Exploiting Intelligence in Fighting Action Games Using Neural Networks

Authors:
Byeong Heon Cho;Sung Hoon Jung;Yeong Rak Seong;Ha Ryoung Oh
Affiliations:
The authors are with the School of Electrical Engineering, Kookmin University, Seoul 136--702, Korea. E-mail: bhcho@etri.re.kr, E-mail: yeong@kookmin.ac.kr, E-mail: hroh@kookmin.ac.kr.,;The author is with the Department of Information and Communication Engineering, Hansung University, Seoul 136--792, Korea. E-mail: shjung@hansung.ac.kr,;The authors are with the School of Electrical Engineering, Kookmin University, Seoul 136--702, Korea. E-mail: bhcho@etri.re.kr, E-mail: yeong@kookmin.ac.kr, E-mail: hroh@kookmin.ac.kr.,;The authors are with the School of Electrical Engineering, Kookmin University, Seoul 136--702, Korea. E-mail: bhcho@etri.re.kr, E-mail: yeong@kookmin.ac.kr, E-mail: hroh@kookmin.ac.kr.,
Venue:
IEICE - Transactions on Information and Systems
Year:
2006

Citing 0
Cited 5

Computerized interactive gaming via supporting vector machines

International Journal of Computer Games Technology
Reinforcement learning of intelligent characters in fighting action games

ICEC'06 Proceedings of the 5th international conference on Entertainment Computing
Adaptation of intelligent characters to changes of game environments

CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I
Evolving bot AI in Unreal™

EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I
Comparison of AI techniques for fighting action games - genetic algorithms/neural networks/evolutionary neural networks

ICEC'07 Proceedings of the 6th international conference on Entertainment Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes novel methods to provide intelligence for characters in fighting action games by using neural networks. First, how a character learns basic game rules and matches against randomly acting opponents is considered. Since each action takes more than one time unit in general fighting action games, the results of a character's action are exposed not immediately but several time units later. We evaluate the fitness of a decision by using the relative score change caused by the decision. Whenever the scores of fighting characters are changed, the decision causing the score change is identified, and then the neural network is trained by using the score difference and the previous input and output values which induced the decision. Second, how to cope more properly with opponents that act with predefined action patterns is addressed. The opponents' past actions are utilized to find out the optimal counter-actions for the patterns. Lastly, a method in order to learn moving actions is proposed. To evaluate the performance of the proposed algorithm, we implement a simple fighting action game. Then the proposed intelligent character (IC) fights with the opponent characters (OCs) which act randomly or with predefined action patterns. The results show that the IC understands the game rules and finds out the optimal counter-actions for the opponents' action patterns by itself.