English

Data-driven policy iteration algorithm for continuous-time stochastic linear-quadratic optimal control problems

Optimization and Control 2022-09-30 v1

Abstract

This paper studies a continuous-time stochastic linear-quadratic (SLQ) optimal control problem on infinite-horizon. A data-driven policy iteration algorithm is proposed to solve the SLQ problem. Without knowing three system coefficient matrices, this algorithm uses the collected data to iteratively approximate a solution of the corresponding stochastic algebraic Riccati equation (SARE). A simulation example is provided to illustrate the effectiveness and applicability of the algorithm.

Keywords

Cite

@article{arxiv.2209.14490,
  title  = {Data-driven policy iteration algorithm for continuous-time stochastic linear-quadratic optimal control problems},
  author = {Heng Zhang and Na Li},
  journal= {arXiv preprint arXiv:2209.14490},
  year   = {2022}
}
R2 v1 2026-06-28T02:20:12.305Z