Biasing Monte-Carlo Rollouts with Potential Field in General Video Game Playing

• Item type: Branch(1)
• 公開日: 2015-09-18
• タイトル / 言語: en
• タイトル: Biasing Monte-Carlo Rollouts with Potential Field in General Video Game Playing
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: メディア・インタラクション
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属(英): en
• 著者所属(英): Ritsumeikan University、Ritsumeikan University、Ritsumeikan University
• 著者名(英): Chun, Yin Chu、Ruck Thawonmas、Tomohiro Harada
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper proposes the use of machine learning techniques potential field and biased Monte Carlo rollouts in General Video Game Playing (GVGP). Monte-Carlo Tree Search is a famous technique for General Video Game Playing, thanks to its adaptability. However, since the rollouts are performed randomly, it may not be able to search the game state efficiently. Existing research has attempted to bias the rollout by using Euclidean distances to the closest sprites as features, and training the bias weights with Evolutionary Strategy. In this paper, we propose the use of potential field features instead of Euclidean distances as the rollout bias, so as to further improve the performance of Monte-Carlo Tree Search in General Video Game Playing.
• 書誌情報: 2015年度 情報処理学会関西支部 支部大会 講演論文集; 巻 2015, 発行日 2015-09-18
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1884-197X
• 出版者 / 言語: ja
• 出版者: 情報処理学会