Paper published in a book (Scientific congresses and symposiums)
Relaxation schemes for min max generalization in deterministic batch mode reinforcement learning
Fonteneau, Raphaël; Ernst, Damien; Boigelot, Bernard et al.
2011In 4th International NIPS Workshop on Optimization for Machine Learning (OPT 2011)
Peer reviewed
 

Files


Full Text
nips2011.pdf
Author postprint (193.68 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Batch mode reinforcement learning; Min max generalization; Non-convex optimization
Abstract :
[en] We study the min max optimization problem introduced in [Fonteneau, 2011] for computing policies for batch mode reinforcement learning in a deterministic setting. This problem is NP-hard. We focus on the two-stage case for which we provide two relaxation schemes. The first relaxation scheme works by dropping some constraints in order to obtain a problem that is solvable in polynomial time. The second relaxation scheme, based on a Lagrangian relaxation where all constraints are dualized, leads to a conic quadratic programming problem. Both relaxation schemes are shown to provide better results than those given in [Fonteneau, 2011].
Disciplines :
Computer science
Author, co-author :
Fonteneau, Raphaël ;  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) > Smart grids
Boigelot, Bernard  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Informatique
Louveaux, Quentin ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Système et modélisation : Optimisation discrète
Language :
English
Title :
Relaxation schemes for min max generalization in deterministic batch mode reinforcement learning
Publication date :
December 2011
Event name :
4th International NIPS Workshop on Optimization for Machine Learning (OPT 2011)
Event place :
Sierra Nevada, Spain
Event date :
December 16th, 2011
Audience :
International
Main work title :
4th International NIPS Workshop on Optimization for Machine Learning (OPT 2011)
Peer reviewed :
Peer reviewed
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Available on ORBi :
since 18 November 2011

Statistics


Number of views
126 (12 by ULiège)
Number of downloads
158 (6 by ULiège)

Bibliography


Similar publications



Contact ORBi