Pareto evolution and co-evolution in cognitive game AI synthesis

Authors:
Yi Jack Yau;Jason Teo;Patricia Anthony
Affiliations:
School of Engineering and Information Technology, Universiti Malaysia Sabah, Kota Kinabalu, Sabah, Malaysia;School of Engineering and Information Technology, Universiti Malaysia Sabah, Kota Kinabalu, Sabah, Malaysia;School of Engineering and Information Technology, Universiti Malaysia Sabah, Kota Kinabalu, Sabah, Malaysia
Venue:
EMO'07 Proceedings of the 4th international conference on Evolutionary multi-criterion optimization
Year:
2007

Citing 4
Cited 2

A Comparison Of Two Competitive Fitness Functions

GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Coevolution of neural networks using a layered pareto archive

Proceedings of the 8th annual conference on Genetic and evolutionary computation
Investigating adaptive mutation in the generalized generation gap (G3) algorithm for unconstrained global optimization

Proceedings of the 2007 ACM symposium on Applied computing
An investigation, using co-evolution, to evolve an Awari player

CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02

Sensitivity versus accuracy in multiclass problems using memetic Pareto evolutionary neural networks

IEEE Transactions on Neural Networks
A multi-objective neural network based method for cover crop identification from remote sensed data

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Pareto-based Differential Evolution (PDE) algorithm is one of the current state-of-the-art Multi-objective Evolutionary Algorithms (MOEAs). This paper describes a series of experiments using PDE for evolving artificial neural networks (ANNs) that act as game-playing agents. Three systems are compared: (i) a canonical PDE system, (ii) a co-evolving PDE system (PCDE) with 3 different setups, and (iii) a co-evolving PDE system that uses an archive (PCDE-A) with 3 different setups. The aim of this study is to provide insights on the effects of including co-evolutionary techniques on a well-known MOEA by investigating and comparing these 3 different approaches in evolving intelligent agents as both first and second players in a deterministic zero-sum board game. The results indicate that the canonical PDE system outperformed both co-evolutionary PDE systems as it was able to evolve ANN agents with higher quality game-playing performance as both first and second game players. Hence, this study shows that a canonical MOEA without co-evolution is desirable for the synthesis of cognitive game AI agents.