Approximate solution for three-player mixed-zero-sum nonlinear game via ADP structure

Yongfeng Lv, Xuemei Ren*, Jing Na, Qinqin Yang, Linwei Li

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In this paper, a three-player mixed-zero-sum game situation with nonlinear dynamics is proposed, and an approximate dynamic programming (ADP) learning scheme is used to solve the proposed problem. First, the problem formulation is presented. A value function for player 1 and 2 nonzero-sum game is constructed, another value function for player 1 and 3 zero-sum game is presented for three-player nonlinear game system. Because of the difficulty to solve the nonlinear Hamilton-Jacobi (HJ) equation, the single-layer critic neural networks are used to approximate the optimal value functions. Then the approximated critic neural networks (NNs) are directly used to learn the optimal solutions for three-player mixed-zero-sum nonlinear game. A novel adaptive law with the estimation performance index is proposed to estimate the unknown coefficient vector. Finally, a simulation example is presented to illustrate the proposed methods.

源语言英语
主期刊名Proceedings of 2017 Chinese Intelligent Systems Conference
编辑Junping Du, Weicun Zhang, Yingmin Jia
出版商Springer Verlag
351-361
页数11
ISBN(印刷版)9789811064951
DOI
出版状态已出版 - 2018
活动Chinese Intelligent Systems Conference, CISC 2017 - Mudanjiang, 中国
期限: 14 10月 201715 10月 2017

出版系列

姓名Lecture Notes in Electrical Engineering
459
ISSN(印刷版)1876-1100
ISSN(电子版)1876-1119

会议

会议Chinese Intelligent Systems Conference, CISC 2017
国家/地区中国
Mudanjiang
时期14/10/1715/10/17

指纹

探究 'Approximate solution for three-player mixed-zero-sum nonlinear game via ADP structure' 的科研主题。它们共同构成独一无二的指纹。

引用此