{"updated":"2025-01-19T10:43:16.470078+00:00","links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00231565","sets":["1164:1165:11326:11415"]},"path":["11415"],"owner":"44499","recid":"231565","title":["転移学習エージェントにおける局所方策の選択的再利用法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-12-19"},"_buckets":{"deposit":"5683ed81-cb5c-4d63-b520-472729bf2a54"},"_deposit":{"id":"231565","pid":{"type":"depid","value":"231565","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"転移学習エージェントにおける局所方策の選択的再利用法の提案","author_link":["625285","625284"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"転移学習エージェントにおける局所方策の選択的再利用法の提案"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"データ工学","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-12-19","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"千葉工業大学大学院先進工学研究科"},{"subitem_text_value":"千葉工業大学先進工学部"}]},"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/231565/files/IPSJ-DBS23178004.pdf","label":"IPSJ-DBS23178004.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DBS23178004.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"13"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"352e1c74-46fd-4df7-9053-0bdf6ea8f267","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":"濱田, 大也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齊藤, 史哲"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10112482","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":"2188-871X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年 AI の行動獲得に対して強化学習が注目されている．強化学習にはタスクの複雑化に伴い試行数が増加する問題がある．これを回避するため，事前に学習した知識を再利用し，試行数を減らす転移学習が注目されている．転移学習の方法の一つに適用可能な知識をランダム選択するεT グリーディがある．しかし，転移する知識の選択において再利用するべき知識とそうでない知識を同等に扱ってしまい，余分な行動選択が増えるという課題がある．そこで，本研究では選択するべき知識に価値を付与し，選択確率に比例させる方法を提案する．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告データベースシステム（DBS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-12-19","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"4","bibliographicVolumeNumber":"2023-DBS-178"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":231565,"created":"2025-01-19T01:31:56.520697+00:00"}