Blackwell optimality in risk-sensitive stochastic control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pitera, Marcin, Stettner, Łukasz
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917210368245760
author Pitera, Marcin
Stettner, Łukasz
author_facet Pitera, Marcin
Stettner, Łukasz
contents In this paper, we consider a discrete-time Markov Decision Process (MDP) on a finite state-action space with a long-run risk-sensitive criterion used as the objective function. We discuss the concept of Blackwell optimality and comment on intricacies which arise when the risk-neutral expectation is replaced by the risk-sensitive entropy. Also, we show the relation between the Blackwell optimality and ultimate stationarity and provide an illustrative example that helps to better understand the structural difference between these two concepts.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13136
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Blackwell optimality in risk-sensitive stochastic control
Pitera, Marcin
Stettner, Łukasz
Optimization and Control
Probability
In this paper, we consider a discrete-time Markov Decision Process (MDP) on a finite state-action space with a long-run risk-sensitive criterion used as the objective function. We discuss the concept of Blackwell optimality and comment on intricacies which arise when the risk-neutral expectation is replaced by the risk-sensitive entropy. Also, we show the relation between the Blackwell optimality and ultimate stationarity and provide an illustrative example that helps to better understand the structural difference between these two concepts.
title Blackwell optimality in risk-sensitive stochastic control
topic Optimization and Control
Probability
url https://arxiv.org/abs/2601.13136