Model-Free Optimal Tracking Control via Critic-Only Q-Learning

doi:10.1109/TNNLS.2016.2585520

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

	Model-Free Optimal Tracking Control via Critic-Only Q-Learning
	Luo, Biao1 ; Liu, Derong 2; Huang, Tingwen 3; Wang, Ding1 ; Luo,Biao
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2016-10-01
卷号	27 期号:10 页码:2134-2144
文章类型	Article
摘要	Model-free control is an important and promising topic in control fields, which has attracted extensive attention in the past few years. In this paper, we aim to solve the model-free optimal tracking control problem of nonaffine non-linear discrete-time systems. A critic-only Q-learning (CoQL) method is developed, which learns the optimal tracking control from real system data, and thus avoids solving the tracking Hamilton-Jacobi-Bellman equation. First, the Q-learning algorithm is proposed based on the augmented system, and its convergence is established. Using only one neural network for approximating the Q-function, the CoQL method is developed to implement the Q-learning algorithm. Furthermore, the convergence of the CoQL method is proved with the consideration of neural network approximation error. With the convergent Q-function obtained from the CoQL method, the adaptive optimal tracking control is designed based on the gradient descent scheme. Finally, the effectiveness of the developed CoQL method is demonstrated through simulation studies. The developed CoQL method learns with off-policy data and implements with a critic-only structure, thus it is easy to realize and overcome the inadequate exploration problem.
其他摘要	无
关键词	Critic-only Q-learning (Coql) Model-free Nonaffine Nonlinear Systems Optimal Tracking Control
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2016.2585520
关键词[WOS]	TIME NONLINEAR-SYSTEMS ; H-INFINITY CONTROL ; ADAPTIVE OPTIMAL-CONTROL ; SPATIALLY DISTRIBUTED PROCESSES ; LINEAR-SYSTEMS ; CONTROL DESIGN ; UNKNOWN DYNAMICS ; CONTROL SCHEME ; ATTITUDE TRACKING ; POLICY ITERATION
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61233001 ; State Key Laboratory of Management and Control for Complex Systems ; National Priorities Research Program through the Qatar National Research Fund (a member of Qatar Foundation)(NPRP 7-1482-1-278) ; 61273140 ; 61304086 ; 61374105 ; 61503377 ; 61533017 ; U1501251)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000384644000012
引用统计	被引频次：247[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/173211/12301
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
通讯作者	Luo,Biao
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 3.Texas A&M Univ Qatar, Doha 23874, Qatar
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Luo, Biao,Liu, Derong,Huang, Tingwen,et al. Model-Free Optimal Tracking Control via Critic-Only Q-Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2016,27(10):2134-2144.
APA	Luo, Biao,Liu, Derong,Huang, Tingwen,Wang, Ding,&Luo,Biao.(2016).Model-Free Optimal Tracking Control via Critic-Only Q-Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,27(10),2134-2144.
MLA	Luo, Biao,et al."Model-Free Optimal Tracking Control via Critic-Only Q-Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 27.10(2016):2134-2144.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2016IEEE TNNLS Model（1521KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载