{"updated":"2025-01-20T18:55:34.015466+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00142572","sets":["1164:5305:7915:8283"]},"path":["8283"],"owner":"11","recid":"142572","title":["ニューラルネットワークを用いた麻雀の打牌選択方法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2015-06-27"},"_buckets":{"deposit":"fabcd7c4-02b3-41a1-80f9-16bb0ce47943"},"_deposit":{"id":"142572","pid":{"type":"depid","value":"142572","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"ニューラルネットワークを用いた麻雀の打牌選択方法の提案","author_link":["212093","212092","212091","212094"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ニューラルネットワークを用いた麻雀の打牌選択方法の提案"},{"subitem_title":"Selections of Discarding Mahjong Piece Using Neural Network","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"不完全情報ゲーム","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2015-06-27","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"富山高等専門学校制御情報システム工学専攻"},{"subitem_text_value":"富山高等専門学校電子情報工学科"}]},"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/142572/files/IPSJ-GI15034008.pdf"},"date":[{"dateType":"Available","dateValue":"2017-06-27"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-GI15034008.pdf","filesize":[{"value":"1.4 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":"6a0596ae-9d39-4613-9594-87829f2dab53","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2015 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"松井, 一晃"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"的場, 隆一"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuaki, Matsui","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ryuichi, Matoba","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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8736","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，不完全情報ゲームの中でも特にルールが複雑である麻雀においてコンピュータプレイヤに打牌選択させる方法を提案する．打牌選択の方法として，現在の局面の状態を入力することにより，各種類の牌について打牌に適しているかを評価した値を出力する 3 層ニューラルネットワークを評価関数として使用している．評価関数の各パラメータの調整には，バックプロパゲーションを用いて教師データの打牌とコンピュータプレイヤの打牌が一致するように調整している．教師データの打牌には，インターネット麻雀サーバである 「東風荘」 のレーティング 2000 以上のプレイヤの牌譜を使用した．現在は，教師データの打牌とコンピュータプレイヤの打牌の一致率は 31.3% である．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Mahjong is one of games with imperfect information, and its rule is very complicated to construct mahjong AI. In this study, as a way of discarding mahjong piece, we employed three layer neural networks to calculate evaluation value of each pieces for discarding. Inputs of the neural networks are a current state and pieces on which a player holds, and outputs are evaluation values for deciding a discard piece. Each parameter of the evaluation function is adjusted by backpropagation. As learning data, we employed score sheets of players who have rating over 2000, from the Internet mahjong sever called ”Tonpuso”. As a result, our NN selects discarding pieces that correspond to learning data with 31.3% accuracy ratio.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告ゲーム情報学（GI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2015-06-27","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"2015-GI-34"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:20:00.475484+00:00","id":142572,"links":{}}