Paper published in a book (Scientific congresses and symposiums)
Approximate reinforcement learning: an overview
Busoniu, Lucian; Babuska, Robert; De Schutter, Bart et al.
2011In Proceedings of the 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11)
Peer reviewed
 

Files


Full Text
adprl11_Busoniu_et_al.pdf
Publisher postprint (203.59 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
reinforcement learning; function approximation; value iteration; policy iteration; policy search
Abstract :
[en] Reinforcement learning (RL) allows agents to learn how to optimally interact with complex environments. Fueled by recent advances in approximation-based algorithms, RL has obtained impressive successes in robotics, artificial intelligence, control, operations research, etc. However, the scarcity of survey papers about approximate RL makes it difficult for newcomers to grasp this intricate field. With the present overview, we take a step toward alleviating this situation. We review methods for approximate RL, starting from their dynamic programming roots and organizing them into three major classes: approximate value iteration, policy iteration, and policy search. Each class is subdivided into representative categories, highlighting among others offline and online algorithms, policy gradient methods, and simulation-based techniques. We also compare the different categories of methods, and outline possible ways to enhance the reviewed algorithms.
Disciplines :
Computer science
Author, co-author :
Busoniu, Lucian
Babuska, Robert
De Schutter, Bart
Ernst, Damien  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
Approximate reinforcement learning: an overview
Publication date :
April 2011
Event name :
Proceedings of the 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11)
Event place :
Paris, France
Event date :
April 11-15, 2011
Audience :
International
Main work title :
Proceedings of the 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11)
Peer reviewed :
Peer reviewed
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Available on ORBi :
since 14 April 2011

Statistics


Number of views
196 (3 by ULiège)
Number of downloads
1050 (1 by ULiège)

Scopus citations®
 
47
Scopus citations®
without self-citations
47
OpenCitations
 
21

Bibliography


Similar publications



Contact ORBi