{"id":212817,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00212817","sets":["1164:4402:10541:10706"]},"path":["10706"],"owner":"44499","recid":"212817","title":["Towards Personalized Autonomous Driving: Deep Reinforcement Learning from Human Feedback"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-09-08"},"_buckets":{"deposit":"edb8dcd1-8ffc-40e2-8c68-271e26a0bdee"},"_deposit":{"id":"212817","pid":{"type":"depid","value":"212817","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Towards Personalized Autonomous Driving: Deep Reinforcement Learning from Human Feedback","author_link":["543522","543524","543521","543528","543526","543527","543523","543525"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Towards Personalized Autonomous Driving: Deep Reinforcement Learning from Human Feedback"},{"subitem_title":"Towards Personalized Autonomous Driving: Deep Reinforcement Learning from Human Feedback","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2021-09-08","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Faculty of Science and Engineering, Waseda University"},{"subitem_text_value":"Faculty of Science and Engineering, Waseda University"},{"subitem_text_value":"Presently with National Institute of Informatics／Faculty of Science and Engineering, Waseda University"},{"subitem_text_value":"Presently with National Institute of Informatics／Faculty of Science and Engineering, Waseda University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Science and Engineering, Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Science and Engineering, Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Presently with National Institute of Informatics / Faculty of Science and Engineering, Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Presently with National Institute of Informatics / Faculty of Science and Engineering, Waseda University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/212817/files/IPSJ-ICS21204011.pdf","label":"IPSJ-ICS21204011.pdf"},"date":[{"dateType":"Available","dateValue":"2023-09-08"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ICS21204011.pdf","filesize":[{"value":"1.0 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"25"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"43e3d0c0-234e-4ed7-8ef3-69ccdcf46b84","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Jiali, Ling"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jialong, Li"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kenji, Tei"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinichi, Honiden"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Jiali, Ling","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jialong, Li","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kenji, Tei","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinichi, Honiden","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11135936","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-885X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"In modern society, personalization is one of the important indicators to attract customers. And this is the same in the field of autonomous driving. Personalized autonomous driving can not only meet the different passengers' riding preferences but also relieve the pressure and distrust caused by autonomous driving to a certain extent. In this research, We regard human as another agent, and vehicles and humans are in a cooperative relationship. And we propose a composite reward model based on reinforcement learning, which combines the passenger's feedback on autonomous driving behavior. The system proposed in this study can learn personalized driving behavior based on passenger feedback.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In modern society, personalization is one of the important indicators to attract customers. And this is the same in the field of autonomous driving. Personalized autonomous driving can not only meet the different passengers' riding preferences but also relieve the pressure and distrust caused by autonomous driving to a certain extent. In this research, We regard human as another agent, and vehicles and humans are in a cooperative relationship. And we propose a composite reward model based on reinforcement learning, which combines the passenger's feedback on autonomous driving behavior. The system proposed in this study can learn personalized driving behavior based on passenger feedback.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"3","bibliographic_titles":[{"bibliographic_title":"研究報告知能システム（ICS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-09-08","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"11","bibliographicVolumeNumber":"2021-ICS-204"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T17:21:50.516192+00:00","created":"2025-01-19T01:13:44.819202+00:00","links":{}}