Continuous-Time Robust Dynamic Programming

作者：Tao Bian, Zhong‐Ping Jiang · 发表于：SIAM Journal on Control and Optimization · 年份：2019 · DOI：10.1137/18m1214147 · 被引用次数：50 · 研究领域：Adaptive Dynamic Programming Control、Agricultural risk and resilience、Optimization and Variational Analysis

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.