{"updated":"2025-01-19T11:22:54.183569+00:00","links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229875","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"229875","title":["強化学習の価値関数近似器としてSDNNを用いた格闘ゲームAI"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"45b83c51-28b6-49ac-a9e8-5e55c4b18491"},"_deposit":{"id":"229875","pid":{"type":"depid","value":"229875","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"強化学習の価値関数近似器としてSDNNを用いた格闘ゲームAI","author_link":["618375","618373","618374","618372"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"強化学習の価値関数近似器としてSDNNを用いた格闘ゲームAI"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2023-02-16","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"帝京大"},{"subitem_text_value":"帝京大"},{"subitem_text_value":"帝京大"},{"subitem_text_value":"帝京大"}]},"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/229875/files/IPSJ-Z85-6P-02.pdf","label":"IPSJ-Z85-6P-02.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-6P-02.pdf","filesize":[{"value":"2.0 MB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"b4fe3b76-be0f-43e7-aeb2-feb5c1f0faad","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"小川, 拓実"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"阿久津, 光範"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"金, 致中"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山根, 健"}],"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_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"格闘ゲームにおいて自律的な敵キャラクタは重要な要素であり，設計方法が課題となる．ルールベースの設計法では強さに限界があり，強化学習を用いる方法では学習効率が悪い．強化学習に関して，新保らは価値関数近似器として選択的不感化ニューラルネット（SDNN）を用いることでAcrobotタスクにおいて効率的に学習できることを示した．しかし，格闘ゲームのような多くの行動を扱うタスクへの適用例はない．そこで，本研究では，多くの行動を分散的な表現を用いて扱えるように新保らの方法を拡張し，強化学習を用いた格闘ゲームAIの設計方法を提案する．また，サンプルAIと対戦させて，提案手法の性能や学習効率，複数の対戦相手への適応性を評価する．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"150","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"149","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229875,"created":"2025-01-19T01:29:18.001885+00:00"}