Bandit based Monte-Carlo Planning (2006)
Cached
Download Links
- [zaphod.aml.sztaki.hu]
- [www.sztaki.hu]
- [www.ualberta.ca]
- DBLP
Other Repositories/Bibliography
| Venue: | In: ECML-06. Number 4212 in LNCS |
| Citations: | 111 - 4 self |
BibTeX
@INPROCEEDINGS{Kocsis06banditbased,
author = {Levente Kocsis and Csaba Szepesvári},
title = {Bandit based Monte-Carlo Planning},
booktitle = {In: ECML-06. Number 4212 in LNCS},
year = {2006},
pages = {282--293},
publisher = {Springer}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Abstract. For large state-space Markovian Decision Problems Monte-Carlo planning is one of the few viable approaches to find near-optimal solutions. In this paper we introduce a new algorithm, UCT, that applies bandit ideas to guide Monte-Carlo planning. In finite-horizon or discounted MDPs the algorithm is shown to be consistent and finite sample bounds are derived on the estimation error due to sampling. Experimental results show that in several domains, UCT is significantly more efficient than its alternatives. 1
