Reinforcement learning is an unsupervisedmachine learning method in the field of ArtificialIntelligence and offers high performance in simulating thethinking ability of a human. However, it requires a trialand-error process to achieve this goal. In the research fieldof game AIs, it is a good approach that can give the nonplayer-characters (NPCs) in digital games more human-likequalities. In this paper, we try to build a Tank-battlecomputer game and use the methodology of reinforcementlearning for the NPCs (the tanks). The goal of this paper isto make this game become more interesting due to theenhanced interactions with the more intelligent NPCs.
展开▼