论文信息 - Neural networks compete with expert human players in solving the Double Dummy Bridge Problem

Neural networks compete with expert human players in solving the Double Dummy Bridge Problem

Artificial neural networks, trained only on sample bridge deals, without presentation of any human knowledge as well as the rules of the game, are applied to solving the Double Dummy Bridge Problem (DDBP). The problem, in its basic form, consist in estimation of the number of tricks to be taken by one pair of bridge players.

Jacek Mandziuk | Krzysztof Mossakowski

[1] Manny Rayner,et al. Pragmatic reasoning in bridge , 1993 .

[2] Manny Rayner,et al. Contract bridge as a Micro-world for reasoning about communication agents , 1990 .

[3] Matthew L. Ginsberg,et al. GIB: Imperfect Information in a Computationally Challenging Game , 2011, J. Artif. Intell. Res..

[4] R. Frey,et al. The official encyclopedia of bridge , 1976 .

[5] Jacek Mandziuk,et al. Learning Without Human Expertise: A Case Study of the Double Dummy Bridge Problem , 2009, IEEE Transactions on Neural Networks.

[6] Jacek Mandziuk,et al. Example-based Estimation of Hand's Strength in the Game of Bridge with or without Using Explicit Human Knowledge , 2007, 2007 IEEE Symposium on Computational Intelligence and Data Mining.

[7] Jacek Mandziuk,et al. Artificial Neural Networks for Solving Double Dummy Bridge Problems , 2004, ICAISC.

[8] B. Yegnanarayana,et al. Neural networks for contract bridge bidding , 1996 .

[9] Jacek Mandziuk,et al. Neural Networks and the Estimation of Hands' Strength in Contract Bridge , 2006, ICAISC.

[10] Monika Köhle,et al. Erfahrungen mit einem Neuralen Netz, das BRIDGE spielen lernt , 1989, ÖGAI.