Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics

doi:10.1049/iet-cta.2015.0769

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

	Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics
	Zhu, Yuanheng1 ; Zhao, Dongbin1 ; Li, Xiangjun 2
刊名	IET CONTROL THEORY AND APPLICATIONS
	2016-08-08
卷号	10 期号:12 页码:1339-1347
关键词	Nonlinear Control Systems Continuous Time Systems Learning (Artificial Intelligence) Optimal Control Dynamic Programming Lyapunov Methods Linear Systems Reinforcement Learning Continuous-time Problem Nonlinear Optimal Tracking Problem Adaptive Dynamic Programming Model-free Adaptive Optimal Tracking Algorithm Lyapunov Analysis Linear System
DOI	10.1049/iet-cta.2015.0769
文献子类	Article
英文摘要	The optimal tracking of non-linear systems without knowing system dynamics is an important and intractable problem. Based on the framework of reinforcement learning (RL) and adaptive dynamic programming, a model-free adaptive optimal tracking algorithm is proposed in this study. After constructing an augmented system with the tracking errors and the reference states, the tracking problem is converted to a regulation problem with respect to the new system. Several RL techniques are synthesised to form a novel algorithm which learns the optimal solution online in real time without any information of the system dynamics. Continuous adaptation laws are defined by the current observations and the past experience. The convergence is guaranteed by Lyapunov analysis. Two simulations on a linear and a non-linear systems demonstrate the performance of the proposed approach.
WOS关键词	ADAPTIVE OPTIMAL-CONTROL ; UNKNOWN DYNAMICS ; POLICY ITERATION ; LINEAR-SYSTEMS ; ALGORITHM
WOS研究方向	Automation & Control Systems ; Engineering ; Instruments & Instrumentation
语种	英语
WOS记录号	WOS:000381410000004
资助机构	National Natural Science Foundation of China (NSFC)(61273136 ; Beiing Nova Program(Z141101001814094) ; Science and Technology Foundation of SGCC(DG71-14-032) ; 61573353 ; 61533017)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/12655]
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, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.China Elect Power Res Inst, Elect Engn & New Mat Dept, Beijing 100192, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Yuanheng,Zhao, Dongbin,Li, Xiangjun. Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics[J]. IET CONTROL THEORY AND APPLICATIONS,2016,10(12):1339-1347.
APA	Zhu, Yuanheng,Zhao, Dongbin,&Li, Xiangjun.(2016).Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics.IET CONTROL THEORY AND APPLICATIONS,10(12),1339-1347.
MLA	Zhu, Yuanheng,et al."Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics".IET CONTROL THEORY AND APPLICATIONS 10.12(2016):1339-1347.