A Study on Genetic Algorithm and Neural Network for Implementing Mini-Games
檔案
本條目沒有附加檔案。
日期
2010-01-01
期刊名稱
INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI 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.