Paper published in a book (Scientific congresses and symposiums)
An Optimistic Posterior Sampling Strategy for Bayesian Reinforcement Learning
Fonteneau, Raphaël; Korda, Nathan; Munos, Rémi
2013In NIPS 2013 Workshop on Bayesian Optimization (BayesOpt2013)
Peer reviewed
 

Files


Full Text
OPS_BRL.pdf
Author postprint (359.44 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Reinforcement Learning; Bayesian Optimization; Markov Decision Processes
Abstract :
[en] We consider the problem of decision making in the context of unknown Markov decision processes with finite state and action spaces. In a Bayesian reinforcement learning framework, we propose an optimistic posterior sampling strategy based on the maximization of state-action value functions of MDPs sampled from the posterior. First experiments are promising.
Disciplines :
Computer science
Author, co-author :
Fonteneau, Raphaël ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Korda, Nathan;  University of Oxford, England
Munos, Rémi;  Inria Lille - Nord Europe
Language :
English
Title :
An Optimistic Posterior Sampling Strategy for Bayesian Reinforcement Learning
Publication date :
2013
Event name :
NIPS 2013 Workshop on Bayesian Optimization (BayesOpt2013)
Event date :
10 décembre 2013
Main work title :
NIPS 2013 Workshop on Bayesian Optimization (BayesOpt2013)
Peer reviewed :
Peer reviewed
Available on ORBi :
since 21 January 2014

Statistics


Number of views
216 (2 by ULiège)
Number of downloads
590 (2 by ULiège)

Bibliography


Similar publications



Contact ORBi