Q-Learning for Feedback Nash Strategy of Finite-Horizon Nonzero-Sum Difference Games

Title: Q-Learning for Feedback Nash Strategy of Finite-Horizon Nonzero-Sum Difference Games
Creator: Zhang, Zhaorong; Xu, Juanjuan; Fu, Minyue
Relation: ARC.DP200103507 http://purl.org/au-research/grants/arc/DP200103507
Relation: IEEE Transactions on Cybernetics Vol. 52, Issue 9, p. 9170-9178
Publisher Link: http://dx.doi.org/10.1109/TCYB.2021.3052832
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Resource Type: journal article
Date: 2022
Description: In this article, we study the feedback Nash strategy of the model-free nonzero-sum difference game. The main contribution is to present the Q -learning algorithm for the linear quadratic game without prior knowledge of the system model. It is noted that the studied game is in finite horizon which is novel to the learning algorithms in the literature which are mostly for the infinite-horizon Nash strategy. The key is to characterize the Q -factors in terms of the arbitrary control input and state information. A numerical example is given to verify the effectiveness of the proposed algorithm.
Subject: feedback nash strategy; finite horizon difference game; Q-learning
Identifier: http://hdl.handle.net/1959.13/1466516
Identifier: uon:47573
Identifier: ISSN:2168-2267
Language: eng
Reviewed