English

Linear Convergence of Data-Enabled Policy Optimization for Linear Quadratic Tracking

Systems and Control 2024-10-10 v1 Systems and Control Optimization and Control

Abstract

Data-enabled policy optimization (DeePO) is a newly proposed method to attack the open problem of direct adaptive LQR. In this work, we extend the DeePO framework to the linear quadratic tracking (LQT) with offline data. By introducing a covariance parameterization of the LQT policy, we derive a direct data-driven formulation of the LQT problem. Then, we use gradient descent method to iteratively update the parameterized policy to find an optimal LQT policy. Moreover, by revealing the connection between DeePO and model-based policy optimization, we prove the linear convergence of the DeePO iteration. Finally, a numerical experiment is given to validate the convergence results. We hope our work paves the way to direct adaptive LQT with online closed-loop data.

Keywords

Cite

@article{arxiv.2410.05596,
  title  = {Linear Convergence of Data-Enabled Policy Optimization for Linear Quadratic Tracking},
  author = {Shubo Kang and Feiran Zhao and Keyou You},
  journal= {arXiv preprint arXiv:2410.05596},
  year   = {2024}
}

Comments

6 pages, 1 figures, submitted to ACC 2025

R2 v1 2026-06-28T19:12:18.836Z