Multi-objective evolution of neural Go players

Kar, Bin Tan and Teo, Jason Tze Wi and Patricia Anthony (2010) Multi-objective evolution of neural Go players. In: 3rd IEEE International Conference on Digital Game and Intelligent Toy Enhanced Learning (DIGITEL 2010), 12-16 April 2010, Kaohsiung, Taiwan.

Full text not available from this repository.

Abstract

Solving multi-objective optimization problems (MOPs) using evolutionary algorithms (EAs) has been gaining a lot of interest recently. Go is a hard and complex board game. Using EAs, a computer may learn to play the game of Go by playing the games repeatedly and gaining the experience from these repeated plays. In this project, artificial neural networks (ANNs) are evolved with the Pareto Archived Evolution Strategies (PAES) for the computer player to automatically learn and optimally play the small board Go game. ANNs will be automatically evolved with the least amount of complexity (number of hidden units) to optimally play he Go game. The complexity of ANN is of particular importance since it will influence the generalization capability of the evolved network. Hence, there are two conflicting objectives in this study; first is maximizing the Go game fitness score and the second is reducing the complexity in the ANN. Several comparative empirical experiments were conducted that showed that the multi-objective optimization with two distinct and conflicting fitness functions outperformed the single-objective optimization which only optimized the first objective with no selection pressure selection on the second objective. © 2010 IEEE.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Keyword: Artificial neural networks, Board games, Fitness functions, Generalization capability, Go-game, Hidden units, Multi objective, Multi-objective optimization problem, Pareto archived evolution strategies, Selection pressures, Single objective optimization
Subjects: Q Science > QA Mathematics > QA1-939 Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Department: SCHOOL > School of Engineering and Information Technology
Depositing User: ADMIN ADMIN
Date Deposited: 07 Mar 2011 11:24
Last Modified: 29 Dec 2014 16:16
URI: https://eprints.ums.edu.my/id/eprint/2051

Actions (login required)

View Item View Item