JAIST Repository >
School of Transdisciplinary Science >
Conference Papers >
Conference Papers >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/18240
|
Title: | Playing Good-Quality Games with Weak Players by Combining Programs with Different Roles |
Authors: | Hsueh, Chu-Hsuan Ikeda, Kokolo |
Keywords: | teaching strength adjustment entertaining Go |
Issue Date: | 2022-09-20 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Magazine name: | 2022 IEEE Conference on Games (CoG 2022) |
Volume: | 2022 |
DOI: | 10.1109/CoG51982.2022.9893698 |
Abstract: | Computer programs have become stronger than toprated human players in several games. However, weak players may not enjoy playing against these strong programs. In this study, we propose combining two programs with different roles to create programs suitable for weak players. We use a superhuman program that generates candidate moves and evaluates how good the moves are, as well as a program that evaluates the moves’ naturalness. We implement an instance for Go, which employs a superhuman program, KataGo, and a neural network trained using human games. Experiments show that the proposed method is promising for playing good-quality games with weak players. |
Rights: | This is the author's version of the work. Copyright (C) 2022 IEEE. 2022 IEEE Conference on Games (CoG). DOI: 10.1109/CoG51982.2022.9893698. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
URI: | http://hdl.handle.net/10119/18240 |
Material Type: | author |
Appears in Collections: | d11-1. 会議発表論文 (Conference Papers)
|
Files in This Item:
File |
Description |
Size | Format |
I-IKEDA-K0405-16.pdf | | 192Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|