{"id":17238,"updated":"2025-01-22T23:27:04.736089+00:00","links":{},"created":"2025-01-18T22:50:17.365827+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00017238","sets":["934:989:1006:1007"]},"path":["1007"],"owner":"1","recid":"17238","title":["遺伝的プログラミングと強化学習の統合に基づく実ロボットの行動獲得"],"pubdate":{"attribute_name":"公開日","attribute_value":"2004-02-15"},"_buckets":{"deposit":"c3293a1d-a7f8-4be2-a496-c6bf6be6301a"},"_deposit":{"id":"17238","pid":{"type":"depid","value":"17238","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"遺伝的プログラミングと強化学習の統合に基づく実ロボットの行動獲得","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"遺伝的プログラミングと強化学習の統合に基づく実ロボットの行動獲得"},{"subitem_title":"Integration of Genetic Programming and Reinforcement Learning for Real Robots","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"GP","subitem_subject_scheme":"Other"}]},"item_type_id":"3","publish_date":"2004-02-15","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院新領域創成科学研究科"},{"subitem_text_value":"東京大学大学院新領域創成科学研究科"},{"subitem_text_value":"東京大学大学院新領域創成科学研究科"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Frontier Science, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Frontier Science, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Frontier Science, The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/17238/files/IPSJ-TOM4502015.pdf"},"date":[{"dateType":"Available","dateValue":"2006-02-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TOM4502015.pdf","filesize":[{"value":"261.5 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"0164a4a3-86e8-46ca-b4aa-84a202babeff","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2004 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"神尾, 正太郎"},{"creatorName":"三橋, 秀行"},{"creatorName":"伊庭, 斉志"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shotaro, Kamio","creatorNameLang":"en"},{"creatorName":"Hideyuki, Mitsuhashi","creatorNameLang":"en"},{"creatorName":"Hitoshi, Iba","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_3_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11464803","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_3_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7780","subitem_source_identifier_type":"ISSN"}]},"item_3_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本論文では，遺伝的プログラミングと強化学習を統合した，実ロボットでの実時間学習が可能な手法を提案する．提案手法では，高精度のシミュレータは必要としない．なぜなら学習はシミュレータ上だけではなく，実ロボット上でも行われるからである．このため実ロボットでの最適行動を得ることができる．本論文では提案手法に基づき実ロボットAIBOで行った実験結果を示し，提案手法が従来のQ学習手法よりも性能が良いことを示す．","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We propose an integrated technique of genetic programming (GP) and reinforcement learning (RL) that allows a real robot to execute real-time learning. Our technique does not need a precise simulator because learning is done with a real robot. Moreover, our technique makes it possible to learn optimal actions in real robots. We show the result of an experiment with a real robot AIBO and represents the result which proves proposed technique performs better than traditional Q-learning method.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"143","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌数理モデル化と応用（TOM）"}],"bibliographicPageStart":"134","bibliographicIssueDates":{"bibliographicIssueDate":"2004-02-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"SIG02(TOM10)","bibliographicVolumeNumber":"45"}]},"relation_version_is_last":true,"weko_creator_id":"1"}}