Exploiting Game Decompositions in Monte Carlo Tree Search


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).

16th Advances in Computer Games Conference, ACG 2019, Held in Conjunction with the 28th International Conference on Artificial Intelligence, IJCAI 2019, Macao, China, 11-13 August, 2019