{"created":"2026-02-17T06:52:07.265525+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02007487","sets":["1164:5305:1771205017738:1771205084619"]},"path":["1771205084619"],"owner":"80578","recid":"2007487","title":["強化学習によるゲームメカニクス定量化フレームワークの提案"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2026-02-23"},"_buckets":{"deposit":"c6cfbaa1-6e48-4fd7-aa59-5a9acdbf2042"},"_deposit":{"id":"2007487","pid":{"type":"depid","value":"2007487","revision_id":0},"owners":[80578],"status":"published","created_by":80578},"item_title":"強化学習によるゲームメカニクス定量化フレームワークの提案","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"強化学習によるゲームメカニクス定量化フレームワークの提案","subitem_title_language":"ja"}]},"item_type_id":"4","publish_date":"2026-02-23","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東北大学大学院情報科学研究科"}]},"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/2007487/files/IPSJ-GI26057020.pdf","label":"IPSJ-GI26057020.pdf"},"date":[{"dateType":"Available","dateValue":"2028-02-23"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-GI26057020.pdf","filesize":[{"value":"3.7 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":"18"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"d989c0ee-add6-4f8a-9b2a-b0d6308a605b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2026 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"亀井,尚平"}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11362144","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":"2188-8736","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究は、ゲームデザインにおけるメカニクス差分が、プレイ中のダイナミクスおよび体験に与える影響を、再現可能に比較・評価するための枠組みを提案する。MDA（Mechanics, Dynamics, Aesthetics）フレームワークを理論基盤とし、エージェントベースモデリングによりメカニクス差分を導入したゲーム環境において、強化学習エージェントをプレイヤーモデルとして反復プレイさせる。学習過程に現れる移動平均成功率の推移をMDAにおけるChallenge体験の指標として、またTD誤差の時間推移を、予測が裏切られながら探索が継続される度合い、すなわちDiscovery体験を反映する指標として扱う。統計的比較には混合効果モデルを用い、エピソード進行に伴う時間構造を含めてメカニクス効果を推定する。ケーススタディとして基礎的な検証を行うため、シンプルなゲームとしてじゃんけんおよび迷路探索を対象とし、ランダム性や行動制約といった分類可能なゲームメカニクスを追加した際に生じる影響を本枠組みにより分析する。これにより、設計意図に基づく体験的な仮説を、学習曲線と統計推定を通じて検証可能な形へ翻訳し、ゲームデザインと計算論的手法を結び付けるための基盤としての実証的価値を示す。","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告ゲーム情報学（GI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2026-02-23","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"20","bibliographicVolumeNumber":"2026-GI-57"}]},"relation_version_is_last":true,"weko_creator_id":"80578"},"id":2007487,"updated":"2026-02-17T06:52:11.693935+00:00","links":{}}