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

2021/04/14 by Tomasz R. Bielecki, Tao Chen, Bielecki, Tomasz R. +3
Economics, Econometrics and Finance · Social Sciences · #49L20 #60J05 #60J20 #62F25 #91A10 #91G10 #91G80 #93C40 #93E35 #FOS: Mathematics #Insurance, Mortality, Demography, Risk Management #Optimization and Control (math.OC) #Stochastic processes and financial applications

paper · pdf · doi:10.48550/arxiv.2104.06915

openalex publication_date 2021/04/14 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

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.

Related

• Risk-sensitive control of continuous time Markov chains
• Adaptive Robust Control Under Model Uncertainty
• Markov Decision Processes with Risk-Sensitive Criteria: An Overview
• Risk-sensitive Semi-Markov Decision Problems with Discounted Cost and General Utilities
• Time-inconsistent Markovian control problems under model uncertainty with application to the mean-variance portfolio selection