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
234 (2 by ULiège)
Number of downloads
632 (3 by ULiège)

Bibliography


Similar publications



Sorry the service is unavailable at the moment. Please try again later.
Contact ORBi