DRE-Bot: A Hierarchical First Person Shooter Bot Using Multiple Sarsa(λ) Reinforcement Learners
This work addresses the challenge of creating adaptive bots for FPS games, but it is incremental as it applies an existing reinforcement learning method to a specific gaming domain.
The paper tackled the problem of controlling non-player characters in the First Person Shooter game Unreal Tournament 2004 by proposing the DRE-Bot architecture, which uses three reinforcement learners based on the tabular Sarsa(λ) algorithm, and tested its performance against fixed strategy bots, varying parameters like γ and λ to assess their effects.
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.