JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >

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/10119/11412

タイトル: Adaptive Point-Based Value Iteration for Continuous States POMDP in Goal-Directed Imitation Learning
著者: Pratama, Ferdian Adi
Lee, Hosun
Lee, Geunho
Chong, Nak Young
キーワード: Imitation
Sequential Decision Making
Motion Planning
発行日: 2012-11
出版者: Institute of Electrical and Electronics Engineers (IEEE)
誌名: 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)
開始ページ: 249
終了ページ: 254
DOI: 10.1109/URAI.2012.6462987
抄録: In motion planning and robot navigation, continuous domain would be the natural way of representation of state space. However, discretization is needed in order to deal with continuous state space. Results precision depends on the discretization, which leads to a problem of ”curse of dimensionality”. We present a new approximation approach of goal-directed imitation learning algorithm using the point-based value iteration algorithm that deals with continuous domain in motion planning. We demonstrate our algorithm in the V-REP robot simulator, to validate the experimental result.
Rights: This is the author's version of the work. Copyright (C) 2012 IEEE. 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), 2012, 249-254. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
URI: http://hdl.handle.net/10119/11412
資料タイプ: author
出現コレクション:b11-1. 会議発表論文・発表資料 (Conference Papers)


ファイル 記述 サイズ形式
19094.pdf436KbAdobe 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