AAAI 2024technical2 citations
Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes
David Klaška, Antonín Kučera, Vojtěch Kůr, Vít Musil, Vojtěch Řehák
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.
BibTeX
@article{Klaška_Kučera_Kůr_Musil_Řehák_2024, title={Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29993}, DOI={10.1609/aaai.v38i18.29993}, abstractNote={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.}, number={18}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Klaška, David and Kučera, Antonín and Kůr, Vojtěch and Musil, Vít and Řehák, Vojtěch}, year={2024}, month={Mar.}, pages={20143-20150} }