artificial intelligence, first person shooter game, non-player character, reinforcement learning
This paper describes an architecture for controlling non-player characters (NPC) in the First Person Shooter (FPS) game Unreal Tournament 2004. Specifically, the DRE-Bot architecture is made up of three reinforcement learners, Danger, Replenish and Explore, which use the tabular Sarsa(λ) algorithm. This algorithm enables the NPC to learn through trial and error building up experience over time in an approach inspired by human learning. Experimentation is carried to measure the performance of DRE-Bot when competing against fixed strategy bots that ship with the game. The discount parameter, γ, and the trace parameter, λ, are also varied to see if their values have an effect on the performance.