New solver and optimal anticipation strategies design based on evolutionary computation for the game of MasterMind

详细信息    查看全文

• 作者：J. Maestro-Montojo (1)
  S. Salcedo-Sanz (1)
  J. J. Merelo (2)
  
• 关键词：MasterMind ; Evolutionary algorithms ; Genetic programming ; Anticipation strategies ; Puzzles
• 刊名：Evolutionary Intelligence
• 出版年：2014
• 出版时间：March 2014
• 年：2014
• 卷：6
• 期：4
• 页码：219-228
• 全文大小：665 KB
• 作者单位：J. Maestro-Montojo (1)
  S. Salcedo-Sanz (1)
  J. J. Merelo (2)
  
  1. Department of Signal Theory and Communications, Escuela Polit茅cnica Superior, Universidad de Alcal谩, 28871 Alcal谩 de Henares, Madrid, Spain
  2. Departamento de Arquitectura y Tecnolog铆a de Computadores, Universidad de Granada, Granada, Spain
  
• ISSN：1864-5917

文摘

This paper presents and compares several evolutionary solutions for the well-known MasterMind game, a classic board game invented in the 1970s. First, we propose a novel evolutionary approach (which we call nested hierarchical evolutionary search) to solve the MasterMind game, comparing the obtained results with that of existing algorithms. Second, we show how to design novel game anticipation strategies for the MasterMind game, by applying genetic programming. In this case we compare the performance of the new obtained strategies with that of the classical ones, obtaining advantages in all the cases tested.