Skip to Main content Skip to Navigation
Conference papers

Recherche Monte Carlo multi-arbres pour l'exploitation des jeux décomposés

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 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 (Nono-gramme).
Document type :
Conference papers
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download
Contributor : Tiago de Lima Connect in order to contact the contributor
Submitted on : Tuesday, October 1, 2019 - 12:08:01 AM
Last modification on : Wednesday, April 28, 2021 - 6:44:10 PM


Files produced by the author(s)


  • HAL Id : hal-02301981, version 1


Aline Hufschmitt, Jean-Noël Vittaut, Nicolas Jouandeau. Recherche Monte Carlo multi-arbres pour l'exploitation des jeux décomposés. 13èmes Journées d’Intelligence Artificielle Fondamentale (JIAF 2019), Jul 2019, Toulouse, France. ⟨hal-02301981⟩



Record views


Files downloads