Adjusting the evaluation function for weakening the competency level of a computer shogi program

Article type: Research Article

Authors: Nakamichi, Takafumi^{; *} | Ito, Takeshi

Affiliations: The University of Electro-Communications, Japan

Correspondence: [*] Corresponding author. Department of Communication Engineering and Informatics, The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo 182-8585, Japan Tel.: 042-443-5370; Fax: 042-443-5370; E-mail: [email protected].

Abstract: This study proposes a machine learning-based evaluation function that intentionally weakens the competency level of an AI program based on the game records of amateur players. By regulating the evaluation function, it is possible to intentionally weaken the AI relative to existing methods in an equivalent search space. In addition, a subjective evaluation of naturalness was conducted by using a panel of experts to rate the proposed AI technique against conventional AI techniques at equivalent levels of weakness. The analysis revealed the elements of “human-likeness” present in the shogi game records and identified key similarities and differences between amateur and professional players.

Keywords: Applications of AI, education, game AI, believable Bot, humanness, human-like AI, turing test, gaming experience

DOI: 10.3233/ICG-180042

Journal: ICGA Journal, vol. 40, no. 1, pp. 15-31, 2018