loading...
NEFRL: A New Neuro-Fuzzy System for Episodic Reinforcement Learning Tasks
Jeju Island, Korea October 11-October 13
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/FBIT.2007.1392007 Frontiers in the Convergence of ...
 This Article 
 
Buy PURCHASE ARTICLE: $19
PDF
HTML
IEEE Xplore Subscribers
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
ASCII Text
x 
 
Babak Behsaz, Reza Safabakhsh, "NEFRL: A New Neuro-Fuzzy System for Episodic Reinforcement Learning Tasks," Frontiers in the Convergence of Bioscience and Information Technologies, pp. 819-826, 2007 Frontiers in the Convergence of Bioscience and Information Technologies, 2007.
 
 
BibTex
x
 
@article{ 10.1109/FBIT.2007.139,
author = {Babak Behsaz and Reza Safabakhsh},
title = {NEFRL: A New Neuro-Fuzzy System for Episodic Reinforcement Learning Tasks},
journal ={Frontiers in the Convergence of Bioscience and Information Technologies},
volume = {0},
year = {2007},
isbn = {978-0-7695-2999-8},
pages = {819-826},
doi = {http://doi.ieeecomputersociety.org/10.1109/FBIT.2007.139},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Frontiers in the Convergence of Bioscience and Information Technologies
TI - NEFRL: A New Neuro-Fuzzy System for Episodic Reinforcement Learning Tasks
SN - 978-0-7695-2999-8
SP819
EP826
A1 - Babak Behsaz,
A1 - Reza Safabakhsh,
PY - 2007
VL - 0
JA - Frontiers in the Convergence of Bioscience and Information Technologies
ER -
 
In this paper, we propose a new neuro-fuzzy system for episodic reinforcement learning tasks, NEFRL. While NEFRL has all benefits of a neuro-fuzzy architecture, it has the additional advantage that it can learn with a numerical evaluation of performance and there is no need for training input-output pairs. Also, we show that the learning algorithm of this system converges with probability one to a local maximum of the average numerical performance signal. Our experimental results for the Pole-Balancing Task show the power of this system even without any prior domain knowledge.
Citation:
Babak Behsaz, Reza Safabakhsh, "NEFRL: A New Neuro-Fuzzy System for Episodic Reinforcement Learning Tasks," fbit, pp.819-826, 2007 Frontiers in the Convergence of Bioscience and Information Technologies, 2007
Usage of this product signifies your acceptance of the Terms of Use.