This repository is by Quang Huy Dao and Duc Cuong Nguyen and contains source code to reproduce the experiments in our paper "A model free approach for continuous-time optimal tracking control with unknown user-define cost and constrained control input via advantage function.".
This paper introduces a novel off-policy continuous-time Q-learning framework for solving LQR and LQT problems with input constraints. By leveraging an Advantage function for linear continuous systems, the method eliminates the need for prior weight matrices, state resetting, or predefined controllers, and provides model-free algorithms validated through F-16 aircraft simulations.
If you find this repository helpful in your publications, please consider citing our paper.
@article{nguyen2025modelfreeapproachcontinuoustime,
title={A model free approach for continuous-time optimal tracking control with unknown user-define cost and constrained control input via advantage function},
author={Duc Cuong Nguyen and Quang Huy Dao and Phuong Nam Dao},
year={2025},
journal={Arxiv},
url={https://arxiv.org/abs/2509.16821},
}