Title :
Online evolution in Unreal Tournament 2004
Author :
Patrick, Matthew
Author_Institution :
Univ. of York, York, UK
Abstract :
Traditional approaches to game AI often feature behaviour that is scripted and predictable. Previous attempts at adaptive AI have struggled to get agents to learn quickly enough. This paper aims to show adaptation using online evolution is feasible and that it can can be incorporated with minimal change to the existing AI. A new approach is presented for evolving game agents online using an Evolution Strategy.
Keywords :
Internet; artificial intelligence; computer games; evolutionary computation; Unreal Tournament 2004; evolution strategy; feature behaviour; game AI; game agent; online evolution; Analysis of variance; Artificial intelligence; Computer architecture; Conferences; Convergence; Games; Weapons;
Conference_Titel :
Computational Intelligence and Games (CIG), 2010 IEEE Symposium on
Conference_Location :
Dublin
Print_ISBN :
978-1-4244-6295-7
Electronic_ISBN :
978-1-4244-6296-4
DOI :
10.1109/ITW.2010.5593348
