Open Access. Powered by Scholars. Published by Universities.®
Computer Science Faculty Publications
Xpilot; Xpilot-AI; Anytime Learning; Punctuated Anytime Learning; Fitness Biasing; Genetic Algorithm; Real-time Learning; Video Game Learning; On-line Learning
Articles 1 - 1 of 1
Full-Text Articles in Computer Engineering
Fitness Biasing For Evolving An Xpilot Combat Agent, Gary Parker, Phil Fritzsche
Fitness Biasing For Evolving An Xpilot Combat Agent, Gary Parker, Phil Fritzsche
Computer Science Faculty Publications
In this paper we present an application of Fitness Biasing, a type of Punctuated Anytime Learning, for learning autonomous agents in the space combat game Xpilot. Fitness Biasing was originally developed as a means of linking the model to the actual robot in evolutionary robotics. We use fitness biasing with a standard genetic algorithm to learn control programs for a video game agent in real-time. Xpilot-AI, an Xpilot add-on designed for testing learning systems, is used to evolve the controller in the background while periodic checks in normal game play are used to compensate for errors produced by running the …