{"created":"2023-07-25T10:22:56.216109+00:00","id":1487,"links":{},"metadata":{"_buckets":{"deposit":"5285a158-b638-42c6-8b84-e4f01fdf6423"},"_deposit":{"created_by":10,"id":"1487","owners":[10],"pid":{"revision_id":0,"type":"depid","value":"1487"},"status":"published"},"_oai":{"id":"oai:pu-hiroshima.repo.nii.ac.jp:00001487","sets":["135:146:155"]},"author_link":["3009"],"control_number":"1487","item_10003_biblio_info_7":{"attribute_name":"bibliographic_information","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2012","bibliographicIssueDateType":"Issued"},"bibliographicPageEnd":"10","bibliographicPageStart":"7","bibliographic_titles":[{"bibliographic_title":"第17回日本知能情報ファジィ学会中国四国支部大会予稿集"}]}]},"item_10003_description_19":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_10003_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"Hierarchical Modular Reinforcement Learning(HMRL), consists of 2 layered learning where Profit-Sharing works to plan a target　position in the higher layer and Q-learning trains the state-action pair to the target in the lower layer. In this paper, we expanded HMRL to multi-target problem under the consideration of the distance between target. We try to extract the knowledge related to state-action rules by C4.5. The state-action decision is implemented by using the acquired knowledge.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_10003_description_6":{"attribute_name":"内容記述","attribute_value_mlt":[{"subitem_description":"開催日：平成24年12月22日　会場：山口大学","subitem_description_type":"Other"}]},"item_10003_publisher_8":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"日本知能情報ファジィ学会"}]},"item_10003_version_type_20":{"attribute_name":"出版タイプ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_ab4af688f83e57aa","subitem_version_type":"AM"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"伊賀上, 大輔","creatorNameLang":"ja"},{"creatorName":"イガウエ, ダイスケ","creatorNameLang":"ja-Kana"},{"creatorName":"IGAUE, Daisuke","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"市村, 匠","creatorNameLang":"ja"},{"creatorName":"イチムラ, タクミ","creatorNameLang":"ja-Kana"},{"creatorName":"ICHIMURA, Takumi","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"3009","nameIdentifierScheme":"WEKO"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2023-04-18"}],"filename":"IchimuraT040.pdf","filesize":[{"value":"125 KB"}],"format":"application/pdf","mimetype":"application/pdf","url":{"url":"https://pu-hiroshima.repo.nii.ac.jp/record/1487/files/IchimuraT040.pdf"},"version_id":"44e62259-69ae-481c-9af7-b74458f2dd12"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"item_resource_type","attribute_value_mlt":[{"resourcetype":"conference paper","resourceuri":"http://purl.org/coar/resource_type/c_5794"}]},"item_title":"複数ターゲットによる階層型モジュラー強化学習結果からの知識獲得","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"複数ターゲットによる階層型モジュラー強化学習結果からの知識獲得","subitem_title_language":"ja"},{"subitem_title":"Hierarchical Modular Reinforcement Learning method in Multi-target Problem and Its Knowledge Acquisition of State-Action Rules","subitem_title_language":"en"}]},"item_type_id":"10003","owner":"10","path":["155"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2023-04-18"},"publish_date":"2023-04-18","publish_status":"0","recid":"1487","relation_version_is_last":true,"title":["複数ターゲットによる階層型モジュラー強化学習結果からの知識獲得"],"weko_creator_id":"10","weko_shared_id":-1},"updated":"2024-12-25T05:16:27.116321+00:00"}