Efficient selectivity and backup operators in Monte-Carlo tree search

DMCA

Efficient selectivity and backup operators in Monte-Carlo tree search (2006)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Rémi Coulom

Venue:	In: Proceedings Computers and Games 2006
Citations:	232 - 3 self

BibTeX

@INPROCEEDINGS{Coulom06efficientselectivity,
    author = {Rémi Coulom},
    title = {Efficient selectivity and backup operators in Monte-Carlo tree search},
    booktitle = {In: Proceedings Computers and Games 2006},
    year = {2006},
    publisher = {Springer-Verlag}
}

OpenURL

Abstract

Abstract. Monte-Carlo evaluation consists in estimating a position by averaging the outcome of several random continuations, and can serve as an evaluation function at the leaves of a min-max tree. This paper presents a new framework to combine tree search with Monte-Carlo evaluation, that does not separate between a min-max phase and a Monte-Carlo phase. Instead of backing-up the min-max value close to the root, and the average value at some depth, a more general backup operator is defined that progressively changes from averaging to min-max as the number of simulations grows. This approach provides a fine-grained control of the tree growth, at the level of individual simulations, and allows efficient selectivity methods. This algorithm was implemented in a 9 × 9 Go-playing program, Crazy Stone, that won the 10th KGS computer-Go tournament. 1

Keyphrases

backup operator monte-carlo tree search efficient selectivity monte-carlo evaluation min-max phase tree search several random continuation fine-grained control new framework general backup operator 10th kg computer-go tournament min-max tree average value monte-carlo phase individual simulation tree growth go-playing program efficient selectivity method simulation grows crazy stone min-max value evaluation function

DMCA