{"id":216461,"created":"2025-01-19T01:17:04.158490+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216461","sets":["1164:4402:10858:10859"]},"path":["10859"],"owner":"44499","recid":"216461","title":["DA3: マルチエージェント深層強化学習における協調行動の解釈性確立と対ノイズ性能の検証"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-02-14"},"_buckets":{"deposit":"50855a7d-7b49-4f88-a977-a0a81fe74325"},"_deposit":{"id":"216461","pid":{"type":"depid","value":"216461","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"DA3: マルチエージェント深層強化学習における協調行動の解釈性確立と対ノイズ性能の検証","author_link":["558853","558852"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"DA3: マルチエージェント深層強化学習における協調行動の解釈性確立と対ノイズ性能の検証"}]},"item_type_id":"4","publish_date":"2022-02-14","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知識ソフトウェア研究室"},{"subitem_text_value":"早稲田大学基幹理工学研究科知識ソフトウェア研究室"}]},"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/216461/files/IPSJ-ICS22205008.pdf","label":"IPSJ-ICS22205008.pdf"},"date":[{"dateType":"Available","dateValue":"2024-02-14"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ICS22205008.pdf","filesize":[{"value":"1.6 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":"25"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"b8b5344c-a911-4d0a-beb6-88da1e152805","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"元川, 善就"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"菅原, 俊治"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11135936","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":"2188-885X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本稿では，マルチエージェント深層強化学習におけるノイズの影響度を学習し，自律的に抑制する distributed attentional actor architecture model for multi-agent system（DA3）を提案する．ノイズは多くの分野に存在し，長年の間その特性の解明や抑制手法が考案されてきた．特に，周囲の限られた情報をもとに他のエージェントとの協調・調整，さらに相互協力を前提とした互恵行動を獲得する必要のあるマルチエージェントシステムにおいても，ノイズ抑制や排除は重要な研究テーマである．本提案である DA3 は attention mechanism を内包しているため，エージェントは観測情報を取捨選択しながら環境に適応することが可能である．実験結果から，観測情報内のノイズや協調行動に無関係な第三者的エージェントに惑わされることなく，他エージェントとの協調行動を獲得し，attention mechanism を持たないベースライン (ここでは DQN) よりも高い学習性能を達成することを示す．また，DA3 内部に存在する attentional weights を解析することで，これまでブラックボックスとされてきたエージェントの行動決定過程におけるノイズの影響度などを把握できることを示す．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告知能システム（ICS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-02-14","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"2022-ICS-205"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T15:50:24.807131+00:00","links":{}}