Multiple Overlapping Tiles for Contextual Monte Carlo Tree Search

Arpad Rimmel 1 Fabien Teytaud 1, 2, 3
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
2 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France
Abstract : Monte Carlo Tree Search is a recent algorithm that achieves more and more successes in various domains. We propose an improvement of the Monte Carlo part of the algorithm by modifying the simulations depending on the context. The modification is based on a reward function learned on a tiling of the space of Monte Carlo simulations. The tiling is done by regrouping the Monte Carlo simulations where two moves have been selected by one player. We show that it is very efficient by experimenting on the game of Havannah.
Complete list of metadatas
Contributor : Fabien Teytaud <>
Submitted on : Monday, February 15, 2010 - 10:47:54 AM
Last modification on : Monday, December 9, 2019 - 5:24:06 PM
Long-term archiving on: Thursday, June 30, 2011 - 11:24:42 AM


Files produced by the author(s)


  • HAL Id : inria-00456422, version 1


Arpad Rimmel, Fabien Teytaud. Multiple Overlapping Tiles for Contextual Monte Carlo Tree Search. Evostar, Apr 2010, Istanbul, Turkey. ⟨inria-00456422v1⟩



Record views


Files downloads