Simulation of Strategic Evolution in 5-player Werewolf

Abstract

In recent years, the game “Werewolf” has been drawing attention in the field of Artificial Intelligence. In this paper, we propose a method to simulate the evolution of strategy in order to investigate whether a strategy that always dominates other strategies is discovered in the 5-player werewolf regulation in future AI Wolf Competition. As a result of the simulation, we found that we can not reach a strategy that always has a dominant advantage, and eventually the strategy will continue to change periodically.