Presentation 2003/10/16
Learning Arm's Posture Control using Reinforcement Learning and Feedback Error Learning
Hiroyuki KAMBARA, Kyuengbo MIN, Jaehyo KIM, Makoto SATO, Yasuharu KOIKE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a learning system with Actor-Critic method and feedback error learning. Actor-Critic method is one of the major framework in reinforcement learning. We use this method for obtaining the feedback controller in feedback error learning architecture, and Actor's output is used as an error signal of inverse dynamics model. By appling the proposed learning system to arm's posture control, we shows that a proper feedforward motor command could be acquired from all by a scalar value of reward.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reinforcement Learing / Actor-Critic / Feedback Error Learing / Inverse Dynamics Model / Posture Control
Paper # PRMU2003-124,NC2003-55
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/10/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning Arm's Posture Control using Reinforcement Learning and Feedback Error Learning
Sub Title (in English)
Keyword(1) Reinforcement Learing
Keyword(2) Actor-Critic
Keyword(3) Feedback Error Learing
Keyword(4) Inverse Dynamics Model
Keyword(5) Posture Control
1st Author's Name Hiroyuki KAMBARA
1st Author's Affiliation Department of Computational Intelligence and Systems Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology()
2nd Author's Name Kyuengbo MIN
2nd Author's Affiliation JST PRESTO, Precision and Intelligence Laboratory, Tokyo Institute of Technology
3rd Author's Name Jaehyo KIM
3rd Author's Affiliation Precision and Intelligence Laboratory, Tokyo Institute of Technology
4th Author's Name Makoto SATO
4th Author's Affiliation Precision and Intelligence Laboratory, Tokyo Institute of Technology
5th Author's Name Yasuharu KOIKE
5th Author's Affiliation JST PRESTO, Precision and Intelligence Laboratory, Tokyo Institute of Technology
Date 2003/10/16
Paper # PRMU2003-124,NC2003-55
Volume (vol) vol.103
Number (no) 389
Page pp.pp.-
#Pages 6
Date of Issue