Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

Online reinforcement learning multiplayer non-zero sum games of continuous-time Markov jump linear systems

Xin, X., Tu, Y., Stojanovic, V., Wang, H.ORCID: 0000-0003-2789-9530, Shi, K., He, S. and Pan, T. (2022) Online reinforcement learning multiplayer non-zero sum games of continuous-time Markov jump linear systems. Applied Mathematics and Computation, 412 . Art. 126537.

Link to Published Version: https://doi.org/10.1016/j.amc.2021.126537
*Subscription may be required

Abstract

In this paper, a novel online mode-free integral reinforcement learning algorithm is proposed to solve the multiplayer non-zero sum games. We first collect and learn the subsystems information of states and inputs; then we use the online learning to compute the corresponding coupled algebraic Riccati equations. The policy iterative algorithm proposed in this paper can solve the coupled algebraic Riccati equations corresponding to the multiplayer non-zero sum games. Finally, the effectiveness and feasibility of the design method of this paper is proved by simulation example with three players.

Item Type: Journal Article
Murdoch Affiliation(s): Engineering and Energy
Publisher: Elsevier
Copyright: © 2021 Elsevier Inc.
URI: http://researchrepository.murdoch.edu.au/id/eprint/61870
Item Control Page Item Control Page