Multi-agent Reinforcement Learning Based Approach for Periodic-review Joint Replenishment Problem under Practical Cost Structures

• Item type: Trans(1)
• 公開日: 2021-03-16
• タイトル: Multi-agent Reinforcement Learning Based Approach for Periodic-review Joint Replenishment Problem under Practical Cost Structures
• タイトル / 言語: en
• タイトル: Multi-agent Reinforcement Learning Based Approach for Periodic-review Joint Replenishment Problem under Practical Cost Structures
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [オリジナル論文] joint replenishment problem, multi-product inventory, multi-agent reinforcement learning, credit assignment, joint action selection
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Graduate School of Engineering, The University of Tokyo
• 著者所属: Graduate School of Engineering, The University of Tokyo
• 著者所属: Graduate School of Engineering, The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering, The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering, The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering, The University of Tokyo
• 著者名: Hiroshi, Suetsugu; Yoshiaki, Narusue; Hiroyuki, Morikawa
• 著者名(英): Hiroshi, Suetsugu; Yoshiaki, Narusue; Hiroyuki, Morikawa
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: 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.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: 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.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11464803
• 書誌情報: 情報処理学会論文誌数理モデル化と応用（TOM）; 巻 14, 号 2, p. 1-12, 発行日 2021-03-16
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7780
• 出版者 / 言語: ja
• 出版者: 情報処理学会