Nash Tracking Controls of Multi-input Nonzero-Sum Game System with Reinforcement Learning

Yongfeng Lv, Xuemei Ren, Linwei Li, Jing Na

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper addresses Nash optimal tracking controls of the unknown multi-player game system with a reinforcement learning scheme. We propose a single-layer neural network to approximate the unknown multi-player system, where the system can be accurately identified. It is then used to calculate the Nash tracking controls, which are designed by two parts: the steady-state control and the optimal feedback tracking control. The optimal feedback tracking controls are obtained by using the HJB equation with the reinforcement learning scheme. The convergences of the NN weights and the approximated optimal controls are analyzed. Finally, a simulation is provided to illustrate the effectiveness of the methods in this paper.

Original languageEnglish
Title of host publicationProceedings of the 37th Chinese Control Conference, CCC 2018
EditorsXin Chen, Qianchuan Zhao
PublisherIEEE Computer Society
Pages2765-2769
Number of pages5
ISBN (Electronic)9789881563941
DOIs
Publication statusPublished - 5 Oct 2018
Event37th Chinese Control Conference, CCC 2018 - Wuhan, China
Duration: 25 Jul 201827 Jul 2018

Publication series

NameChinese Control Conference, CCC
Volume2018-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference37th Chinese Control Conference, CCC 2018
Country/TerritoryChina
CityWuhan
Period25/07/1827/07/18

Keywords

  • Multi-input system
  • Nash equilibrium
  • Neural networks
  • Nonzero-sum game
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Nash Tracking Controls of Multi-input Nonzero-Sum Game System with Reinforcement Learning'. Together they form a unique fingerprint.

Cite this