Title :
Investigating the effects of learning speeds on Xpilot agent evolution
Author :
Parker, Gary ; Fritzsche, Phil
Author_Institution :
Comput. Sci., Connecticut Coll., New London, CT, USA
Abstract :
In this paper we present a comparison of the effects of varying play speeds on a genetic algorithm in the space combat game Xpilot. Xpilot-AI, an Xpilot add-on designed for testing learning systems, is used to evolve the controller for an Xpilot combat agent at varying frames per second to determine an optimal speed for learning. The controller is a rule-based system modified to work with a genetic algorithm that learns numeric parameters for the agent´s rule base. The goal of this research is to increase the quality and speed of standard learning algorithms in Xpilot as well as determine a suitable speed for employing Punctuated Anytime Learning (PAL) in the Xpilot-AI environment. PAL is the learning component of an overall system of autonomous agent control with real-time learning.
Keywords :
computer games; genetic algorithms; knowledge based systems; learning (artificial intelligence); Xpilot agent evolution; Xpilot combat agent controller; Xpilot-AI environment; autonomous agent control; genetic algorithm; learning component; learning speeds; learning systems testing; numeric parameters; optimal speed; punctuated anytime learning; real-time learning; rule base; rule-based system; space combat game Xpilot; standard learning algorithms; Games; Genetic algorithms; Learning systems; Marine vehicles; Radar tracking; Real time systems; Servers; Autonomous system control; Fitness Biasing; Genetic Algorithm; On-line learning; Punctuated Anytime Learning; Real-time Learning; Video Game Learning; Xpilot; Xpilot-AI;
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
978-1-4577-0652-3
DOI :
10.1109/ICSMC.2011.6084062
