Towards staged evolution of an artificial player for Hex by enlarging the boardsize during training

Although the game of Hex has simple rules it is a challenging task for machine learning and therefore a possible testbed for incremental learning. This article first describes a possibility how to implement a simple learning artificial player for Hex. Some pilot training experiments indicate that evolutionary hill climbing is able to improve the playing strength of the player. However, the strategy to facilitate the process of learning by first using a small sized board and after some training to increase the board size seems not to work.

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

[2]  Robert E. Tarjan,et al.  A Combinatorial Problem Which Is Complete in Polynomial Space , 1976, JACM.

[3]  Jack van Rijswijck.  Are Bees Better than Fruitflies? , 2000, Canadian Conference on AI.

[4]  M. Buro,et al.  HOW MACHINES HAVE REARNEA TO PLAY OTHELLO , 1999 .

[5]  D. B. Fogel,et al.  Using evolutionary programing to create neural networks that are capable of playing tic-tac-toe , 1993, IEEE International Conference on Neural Networks.

[6]  David N. L. Levy,et al.  The Sex Algorithm in Computer Chess , 1989, J. Int. Comput. Games Assoc..

[7]  Stephan K. Chalup,et al.  Incremental Learning in Biological and Machine Learning Systems , 2002, Int. J. Neural Syst..

[8]  Richard S. Sutton,et al.  Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[9]  Stephan K. Chalup,et al.  A study on hill climbing algorithms for neural network training , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[10]  Vadim V. Anshelevich,et al.  A hierarchical approach to computer Hex , 2002, Artif. Intell..

[11]  Jordan B. Pollack,et al.  Co-Evolution in the Successful Learning of Backgammon Strategy , 1998, Machine Learning.

[12]  Stefan Reisch,et al.  Hex ist PSPACE-vollständig , 1981, Acta Informatica.

[13]  Jing Yang,et al.  New Winning and Losing Positions for 7x7 HEx , 2002, Computers and Games.

[14]  J. Elman.  Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[15]  Padhraic Smyth,et al.  Discrete recurrent neural networks for grammatical inference , 1994, IEEE Trans. Neural Networks.

[16]  Gerald Tesauro,et al.  Programming backgammon using self-teaching neural nets , 2002, Artif. Intell..

[17]  Aske Plaat,et al.  RESEARCH RE: SEARCH & RE-SEARCH , 1996 .

[18]  Vadim V. Anshelevich.  Hexy Wins Hex Tournament , 2000, J. Int. Comput. Games Assoc..

[19]  G. Tesauro.  Practical Issues in Temporal Difference Learning , 1992 .

[20]  Andrew Tridgell,et al.  Learning to Play Chess Using Temporal Differences , 2000, Machine Learning.

[21]  Andrew Tridgell,et al.  TDLeaf(lambda): Combining Temporal Difference Learning with Game-Tree Search , 1999, ArXiv.

[22]  Vadim V. Anshelevich,et al.  The Game of Hex: An Automatic Theorem Proving Approach to Game Programming , 2000, AAAI/IAAI.

[23]  Donald E. Knuth,et al.  The Solution for the Branching Factor of the Alpha-Beta Pruning Algorithm , 1981, ICALP.

[24]  D. Gale.  The Game of Hex and the Brouwer Fixed-Point Theorem , 1979 .

[25]  Arthur L. Samuel,et al.  Some studies in machine learning using the game of checkers" in computers and thought eds , 1995 .

[26]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[27]  Terrence J. Sejnowski,et al.  Temporal Difference Learning of Position Evaluation in the Game of Go , 1993, NIPS.

[28]  Janet Wiles,et al.  The challenge of Go as a domain for AI research: a comparison between Go and chess , 1995, Proceedings of Third Australian and New Zealand Conference on Intelligent Information Systems. ANZIIS-95.