IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
... (for ESS/CS/ES/ISS)
Tech. Rep. Archives
... (for ES/CS)
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2011-11-09 15:45
Active Value Function Estimation Based On Transition Probability Estimation
Masahiro Kohjima (Tokyo Tech)
Abstract (in Japanese) (See Japanese page) 
(in English) It is considered to be a great importance in reinforcement learning to estimate value function precisely. In this study, the author proposes active learning algorithm for model based value function estimation, which computes value function using estimated transition probability. Its data sampling scheme is based on optimal ratio of the number of data to minimize asymptotic squared error of value function.
Experimental results show the effectiveness of proposed algorithm.
Keyword (in Japanese) (See Japanese page) 
(in English) reinforcement learning / markov decision processes / transition probability estimation / model based algorithm / active learning / asymptotic theory / /  
Reference Info. IEICE Tech. Rep., vol. 111, no. 275, IBISML2011-51, pp. 61-66, Nov. 2011.
Paper # IBISML2011-51 
Date of Issue 2011-11-02 (IBISML) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380

Conference Information
Committee IBISML  
Conference Date 2011-11-09 - 2011-11-11 
Place (in Japanese) (See Japanese page) 
Place (in English) Nara Womens Univ. 
Topics (in Japanese) (See Japanese page) 
Topics (in English) The 14th IBIS workshop 
Paper Information
Registration To IBISML 
Conference Code 2011-11-IBISML 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Active Value Function Estimation Based On Transition Probability Estimation 
Sub Title (in English)  
Keyword(1) reinforcement learning  
Keyword(2) markov decision processes  
Keyword(3) transition probability estimation  
Keyword(4) model based algorithm  
Keyword(5) active learning  
Keyword(6) asymptotic theory  
Keyword(7)  
Keyword(8)  
1st Author's Name Masahiro Kohjima  
1st Author's Affiliation Tokyo Institute Of Technology (Tokyo Tech)
2nd Author's Name  
2nd Author's Affiliation ()
3rd Author's Name  
3rd Author's Affiliation ()
4th Author's Name  
4th Author's Affiliation ()
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
Date Time 2011-11-09 15:45:00 
Presentation Time 180 
Registration for IBISML 
Paper # IEICE-IBISML2011-51 
Volume (vol) IEICE-111 
Number (no) no.275 
Page pp.61-66 
#Pages IEICE-6 
Date of Issue IEICE-IBISML-2011-11-02 


[Return to Top Page]

[Return to IEICE Web Page]


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