Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{2396817,
author = {Klaška, David and Kučera, Antonín and Kůr, Vojtěch and Musil, Vít and Řehák, Vojtěch},
address = {Neuveden},
booktitle = {Proceedings of 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)},
doi = {http://dx.doi.org/10.1609/aaai.v38i18.29993},
edition = {Washington, DC,},
editor = {Wooldridge M., Dy J., Natarajan S.},
keywords = {Markov decision processes; invariant distribution},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Neuveden},
isbn = {978-1-57735-887-9},
pages = {20143-20150},
publisher = {AAAI Press},
title = {Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/29993},
year = {2024}
}
TY - JOUR
ID - 2396817
AU - Klaška, David - Kučera, Antonín - Kůr, Vojtěch - Musil, Vít - Řehák, Vojtěch
PY - 2024
TI - Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes
PB - AAAI Press
CY - Neuveden
SN - 9781577358879
KW - Markov decision processes
KW - invariant distribution
UR - https://ojs.aaai.org/index.php/AAAI/article/view/29993
N2 - 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.
ER -
KLAŠKA, David, Antonín KUČERA, Vojtěch KŮR, Vít MUSIL a Vojtěch ŘEHÁK. Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes. In Wooldridge M., Dy J., Natarajan S. \textit{Proceedings of 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)}. Washington, DC,. Neuveden: AAAI Press, 2024, s.~20143-20150. ISBN~978-1-57735-887-9. Dostupné z: https://dx.doi.org/10.1609/aaai.v38i18.29993.
|
