An Implementation of Intelligent Game Characters using Neural Networks


The KIPS Transactions:PartB , Vol. 11, No. 7, pp. 831-840, Dec. 2004
10.3745/KIPSTB.2004.11.7.831,   PDF Download:

Abstract

In this paper, we propose a scheme to implement intelligent game characters based on neural networks. Neural networks that implement intelligent game character receive the action of an opponent character and the distance between them, decide intelligent character's action, and output the decision. The neural networks are trained by reinforcement learning using the scores acquired by the actions of two characters as reinforcement values. To show the usefulness of the proposed scheme, a simple fighting action game is implemented and various experiments are performed. Experimental results show that proposed intelligent characters can learn the rule of the game. The proposed scheme can be applied to massively multiple online games as well as fighting action games.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
B. H. Cho, S. H. Jung, Y. R. Seong, H. R. Oh, "An Implementation of Intelligent Game Characters using Neural Networks," The KIPS Transactions:PartB , vol. 11, no. 7, pp. 831-840, 2004. DOI: 10.3745/KIPSTB.2004.11.7.831.

[ACM Style]
Byeong Heon Cho, Sung Hoon Jung, Yeong Rak Seong, and Ha Ryoung Oh. 2004. An Implementation of Intelligent Game Characters using Neural Networks. The KIPS Transactions:PartB , 11, 7, (2004), 831-840. DOI: 10.3745/KIPSTB.2004.11.7.831.