Risk-averse formulations of Stochastic Optimal Control and Markov Decision Processes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shapiro, Alexander, Li, Yan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915298152546304
author Shapiro, Alexander
Li, Yan
author_facet Shapiro, Alexander
Li, Yan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16651
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Risk-averse formulations of Stochastic Optimal Control and Markov Decision Processes
Shapiro, Alexander
Li, Yan
Optimization and Control
Statistics Theory
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.
title Risk-averse formulations of Stochastic Optimal Control and Markov Decision Processes
topic Optimization and Control
Statistics Theory
url https://arxiv.org/abs/2505.16651