Exploiting Game Decompositions in Monte Carlo Tree Search - Archive ouverte HAL Access content directly
Conference Papers Year :

Exploiting Game Decompositions in Monte Carlo Tree Search

Abstract

In this paper, we propose a variation of the MCTS framework to perform a search in several trees to exploit game decompositions. Our Multiple Tree MCTS (MT-MCTS) approach builds simultaneously multiple MCTS trees corresponding to the different sub-games and allows , like MCTS algorithms, to evaluate moves while playing. We apply MT-MCTS on decomposed games in the General Game Playing framework. We present encouraging results on single player games showing that this approach is promising and opens new avenues for further research in the domain of decomposition exploitation. Complex compound games are solved from 2 times faster (Incredible) up to 25 times faster (Nonogram).
Fichier principal
Vignette du fichier
Hufschmitt-2019-Exploiting.pdf (377.36 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02317329 , version 1 (16-10-2019)
hal-02317329 , version 2 (11-12-2020)

Identifiers

  • HAL Id : hal-02317329 , version 2

Cite

Aline Hufschmitt, Jean-Noël Vittaut, Nicolas Jouandeau. Exploiting Game Decompositions in Monte Carlo Tree Search. 16th Advances in Computer Games Conference, Aug 2019, Macao, China. ⟨hal-02317329v2⟩
149 View
209 Download

Share

Gmail Facebook Twitter LinkedIn More