Bounding the Difference between the Values of Robust and Non-Robust Markov Decision Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Neufeld, Ariel, Sester, Julian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918002733088768
author Neufeld, Ariel
Sester, Julian
author_facet Neufeld, Ariel
Sester, Julian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_05520
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bounding the Difference between the Values of Robust and Non-Robust Markov Decision Problems
Neufeld, Ariel
Sester, Julian
Optimization and Control
Probability
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.
title Bounding the Difference between the Values of Robust and Non-Robust Markov Decision Problems
topic Optimization and Control
Probability
url https://arxiv.org/abs/2308.05520