Applying and Improving Monte-Carlo Tree Search in a Fighting Game AI

This paper evaluates the performance of Monte-Carlo Tree Search (MCTS) in a fighting game Al and proposes an improvement for the algorithm. Most existing fighting game Als rely on rule bases and react to every situation with pre-defined actions, making them predictable for human players. We attempt to overcome this weakness by applying MCTS, which can adapt to different circumstances without relying on pre-defined action patterns or tactics. In this paper, an Al based on Upper Confidence bounds applied to Trees (UCT) and MCTS is first developed. Next, the paper proposes improving the Al with Roulette Selection and a rule base. Through testing and evaluation using Fighting ICE, an international fighting game Al competition platform, it is proven that the aforementioned MCTS-based Al is effective in a fighting game, and our proposed improvement can further enhance its performance.