模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2019, Vol. 32 Issue (4): 345-352    DOI: 10.16451/j.cnki.issn1003-6059.201904008
Ressarches and Applications Current Issue| Next Issue| Archive| Adv Search |
Data Driven Optimal Stabilization Control and Simulation Based on Reinforcement Learning
LU Chaolun1, LI Yongqiang1, FENG Yuanjing1
1.College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023

Download: PDF (1204 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Q-learning algorithm is used to solve the optimal stabilization control problem while only the data, rather than the model of the plant, is available. Due to the continuity of state space and control space, Q-learning can only be implemented in an approximate manner. Therefore, the proposed approximate Q-learning algorithm can obtain only one suboptimal controller. Although the obtained controller is suboptimal, the simulation shows that the closed-loop domain of attraction of the proposed algorithm is broader and the cost function is also smaller than the linear quadratic regulator and deep deterministic policy gradient method for the strongly nonlinear plant.


Key wordsQ-Learning      Data Driven      Optimal Control      Domain of Attraction     
Received: 11 October 2018     
ZTFLH: TP 273+.1  
Fund:Supported by National Natural Science Foundation of China(No.61703369), Zhejiang Key Research and Development Program(No.2017C03039), Major Science and Technology Project of Wenzhou(No.ZS2017007)
About author:: LU Chaolun, Ph.D. candidate. His research interests include data-driven control and reinforcement learning.LI Yongqiang, Ph.D., lecturer. His research interests include data-driven control and optimal control.FENG Yuanjing(Corresponding author), Ph.D., professor. His research interests include image processing and intelligent optimization.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
LU Chaolun
LI Yongqiang
FENG Yuanjing
Cite this article:   
LU Chaolun,LI Yongqiang,FENG Yuanjing. Data Driven Optimal Stabilization Control and Simulation Based on Reinforcement Learning[J]. , 2019, 32(4): 345-352.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201904008      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2019/V32/I4/345
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn