{"updated":"2025-01-19T11:14:33.382951+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00230213","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"230213","title":["畳み込みニューラルネットワークを用いたProfit SharingにおけるExperience Replayの利用"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"83bf163e-cbab-4e45-8f90-0db72a4f46e3"},"_deposit":{"id":"230213","pid":{"type":"depid","value":"230213","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"畳み込みニューラルネットワークを用いたProfit SharingにおけるExperience Replayの利用","author_link":["619380","619381"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"畳み込みニューラルネットワークを用いたProfit SharingにおけるExperience Replayの利用"}]},"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":"2023-02-16","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":"東京工科大"},{"subitem_text_value":"東京工科大"}]},"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/230213/files/IPSJ-Z85-6W-05.pdf","label":"IPSJ-Z85-6W-05.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-6W-05.pdf","filesize":[{"value":"100.9 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"b3b2856e-442c-4877-946f-8ca3aa5f5ac8","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"久保田, 英豊"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"長名, 優子"}],"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":"本研究では、畳み込みニューラルネットワークを用いたProfit SharingにおけるExperience Replayの利用を提案する。Profit Sharingにおける行動価値を学習する場合には、Deep Q NetworkにおけるExperience Replayをそのまま利用することはできない。Profit Sharingにおける行動価値を学習する際の誤差関数では報酬分配量が教師信号として用いられるため、メモリに観測、行動、報酬分配量の3つを蓄積しておくこととする。こうすることで、メモリに蓄積したデータからランダムにとり出してミニバッチを生成することが可能となり、学習の際に何度もデータを利用することが可能になる。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"856","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"855","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:29:50.138928+00:00","id":230213,"links":{}}