Paper published in a book (Scientific congresses and symposiums)
Reinforcement learning with raw image pixels as input state
Ernst, Damien; Marée, Raphaël; Wehenkel, Louis
2006In Advances in machine vision, image processing & pattern analysis (Lecture notes in computer science, Vol. 4153)
Peer reviewed
 

Files


Full Text
ernst-iwicpas-2006.pdf
Author postprint (186.09 kB)
Download
Annexes
ernst-iwicpas-2006-slides.pdf
Publisher postprint (203.92 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Reinforcement Learning; image; fitted Q iteration
Abstract :
[en] We report in this paper some positive simulation results obtained when image pixels are directly used as input state of a reinforcement learning algorithm. The reinforcement learning algorithm chosen to carry out the simulation is a batch-mode algorithm known as fitted Q iteration.
Disciplines :
Computer science
Author, co-author :
Ernst, Damien  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Marée, Raphaël  ;  Université de Liège - ULiège > Systèmes et modélisation
Wehenkel, Louis  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
Reinforcement learning with raw image pixels as input state
Publication date :
2006
Event name :
International Workshop on Intelligent Computing in Pattern Analysis/Synthesis (IWICPAS)
Event place :
Xi'an, China
Event date :
August 26-27, 2006
Audience :
International
Main work title :
Advances in machine vision, image processing & pattern analysis (Lecture notes in computer science, Vol. 4153)
Publisher :
Springer-Verlag Berlin, Berlin, Germany
ISBN/EAN :
978-3-540-37597-5
Peer reviewed :
Peer reviewed
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Available on ORBi :
since 25 November 2008

Statistics


Number of views
137 (13 by ULiège)
Number of downloads
539 (3 by ULiège)

Scopus citations®
 
9
Scopus citations®
without self-citations
6

Bibliography


Similar publications



Contact ORBi