Abstract
Using advanced deep learning methods, artificial intelligence is able to achieve unprecedented high performance in playing complex board games. However, in conventional practice, models for different games require separate training with domain-specific datasets, which is not conducive to enable the full use of the correlation between tasks and may cause unnecessary consumption of computing resources. This paper presents a novel multi-task learning framework for the training of deep-convolutional-neural-network-based evaluation functions for two heterogeneous but related games – chess and shogi. Experimental results show that the application of the proposed framework improved the prediction accuracy for both networks with limited training steps.
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
References
Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354 (2017)
Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Silver, D., et al.: Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1712.01815 (2017)
Lai, M.: Giraffe: using deep reinforcement learning to play chess. arXiv preprint arXiv:1509.01549 (2015)
Baxter, J., Tridgell, A., Weaver, L.: Learning to play chess using temporal-differences. Mach. Learn. 40(3), 242–263 (2000)
David, O.E., Netanyahu, N.S., Wolf, L.: DeepChess: end-to-end deep neural network for automatic learning in chess. In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9887, pp. 88–96. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44781-0_11
Wan, S., Kaneko, T.: Building evaluation functions for chess and shogi with uniformity regularization networks. In: IEEE Conference on Computational Intelligence and Games (2018)
Evgeniou, T., Pontil, M.: Regularized multi-task learning. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 109–117. ACM (2004)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hoki, K., Kaneko, T.: Large-scale optimization for evaluation functions with minimax search. Mach. Learn. 49, 527–568 (2014)
Tesauro, G.: Comparison training of chess evaluation functions. In: Machines that Learn to Play Games, pp. 117–130. Nova Science Publishers, Inc. (2001)
Romstad, T., Costalba, M., Kiiski, J.: Stockfish: A Strong Open Source Chess Engine (2018). https://stockfishchess.org
Acknowledgement
A part of this work was supported by JSPS KAKENHI Grant Number 16H02927 and by JST, PRESTO.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Wan, S., Kaneko, T. (2018). Heterogeneous Multi-task Learning of Evaluation Functions for Chess and Shogi. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11303. Springer, Cham. https://doi.org/10.1007/978-3-030-04182-3_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-04182-3_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04181-6
Online ISBN: 978-3-030-04182-3
eBook Packages: Computer ScienceComputer Science (R0)