Multiple Overlapping Tiles for Contextual Monte Carlo Tree Search

Arpad Rimmel 1 Fabien Teytaud 1, 2, 3
1 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
2 TANC - Algorithmic number theory for cryptology
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
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

Cited literature [12 references]  Display  Hide  Download
Contributor : Fabien Teytaud <>
Submitted on : Wednesday, March 16, 2011 - 3:43:23 PM
Last modification on : Wednesday, March 27, 2019 - 4:41:29 PM


Files produced by the author(s)


  • HAL Id : inria-00456422, version 2



Arpad Rimmel, Fabien Teytaud. Multiple Overlapping Tiles for Contextual Monte Carlo Tree Search. Evostar, Apr 2010, Istanbul, Turkey. ⟨inria-00456422v2⟩



Record views


Files downloads