Skip to Main content Skip to Navigation
Conference papers

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).
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-02317329
Contributor : Jean-Noël Vittaut <>
Submitted on : Friday, December 11, 2020 - 8:37:17 PM
Last modification on : Thursday, April 29, 2021 - 11:53:40 PM

File

Hufschmitt-2019-Exploiting.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02317329, version 2

Citation

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⟩

Share

Metrics

Record views

54

Files downloads

110