Split Moves for Monte-Carlo Tree Search


  • Jakub Kowalski University of Wrocław
  • Maksymilian Mika University of Wrocław
  • Wojciech Pawlik University of Wrocław
  • Jakub Sutowicz University of Wrocław
  • Marek Szykuła University of Wrocław
  • Mark H. M. Winands Maastricht University




Search And Optimization (SO)


In many games, moves consist of several decisions made by the player. These decisions can be viewed as separate moves, which is already a common practice in multi-action games for efficiency reasons. Such division of a player move into a sequence of simpler / lower level moves is called splitting. So far, split moves have been applied only in forementioned straightforward cases, and furthermore, there was almost no study revealing its impact on agents' playing strength. Taking the knowledge-free perspective, we aim to answer how to effectively use split moves within Monte-Carlo Tree Search (MCTS) and what is the practical impact of split design on agents' strength. This paper proposes a generalization of MCTS that works with arbitrarily split moves. We design several variations of the algorithm and try to measure the impact of split moves separately on efficiency, quality of MCTS, simulations, and action-based heuristics. The tests are carried out on a set of board games and performed using the Regular Boardgames General Game Playing formalism, where split strategies of different granularity can be automatically derived based on an abstract description of the game. The results give an overview of the behavior of agents using split design in different ways. We conclude that split design can be greatly beneficial for single- as well as multi-action games.




How to Cite

Kowalski, J., Mika, M., Pawlik, W., Sutowicz, J., Szykuła, M., & Winands, M. H. M. (2022). Split Moves for Monte-Carlo Tree Search. Proceedings of the AAAI Conference on Artificial Intelligence, 36(9), 10247-10255. https://doi.org/10.1609/aaai.v36i9.21265



AAAI Technical Track on Search and Optimization