Iterative Adaptive Dynamic Programming for Solving Unknown Nonlinear Zero-Sum Game Based on Online Data

doi:10.1109/TNNLS.2016.2561300

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 > 深度强化学习

	Iterative Adaptive Dynamic Programming for Solving Unknown Nonlinear Zero-Sum Game Based on Online Data
	Zhu, Yuanheng1 ; Zhao, Dongbin1,2 ; Li, Xiangjun 3
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2017-03-01
卷号	28 期号:3 页码:714-725
关键词	Adaptive Dynamic Programming (Adp) H-infinity Control Policy Iteration (Pi) Zero-sum Game (Zsg)
DOI	10.1109/TNNLS.2016.2561300
文献子类	Article
英文摘要	H-infinity control is a powerful method to solve the disturbance attenuation problems that occur in some control systems. The design of such controllers relies on solving the zero-sum game (ZSG). But in practical applications, the exact dynamics is mostly unknown. Identification of dynamics also produces errors that are detrimental to the control performance. To overcome this problem, an iterative adaptive dynamic programming algorithm is proposed in this paper to solve the continuous-time, unknown nonlinear ZSG with only online data. A model-free approach to the Hamilton-Jacobi-Isaacs equation is developed based on the policy iteration method. Control and disturbance policies and value are approximated by neural networks (NNs) under the critic-actor-disturber structure. The NN weights are solved by the least-squares method. According to the theoretical analysis, our algorithm is equivalent to a Gauss-Newton method solving an optimization problem, and it converges uniformly to the optimal solution. The online data can also be used repeatedly, which is highly efficient. Simulation results demonstrate its feasibility to solve the unknown nonlinear ZSG. When compared with other algorithms, it saves a significant amount of online measurement time.
WOS关键词	H-INFINITY CONTROL ; STATE-FEEDBACK CONTROL ; DISCRETE-TIME-SYSTEMS ; POLICY UPDATE ALGORITHM ; LEARNING ALGORITHM ; CRITIC DESIGNS ; CONTROL LAWS ; APPROXIMATION ; EQUATIONS
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000395980500020
资助机构	National Natural Science Foundation of China(61273136 ; Beijing Nova Program(Z141101001814094) ; Science and Technology Foundation of State Grid Corporation of China(DG71-14-032) ; 61573353 ; 61533017)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/14403]
专题	复杂系统管理与控制国家重点实验室_深度强化学习
作者单位	1.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.China Elect Power Res Inst, State Key Lab Control & Operat Renewable Energy &, Beijing 100192, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Yuanheng,Zhao, Dongbin,Li, Xiangjun. Iterative Adaptive Dynamic Programming for Solving Unknown Nonlinear Zero-Sum Game Based on Online Data[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2017,28(3):714-725.
APA	Zhu, Yuanheng,Zhao, Dongbin,&Li, Xiangjun.(2017).Iterative Adaptive Dynamic Programming for Solving Unknown Nonlinear Zero-Sum Game Based on Online Data.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,28(3),714-725.
MLA	Zhu, Yuanheng,et al."Iterative Adaptive Dynamic Programming for Solving Unknown Nonlinear Zero-Sum Game Based on Online Data".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 28.3(2017):714-725.