{"links":{},"id":210341,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00210341","sets":["934:989:10456:10521"]},"path":["10521"],"owner":"44499","recid":"210341","title":["Multi-agent Reinforcement Learning Based Approach for Periodic-review Joint Replenishment Problem under Practical Cost Structures"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-16"},"_buckets":{"deposit":"2fbc6d17-23e6-449b-bdbd-5ccd35597d6c"},"_deposit":{"id":"210341","pid":{"type":"depid","value":"210341","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Multi-agent Reinforcement Learning Based Approach for Periodic-review Joint Replenishment Problem under Practical Cost Structures","author_link":["532277","532276","532275","532273","532278","532274"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Multi-agent Reinforcement Learning Based Approach for Periodic-review Joint Replenishment Problem under Practical Cost Structures"},{"subitem_title":"Multi-agent Reinforcement Learning Based Approach for Periodic-review Joint Replenishment Problem under Practical Cost Structures","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[オリジナル論文] joint replenishment problem, multi-product inventory, multi-agent reinforcement learning, credit assignment, joint action selection","subitem_subject_scheme":"Other"}]},"item_type_id":"3","publish_date":"2021-03-16","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/210341/files/IPSJ-TOM1402002.pdf","label":"IPSJ-TOM1402002.pdf"},"date":[{"dateType":"Available","dateValue":"2023-03-16"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TOM1402002.pdf","filesize":[{"value":"540.2 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"20243145-f477-4766-bfc3-9b70af786cb0","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hiroshi, Suetsugu"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoshiaki, Narusue"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroyuki, Morikawa"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hiroshi, Suetsugu","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoshiaki, Narusue","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroyuki, Morikawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_3_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11464803","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_3_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7780","subitem_source_identifier_type":"ISSN"}]},"item_3_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"A periodic-review joint replenishment problem is considered. In literature, can-order and modified periodic-review policies have been proposed, and either of them cannot always outperform the other depending on the demand characteristics. In addition, whereas numerous types of joint-replenishment cost structures exist in practical settings, most studies have assumed the fixed joint-replenishment costs, and for the periodic-review system, no study has been conducted to incorporate the practical cost structures into the existing policies. In this study, a multi-agent reinforcement learning-based solution for a joint replenishment problem is proposed, which can be used for problems with several demand settings, and be applied for various cost structures with minor modification. Our numerical experiments demonstrate that the performance of our proposed agent equals or surpasses that of the existing policies, which are can-order, and modified periodic policies.","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"A periodic-review joint replenishment problem is considered. In literature, can-order and modified periodic-review policies have been proposed, and either of them cannot always outperform the other depending on the demand characteristics. In addition, whereas numerous types of joint-replenishment cost structures exist in practical settings, most studies have assumed the fixed joint-replenishment costs, and for the periodic-review system, no study has been conducted to incorporate the practical cost structures into the existing policies. In this study, a multi-agent reinforcement learning-based solution for a joint replenishment problem is proposed, which can be used for problems with several demand settings, and be applied for various cost structures with minor modification. Our numerical experiments demonstrate that the performance of our proposed agent equals or surpasses that of the existing policies, which are can-order, and modified periodic policies.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"12","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌数理モデル化と応用（TOM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"14"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:11:34.237688+00:00","updated":"2025-01-19T18:11:32.005078+00:00"}