# Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search

1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
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 Go-playing program, Crazy Stone, that won the gold medal of the $9 \times 9$ Go tournament at the 11th Computer Olympiad.
Document type :
Conference papers

Cited literature [27 references]

https://hal.inria.fr/inria-00116992
Contributor : Rémi Coulom <>
Submitted on : Wednesday, November 29, 2006 - 12:12:56 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on: Tuesday, April 6, 2010 - 11:37:51 PM

### File

CG2006.pdf
Publisher files allowed on an open archive

### Identifiers

• HAL Id : inria-00116992, version 1

### Citation

Rémi Coulom. Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search. 5th International Conference on Computer and Games, May 2006, Turin, Italy. ⟨inria-00116992⟩

Record views