916, "count": 10, "is_parallel": true, "self": 0.0024028670009101916 } } }, "UnityEnvironment.step": { "total": 0.03579615099988587, "count": 1, "is_parallel": true, "self": 0.0005860109999957785, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037038199980088393, "count": 1, "is_parallel": true, "self": 0.00037038199980088393 }, "communicator.exchange": { "total": 0.032826068000304076, "count": 1, "is_parallel": true, "self": 0.032826068000304076 }, "steps_from_proto": { "total": 0.0020136899997851287, "count": 1, "is_parallel": true, "self": 0.00044138600014775875, "children": { "_process_rank_one_or_two_observation": { "total": 0.00157230399963737, "count": 10, "is_parallel": true, "self": 0.00157230399963737 } } } } } } }, "UnityEnvironment.step": { "total": 223.6801356439969, "count": 18191, "is_parallel": true, "self": 10.647289301008641, "children": { "UnityEnvironment._generate_step_input": { "total": 5.95186084197303, "count": 18191, "is_parallel": true, "self": 5.95186084197303 }, "communicator.exchange": { "total": 171.8130052550091, "count": 18191, "is_parallel": true, "self": 171.8130052550091 }, "steps_from_proto": { "total": 35.26798024600612, "count": 18191, "is_parallel": true, "self": 6.2136517290123265, "children": { "_process_rank_one_or_two_observation": { "total": 29.05432851699379, "count": 181910, "is_parallel": true, "self": 29.05432851699379 } } } } } } } } } } }, "trainer_advance": { "total": 125.9926797310045, "count": 18192, "self": 0.48252781598102956, "children": { "process_trajectory": { "total": 28.4130947090257, "count": 18192, "self": 28.0096038550264, "children": { "RLTrainer._checkpoint": { "total": 0.4034908539993012, "count": 4, "self": 0.4034908539993012 } } }, "_update_policy": { "total": 97.09705720599777, "count": 90, "self": 40.2032915549853, "children": { "TorchPPOOptimizer.update": { "total": 56.89376565101247, "count": 4587, "self": 56.89376565101247 } } } } } } }, "trainer_threads": { "total": 1.0799999472510535e-06, "count": 1, "self": 1.0799999472510535e-06 }, "TrainerController._save_models": { "total": 0.08949466800004302, "count": 1, "self": 0.0009230229998138384, "children": { "RLTrainer._checkpoint": { "total": 0.08857164500022918, "count": 1, "self": 0.08857164500022918 } } } } } } }