Risk-sensitive Markov decision problems under model uncertainty: finite time horizon case

TL;DR

This paper investigates risk-sensitive Markov decision processes with finite horizons under model uncertainty, employing adaptive robust control and machine learning to develop solutions.

Contribution

It introduces a novel approach combining adaptive robust control with machine learning for risk-sensitive finite-horizon MDPs under model uncertainty.

Findings

Develops a new framework for risk-sensitive control under uncertainty.

Demonstrates effectiveness through theoretical analysis and simulations.

Bridges adaptive robust control with machine learning techniques.

Abstract

In this paper we study a class of risk-sensitive Markovian control problems in discrete time subject to model uncertainty. We consider a risk-sensitive discounted cost criterion with finite time horizon. The used methodology is the one of adaptive robust control combined with machine learning.