A study on genetic algorithm and neural network for implementing mini-games

Phasit Charoenkwan*, Shih Wei Fang, Sai-Keung Wong

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2010
Pages158-165
Number of pages8
DOIs
StatePublished - 1 Dec 2010
Event2010 15th Conference on Technologies and Applications of Artificial Intelligence, TAAI 2010 - Hsinchu, Taiwan
Duration: 18 Nov 201020 Nov 2010

Publication series

NameProceedings - International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2010

Conference

Conference2010 15th Conference on Technologies and Applications of Artificial Intelligence, TAAI 2010
Country/TerritoryTaiwan
CityHsinchu
Period18/11/1020/11/10

Keywords

  • Artificial intelligence
  • Evolutionary robotics
  • Games

Fingerprint

Dive into the research topics of 'A study on genetic algorithm and neural network for implementing mini-games'. Together they form a unique fingerprint.

Cite this