{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00225535","sets":["1164:2822:11181:11182"]},"path":["11182"],"owner":"44499","recid":"225535","title":["深層強化学習を用いた発見的二次無制約二値最適化ソルバーの学習"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-03-16"},"_buckets":{"deposit":"a1b06474-ff6a-452c-82d3-0318306decf2"},"_deposit":{"id":"225535","pid":{"type":"depid","value":"225535","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"深層強化学習を用いた発見的二次無制約二値最適化ソルバーの学習","author_link":["596982","596981","596980"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"深層強化学習を用いた発見的二次無制約二値最適化ソルバーの学習"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"深層学習","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-03-16","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京都大学大学院情報学研究科"},{"subitem_text_value":"京都大学大学院情報学研究科"},{"subitem_text_value":"京都大学大学院情報学研究科"}]},"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/225535/files/IPSJ-EMB23062028.pdf","label":"IPSJ-EMB23062028.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-EMB23062028.pdf","filesize":[{"value":"1.1 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"42"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"f8a84cf5-9e03-4720-85a0-ba961542d37c","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"額見, 怜央"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"安戸, 僚汰"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高木, 直史"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12149313","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":"2188-868X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，深層強化学習を用いた組合せ最適化問題に関する探究的なアプローチにより，新たなアルゴリズムの発見が研究されている．本研究では多くの組合せ最適化問題を等価に統一した形で変換でき，変換前の問題の種類に関わらず無制約で目的関数の最小化を図ることが特徴となる二次無制約二値最適化問題 (Quadratic Unconstrained Binary Optimization, QUBO) に変換された組合せ最適化問題における深層強化学習の活用を行うことを提案する．提案手法は既存のΔベースのフリップポリシーを深層強化学習に置き換える．環境とのインタラクションにより自ら試行錯誤し，取るべき行動を選択するための方策を自分で学んでいくエージェントの学習により，本問題を深層強化学習の枠組みにおいて長期的な報酬を最大化し，QUBO を効率的に解く AI によるアルゴリズム設計手法を発見できるかどうかの調査と評価を行った．結果として学習時の QUBO 行列サイズに制限されることなく，学習済みモデルは greedy に行動したときに到達した局所的最適解を数% 向上した精度で最適化を図ることができた．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告組込みシステム（EMB）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-03-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"28","bibliographicVolumeNumber":"2023-EMB-62"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":225535,"updated":"2025-01-19T12:46:40.212645+00:00","links":{},"created":"2025-01-19T01:25:02.588274+00:00"}