Comparing evolutionary algorithms to solve the game of mastermind

Authors:
Javier Maestro-Montojo;Juan Julián Merelo;Sancho Salcedo-Sanz
Affiliations:
Department of Signal Processing and Communications, Universidad de Alcalá, Madrid, Spain;Departamento de Arquitectura y Tecnología de Computadores, Universidad de Granada, Granada, Spain;Departamento de Arquitectura y Tecnología de Computadores, Universidad de Granada, Granada, Spain
Venue:
EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation
Year:
2013

Citing 7
Cited 0

Mastermind by evolutionary algorithms

Proceedings of the 1999 ACM symposium on Applied computing
Solving Master Mind Using GAs and Simulated Annealing: A Case of Dynamic Constraint Optimization

PPSN IV Proceedings of the 4th International Conference on Parallel Problem Solving from Nature
Playing mastermind logically

ACM SIGART Bulletin
A Two-Phase Optimization Algorithm For Mastermind

The Computer Journal
Efficient solutions for Mastermind using genetic algorithms

Computers and Operations Research
Finding a needle in a haystack using hints and evolutionary computation: the case of evolutionary MasterMind

Applied Soft Computing
Solving mastermind using genetic algorithms

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartII

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we propose a novel evolutionary approach to solve the Mastermind game, and compare the results obtained with that of existing algorithms. The new evolutionary approach consists of a hierarchical one involving two different evolutionary algorithms, one for searching the set of eligible codes, and the second one to choose the best code to be played at a given stage of the game. The comparison with existing algorithms provides interesting conclusions regarding the performance of the algorithms and how to improve it in the future. However, it is clear that Entropy is a better scoring strategy than Most Parts, at least for these sizes, being able to obtain better results, independently of the evolutionary algorithm.