Distributionally Robust Optimal Control and MDP Modeling

Published: 2021/04/28, Updated: 2021/08/14

Robust Optimization, Stochastic Programming bellman equations, distributional robustness, duality, dynamic programming, markov decision processes, optimal control, rectangularity, risk measures, stochastic games Short URL: https://optimization-online.org/?p=17080

In this paper, we discuss Optimal Control and Markov Decision Process (MDP) formulations of multistage optimization problems when the involved probability distributions are not known exactly, but rather are assumed to belong to specified ambiguity families. The aim of this paper is to clarify a connection between such distributionally robust approaches to multistage stochastic optimization.

Article

Download

View Distributionally Robust Optimal Control and MDP Modeling