New Applications of the Monte-Carlo Tree Search to Computer Daihinmin

Seiya OKUBO; Mitsuo WAKATSUKI; Tasuku MITSUISHI; Yasuki DOBASHI; Tetsuro NISHINO

doi:10.52731/ijscai.v4.i1.514

Seiya OKUBO University of Shizuoka
Mitsuo WAKATSUKI The University of Electro-Communications
Tasuku MITSUISHI The University of Electro-Communications
Yasuki DOBASHI The University of Electro-Communications
Tetsuro NISHINO The University of Electro-Communications

DOI: https://doi.org/10.52731/ijscai.v4.i1.514

Keywords: Computer Daihinmin, Game Informatics, Monte Carlo Method

Abstract

The Monte Carlo tree search is popular in computer programs that play games. In this study, we present two new applications of the Monte Carlo method for the card game Daihinmin: as a method for setting good evaluation values in repeated plays, and as a method for increasing or decreasing the score of a target player.

References

M. Wakatsuki, Y. Dobashi, T. Mitsuishi, S. Okubo, and T. Nishino, “Strengthening Methods of Computer Daihinmin Programs,” Proceedings of the CAINE 2017,ISCA, pp.229–236, 2017.

S. Okubo, T. Aayabe, and T. Nishino, “Cluster Analysis using N-gram Statistics for Daihinmin Programs and Performance Evaluations,” International Journal of Software Innovation (IJSI), vol. 4, Issue 2, pp. 33–57, 2016.

S. Morita and K. Matsuzaki, “Proposal of Rating Algorithms Considering Inhomogeneity of Initial Hand in Daihinmin,” GI, vol. 2014-GI-31, no. 14, pp. 1–5, 2014.

T. Nishino and S. Okubo, “Computer Daihinmin(Mind Games),” Journal of Japanese Society for Artificial Intelligence, vol. 24, no. 3, pp. 361–366, May 2009.

M. Konishi, S. Okubo, M. Wakatsuki, and T. Nishino, “Decision Tree Analysis in Game Informatics,” 5th International Conference on Applied Computing & Information Technology (ACIT2017), 2017.

M. Wakatsuki, M. Fujimura, and T. Nishino, “A Decision Making Method Based on Society of Mind Theory in Multi-player Imperfect Information Games,” International Journal of Software Innovation (IJSI), vol. 4, Issue 2, pp. 58–70, 2016.

P. Auer, N. Cesa-Bianchi, and P. Fischer, “Finite-time Analysis of the Multiarmed Bandit Problem,” Machine Learning, vol. 47, no. 2, pp. 235–256, May 2002.

D. Silver and G. Tesauro, “Monte-carlo Simulation Balancing,” in Proceedings of the 26th Annual International Conference on Machine Learning, ser. ICML ’09. ACM, 2009, pp. 945–952.

F. Suto, K. Narisawa, and A. Shinohara, “Development of Client “Snowl” for Computer Daihinmin Convention,” Computer DAIHINMIN Symposium 2010, 2010.

K. Ohto and T. Tanaka, “Supervised Learning of Policy Function Based on Policy Gradients and Application to Monte Carlo Simulation in Daihinmin,” GI, vol. 2016-GI-35, no. 10, pp. 1–8, Mar 2016.

K. Tagashira and Y. Tajima, “Heuristics Implementation and Evaluations for Computer Daihinmin,” IPSJ Journal, vol. 57, no. 11, pp. 2403–2413, Nov 2016.

K. Tagashira, Y. Tajima, and G. Kikui, “Heuristics for Daihinmin and their Effectiveness,” International Journal of Computer and Information Science, vol. 17, no. 2, pp. 7–14, Jul 2016.