{"created":"2023-07-25T09:05:57.999902+00:00","id":4115,"links":{},"metadata":{"_buckets":{"deposit":"5b1cf06c-4a74-475c-b02f-751af38e718f"},"_deposit":{"created_by":3,"id":"4115","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"4115"},"status":"published"},"_oai":{"id":"oai:toyama.repo.nii.ac.jp:00004115","sets":["496:556:559:560:584"]},"author_link":["56172","56170","56171","56169"],"item_3_alternative_title_19":{"attribute_name":"その他（別言語等）のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Mathematical Model of Reinforced Learning"}]},"item_3_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"1973-03","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1/2","bibliographicPageEnd":"6","bibliographicPageStart":"1","bibliographicVolumeNumber":"24","bibliographic_titles":[{"bibliographic_title":"富山大学工学部紀要"}]}]},"item_3_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"近年，巷に情報革命がさけばれているが，ことに飛躍的発展をもたらしたともいうべき電子計算機がこれに拍車をかけてきた。21世紀には情報化時代の最盛期を迎えるだろうと期待されている。一方，その時代においては自動制御方式はますます複雑かつ大規模な制御対象物と取りくむだろう。そして人間の代行である電子計算機も以前にまして知的な能力が要求されるようになるであろう。現在の電子計算機は開発当初とは桁違いの優秀性をもっているが，これでも充分ではなく，諸処の問題を生みつつある。たとえばパターン認識，機械翻訳，機械診断等において。これに対処するためには人間のもつ脳機構自体を再度見直す必要がある。すなわち脳の中枢に刺激が与えられた場合，脳はいかにして敏速かつ明確にその情報処理し反応を引き起こさせるかという，その過程を分析してみなければならない。うちでも学習機能は脳のもつ重要な機能の一つであり，学習心理学の分野でもにわかに研究が推進されてきている。しかし，今日なおその機構については未知の分野が多く，研究はその緒についたばかりである。本論では強化学習にもとずく行動を数学的手法を用いて分析分し，心理学的事実との比較検討をおこなう。","subitem_description_type":"Abstract"}]},"item_3_description_40":{"attribute_name":"資源タイプ(DSpace)","attribute_value_mlt":[{"subitem_description":"Article","subitem_description_type":"Other"}]},"item_3_description_6":{"attribute_name":"引用","attribute_value_mlt":[{"subitem_description":"富山大学工学部紀要，24(1/2)","subitem_description_type":"Other"}]},"item_3_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"56171","nameIdentifierScheme":"WEKO"}],"names":[{"name":"YAGI, Hiroshi"}]},{"nameIdentifiers":[{"nameIdentifier":"56172","nameIdentifierScheme":"WEKO"}],"names":[{"name":"EGAWA, Takashi"}]}]},"item_3_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.15099/00004109","subitem_identifier_reg_type":"JaLC"}]},"item_3_publisher_33":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"富山大学工学部"}]},"item_3_source_id_10":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00175872","subitem_source_identifier_type":"NCID"}]},"item_3_source_id_8":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"03871339","subitem_source_identifier_type":"ISSN"}]},"item_3_subject_22":{"attribute_name":"国立国会図書館分類","attribute_value_mlt":[{"subitem_subject":"ZM2","subitem_subject_scheme":"NDLC"}]},"item_3_version_type_16":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_970fb48d4fbd8a85","subitem_version_type":"VoR"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"八木, 寛"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"江川, 隆"}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2016-02-16"}],"displaytype":"detail","filename":"Kokiyo_24_01_Page001to006.pdf","filesize":[{"value":"3.1 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"Kokiyo_24_01_Page001to006.pdf","url":"https://toyama.repo.nii.ac.jp/record/4115/files/Kokiyo_24_01_Page001to006.pdf"},"version_id":"33524dcf-704d-4c53-a29c-3bbbba26577e"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"強化学習","subitem_subject_scheme":"Other"},{"subitem_subject":"数学的モデル","subitem_subject_scheme":"Other"},{"subitem_subject":"学習機能","subitem_subject_scheme":"Other"},{"subitem_subject":"学習理論","subitem_subject_scheme":"Other"},{"subitem_subject":"学習能力","subitem_subject_scheme":"Other"},{"subitem_subject":"学習機械","subitem_subject_scheme":"Other"},{"subitem_subject":"学習曲線","subitem_subject_scheme":"Other"},{"subitem_subject":"学習能率","subitem_subject_scheme":"Other"},{"subitem_subject":"学習量","subitem_subject_scheme":"Other"},{"subitem_subject":"報酬訓練","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"departmental bulletin paper","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"強化学習の数学的モデル","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"強化学習の数学的モデル"}]},"item_type_id":"3","owner":"3","path":["584"],"pubdate":{"attribute_name":"公開日","attribute_value":"2012-09-27"},"publish_date":"2012-09-27","publish_status":"0","recid":"4115","relation_version_is_last":true,"title":["強化学習の数学的モデル"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2023-07-25T15:11:54.143190+00:00"}