Paper published in a book (Scientific congresses and symposiums)
Optimal sample selection for batch-mode reinforcement learning
Rachelson, Emmanuel; Schnitzler, François; Wehenkel, Louis et al.
2011In Proceedings of the 3rd International Conference on Agents and Artificial Intelligence (ICAART 2011)
Peer reviewed
 

Files


Full Text
icaart-2011.pdf
Publisher postprint (794.26 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
stochastic optimal control; sample control; reinforcement learning
Abstract :
[en] We introduce the Optimal Sample Selection (OSS) meta-algorithm for solving discrete-time Optimal Control problems. This meta-algorithm maps the problem of finding a near-optimal closed-loop policy to the identification of a small set of one-step system transitions, leading to high-quality policies when used as input of a batch-mode Reinforcement Learning (RL) algorithm. We detail a particular instance of this OSS metaalgorithm that uses tree-based Fitted Q-Iteration as a batch-mode RL algorithm and Cross Entropy search as a method for navigating efficiently in the space of sample sets. The results show that this particular instance of OSS algorithms is able to identify rapidly small sample sets leading to high-quality policies
Disciplines :
Computer science
Author, co-author :
Rachelson, Emmanuel 
Schnitzler, François ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Wehenkel, Louis  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Ernst, Damien  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
Optimal sample selection for batch-mode reinforcement learning
Publication date :
2011
Event name :
3rd International Conference on Agents and Artificial Intelligence (ICAART 2011)
Event place :
Rome, Italy
Event date :
28-30 January 2011
Audience :
International
Main work title :
Proceedings of the 3rd International Conference on Agents and Artificial Intelligence (ICAART 2011)
Peer reviewed :
Peer reviewed
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Available on ORBi :
since 03 February 2011

Statistics


Number of views
203 (15 by ULiège)
Number of downloads
308 (4 by ULiège)

Scopus citations®
 
8
Scopus citations®
without self-citations
6

Bibliography


Similar publications



Contact ORBi