Abstract
This paper addresses learning of a reasonably accurate evaluation function of Shogi (Japanese Chess) positions through learning from records of games. Accurate evaluation of a Shogi position is indispensable for a computer Shogi program. A Shogi position is projected into several semantic features characterizing the position. Using such features as input, we employ reinforcement learning with a multi-layer perceptron as a nonlinear function approximator. We prepare two completely different sets of games: games played by computer Shogi programs and games played by professional Shogi players. Then we built two evaluation functions by separate learning based on two different sets of games, and compared the results to find several interesting tendencies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bishop, C.M.: Neural networks for pattern recognition. Clarendon Press (1995)
Grimbergen, R.: An evaluation function for shogi. In: Proc. Game Programming Workshop in Japan ’97, pp. 159–168 (1997)
Iida, H., Sakuta, M., Rollason, J.: Computer shogi. Artificial Intelligence 134(1-2), 121–144 (2002)
Levy, D.N., Newborn, M.: How computers play chess. Comp. Sci. Press (1991)
Sutton, R.S., Barto, A.G.: Reinforcement learning. MIT Press, Cambridge (1998)
Tanimoto, S., Nakano, R.: Learning an evaluation function for shogi from data of games. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds.) KES 2004. LNCS (LNAI), vol. 3213, pp. 609–615. Springer, Heidelberg (2004)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Inagaki, K., Nakano, R. (2007). Learning Evaluation Functions of Shogi Positions from Different Sets of Games. In: Apolloni, B., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2007. Lecture Notes in Computer Science(), vol 4694. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74829-8_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-74829-8_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74828-1
Online ISBN: 978-3-540-74829-8
eBook Packages: Computer ScienceComputer Science (R0)