Hybrid Evolutionary Learning Approaches for The Virus Game

Author

Naveed, M.H. ; Cowling, P.I. ; Hossain, M.A.

Author_Institution

Dept. of Comput., Bradford Univ.

fYear

2007

fDate

1-5 April 2007

Firstpage

196

Lastpage

202

Abstract

This paper investigates the effectiveness of hybrids of learning and evolutionary approaches to find weights and topologies for an artificial neural network (ANN) which is used to evaluate board positions for a two-person zero-sum game, the virus game. Two hybrid approaches: evolutionary RPROP (resilient backpropagation) and evolutionary BP (backpropagation) are described and empirically compared with BP, RPROP, iRPROP (improved RPROP) and evolutionary learning approaches. The results show that evolutionary RPROP and evolutionary BP have significantly better generalisation performance than their constituent learning and evolutionary methods.

Keywords

backpropagation; computer games; evolutionary computation; artificial neural network; board position; evolutionary RPROP; evolutionary backpropagation; gradient-based learning; hybrid evolutionary learning; resilient backpropagation; two-person zero-sum game; virus game; Artificial neural networks; Backpropagation; Computational intelligence; Computer networks; Electronic mail; Evolutionary computation; Genetic algorithms; Learning systems; Network topology; Neural networks; Gradient-based learning; The Virus Game; evolutionary learning; hybrid learning techniques;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Games, 2007. CIG 2007. IEEE Symposium on

Conference_Location

Honolulu, HI

Print_ISBN

1-4244-0709-5

Type

conf

DOI

10.1109/CIG.2007.368098

Filename

4219043