The ancient oriental game of Go has long been considered a grand challenge for artificial intelligence. For decades, computer Go has defied the classical methods in game tree search that worked so successfully for chess and checkers. How- ever, recent play in computer Go has been transformed by a new paradigm for tree search based on Monte-Carlo methods. Programs based on Monte-Carlo tree search now play at human-master levels and are beginning to challenge top professional players. In this paper we describe the leading algorithms for Monte-Carlo tree search and explain how they have advanced the state of the art in computer Go.
%0 Journal Article
%1 GKSSSST12
%A Gelly, S.
%A Kocsis, L.
%A Schoenauer, M.
%A Sebag, M.
%A Silver, D.
%A Szepesvári, Cs.
%A Teytaud, O.
%D 2012
%J Communications of the ACM
%K Game Go Monte-Carlo UCT, of search, tree
%N 3
%P 106--113
%T The grand challenge of computer Go: Monte Carlo tree search and extensions
%V 55
%X The ancient oriental game of Go has long been considered a grand challenge for artificial intelligence. For decades, computer Go has defied the classical methods in game tree search that worked so successfully for chess and checkers. How- ever, recent play in computer Go has been transformed by a new paradigm for tree search based on Monte-Carlo methods. Programs based on Monte-Carlo tree search now play at human-master levels and are beginning to challenge top professional players. In this paper we describe the leading algorithms for Monte-Carlo tree search and explain how they have advanced the state of the art in computer Go.
@article{GKSSSST12,
abstract = {The ancient oriental game of Go has long been considered a grand challenge for artificial intelligence. For decades, computer Go has defied the classical methods in game tree search that worked so successfully for chess and checkers. How- ever, recent play in computer Go has been transformed by a new paradigm for tree search based on Monte-Carlo methods. Programs based on Monte-Carlo tree search now play at human-master levels and are beginning to challenge top professional players. In this paper we describe the leading algorithms for Monte-Carlo tree search and explain how they have advanced the state of the art in computer Go.},
added-at = {2020-03-17T03:03:01.000+0100},
author = {Gelly, S. and Kocsis, L. and Schoenauer, M. and Sebag, M. and Silver, D. and Szepesv{\'a}ri, {Cs}. and Teytaud, O.},
bibsource = {DBLP, http://dblp.uni-trier.de},
biburl = {https://www.bibsonomy.org/bibtex/2254a3566f89a2f2551bb5c130116e3d0/csaba},
date-added = {2012-06-03 14:31:08 -0600},
date-modified = {2012-06-06 21:29:23 -0600},
ee = {http://doi.acm.org/10.1145/2093548.2093574},
interhash = {dd0a2d1c5be3348d1f6a26aac2e9b7a4},
intrahash = {254a3566f89a2f2551bb5c130116e3d0},
journal = {Communications of the {ACM}},
keywords = {Game Go Monte-Carlo UCT, of search, tree},
number = 3,
pages = {106--113},
pdf = {papers/CACM-MCTS.pdf},
timestamp = {2020-03-17T03:03:01.000+0100},
title = {The grand challenge of computer {G}o: {M}onte {C}arlo tree search and extensions},
volume = 55,
year = 2012
}