JAIST Repository >
School of Knowledge Science >
Articles >
Journal Articles >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/15345

Title: Toward a mechanistic account for imitation learning: an analysis of pendulum swing-up
Authors: Torii, Takuma
Hidaka, Shohei
Keywords: Imitation learning
Goal inference
Dynamical systems
pendulum swing-up
Issue Date: 2017-07-08
Publisher: Springer
Magazine name: New Frontiers in Artificial Intelligence. JSAI-isAI 2016. Lecture Notes in Computer Science
Volume: 10247
Start page: 327
End page: 343
DOI: 10.1007/978-3-319-61572-1_22
Abstract: 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
Material Type: author
Appears in Collections:a10-1. 雑誌掲載論文 (Journal Articles)

Files in This Item:

File Description SizeFormat
23457.pdf2300KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, Japan Advanced Institute of Science and Technology