TY - JOUR
T1 - A Survey of Monte Carlo Tree Search Methods
AU - Browne, Cameron
AU - Powley, Edward Jack
AU - Whitehouse, Daniel
AU - Lucas, Simon M.
AU - Cowling, Peter I.
AU - Rohlfshagen, Philipp
AU - Tavener, Stephen
AU - Liebana, Diego Perez
AU - Samothrakis, Spyridon
AU - Colton, Simon
N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.
PY - 2012
Y1 - 2012
N2 - Monte Carlo tree search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling. It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains. This paper is a survey of the literature to date, intended to provide a snapshot of the state of the art after the first five years of MCTS research. We outline the core algorithm's derivation, impart some structure on the many variations and enhancements that have been proposed, and summarize the results from the key game and nongame domains to which MCTS methods have been applied. A number of open research questions indicate that the field is ripe for future work.
AB - Monte Carlo tree search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling. It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains. This paper is a survey of the literature to date, intended to provide a snapshot of the state of the art after the first five years of MCTS research. We outline the core algorithm's derivation, impart some structure on the many variations and enhancements that have been proposed, and summarize the results from the key game and nongame domains to which MCTS methods have been applied. A number of open research questions indicate that the field is ripe for future work.
U2 - 10.1109/TCIAIG.2012.2186810
DO - 10.1109/TCIAIG.2012.2186810
M3 - Article
VL - 4
SP - 1
EP - 43
JO - IEEE Trans. Comput. Intell. AI Games
JF - IEEE Trans. Comput. Intell. AI Games
IS - 1
ER -