Risk-averse formulations of Stochastic Optimal Control and Markov Decision Processes
Optimization and Control
2025-05-23 v1 Statistics Theory
Statistics Theory
Abstract
The aim of this paper is to investigate risk-averse and distributionally robust modeling of Stochastic Optimal Control (SOC) and Markov Decision Process (MDP). We discuss construction of conditional nested risk functionals, a particular attention is given to the Value-at-Risk measure. Necessary and sufficient conditions for existence of non-randomized optimal policies in the framework of robust SOC and MDP are derived. We also investigate sample complexity of optimization problems involving the Value-at-Risk measure.
Keywords
Cite
@article{arxiv.2505.16651,
title = {Risk-averse formulations of Stochastic Optimal Control and Markov Decision Processes},
author = {Alexander Shapiro and Yan Li},
journal= {arXiv preprint arXiv:2505.16651},
year = {2025}
}