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




Masahiro Shioda;Takeshi Ito

Key Words

artificial intelligence in game ; evaluation function ; machine learning ; self-play ; Shogi


Journal of Information Science and Engineering

Volume or Term/Year and Month of Publication

38卷3期(2022 / 05 / 01)

Page #

591 - 603

Content Language


Chinese Abstract

The artificial 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. Specifically, 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.

Topic Category 基礎與應用科學 > 資訊科學