标题: A Study on Genetic Algorithm and Neural Network for Implementing Mini-Games
作者: Charoenkwan, Phasit
Fang, Shih-Wei
Wong, Sai-Keung
资讯工程学系
Department of Computer Science
关键字: artificial intelligence;evolutionary robotics;games
公开日期: 1-一月-2010
摘要: We study on artificial neural network-based controllers which are either trained or evolved by using the supervised or unsupervised learning approach. We employed backpropagation for the supervised method and the genetic algorithm for the unsupervised method. After training the controllers, we applied the controllers to our three newly designed mini-3D games. We performed a comprehensive study on the performance and weaknesses of the controllers. We emerged the controllers as fundamental tools for giving us more understanding about artificial neural network and its effectiveness in imitating players' behaviours.
URI: http://dx.doi.org/10.1109/TAAI.2010.35
http://hdl.handle.net/11536/146515
ISSN: 2376-6816
DOI: 10.1109/TAAI.2010.35
期刊: INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI 2010)
起始页: 158
结束页: 165
显示于类别:Conferences Paper