Incremental fuzzy clustering for an adaptive backgammon game

Modern game designs rely on artificial intelligence capabilities to create exciting gaming experience. Adaptive artificial intelligence is one of the leading capabilities which enables a computer controlled opponent to improve its logic and to cover its flaws. In this paper an adaptive AI method for a backgammon game is introduced. The specific design of this game makes its flow to rely on the two most important characteristics of most games, chance and the skill of the player. The method introduced in this paper addresses both of these characteristics by using an incremental fuzzy clustering method, derived from weighted fuzzy c-means and an incremental clustering, which adapts itself to its opponent. In the end, the merit of this paper is providing a comparison of the introduced fuzzy method and its corresponding crisp method in performance.

[1]  Frank Dignum,et al.  Games and Agents: Designing Intelligent Gameplay , 2009, Int. J. Comput. Games Technol..

[2]  Teuvo Kohonen,et al.  Self-Organizing Maps, Third Edition , 2001, Springer Series in Information Sciences.

[3]  Hans J. Berliner.  BKG—A Program That Plays Backgammon , 1988 .

[4]  Marimuthu Palaniswami,et al.  Fuzzy c-Means Algorithms for Very Large Data , 2012, IEEE Transactions on Fuzzy Systems.

[5]  Gerald Tesauro,et al.  Neurogammon Wins Computer Olympiad , 1989, Neural Computation.

[6]  Lakhmi C. Jain,et al.  Fuzzy clustering models and applications , 1997, Studies in Fuzziness and Soft Computing.

[7]  Steven R. Young,et al.  A Fast and Stable Incremental Clustering Algorithm , 2010, 2010 Seventh International Conference on Information Technology: New Generations.

[8]  Jiawei Han,et al.  Efficient and Effective Clustering Methods for Spatial Data Mining , 1994, VLDB.

[9]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[10]  Tian Zhang,et al.  BIRCH: an efficient data clustering method for very large databases , 1996, SIGMOD '96.

[11]  Gerald Tesauro,et al.  TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play , 1994, Neural Computation.