IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2006-03-17 11:00
Considering model error when applying an reinforcement learning method to control of a real robot
Yoichi Tokita, Yutaka Nakamura (NAIST), Junichiro Yoshimoto (OIST), Shin Ishii (NAIST)
Abstract (in Japanese) (See Japanese page) 
(in English) Because reinforcement learning (RL) methods have an advantage such that a control rule can be obtained autonomously without any knowledge of the target system. RL methods have been successfully applied to automatic control of various robots such as balancing control of a cart-pole. However, most real control problems have non-linear dynamics with a large number of degrees of freedom, therefore it is necessary to develop an RL method to deal with such situations. This difficulty is called ``curse of dimensionality'' in the context of RL. We formarly proposed an RL method that switches controllers which had been developed in the field of control theory, and applied our method to an automatic control problem of an acrobot. The results showed that a good controller for a simulator can be obtained autonomously but the control of the real acrobot was not stable. In the current study, we propose an RL method which is robust against the system identification error, and show that a good controller for a real robot can be obtained by our method.
Keyword (in Japanese) (See Japanese page) 
(in English) reinforcement learning / system identification / acrobot / / / / /  
Reference Info. IEICE Tech. Rep., vol. 105, no. 659, NC2005-154, pp. 19-24, March 2006.
Paper # NC2005-154 
Date of Issue 2006-03-10 (NC) 
ISSN Print edition: ISSN 0913-5685
Download PDF

Conference Information
Committee NC  
Conference Date 2006-03-15 - 2006-03-17 
Place (in Japanese) (See Japanese page) 
Place (in English) Tamagawa University 
Topics (in Japanese) (See Japanese page) 
Topics (in English) General 
Paper Information
Registration To NC 
Conference Code 2006-03-NC 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Considering model error when applying an reinforcement learning method to control of a real robot 
Sub Title (in English)  
Keyword(1) reinforcement learning  
Keyword(2) system identification  
Keyword(3) acrobot  
Keyword(4)  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Yoichi Tokita  
1st Author's Affiliation Nara Institute of Science and Technology (NAIST)
2nd Author's Name Yutaka Nakamura  
2nd Author's Affiliation Nara Institute of Science and Technology (NAIST)
3rd Author's Name Junichiro Yoshimoto  
3rd Author's Affiliation Okinawa Institute of Science and Technology (OIST)
4th Author's Name Shin Ishii  
4th Author's Affiliation Nara Institute of Science and Technology (NAIST)
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2006-03-17 11:00:00 
Presentation Time 25 minutes 
Registration for NC 
Paper # NC2005-154 
Volume (vol) vol.105 
Number (no) no.659 
Page pp.19-24 
#Pages
Date of Issue 2006-03-10 (NC) 


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan