A new paper was accepted to AAAI 2024!

A paper Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes written by David Klaška, Antonín Kučera, Vojtěch Kůr, Vít Musil, and Vojtěch Řehák, has been accepted to AAAI 2024.

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 in the sense that 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.