{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00099288","sets":["1164:5305:7501:7502"]},"path":["7502"],"owner":"11","recid":"99288","title":["コンピュータ将棋におけるSVMを用いたMove Orderingの効率化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2014-03-10"},"_buckets":{"deposit":"223d14f5-6c48-4ab4-ac89-60ce632f4fb2"},"_deposit":{"id":"99288","pid":{"type":"depid","value":"99288","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"コンピュータ将棋におけるSVMを用いたMove Orderingの効率化","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"コンピュータ将棋におけるSVMを用いたMove Orderingの効率化"},{"subitem_title":"Efficiency of Move Ordering using SVM in Computer Shogi","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2014-03-10","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京農工大学大学院産業技術専攻"},{"subitem_text_value":"東京農工大学工学研究院"},{"subitem_text_value":"東京農工大学"},{"subitem_text_value":"東京農工大学工学研究院"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Master of Technology Management, Tokyo University of Agriculture and Technology","subitem_text_language":"en"},{"subitem_text_value":"Institute of Engineering, Tokyo University of Agriculture and Technology","subitem_text_language":"en"},{"subitem_text_value":"Tokyo University of Agriculture and Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer and Information Sciences, Tokyo University of Agriculture and Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/99288/files/IPSJ-GI14031009.pdf"},"date":[{"dateType":"Available","dateValue":"2016-03-10"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-GI14031009.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"18"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"9dbb48bc-9676-4956-be7f-5a907bb2ca39","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2014 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"野口, 拓央"},{"creatorName":"古宮, 嘉那子"},{"creatorName":"並木, 美太郎"},{"creatorName":"小谷, 善行"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takuhiro, Noguchi","creatorNameLang":"en"},{"creatorName":"Kanako, Komiya","creatorNameLang":"en"},{"creatorName":"Mitaro, Namiki","creatorNameLang":"en"},{"creatorName":"Yoshiyuki, Kotani","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11362144","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本稿では機械学習手法の 1 種である Support Vector Regression (SVR) を用いたコンピュータ将棋の Move Ordering (MO) を提案する．MO はコンピュータ将棋の探索を効率化のため可能手をなるべく良い手から順番に先頭から並べかえる手法である．MO では可能手を 1 手ごとに探索して評価関数を適用すると処理に時間が必要であるため効率化の余地が大きい．そこで本稿では可能手から特徴を抽出して SVR で手の優先度を求めて評価関数を用いずに実行できる MO を考案し、MO を高速化して探索を効率化する手法を提案した．本手法の MO をした後にプロが指した手の MO による平均順位を測定したところ既存手法に 2 手ほど及ばなかったが既存手法と近い結果を出した．また速度が速かったため SVR に評価関数を用いた探索の代替手段となりうる可能性が示唆された．しかし，本手法の性能を確認するために 200 回対局を行ったところ，86-111-3 という結果を得て有意に負け越してしまった．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper proposes Move Ordering (MO) of the computer Shogi using Support Vector Regression (SVR), which is one sort of the watching learning technique. MO is the technique of arranging moves in the order of value of them to increase efficiency of search of computer Shogi. There is room for further improvement in efficiency of MO because it is time － consuming; the move search is performed and the evaluation function is applied one by one. So this paper proposes MO using SVR to speed up MO and enhances efficiency on search. It extracts features of possible moves and gets the priority of moves using SVR. The average rounds of the professional player's moves were checked to evaluate the method. It showed the MO using SVR can alternate move search and evaluation function in the future because the average \\difference of ranks was only two and it is faster. However, the move search and evaluation function an outperformed MO using SVR significantly when 200 games were performed. The result was 86-111-3.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告ゲーム情報学（GI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2014-03-10","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"9","bibliographicVolumeNumber":"2014-GI-31"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":99288,"updated":"2025-01-21T12:07:36.532874+00:00","links":{},"created":"2025-01-18T23:45:20.518148+00:00"}