Continuous-Time Robust Dynamic Programming

Continuous-Time Robust Dynamic Programming
复制标题

连续时间鲁棒动态规划

DOI:
10.1137/18m1214147
复制
发表时间:
2019
影响因子:
2.2
通讯作者:
Jiang, Zhong-Ping
Jiang, Zhong-Ping
中科院分区:
数学2区
文献类型:
--
作者:
Bian, Tao;Jiang, Zhong-Ping

文献摘要

参考文献

被引文献

相似文献

针对一类连续时间动态系统,提出了一种新的理论--鲁棒动态规划。与传统的动态规划方法不同,该理论为分析动态规划算法的稳健性,特别是发展新的自适应最优控制和强化学习方法提供了基本工具。为了展示这一新框架的潜力,文中给出了它在随机最优控制和分散最优控制领域的两个应用实例。文中还给出了两个来自金融和工程行业的数值例子,以及所提出的框架的几个可能的扩展。
This paper presents a new theory, known as robust dynamic programming, for a class of continuous-time dynamical systems. Different from traditional dynamic programming (DP) methods, this new theory serves as a fundamental tool to analyze the robustness of DP algorithms, and, in particular, to develop novel adaptive optimal control and reinforcement learning methods. In order to demonstrate the potential of this new framework, two illustrative applications in the fields of stochastic and decentralized optimal control are presented. Two numerical examples arising from both finance and engineering industries are also given, along with several possible extensions of the proposed framework.
DOI: 10.1137/0309016
发表时间: 1971-05
期刊: Siam Journal on Control
影响因子: --
作者:
U. Haussmann
通讯作者: U. Haussmann
DOI: 10.1287/moor.2016.0779
发表时间: 2016-11-01
影响因子: 1.7
作者:
Lim, Shiau Hong;Xu, Huan;Mannor, Shie
通讯作者: Mannor, Shie
DOI: --
发表时间: 2017
期刊:
影响因子: --
作者:
A. Barto;P. Thomas;R. Sutton
通讯作者: R. Sutton
DOI: 10.1109/9.580874
发表时间: 1997-05-01
影响因子: 6.8
作者:
Tsitsiklis, JN;VanRoy, B
通讯作者: VanRoy, B