{"id":236318,"updated":"2025-01-19T09:18:25.968795+00:00","links":{},"created":"2025-01-19T01:38:18.231456+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236318","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236318","title":["学習オートマトンを用いたQ-学習の高速化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"83ede28e-24aa-4170-9892-c3a42603c443"},"_deposit":{"id":"236318","pid":{"type":"depid","value":"236318","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"学習オートマトンを用いたQ-学習の高速化","author_link":["645919","645920"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"学習オートマトンを用いたQ-学習の高速化"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2024-03-01","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"松江高専"},{"subitem_text_value":"松江高専"}]},"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/236318/files/IPSJ-Z86-2X-08.pdf","label":"IPSJ-Z86-2X-08.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-2X-08.pdf","filesize":[{"value":"266.6 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"00790639-327d-4a47-9e5c-98783b1d890b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"小山, 裕"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"原, 元司"}],"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_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"マルコフ決定過程における強化学習の代表例であるQ-学習は，各状態における行動を無限回選択する場合に，Q値が最適な値に概収束(確率1収束)することが証明されている．しかし，これまでにQ-学習で提案されている行動選択法では，最適行動の選択確率の収束特性について概収束よりも弱いε-最適(確率収束)の概念で学習性能が議論されている．これに対し，筆者らはある条件を満たした確率的環境下で最適となるβ-タイプ学習オートマトンをQ-学習の行動選択手法に導入した「LQ-学習」を提案する．ε-greedy法といった代表的な行動選択法によるQ-学習に対して，LQ-学習が優速であることを報告する．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"972","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"971","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}