Efficient implementation of breadth first search for general video game playing

Abstract

This paper proposes an efficient implementation of Breadth First Search (BFS) for General Video Game Playing (GVGP). This method is specialized for deterministic games, which often cannot be solved by a single action and require a more extensive search to solve. Most existing AI programs cannot search the game space efficiently, and thus perform poorly in deterministic games. To improve the efficiency of tree search, we propose limiting the branching of game tree in BFS. Hash code is assigned to each tree node and used to identify similar game states. A tree node with a game state that has been visited in previous search will not be expanded. Using a deterministic game set for evaluation, our experiment shows that the proposed method outperforms existing methods.