{"id":213432,"updated":"2025-01-19T17:09:50.589823+00:00","links":{},"created":"2025-01-19T01:14:18.643451+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00213432","sets":["6164:6165:6210:10734"]},"path":["10734"],"owner":"44499","recid":"213432","title":["大貧民における学習を用いた合理的なプレイアウトによる指し手の探索手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-11-06"},"_buckets":{"deposit":"62e61fa5-8152-4110-9e00-e53f73c7c9e0"},"_deposit":{"id":"213432","pid":{"type":"depid","value":"213432","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"大貧民における学習を用いた合理的なプレイアウトによる指し手の探索手法","author_link":["546118","546117","546120","546119"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"大貧民における学習を用いた合理的なプレイアウトによる指し手の探索手法"},{"subitem_title":"Search Method for Playing Daihinmin with Rational PlayoutBased on Machine Learning","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"大貧民","subitem_subject_scheme":"Other"},{"subitem_subject":"モンテカルロ法","subitem_subject_scheme":"Other"},{"subitem_subject":"ニューラルネットワーク","subitem_subject_scheme":"Other"},{"subitem_subject":"LSTM","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2021-11-06","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大学情報学群情報科学類"},{"subitem_text_value":"筑波大学システム情報系"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"College of Information Science, University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Engineering, Information and Systems, Universityof Tsukuba","subitem_text_language":"en"}]},"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/213432/files/IPSJ-GPWS2021011.pdf","label":"IPSJ-GPWS2021011.pdf"},"date":[{"dateType":"Available","dateValue":"2021-11-06"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-GPWS2021011.pdf","filesize":[{"value":"905.5 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"18"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"0c0057f6-6acc-4bc2-be14-f91cd68cfc8e","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"徳永, 和真"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"長谷部, 浩二"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuma, Tokunaga","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Koji, Hasebe","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究は，モンテカルロ法によるゲームの指し手の探索におけるプレイアウトの精度を，学習によって得られたモデルを用いて向上させる方法を提案する．より具体的には，プレイアウトにおける指し手の選択と相手の手札の推測のそれぞれを，CNN（Convolutional Neural Network）と LSTM（LongShort-Term Memory）によって得られたモデルをもとに行う．特にここでは，多人数不完全情報ゲームの一種である大貧民と呼ばれるトランプゲームを対象とする．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We propose a method to improve the accuracy of playout in the Monte Carlo method with models obtained by machine learning. More specifically, the choice of move and the estimation of the opponent’s hand in a playout are performed based on the models obtained by CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory). Here we focus on a card game called Daihinmin, which is a kind of multi-player incomplete information game.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"67","bibliographic_titles":[{"bibliographic_title":"ゲームプログラミングワークショップ2021論文集"}],"bibliographicPageStart":"65","bibliographicIssueDates":{"bibliographicIssueDate":"2021-11-06","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}