English

当前位置: 网站首页 > 科研 > 正文

科研

科研

学术论坛:香港理工大学李迅教授学术报告(6月20日)

发布日期:2022-06-20 浏览次数:

报告题目:Stochastic Linear Quadratic Optimal Control Problem: A Reinforcement Learning Method

报告人:李迅香港理工大学应用数学系

报告时间:2022620 15:00-16:00 (北京时间)

报告地点:腾讯会议 ID 175-964-816

主持人:吴先萍

 

报告摘要:This talk adopts a reinforcement learning (RL) method to solve infinite horizon continuous-time stochastic linear quadratic problems, where the drift and diffusion terms in the dynamics may depend on both the state and control. Based on Bellmans dynamic programming principle, we present an online RL algorithm to attain optimal control with partial system information. This algorithm computes the optimal control rather than estimates the system coefficients and solves the related Riccati equation. It only requires local trajectory information, which significantly simplifies the calculation process. We shed light on our theoretical findings using two numerical examples.

 

简介:李迅,香港理工大学教授,博导,主要研究领域为随机控制和金融应用在《SIAM Journal on Control and Optimization》、《Annals of Applied Probability》、《Journal of Differential Equations》、《IEEE Transactions on Automatic Control》、 《Automatica》、 《Mathematical Finance》等国际期刊上发表多篇论文。

联系方式

地址导航:广州市天河区迎龙路161号广东工业大学数学与统计学院
联系电话:020-87084403 邮政编码:510520
邮箱:yysxxy@gdut.edu.cn

contact

School of Mathematics and Statistics, Guangdong University of Technology Copyright.
No. 161 Yinglong Road, Tianhe District, Guangzhou, 510520, P.R.China ;

广东工业大学数学与统计学院 版权所有 粤ICP备05008833号