DOI: 10.5176/978-981-08-5480-5_077
Authors: Jonathan Miles, Tony C. Smith
Abstract:
This paper extends current work in machine learning approaches to game AI by showing how continuous learning methods and reinforcement learning can be used to create bot intelligence that continually learns and adapts through game play experience. We begin by outlining a framework for learning static control models for tanks within the game BZFlag, then extend that framework using continuous learning techniques that allow computer controlled tanks to adapt to the game style of other players, extending overall playability by thwarting attempts to infer the underlying AI. We also show how reinforcement learning can be used to create bots that learn how to play based solely through trial and error, providing game engineers with a practical means to produce large numbers of bots, each with individual intelligences and unique behaviours, all from a single initial AI model.
Updating...