학술논문
Online evolution in Unreal Tournament 2004
Document Type
Conference
Author
Source
Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games Computational Intelligence and Games (CIG), 2010 IEEE Symposium on. :249-256 Aug, 2010
Subject
Language
ISSN
2325-4270
2325-4289
2325-4289
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.