期刊文献+

Effect of Look-Ahead Depth in Evolutionary Checkers

Effect of Look-Ahead Depth in Evolutionary Checkers
原文传递
导出
摘要 It is intuitive that allowing a deeper search into a game tree will result in a superior player to one that is restricted in the depth of the search that it is allowed to make. Of course, searching deeper into the tree comes at increased computational cost and this is one of the trade-offs that has to be considered in developing a tree-based search algorithm. There has been some discussion as to whether the evaluation function, or the depth of the search, is the main contributory factor in the performance of an evolved checkers player. Some previous research has investigated this question (on Chess and Othello), with differing conclusions. This suggests that different games have different emphases, with respect to these two factors. This paper provides the evidence for evolutionary checkers, and shows that the look-ahead depth (like Chess, perhaps unsurprisingly) is important. This is the first time that such an intensive study has been carried out for evolutionary checkers and given the evidence provided for Chess and Othello this is an important study that provides the evidence for another game. We arrived at our conclusion by evolving various checkers players at different ply depths and by playing them against one another, again at different ply depths. This was combined with the two-move ballot (enabling more games against the evolved players to take place) which provides strong evidence that depth of the look-ahead is important for evolved checkers players. It is intuitive that allowing a deeper search into a game tree will result in a superior player to one that is restricted in the depth of the search that it is allowed to make. Of course, searching deeper into the tree comes at increased computational cost and this is one of the trade-offs that has to be considered in developing a tree-based search algorithm. There has been some discussion as to whether the evaluation function, or the depth of the search, is the main contributory factor in the performance of an evolved checkers player. Some previous research has investigated this question (on Chess and Othello), with differing conclusions. This suggests that different games have different emphases, with respect to these two factors. This paper provides the evidence for evolutionary checkers, and shows that the look-ahead depth (like Chess, perhaps unsurprisingly) is important. This is the first time that such an intensive study has been carried out for evolutionary checkers and given the evidence provided for Chess and Othello this is an important study that provides the evidence for another game. We arrived at our conclusion by evolving various checkers players at different ply depths and by playing them against one another, again at different ply depths. This was combined with the two-move ballot (enabling more games against the evolved players to take place) which provides strong evidence that depth of the look-ahead is important for evolved checkers players.
出处 《Journal of Computer Science & Technology》 SCIE EI CSCD 2012年第5期996-1006,共11页 计算机科学技术学报(英文版)
关键词 evolutionary Checkers look-ahead depth neural network evolutionary Checkers, look-ahead depth, neural network
  • 相关文献

参考文献48

  • 1Turing A M. Computing machinery and intelligence. Mind, 1950, 59: 433-460.
  • 2Samuel A L. Some studies in machine learning using the game of checkers. IBM Journal on Research and Development, 1959, 3(3): 210-229.
  • 3Newborn M. Kasparov versus Deep Blue. Computer Chess Comes of Age. New York: Springer-Verlag, 1996.
  • 4Campbell M, Hoane Jr. A J, Hsu F H. Deep blue. Artificial Intelligence, 2002, 134(1-2): 57-83.
  • 5Schaeffer J. One Jump Ahead: Computer Perfection at Checkers (2nd edition). New York: Springer, 2009.
  • 6Sastry K, Goldberg D, Kendall G. Chapter 4: Genetic algorithms. In Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques, Burke E K, Kendall G (eds.), Springer, 2005, pp.97-125.
  • 7Koza J, Poli R. Chapter 5: Genetic programming. In Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques, Burke E K, Kendall G (eds.), Springer, 2005, pp.127-164.
  • 8Fausett L V. Fundamentals of Neural Networks: Architectures, Algorithms and Applications, Prentice Hall, 1993.
  • 9Yao X. Evolving artificial neural networks. Proc. the IEEE, 1999, 87(9): 1423-1447.
  • 10Jong K A D. Evolutionary Computation: A Unified Approach. Cambridge, USA: MIT Press, 2006.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部