Title :
Evolving expert agent parameters for capture the flag agent in Xpilot
Author :
Parker, Gary ; Penrose, Sarah
Author_Institution :
Dept. of Comput. Sci., Connecticut Coll., New London, CT, USA
Abstract :
Xpilot is an open source, 2d space combat game. Xpilot-AI allows a programmer to write scripts that control an agent playing a game of Xpilot. It provides a reasonable environment for testing learning systems for autonomous agents, both video game agents and robots. In previous work, a wide range of techniques have been used to develop controllers that are focused on the combat skills for an Xpilot agent. In this research, a Genetic Algorithm (GA) was used to evolve the parameters for an expert agent solving the more challenging problem of capture the flag.
Keywords :
computer games; genetic algorithms; learning (artificial intelligence); multi-agent systems; public domain software; GA; Xpilot agent; Xpilot-AI; autonomous agents; combat skills; evolving expert agent parameters; flag capture agent; genetic algorithm; learning systems; open source 2d space combat game; robots; video game agents; Biological cells; Games; Genetic algorithms; Marine vehicles; Radar; Sociology; Statistics; Xpilot-AI; autonomous agent; evolutionary computation; genetic algorithm;
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2012 IEEE International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-1-4673-1713-9
Electronic_ISBN :
978-1-4673-1712-2
DOI :
10.1109/ICSMC.2012.6377824