Estimating the Discarding Tiles by Supervised Learning Using Mahjong Game Records - Collections

＜conference paper＞
Estimating the Discarding Tiles by Supervised Learning Using Mahjong Game Records

Creator	Creator Name 松田, 真治 Matsuda, Shinji マツダ, シンジ Affiliation Affiliation Name 九州大学大学院システム情報科学府 Graduate School of Information Science and Electrical Engineering, Kyushu University
Creator	Author PID K000019 0000-0002-2045-2704 Creator Name 伊東, 栄典 Ito, Eisuke イトウ, エイスケ Affiliation Affiliation Name 九州大学情報基盤研究開発センター Research Institute for Information Technology, Kyushu University
Language	Japanese
Publisher	情報処理学会九州支部
Publisher	Kyushu Branch of the Information Processing Society of Japan
Date	2021-03-01
Source Title	情報処理学会研究報告
Source Title	IPSJ SIG Technical Report
Vol	2021
Issue	A7-3
First Page	1
Last Page	4
Conference	Name 火の国情報シンポジウム Invitation to 2021 "Hinokuni - Land of Fire" Information Processing Symposium Sequence 2021 Sponsor 一般社団法人情報処理学会九州支部 Kyushu Branch of the Information Processing Society of Japan Date 2021年3月1日(月)・2日(火) Venue オンライン開催（大分大学、Ｚｏｏｍ） Online (Oita university, Zoom) Place 大分 Ohita Country Japan
Publication Type	Version of Record
Access Rights	open access
Rights	©2021 Information Processing Society of Japan
	本論文は著作権者である情報処理学会の許可のもとに掲載しています。ご利用の際は著作権法に従ってください。
	The copyright of this material is retained by the Information Processing Society of Japan (IPSJ). This material is published on this web site with the agreement of the author (s) and the IPSJ. Please be complied with Copyright Law of Japan and the Code of Ethics of the IPSJ if any users wish to reproduce, make derivative work, distribute or make available to the public any part or whole thereof.
Related DOI
Related URI	isIdenticalTo https://www.ipsj-kyushu.jp/page/ronbun/hinokuni/1010/Papers/A7-3.pdf
Related HDL
Abstract	ゲームにおける人工知能の活用が進んでいる。完全情報ゲームである将棋や囲碁ではAIが人間のトッププレイヤーを凌駕する成績を残している。近年ではポーカーや麻雀などの不完全情報ゲームにおけるゲームAIの研究も活発になっている。麻雀AI作成の第一歩はトッププレイヤーの模倣である。本研究の目的は麻雀牌譜を用いた教師あり学習による打牌推定である。教師あり学習の訓練データとして、麻雀ゲーム「天鳳」の牌譜データを...用いた。 Research on artificial intelligence in games is becoming more and more active. In complete information games such as Shogi and Go, AI has outperformed top human players. In recent years, research on game AI for incomplete information games such as poker and mahjong has also been active. The first step in creating a mahjong AI is to imitate the top players. The objective of this research is to estimate the tiles to be discarded by supervised learning using mahjong game records. As the training data for supervised learning, we used the mahjong game records of the mahjong game "Tenho".show more

Hide fulltext details.

File	FileType	Size	Views	Description
4740660	pdf	461 KB	1,083

Details

Record ID	4740660
Related URI	https://www.ipsj-kyushu.jp/page/ronbun/hinokuni/1010/Papers/A7-3.pdf
Subject Terms	麻雀
	ニューラルネットワーク
	待ち牌推測
	牌譜
	Mahjong
	Neural network
	Discarding tiles estimation
	Mahjong game record
Created Date	2021.12.16
Modified Date	2023.08.17

Export

Link to this page

Search Other Services

Statistics

＜conference paper＞ Estimating the Discarding Tiles by Supervised Learning Using Mahjong Game Records

Hide fulltext details.

Details

People who viewed this item also viewed

＜conference paper＞
Estimating the Discarding Tiles by Supervised Learning Using Mahjong Game Records