{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00183861","sets":["6164:6165:6210:9269"]},"path":["9269"],"owner":"11","recid":"183861","title":["内部報酬を自動生成する強化学習による一人用RPGの自動攻略"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-11-03"},"_buckets":{"deposit":"8d49b713-e36d-4d53-8bd4-323bf65cefcc"},"_deposit":{"id":"183861","pid":{"type":"depid","value":"183861","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"内部報酬を自動生成する強化学習による一人用RPGの自動攻略","author_link":["404670","404671","404672","404673"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"内部報酬を自動生成する強化学習による一人用RPGの自動攻略"},{"subitem_title":"Automatic capture of one person RPG by reinforcement learning to automatically generate internal compensation","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ゲームAI","subitem_subject_scheme":"Other"},{"subitem_subject":"強化学習","subitem_subject_scheme":"Other"},{"subitem_subject":"内部報酬","subitem_subject_scheme":"Other"},{"subitem_subject":"RPG","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2017-11-03","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学工学部電子情報工学科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科電子情報学専攻"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Information and Communication Engineer-ing, Graduate School of Information Science and Technology, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Department of Information and Communication Engineer-ing, The University of Tokyo","subitem_text_language":"en"}]},"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/183861/files/IPSJ-GPWS2017034.pdf","label":"IPSJ-GPWS2017034.pdf"},"date":[{"dateType":"Available","dateValue":"2017-11-03"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-GPWS2017034.pdf","filesize":[{"value":"732.6 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"18"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"c4f02fc8-a14d-4a7d-b02e-39b29c7629fa","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2017 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"加納, 由希夫"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"鶴岡, 慶雅"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yukio, Kano","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoshimasa, Tsuruoka","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"AIが内部報酬を自動生成することによって，外部報酬を利用しない自律的な強化学習を実現することは，報酬設計が困難であるような現実世界の問題に人工知能を応用させる上で非常に重要な課題の一つである．内部報酬を自動で生成する手法の一つにICM(Pathak,2017) があり，A3C(Mnih,2016)の報酬にICMの内部報酬を用いた強化学習は，VizDoomやSuper Mario Bros などのゲームにおいて高い学習成果を示している．本研究では，ゲームの初期状態が毎回変化するという特徴を持つローグライクゲームに対して，ICMの手法を適用して効率的な強化学習を行えるようにすることを目指す．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Realization of autonomous reinforcement learning that does not use external compensation by automatically generating internal compensation from AI is extremely important in applying artificial intelli-gence to real world problems where compensation design is difficult. ICM (Pathak, 2017) is one method to automatically generate internal compensation, reinforcement learning using internal compensation of ICM for remuneration of A3C (Mnih, 2016) is used in games such as VizDoom and Super Mario Bros. It shows high learning outcome. In this research, we aim to enable efficient reinforcement learning by applying ICM method to roguelike games, which features the initial state of the game changing every time.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"225","bibliographic_titles":[{"bibliographic_title":"ゲームプログラミングワークショップ2017論文集"}],"bibliographicPageStart":"219","bibliographicIssueDates":{"bibliographicIssueDate":"2017-11-03","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2017"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"updated":"2025-01-20T03:31:01.828482+00:00","created":"2025-01-19T00:51:21.092316+00:00","links":{},"id":183861}