Online Pareto optimal control of mean-field stochastic multi-player systems using policy iteration

扫码查看

原文链接

万方数据
维普

外文摘要：In this study,the Pareto optimal strategy problem was investigated for multi-player mean-field stochastic systems governed by Itô differential equations using the reinforcement learning(RL)method.A partially model-free solution for Pareto-optimal control was derived.First,by applying the convexity of cost functions,the Pareto optimal control problem was solved using a weighted-sum optimal control problem.Subsequently,using on-policy RL,we present a novel policy iteration(PI)algorithm based on the H-representation technique.In particular,by alternating between the policy evaluation and policy update steps,the Pareto optimal control policy is obtained when no further improvement occurs in system performance,which eliminates directly solving complicated cross-coupled generalized algebraic Riccati equations(GAREs).Practical numerical examples are presented to demonstrate the effectiveness of the proposed algorithm.

外文关键词：

mean-field stochastic systemsPareto optimal controlpolicy iteration schemeH-representation

作者：

Xiushan JIANG、Yanshuang WANG、Dongya ZHAO、Ling SHI

展开 >

作者单位：

College of New Energy,China University of Petroleum(East China),Qingdao 266580,China

Department of Electronic and Computer Engineering,Hong Kong University of Science and Technology,Hong Kong 999077,China

基金：

国家自然科学基金国家自然科学基金国家自然科学基金山东省自然科学基金中央高校基本科研业务费专项Outstanding Youth Innovation Team in Shandong Higher Education Institutions

项目编号：

621034421232634362373229ZR2021QF08023CX06024A2023KJ061

出版年：

2024

DOI：

10.1007/s11432-023-3982-y

中国科学:信息科学(英文版)

中国科学院

中国科学:信息科学(英文版)

CSTPCDEI

影响因子：0.715

ISSN：1674-733X

年,卷(期)：2024.67(4)

参考文献量33