Work

Bounding the difference between the values of robust and non-robust Markov decision problems

Year: 2024

Type: article

Abstract: In this note we provide an upper bound for the difference between the value function of a distributionally robust Markov decision problem and the value function of a non-robust Markov decision problem, where the ambiguity set of probability kernels of the distributionally robust Markov decision process is described by a Wasserstein ball around some reference kernel whereas the non-robust Markov decision process behaves according to a fixed probability kernel contained in the ambiguity set. Our derived upper bound for the difference between the value functions is dimension-free and depends linearly on the radius of the Wasserstein ball.

Source: Journal of Applied Probability

DOI: 10.1017/jpr.2024.88

Authors: Ariel Neufeld, Julian Sester

Institutions: Nanyang Technological University, National University of Singapore

Language: English

Topic: Risk and Portfolio Optimization

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: hybrid

Estimated APC paid: $3,450

Funder: Ministry of Education, India