Neural-network-based synchronous iteration learning method for multi-player zero-sum games

doi:10.1016/j.neucom.2017.02.051

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 复杂系统智能机理与平行控制团队

	Neural-network-based synchronous iteration learning method for multi-player zero-sum games
	Song, Ruizhuo 1; Wei, Qinglai2 ; Song, Biao 1
发表期刊	NEUROCOMPUTING
	2017-06-14
卷号	242 页码:73-82
文章类型	Article
摘要	In this paper, a synchronous solution method for multi-player zero-sum games without system dynamics is established based on neural network. The policy iteration (PI) algorithm is presented to solve the Hamilton-Jacobi-Bellman (HJB) equation. It is proven that the obtained iterative cost function is convergent to the optimal game value. For avoiding system dynamics, off-policy learning method is given to obtain the iterative cost function, controls and disturbances based on Pl. Critic neural network (CNN), action neural networks (ANNs) and disturbance neural networks (DNNs) are used to approximate the cost function, controls and disturbances. The weights of neural networks compose the synchronous weight matrix, and the uniformly ultimately bounded (UUB) of the synchronous weight matrix is proven. Two examples are given to show that the effectiveness of the proposed synchronous solution method for multi-player ZS games. (C) 2017 Elsevier B.V. All rights reserved.
关键词	Adaptive Dynamic Programming Approximate Dynamic Programming Adaptive Critic Designs Multi-player Iteration Learning Neural Network
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.neucom.2017.02.051
关键词[WOS]	DISCRETE-TIME-SYSTEMS ; ADAPTIVE TRACKING CONTROL ; NONLINEAR-SYSTEMS ; POLICY ITERATION ; DEAD-ZONE ; DESIGN ; INPUT ; ALGORITHM
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61304079 ; Fundamental Research Funds for the Central Universities(FRF-TP-15-056A3) ; Open Research Project from SKLMCCS(20150104) ; 61673054 ; 61374105)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000399859500007
引用统计	被引频次：34[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/15265
专题	多模态人工智能系统全国重点实验室_复杂系统智能机理与平行控制团队
作者单位	1.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Song, Ruizhuo,Wei, Qinglai,Song, Biao. Neural-network-based synchronous iteration learning method for multi-player zero-sum games[J]. NEUROCOMPUTING,2017,242:73-82.
APA	Song, Ruizhuo,Wei, Qinglai,&Song, Biao.(2017).Neural-network-based synchronous iteration learning method for multi-player zero-sum games.NEUROCOMPUTING,242,73-82.
MLA	Song, Ruizhuo,et al."Neural-network-based synchronous iteration learning method for multi-player zero-sum games".NEUROCOMPUTING 242(2017):73-82.