Asymptotically optimal decentralized control for large population stochastic multiagent systems

doi:10.1109/TAC.2008.929370

CSpace > 系统科学研究所

	Asymptotically optimal decentralized control for large population stochastic multiagent systems
	Li, Tao; Zhang, Ji-Feng
	2008-08-01
发表期刊	IEEE TRANSACTIONS ON AUTOMATIC CONTROL
ISSN	0018-9286
卷号	53 期号:7 页码:1643-1660
摘要	The interaction of interest-coupled decision-makers and the uncertainty of individual behavior are prominent characteristics of multiagent systems (MAS). How to break through the framework of conventional control theory, which aims at single decision-maker and single decision objective, and to extend the methodology and tools in the stochastic adaptive control theory to analyze MAS are of great significance. In this paper, a preliminary exploration is made in this direction, and the decentralized control problem is considered for large population stochastic MAS with coupled cost functions. Different from the deterministic discounted costs in the existing differential game models, a time-averaged stochastic cost function is adopted for each agent. The decentralized control law is constructed based on the state aggregation method and tracking-like quadratic optimal control. By using probability limit theory, the stability and optimality of the closed-loop system are analyzed. The main contributions of this paper include the following points. 1) The concepts of asymptotic Nash-equilibrium in probability and almost surely, respectively, are introduced and the relationship between these concepts is illuminated, which provide necessary tools for analyzing the optimality of the decentralized control laws. 2) The closed-loop system is shown to be almost surely uniformly stable, and bounded independently of the number of agents N. 3) The population state average (PSA) is shown to converge to the infinite population mean (IPM) trajectory in the sense of both L(2)-norm and time average almost surely, as N increases to infinity. 4) The decentralized control law is designed and shown to be almost surely asymptotically optimal; the cost of each agent based on local measurements converges to that based on global measurements almost surely, as N increases to infinity.
关键词	asymptotic Nash equilibrium decentralized control multiagent systems stochastic cost function stochastic differential game
DOI	10.1109/TAC.2008.929370
语种	英语
资助项目	National Natural Foundation of China[60221301] ; National Natural Foundation of China[60674038]
WOS研究方向	Automation & Control Systems ; Engineering
WOS类目	Automation & Control Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:000259263900006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/5794
专题	系统科学研究所
通讯作者	Li, Tao
作者单位	Chinese Acad Sci, Acad Math & Syst Sci, Inst Syst Sci, Key Lab Syst & Control, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Tao,Zhang, Ji-Feng. Asymptotically optimal decentralized control for large population stochastic multiagent systems[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL,2008,53(7):1643-1660.
APA	Li, Tao,&Zhang, Ji-Feng.(2008).Asymptotically optimal decentralized control for large population stochastic multiagent systems.IEEE TRANSACTIONS ON AUTOMATIC CONTROL,53(7),1643-1660.
MLA	Li, Tao,et al."Asymptotically optimal decentralized control for large population stochastic multiagent systems".IEEE TRANSACTIONS ON AUTOMATIC CONTROL 53.7(2008):1643-1660.