Istvan Szita, András Lörincz
Optimistic initialization and greediness lead to polynomial time learning in factored MDPs
ICML, 2009.
@inproceedings{ICML-2009-SzitaL,
author = "Istvan Szita and András Lörincz",
booktitle = "{Proceedings of the 26th International Conference on Machine Learning}",
doi = "10.1145/1553374.1553502",
isbn = "978-1-60558-516-1",
pages = "1001--1008",
publisher = "{ACM}",
series = "{ACM International Conference Proceeding Series}",
title = "{Optimistic initialization and greediness lead to polynomial time learning in factored MDPs}",
volume = 382,
year = 2009,
}











