JISE


  [ 1 ] [ 2 ] [ 3 ] [ 4 ] [ 5 ] [ 6 ] [ 7 ] [ 8 ] [ 9 ] [ 10 ] [ 11 ] [ 12 ]


Journal of Information Science and Engineering, Vol. 38 No. 3, pp. 591-603


Improving Mini-Shogi Engine Using Self-play and Possibility of White's Advantage


Masahiro Shioda and Takeshi Ito
Graduate School of Informatics and Engineering
The University of Electro-Communications
Tokyo, 182-0021 Japan
E-mail: shioda@minerva.cs.uec.ac.jp; taito@mbc.nifty.com


The arti cial intelligence (AI) in Shogi has made rapid progress recently, owing to the recent establishment of a method of learning evaluation via self-play. In this paper, we applied this method to Mini-Shogi to verify the effect. Speci cally, we used YaneuraOu Shogi engine to develop the Mini-Shogi program and trained a neural network-based evaluation function. Our program won all competitions in which we participated in 2020. Moreover, the experimental results suggest the second-move (White) advantage in Mini-Shogi.


Keywords: artificial intelligence in game, evaluation function, machine learning, self-play, Shogi

  Retrieve PDF document (JISE_202203_06.pdf)