Monte-Carlo Opening Books for Amazons

Automatically creating opening books is a natural step towards the building of strong game-playing programs, especially when there is little available knowledge about the game. However, while recent popular Monte-Carlo Tree-Search programs showed strong results for various games, we show here that programs based on such methods cannot efficiently use opening books created using algorithms based on minimax. To overcome this issue, we propose to use an MCTS-based technique, Meta-MCTS, to create such opening books. This method, while requiring some tuning to arrive at the best opening book possible, shows promising results to create an opening book for the game of the Amazons, even if this is at the cost of removing its Monte-Carlo part.

[1]  Henry Avetisyan,et al.  Selective Search in an Amazons Program , 2002, Computers and Games.

[2]  Thomas R. Lincke,et al.  Strategies for the Automatic Construction of Opening Books , 2000, Computers and Games.

[3]  Mark H. M. Winands,et al.  Evaluation Function Based Monte-Carlo LOA , 2009, ACG.

[4]  H. Jaap van den Herik,et al.  Progressive Strategies for Monte-Carlo Tree Search , 2008 .

[5]  Olivier Teytaud,et al.  Meta Monte-Carlo Tree Search for Automatic Opening Book Generation , 2009 .

[6]  Richard J. Lorentz.  INVADER Wins Amazons Tournament , 2009 .

[7]  Tzung-Pei Hong,et al.  The Computational Intelligence of MoGo Revealed in Taiwan's Computer Go Tournaments , 2009, IEEE Transactions on Computational Intelligence and AI in Games.

[8]  Michael Buro.  Toward Opening Book Learning , 1999, J. Int. Comput. Games Assoc..

[9]  T. Cazenave.  Reflexive Monte-Carlo Search , 2007 .

[10]  Olivier Teytaud,et al.  Creating an Upper-Confidence-Tree Program for Havannah , 2009, ACG.

[11]  Neil D. Lawrence,et al.  Missing Data in Kernel PCA , 2006, ECML.

[12]  Robert M. Hyatt,et al.  Book Learning - a Methodology to Tune an Opening Book Automatically , 1999, J. Int. Comput. Games Assoc..

[13]  Richard Lorentz,et al.  Generating an Opening Book for Amazons , 2004, Computers and Games.

[14]  Hiroyuki Iida,et al.  Self-playing-based Opening Book Tuning , 2006 .

[15]  Rémi Coulom,et al.  Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search , 2006, Computers and Games.

[16]  Sylvain Gelly,et al.  Modifications of UCT and sequence-like simulations for Monte-Carlo Go , 2007, 2007 IEEE Symposium on Computational Intelligence and Games.

[17]  Tristan Cazenave,et al.  Nested Monte-Carlo Search , 2009, IJCAI.

[18]  Richard J. Lorentz.  Amazons Discover Monte-Carlo , 2008, Computers and Games.

[19]  Bruce Abramson,et al.  Expected-Outcome: A General Model of Static Evaluation , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Ulf Lorenz,et al.  Innovative Opening-Book Handling , 2006, ACG.

[21]  Zongmin Ma,et al.  Computers and Games , 2008, Lecture Notes in Computer Science.

[22]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

[23]  Julien Kloetzer,et al.  Monte-Carlo techniques : applications to the game of the Amazons , 2010 .