{"created":"2025-01-19T01:39:32.716522+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00237103","sets":["6504:11678:11684"]},"path":["11684"],"owner":"44499","recid":"237103","title":["ポテンシャル法と強化学習を用いたサンプル効率改善に関する検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"cb1cf402-5f8d-4fa2-b5c8-dee643cdc828"},"_deposit":{"id":"237103","pid":{"type":"depid","value":"237103","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"ポテンシャル法と強化学習を用いたサンプル効率改善に関する検討","author_link":["648342","648341"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ポテンシャル法と強化学習を用いたサンプル効率改善に関する検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"コンピュータと人間社会","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2024-03-01","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":"日大"},{"subitem_text_value":"日大"}]},"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/237103/files/IPSJ-Z86-6ZM-04.pdf","label":"IPSJ-Z86-6ZM-04.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-04"}],"format":"application/pdf","filename":"IPSJ-Z86-6ZM-04.pdf","filesize":[{"value":"640.3 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"42eee8c3-c207-4b39-9a58-0f1fa1648b12","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"榎本, 隆士"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"栁澤, 一機"}],"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":"近年，人工知能の知識を持った技術者の育成が重要となっている．人工知能技術の1つである強化学習は，学習環境を用意することで自ら学習を行うが，学習に膨大な時間を必要とするため強化学習をテーマとした教材では学習から結果の確認までに時間がかかる．本研究では強化学習のサンプル効率の改善を目的とし，強化学習の1手法であるQ学習を用いて鬼ごっこをテーマとしたシミュレーション環境を作成した．障害物と目的地に関数を定義してそれの勾配にそった経路で目的地までの経路を出すポテンシャル法とQ学習を組み合わせ，探索にポテンシャル法を用いることでサンプル効率が改善されているかの検討を行った．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"994","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"993","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":237103,"updated":"2025-01-19T08:59:47.047055+00:00","links":{}}