JAIST Repository >
a. 知識科学研究科・知識科学系 >
a10. 学術雑誌論文等 >
a10-1. 雑誌掲載論文 >

このアイテムの引用には次の識別子を使用してください: http://hdl.handle.net/10119/15345

タイトル: Toward a mechanistic account for imitation learning: an analysis of pendulum swing-up
著者: Torii, Takuma
Hidaka, Shohei
キーワード: Imitation learning
Goal inference
Dynamical systems
pendulum swing-up
発行日: 2017-07-08
出版者: Springer
誌名: New Frontiers in Artificial Intelligence. JSAI-isAI 2016. Lecture Notes in Computer Science
巻: 10247
開始ページ: 327
終了ページ: 343
DOI: 10.1007/978-3-319-61572-1_22
抄録: Learning an action from others require to infer their underlying goals, and recent psychological studies have reported behavioral evidences that young children do infer others’ underlying goals by observing their actions. The goal of the present study is to propose a mechanistic account for how this goal inference is possible by observing others’actions. For this purpose, we performed a series of simulations in which two agents control pendulums toward different goals, and analyzed with which types of features it is possible to infer their different latent goals and control schemes. Our analysis showed that pointwise dimension, a type of fractal dimension, of the pendulum movements is sufficiently informative to classify the types of agents. With respect to its invariant nature, this result suggests that the fine-grained movement patterns such as the fractal dimension reflect the structure of the underlying control schemes and goals.
Rights: This is the author-created version of Springer, Takuma Torii, Shohei Hidaka, New Frontiers in Artificial Intelligence. JSAI-isAI 2016. Lecture Notes in Computer Science, 10247, 2017, 327-343. The original publication is available at www.springerlink.com, http://dx.doi.org/10.1007/978-3-319-61572-1_22
URI: http://hdl.handle.net/10119/15345
資料タイプ: author
出現コレクション:a10-1. 雑誌掲載論文 (Journal Articles)


ファイル 記述 サイズ形式
23457.pdf2300KbAdobe PDF見る/開く



お問い合わせ先 : 北陸先端科学技術大学院大学 研究推進課図書館情報係