loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Fifth International Conference on Hybrid Intelligent Systems (HIS'05)
Hierarchical Reinforcement Learning for Metrical Task Systems
Rio de Janeiro, Brazil
December 06-December 09
ISBN: 0-7695-2457-5
ASCII Text
x 
 
Manoel Junior Leandro de Lima, Jorge Dantas de Melo, Adriao Duarte Doria Neto, "Hierarchical Reinforcement Learning for Metrical Task Systems," Hybrid Intelligent Systems, International Conference on, pp. 251-258, Fifth International Conference on Hybrid Intelligent Systems (HIS'05), 2005.
 
 
BibTex
x
 
@article{ 10.1109/ICHIS.2005.55,
author = {Manoel Junior Leandro de Lima and Jorge Dantas de Melo and Adriao Duarte Doria Neto},
title = {Hierarchical Reinforcement Learning for Metrical Task Systems},
journal ={Hybrid Intelligent Systems, International Conference on},
volume = {0},
year = {2005},
isbn = {0-7695-2457-5},
pages = {251-258},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICHIS.2005.55},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Hybrid Intelligent Systems, International Conference on
TI - Hierarchical Reinforcement Learning for Metrical Task Systems
SN - 0-7695-2457-5
SP251
EP258
A1 - Manoel Junior Leandro de Lima,
A1 - Jorge Dantas de Melo,
A1 - Adriao Duarte Doria Neto,
PY - 2005
KW - null
VL - 0
JA - Hybrid Intelligent Systems, International Conference on
ER -
 
Manoel Junior Leandro de Lima, Universidade Federal do Rio Grande do Norte, Campus Universitario, Natal, Brazil
Jorge Dantas de Melo, Universidade Federal do Rio Grande do Norte, Campus Universitario, Natal, Brazil
Adriao Duarte Doria Neto, Universidade Federal do Rio Grande do Norte, Campus Universitario, Natal, Brazil
The use of reinforcement learning to implement Metrical Task Systems is limited to smaller scale problems due to the curse of dimensionality inherent in the method. This paper aims to present an algorithm based on decomposition techniques which allows us to apply this approach to realistic control problems. It analyzes aspects associated with the quality of the solution and its limitations, as well as discuss about the relevant theoretical topics of the approach presented.
Citation:
Manoel Junior Leandro de Lima, Jorge Dantas de Melo, Adriao Duarte Doria Neto, "Hierarchical Reinforcement Learning for Metrical Task Systems," his, pp.251-258, Fifth International Conference on Hybrid Intelligent Systems (HIS'05), 2005
Usage of this product signifies your acceptance of the Terms of Use.