{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00050681","sets":["1164:4402:4442:4446"]},"path":["4446"],"owner":"1","recid":"50681","title":["強化学習における環境変化認識法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2000-01-12"},"_buckets":{"deposit":"95e24e6b-dc13-44d9-806b-0be2e8e50bb7"},"_deposit":{"id":"50681","pid":{"type":"depid","value":"50681","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"強化学習における環境変化認識法","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"強化学習における環境変化認識法"},{"subitem_title":"A recognization method of environmental change on reinforcement learning","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2000-01-12","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"慶應義塾大学大学院理工学研究科"},{"subitem_text_value":"慶應義塾大学大学院理工学研究科"},{"subitem_text_value":"慶應義塾大学大学院理工学研究科"},{"subitem_text_value":"慶應義塾大学大学院理工学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Keio University","subitem_text_language":"en"},{"subitem_text_value":"Keio University","subitem_text_language":"en"},{"subitem_text_value":"Keio University","subitem_text_language":"en"},{"subitem_text_value":"Keio University","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/50681/files/IPSJ-ICS99119016.pdf"},"date":[{"dateType":"Available","dateValue":"2002-01-12"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ICS99119016.pdf","filesize":[{"value":"509.6 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":"25"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"4a7f063f-39ff-4812-a266-b155b95af267","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2000 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山本, 真也"},{"creatorName":"山口, 文彦"},{"creatorName":"斎藤, 博昭"},{"creatorName":"中西, 正和"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shinya, Yamamoto","creatorNameLang":"en"},{"creatorName":"Fumihiko, Yamaguchi","creatorNameLang":"en"},{"creatorName":"Hiroaki, Saito","creatorNameLang":"en"},{"creatorName":"Masakazu, Nakanishi","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"非マルコフ決定過程(non-MDP)の環境における強化学習の問題点の解決法として,環境変化時に何らかの処理を行う方法が提案されている.これらの研究において,環境変化の認識法は確立されていない.本論文では,non-MDPにおける有力な学習エンジンである確率的傾斜法において,学習中に環境変化を認識する方法を提案する.確率的傾斜法の内部変数Wの変化量を調べることにより環境変化を認識する.提案手法は確率的傾斜法が適用できる問題であれば簡単に内部に組み込むことのでき,環境変化の認識を行うことができる.シミュレーション実験により従来の手法の半分程度のステップで環境変化を認識できることを示す.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"There are some methods that resolve problems of reinforcement learning in non Marokov Decision Process(non-MDP) environment on environment changes. The efficient method of recognizing environmental change has not yet been proposed. This paper proposes a method for recognizing environmental changes on Stochastic Gradient Ascent(SGA) which is a major learning engine in non-MDP environment. It uses the change of an internal variable W of SGA. Our method can be easily put in SGA and it is available for all SGA-applicable problems. We had a simulation to show the efficiency of our method and succeeded to reduce the recognition time to almost half of the conventional method.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"116","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告知能と複雑系(ICS)"}],"bibliographicPageStart":"111","bibliographicIssueDates":{"bibliographicIssueDate":"2000-01-12","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3(1999-ICS-119)","bibliographicVolumeNumber":"2000"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":50681,"updated":"2025-01-22T07:31:10.963353+00:00","links":{},"created":"2025-01-18T23:15:24.241323+00:00"}