Reinforcement learning for exploratory linear-quadratic two-person zero-sum stochastic differential games

Zhongshi Sun and Guangyan Jia

Applied Mathematics and Computation, 2023, vol. 442, issue C

Abstract: In this paper, we study an entropy-regularized continuous-time linear-quadratic two-person zero-sum stochastic differential game problem from the perspective of reinforcement learning (RL). By the solvability of a discounted algebraic Riccati equation, we construct a Gaussian closed-loop optimal control pair for the problem, which achieves the best tradeoff between exploration and exploitation. Then, in this exploratory framework, we propose an RL algorithm that relies on only partial system information to solve a stochastic H∞ control problem. The corresponding convergence analysis and simulation examples are also provided to verify the efficiency of the proposed algorithm.

Keywords: Reinforcement learning; Entropy regularization; Stochastic differential game; Linear-quadratic problem (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0096300322008311
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:apmaco:v:442:y:2023:i:c:s0096300322008311

DOI: 10.1016/j.amc.2022.127763

Access Statistics for this article

Applied Mathematics and Computation is currently edited by Theodore Simos

More articles in Applied Mathematics and Computation from Elsevier
Bibliographic data for series maintained by Catherine Liu ().