2024-03-28T18:38:55Zhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_oaipmhoai:ipsj.ixsq.nii.ac.jp:001920532023-11-14T00:51:14Z06164:06165:06210:09595
Pos2Pos: Automatic Position-to-Position Translation in Chess-Like GamesPos2Pos: Automatic Position-to-Position Translation in Chess-Like GamesengChess-like gamesemi-supervised learninghttp://id.nii.ac.jp/1001/00191964/Conference Paperhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_action_common_download&item_id=192053&item_no=1&attribute_id=1&file_no=1Copyright (c) 2018 by the Information Processing Society of JapanThe University of TokyoShanchuan, WanTomoyuki, KanekoChess-like games share much common knowledge that is useful for both human players and computer programs, but is difficult to be well extracted and represented by using existing learning methods. This paper presents a novel semi-supervised learning method for automatically translating positions in one game to equivalent positions in another game. Preliminary experimental results in chess and shogi demonstrated the effectiveness of the proposed method.Chess-like games share much common knowledge that is useful for both human players and computer programs, but is difficult to be well extracted and represented by using existing learning methods. This paper presents a novel semi-supervised learning method for automatically translating positions in one game to equivalent positions in another game. Preliminary experimental results in chess and shogi demonstrated the effectiveness of the proposed method.ゲームプログラミングワークショップ2018論文集201851542018-11-092018-11-05