Abstract
The game of Go has recently been an exuberant topic for AI research, mainly due to advances in Go playing software. Here, we present an application of deep neural networks aiming to improve the experience of humans playing the game of Go online. We have trained a deep convolutional network on 188,700 Go game records to classify players into three categories based on their skill. The method has a very good accuracy of 71.5 % when classifying the skill from a single position, and 77.9 % when aggregating predictions from one game. The performance and low amount of information needed allow for a much faster convergence to true rank on online Go servers, improving user experience for new-coming players. The method will be experimentally deployed on the Online Go Server (OGS).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Andor, D., Alberti, C., Weiss, D., Severyn, A., Presta, A., Ganchev, K., Petrov, S., Collins, M.: Globally normalized transition-based neural networks. arXiv preprint (2016). arXiv:1603.06042
Baudiš, P., Moudřík, J.: On move pattern trends in a large go games corpus. Arxiv, CoRR. http://arXiv.org/abs/1209.5251
Bengio, Y., Boulanger-Lewandowski, N., Pascanu, R.: Advances in optimizing recurrent networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8624–8628. IEEE (2013)
Chollet, F.: Keras (2015). https://github.com/fchollet/keras
Elo, A.E.: The Rating of Chessplayers, Past and Present. Arco, New York (1978)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. Aistats 9, 249–256 (2010)
Herbrich, R., Minka, T., Graepel, T.: Trueskill (tm): A bayesian skill rating system. In: Advances in Neural Information Processing Systems, pp. 569–576 (2006)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint (2015). arXiv:1502.03167
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Mikolov, T., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inform. Process. Syst. 26, 3111–3119 (2013)
Moudřík, J.: Meta-learning methods for analyzing Go playing trends. Master’s thesis, Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic (2013). http://www.j2m.cz/ jm/master_thesis.pdf
Moudřík, J.: deep-go-wrap: Toolkit designed to ease development of your deep neural network models for the game of Go. (2016). https://github.com/jmoudrik/deep-go-wrap
Moudřík, J.: Source code and resources (2016). http://j2m.cz/~jm/archive/2016-08-02/
Moudřík, J., Baudiš, P., Neruda, R.: Evaluating go game records for prediction of player attributes. In: 2015 IEEE Conference on Computational Intelligence and Games (CIG), pp. 162–168. IEEE (2015)
Moudřík, J., Neruda, R.: Evolving non-linear stacking ensembles for prediction of go player attributes. In: 2015 IEEE Symposium Series on Computational Intelligence, pp. 1673–1680. IEEE (2015)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807–814 (2010)
OGS: Online Go Server (OGS) (2016). http://online-go.com
Schmicker, D.: Planes for move prediction, maillist entry. http://computer-go.org/pipermail/computer-go/2015-December/008324.html
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Wikipedia: Alphago versus lee sedol – wikipedia, the free encyclopedia (2016). https://en.wikipedia.org/w/index.php?title=AlphaGo_versus_Lee_Sedol&oldid=732449782, Accessed 12 Sep 2016
Acknowledgments
Authors would like to thank Martin Pilát for valuable discussions. This research has been partially supported by the Czech Science Foundation project no. P103-15-19877S. J. Moudřík has been supported by the Charles University Grant Agency project no. 364015 and by SVV project no. 260 333.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Moudřík, J., Neruda, R. (2016). Determining Player Skill in the Game of Go with Deep Neural Networks. In: Martín-Vide, C., Mizuki, T., Vega-Rodríguez, M. (eds) Theory and Practice of Natural Computing. TPNC 2016. Lecture Notes in Computer Science(), vol 10071. Springer, Cham. https://doi.org/10.1007/978-3-319-49001-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-49001-4_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49000-7
Online ISBN: 978-3-319-49001-4
eBook Packages: Computer ScienceComputer Science (R0)