{"created":"2023-05-15T10:00:41.088612+00:00","id":5048,"links":{},"metadata":{"_buckets":{"deposit":"dee52324-7415-40af-8368-bdd39246537e"},"_deposit":{"created_by":5,"id":"5048","owner":"5","owners":[5],"pid":{"revision_id":0,"type":"depid","value":"5048"},"status":"published"},"_oai":{"id":"oai:miyazaki-u.repo.nii.ac.jp:00005048","sets":["73","73:36","73:36:330","73:36:330:326"]},"author_link":["11805","27422","12201","27425"],"item_10002_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2016-07-29","bibliographicIssueDateType":"Issued"},"bibliographicPageEnd":"225","bibliographicPageStart":"221","bibliographicVolumeNumber":"45","bibliographic_titles":[{"bibliographic_title":"宮崎大学工学部紀要","bibliographic_titleLang":"ja"},{"bibliographic_title":"Memoirs of Faculty of Engineering, University of Miyazaki","bibliographic_titleLang":"en"}]}]},"item_10002_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"Tracking problem is one of the popular benchmark to evaluate reinforcement learning. In the tracking problem, some hunters trace a target and try to catch target in shorter steps. In the paper, we propose to separate decision marking process of reinforcement learning from two points of view; strategy decision and tactical decision. Strategy decision decides the movement policy of the hunters, and tactical decision decides the movement direction of each hunter. Experimental results showed that our method could catch the target with 54% steps by the conventional reinforcement learning.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_10002_publisher_8":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"宮崎大学工学部","subitem_publisher_language":"ja"},{"subitem_publisher":"Faculty of Engineering, University of Miyazaki","subitem_publisher_language":"en"}]},"item_10002_source_id_11":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA00732558","subitem_source_identifier_type":"NCID"}]},"item_10002_source_id_9":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"05404924","subitem_source_identifier_type":"ISSN"}]},"item_10002_version_type_20":{"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":"山森, 一人","creatorNameLang":"ja"},{"creatorName":"ヤマモリ, クニヒト","creatorNameLang":"ja-Kana"},{"creatorName":"Yamamori, Kunihito","creatorNameLang":"en"}],"nameIdentifiers":[{},{}]},{"creatorNames":[{"creatorName":"渡部, 将人","creatorNameLang":"ja"},{"creatorName":"ワタナベ, マサト","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"相川, 勝","creatorNameLang":"ja"},{"creatorName":"アイカワ, マサル","creatorNameLang":"ja-Kana"},{"creatorName":"Aikawa, Masaru","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Watanabe, Masato","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2020-06-21"}],"displaytype":"detail","filename":"p221.pdf","filesize":[{"value":"871.9 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"本文","url":"https://miyazaki-u.repo.nii.ac.jp/record/5048/files/p221.pdf"},"version_id":"b136925a-f0c0-42cf-9781-7b2fdc6b0115"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"Reinforcement Learning, Multi-layer decision making, Tracking problem","subitem_subject_language":"en","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":"意思決定の階層化による強化学習の学習効率の向上","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"意思決定の階層化による強化学習の学習効率の向上","subitem_title_language":"ja"},{"subitem_title":"Accuracy Improvement for TSP by Multi-Level Perturbed Parallel Island Model","subitem_title_language":"en"}]},"item_type_id":"10002","owner":"5","path":["73","36","330","326"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2020-06-21"},"publish_date":"2020-06-21","publish_status":"0","recid":"5048","relation_version_is_last":true,"title":["意思決定の階層化による強化学習の学習効率の向上"],"weko_creator_id":"5","weko_shared_id":2},"updated":"2023-07-30T04:22:20.065305+00:00"}