中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
A Value Iteration Algorithm for Stochastic Linear Quadratic Regulator

文献类型：期刊论文

作者Wang, Hongxia1; Liu, Yihang2; Liu, Xiangqian1
刊名JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS
出版日期2025-07-18
卷号207期号:2页码:14
关键词Stochastic linear quadratic regulation Reinforcement learning Value iteration Policy iteration
ISSN号0022-3239
DOI10.1007/s10957-025-02777-3
英文摘要In this paper, we propose a novel value iteration algorithm for online adaptive optimal control of discrete-time stochastic linear quadratic regulator (LQR) problems. The algorithm iteratively solves the algebraic Riccati equation (ARE) using online information of states and inputs, without requiring the knowledge of the system dynamics. It does not require a discount factor because the issue of excitation noise bias is not present in our algorithm. Firstly, we review the optimal solution for the stochastic LQR problem. Secondly, we offer an offline model-based algorithm for solving ARE and prove its convergence. Thirdly, we present a data-driven online value iteration algorithm for solving ARE. Finally, we evaluate the proposed algorithm by an example.
资助项目the Original Exploratory Program Project of National Natural Science Foundation of China[62450004] ; Original Exploratory Program Project of National Natural Science Foundation of China[U23A20325] ; National Natural Science Foundation of China[ZR2024MF045] ; Natural Science Foundation of Shandong Province
WOS研究方向Operations Research & Management Science ; Mathematics
语种英语
WOS记录号WOS:001531142000002
出版者SPRINGER/PLENUM PUBLISHERS
源URL[http://119.78.100.204/handle/2XEOYT63/42082]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Wang, Hongxia
作者单位1.Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266510, Peoples R China
2.Chinese Acad Sci, CAS Key Lab AI Safety, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Hongxia,Liu, Yihang,Liu, Xiangqian. A Value Iteration Algorithm for Stochastic Linear Quadratic Regulator[J]. JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS,2025,207(2):14.
APA Wang, Hongxia,Liu, Yihang,&Liu, Xiangqian.(2025).A Value Iteration Algorithm for Stochastic Linear Quadratic Regulator.JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS,207(2),14.
MLA Wang, Hongxia,et al."A Value Iteration Algorithm for Stochastic Linear Quadratic Regulator".JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS 207.2(2025):14.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。