{"id":77368,"created":"2025-01-18T23:32:57.787344+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00077368","sets":["1164:2735:6337:6524"]},"path":["6524"],"owner":"10","recid":"77368","title":["強化学習を用いたチーム編成の効率化モデルの提案と環境変化に対する評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-09-08"},"_buckets":{"deposit":"a399d708-aa48-4c5f-b942-6677b1e55dd7"},"_deposit":{"id":"77368","pid":{"type":"depid","value":"77368","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"強化学習を用いたチーム編成の効率化モデルの提案と環境変化に対する評価","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"強化学習を用いたチーム編成の効率化モデルの提案と環境変化に対する評価"},{"subitem_title":"Efficient Team Formation based on Learning and Reorganization and Influence of Change of Tasks","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2011-09-08","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"早稲田大学基幹理工学研究科情報理工学専攻"},{"subitem_text_value":"早稲田大学基幹理工学研究科情報理工学専攻"}]},"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/77368/files/IPSJ-MPS11085028.pdf"},"date":[{"dateType":"Available","dateValue":"2013-09-08"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MPS11085028.pdf","filesize":[{"value":"1.1 MB"}],"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":"f921b08a-b521-451c-9602-9e8cec99ac03","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2011 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"佐藤, 大樹"},{"creatorName":"菅原, 俊治"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Daiki, Satoh","creatorNameLang":"en"},{"creatorName":"Sugawara, Toshiharu","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10505667","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"インターネット上のサービスに対応したタスクは，それを構成する複数のサブタスクを処理することで達成される．効率的なタスク処理のためには，サブタスクを対応する能力やリソースを持つエージェントに適切に割り当てる必要がある．我々はこれまで，強化学習とネットワーク構造の再構成により，チーム編成を効率化する手法を提案してきた．しかし，そこで用いた学習は，近隣のエージェントの内部状態を既知としており，必ずしも現実のシステムと合致しない．また，実験で仮定したエージェントの配置も固定的であった．本論文では，提案手法を，他のエージェントの内部状態ではなく，近隣からのメッセージと遅延を考慮した減衰率から報酬を求め，それに基づいて Q 学習するようにモデル化する．次に，初期配置によらず，学習と組織構造の変化を組み合わせ既存手法よりも効率化できることを示す．さらに，タスクの種類の変化についても，効率的なチーム編成が可能なことを実験により評価する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"A task in a distributed environment is usually achieved by doing a number of subtasks that require different functions and resources. These subtasks have to be processed cooperatively in the appropriate team of agents that have the required functions with sufficient resources. We showed that the proposed method combines the learning for team formation and reorganization in a way that is adaptive to the environment and that it can improve the overall performance and increase the success in communication delay that may change dynamically. But the machine learning that we used there knows inside state of neighborhood agents and this cannot be assumed in real systems. We propose a method of distributed team formation that uses modified Q-learning with reward based in messages from neighborhood and communication delay. We show that it can improve the overall performance in any initial placement and in environment change of range of task.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告数理モデル化と問題解決（MPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2011-09-08","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"28","bibliographicVolumeNumber":"2011-MPS-85"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"updated":"2025-01-21T20:58:37.320927+00:00","links":{}}