{"id":236007,"created":"2025-01-19T01:37:49.558033+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236007","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236007","title":["依存関係を持つ複数のゴールを達成するための強化学習エージェントの実装"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"37645bfd-59e3-414f-85d8-26f984310318"},"_deposit":{"id":"236007","pid":{"type":"depid","value":"236007","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"依存関係を持つ複数のゴールを達成するための強化学習エージェントの実装","author_link":["644972","644973"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"依存関係を持つ複数のゴールを達成するための強化学習エージェントの実装"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","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":"京大"},{"subitem_text_value":"京大"}]},"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/236007/files/IPSJ-Z86-6Q-04.pdf","label":"IPSJ-Z86-6Q-04.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-6Q-04.pdf","filesize":[{"value":"506.1 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"d5d1ac2c-c173-45d6-a94c-b6d8b39192fc","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":"北河, 英己"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"丁, 世堯"}],"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":"既存の強化学習タスクでは主に単一の目標を追求するものが多いが、実世界では依存関係を持つ複数の目標を同時に達成する必要があるシナリオが多く存在する。既存の強化学習手法でもこのような複雑なタスクへの適応は可能だが、単純なタスクと比較すると性能はよくない。本稿では、マインクラフト風強化学習環境「crafter」を用いて、複数の強化学習手法の性能を比較し評価する。「crafter」は、依存関係を持つ複数のゴールを同時に達成する必要がある複雑なタスクを提供するため、本研究に適している。この研究により、依存関係のある複数の目標を含む複雑なタスクに対する強化学習アプローチの可能性と限界を明らかにする。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"328","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"327","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T09:25:55.524631+00:00","links":{}}