Deep Learning and Block Go

被引:0
作者
Yen, Shi-Jim [1 ]
Lin, Ching-Nung [1 ]
Cheng, Guan-Lun [1 ]
Chen, Jr-Chang [2 ]
机构
[1] Natl Dong Hwa Univ, Dept Comp Sci & Informat Engn, Hualien 97401, Taiwan
[2] Chung Yuan Christian Univ, Dept Appl Math, Taoyuan 32023, Taiwan
来源
2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | 2017年
关键词
Block Go; Computer Go; Deep Learning; Deep Convolutional Neural Network; GAMES; STRATEGIES;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Google Deepmind AlphaGo successfully defeated a professional nine dan Go player last March. One of the reasons is that they use deep learning to do a pure pattern-matching approach and predict the next move. In this paper, we use deep learning on the game of Block Go. Block Go is a variance of Go. In this paper, firstly we introduce the complexity of Block Go which is between checkers and Othello. Then we apply Deep Convolutional Neural Network (DCNN) on Block Go. Finally, we show that Block Go is a good research topic for deep learning.
引用
收藏
页码:2698 / 2701
页数:4
相关论文
共 12 条
  • [1] [Anonymous], 2015, INT C LEARN REPR
  • [2] [Anonymous], 2006, 6062 INRIA
  • [3] PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCH
    Chaslot, Guillaume M. J-B.
    Winands, Mark H. M.
    Van den Herik, H. Jaap
    Uiterwijk, Jos W. H. M.
    Bouzy, Bruno
    [J]. NEW MATHEMATICS AND NATURAL COMPUTATION, 2008, 4 (03) : 343 - 357
  • [4] Coulom R, 2007, ICGA J, V30, P198
  • [5] Human vs. Computer Go: Review and Prospect
    Lee, Chang-Shing
    Wang, Mei-Hui
    Yen, Shi-Jim
    Wei, Ting-Han
    Wu, I-Chen
    Chou, Ping-Chiang
    Chou, Chun-Hsun
    Wang, Ming-Wan
    Yang, Tai-Hsiung
    [J]. IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2016, 11 (03) : 68 - 73
  • [6] Information capture and reuse strategies in Monte Carlo Tree Search, with applications to games of hidden information
    Powley, Edward J.
    Cowling, Peter I.
    Whitehouse, Daniel
    [J]. ARTIFICIAL INTELLIGENCE, 2014, 217 : 92 - 116
  • [7] Russell S., 2003, ARTIFICIAL INTELLI E
  • [8] Mastering the game of Go with deep neural networks and tree search
    Silver, David
    Huang, Aja
    Maddison, Chris J.
    Guez, Arthur
    Sifre, Laurent
    van den Driessche, George
    Schrittwieser, Julian
    Antonoglou, Ioannis
    Panneershelvam, Veda
    Lanctot, Marc
    Dieleman, Sander
    Grewe, Dominik
    Nham, John
    Kalchbrenner, Nal
    Sutskever, Ilya
    Lillicrap, Timothy
    Leach, Madeleine
    Kavukcuoglu, Koray
    Graepel, Thore
    Hassabis, Demis
    [J]. NATURE, 2016, 529 (7587) : 484 - +
  • [9] Tian Y., 2016, BETTER COMPUTER GO P
  • [10] Games solved: Now and in the future
    van den Herik, HJ
    Uiterwijk, JWHM
    van Rjiswijck, J
    [J]. ARTIFICIAL INTELLIGENCE, 2002, 134 (1-2) : 277 - 311