Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes
Multiagent Systems
2023-12-20 v1 Optimization and Control
Abstract
Long-run average optimization problems for Markov decision processes (MDPs) require constructing policies with optimal steady-state behavior, i.e., optimal limit frequency of visits to the states. However, such policies may suffer from local instability, i.e., the frequency of states visited in a bounded time horizon along a run differs significantly from the limit frequency. In this work, we propose an efficient algorithmic solution to this problem.
Cite
@article{arxiv.2312.12325,
title = {Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes},
author = {David Klaška and Antonín Kučera and Vojtěch Kůr and Vít Musil and Vojtěch Řehák},
journal= {arXiv preprint arXiv:2312.12325},
year = {2023}
}