{"id":209715,"created":"2025-01-19T01:11:00.372754+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00209715","sets":["1164:2735:10526:10527"]},"path":["10527"],"owner":"44499","recid":"209715","title":["Generating Intrinsic Rewards by Random Recurrent Network Distillation"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-02-22"},"_buckets":{"deposit":"fb1bb548-04bb-4649-a7e7-f4395af1b9f1"},"_deposit":{"id":"209715","pid":{"type":"depid","value":"209715","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Generating Intrinsic Rewards by Random Recurrent Network Distillation","author_link":["529412","529403","529407","529404","529405","529411","529410","529409","529406","529408"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Generating Intrinsic Rewards by Random Recurrent Network Distillation"},{"subitem_title":"Generating Intrinsic Rewards by Random Recurrent Network Distillation","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2021-02-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology"},{"subitem_text_value":"Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology"},{"subitem_text_value":"Department of Clinical Engineering, College of Life and Health Sciences, Chubu University"},{"subitem_text_value":"Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology"},{"subitem_text_value":"Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Clinical Engineering, College of Life and Health Sciences, Chubu University","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology","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/209715/files/IPSJ-MPS21132015.pdf","label":"IPSJ-MPS21132015.pdf"},"date":[{"dateType":"Available","dateValue":"2023-02-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MPS21132015.pdf","filesize":[{"value":"1.6 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":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"acfb17a0-f6e2-42ec-a5f6-6b60b71c4abf","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":"Zefeng, Xu"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Koichi, Moriyama"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tohgoroh, Matsui"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Atsuko, Mutoh"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuhiro, Inuzuka"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Zefeng, Xu","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Koichi, Moriyama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tohgoroh, Matsui","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Atsuko, Mutoh","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuhiro, Inuzuka","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10505667","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":"2188-8833","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Exploration in sparse reward environments pose significant challenges for many reinforcement learning algorithms. Rather than solely relying on extrinsic rewards provided by environments, many state-of-the-art methods generate intrinsic rewards to encourage the agent explore the environments. However, we found that existing models fall short in some environments, where the agent must visit a same state more than once. Thus, we improve an existing model to propose a novel type of intrinsic exploration bonus which will reward the agent when a new sequence is discovered. The intrinsic reward is the error of a recurrent neural network predicting features of the sequences given by a fixed randomly initialized recurrent neural network. Our approach performs well in some Atari games where conditions must be fulfilled to develop stories.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Exploration in sparse reward environments pose significant challenges for many reinforcement learning algorithms. Rather than solely relying on extrinsic rewards provided by environments, many state-of-the-art methods generate intrinsic rewards to encourage the agent explore the environments. However, we found that existing models fall short in some environments, where the agent must visit a same state more than once. Thus, we improve an existing model to propose a novel type of intrinsic exploration bonus which will reward the agent when a new sequence is discovered. The intrinsic reward is the error of a recurrent neural network predicting features of the sequences given by a fixed randomly initialized recurrent neural network. Our approach performs well in some Atari games where conditions must be fulfilled to develop stories.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告数理モデル化と問題解決（MPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"15","bibliographicVolumeNumber":"2021-MPS-132"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T18:25:39.729736+00:00","links":{}}