Abstract
In Mahjong, there are several objectives at play to win the game: to (1) win early, (2) gain a large number of points, (3) avoid losing points, and (4) prevent other players from winning. These objectives often conflict with each other, thereby creating tradeoffs. In this research, we make a evaluating function of Mahjong as a multiobjective optimization. Further, Mahjong requires multimodal behavior, particularly because the first-place player must win early and avoid losing points by the last-place player gaining a large number of points in the final hand. In this paper, we propose an evaluation function for Mahjong in the form of a multi-objective optimization problem. Modular multi-objective neuro-evolution of augmenting topologies (MM-NEAT) is a framework for evolving modular neural networks in which each module defines a separate policy. Evolution optimize these policies and when to use them. Given the above, we focus on two objectives in one-player Mahjong: to (1) win early and (2) gain a large number of points. We also verify the effectiveness of MM-NEAT for Mahjong.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mizukami, N., Tsuruoka, Y. Building a computer mahjong player based on monte carlo simulation and opponent models. In: 2015 IEEE Conference on Computational Intelligence and Games (CIG), pp. 275–283. IEEE (2015)
Shan, Y.C., Wei, C.H., Lin, C.H., Wu, I., Chuang, L.K., Tang, S.J., et al.: A framework for computer mahjong competitions. ICGA J. 37(1), 44–56 (2014)
Xu, D.: Mahjong AI/analyzer. PhD thesis, California State University, Northridge (2015)
Yoshimura, K., Hochin, T., Nomiya, H.: Searching optimal movements in multi-player games with imperfect information. In: 2016 IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), pp. 1–6. IEEE (2016)
Mizukami, N., Nakahari, R., Ura, A., Miwa, M., Tsuruoka, Y., Chikayama, T., et al.: Adapting one-player mahjong players to four-player mahjong by recognizing folding situations. In: The 18th Game Programming Workshop 2013, pp. 1–7 (2013) (in Japanese)
Kaizu, J., Narisawa, K., Shinohara, A., et al.: A study on the evaluation metrics for flexible strategy in single-player mahjong. In: The 20th Game Programming Workshop 2015, pp. 172–178 (2015) (in Japanese)
Schrum, J., Miikkulainen, R.: Evolving multimodal behavior with modular neural networks in ms. pac-man. In: Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation, pp. 325–332. ACM (2014)
Schrum, J., Miikkulainen, R.: Evolving multimodal networks for multitask games. IEEE Trans. Computat. Intell. AI Games 4(2), 94–111 (2012)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Schrum, J.B.: Evolving multimodal behavior through modular multiobjective neuroevolution. PhD thesis (2014)
C-EGG: Online mahjong tenhou (2007), http://tenhou.net/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Ihara, K., Kato, S. (2018). Neuro-Evolutionary Approach to Multi-objective Optimization in One-Player Mahjong. In: Barolli, L., Enokido, T., Takizawa, M. (eds) Advances in Network-Based Information Systems. NBiS 2017. Lecture Notes on Data Engineering and Communications Technologies, vol 7. Springer, Cham. https://doi.org/10.1007/978-3-319-65521-5_43
Download citation
DOI: https://doi.org/10.1007/978-3-319-65521-5_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65520-8
Online ISBN: 978-3-319-65521-5
eBook Packages: EngineeringEngineering (R0)