Off-Policy Integral Reinforcement Learning Method to Solve Nonlinear Continuous-Time Multiplayer Nonzero-Sum Games

doi:10.1109/TNNLS.2016.2582849

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 平行控制

	Off-Policy Integral Reinforcement Learning Method to Solve Nonlinear Continuous-Time Multiplayer Nonzero-Sum Games
	Song, Ruizhuo 1; Lewis, Frank L.2,3; Wei, Qinglai4
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2017-03-01
卷号	28 期号:3 页码:704-713
关键词	Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Integral Reinforcement Learning (Irl) Nonlinear Systems Nonzero Sum (Nzs) Off-policy
DOI	10.1109/TNNLS.2016.2582849
文献子类	Article
英文摘要	This paper establishes an off-policy integral reinforcement learning (IRL) method to solve nonlinear continuous-time (CT) nonzero-sum (NZS) games with unknown system dynamics. The IRL algorithm is presented to obtain the iterative control and off-policy learning is used to allow the dynamics to be completely unknown. Off-policy IRL is designed to do policy evaluation and policy improvement in the policy iteration algorithm. Critic and action networks are used to obtain the performance index and control for each player. The gradient descent algorithm makes the update of critic and action weights simultaneously. The convergence analysis of the weights is given. The asymptotic stability of the closed-loop system and the existence of Nash equilibrium are proved. The simulation study demonstrates the effectiveness of the developed method for nonlinear CT NZS games with unknown system dynamics.
WOS关键词	OPTIMAL TRACKING CONTROL ; ADAPTIVE OPTIMAL-CONTROL ; H-INFINITY CONTROL ; DIFFERENTIAL-GAMES ; UNKNOWN DYNAMICS ; FEEDBACK-CONTROL ; LINEAR-SYSTEMS ; CONTROL DESIGN ; OUTPUT DATA ; ALGORITHM
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000395980500019
资助机构	Directorate for Biological Sciences through the National Science Foundation(ECCS-1128050) ; National Natural Science Foundation of China(61304079 ; Fundamental Research Funds for the Central Universities(FRF-TP-15-056A3) ; State Key Laboratory of Management and Control for Complex Systems(20150104) ; Office of Naval Research(N00014-13-1-0562) ; Air Force Office of Scientific Research European Office of Aerospace Research and Development(13-3055) ; U.S. Army Research Office(W911NF-11-D-0001) ; China National Natural Science Foundation(61120106011) ; China Education Ministry Project 111(B08015) ; 61433004 ; 61374105)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/14397]
专题	复杂系统管理与控制国家重点实验室_平行控制
作者单位	1.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 2.Univ Texas Arlington, UTA Res Inst, Arlington, TX 76019 USA 3.Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Shenyang 110819, Peoples R China 4.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,Lewis, Frank L.,Wei, Qinglai. Off-Policy Integral Reinforcement Learning Method to Solve Nonlinear Continuous-Time Multiplayer Nonzero-Sum Games[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2017,28(3):704-713.
APA	Song, Ruizhuo,Lewis, Frank L.,&Wei, Qinglai.(2017).Off-Policy Integral Reinforcement Learning Method to Solve Nonlinear Continuous-Time Multiplayer Nonzero-Sum Games.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,28(3),704-713.
MLA	Song, Ruizhuo,et al."Off-Policy Integral Reinforcement Learning Method to Solve Nonlinear Continuous-Time Multiplayer Nonzero-Sum Games".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 28.3(2017):704-713.