Off-policy Learning with Eligibility Traces: A Survey

Matthieu Geist 1, 2 Bruno Scherrer 3
3 MAIA - Autonomous intelligent machine
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : In the framework of Markov Decision Processes, we consider linear \emph{off-policy} learning, that is the problem of learning a linear approximation of the value function of some fixed policy from one trajectory possibly generated by some other policy. We briefly review \emph{on-policy} learning algorithms of the literature (gradient-based and least-squares-based), adopting a unified algorithmic view. Then, we highlight a systematic approach for adapting them to \emph{off-policy} learning \emph{with eligibility traces}. This leads to some known algorithms -- off-policy LSTD($\lambda$), LSPE($\lambda$), TD($\lambda$), TDC/GQ($\lambda$) -- and suggests new extensions -- off-policy FPKF($\lambda$), BRM($\lambda$), gBRM($\lambda$), GTD2($\lambda$). We describe a comprehensive algorithmic derivation of all algorithms in a recursive and memory-efficent form, discuss their known convergence properties and illustrate their relative empirical behavior on Garnet problems. Our experiments suggest that the most standard algorithms on and off-policy LSTD($\lambda$)/LSPE($\lambda$) -- and TD($\lambda$) if the feature space dimension is too large for a least-squares approach -- perform the best.
Type de document :
Article dans une revue
Journal of Machine Learning Research, Journal of Machine Learning Research, 2014, 15 (1), pp.289-333
Liste complète des métadonnées
Contributeur : Bruno Scherrer <>
Soumis le : vendredi 20 décembre 2013 - 10:35:19
Dernière modification le : jeudi 22 février 2018 - 01:18:30
Document(s) archivé(s) le : vendredi 21 mars 2014 - 10:15:29


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00921275, version 1


Matthieu Geist, Bruno Scherrer. Off-policy Learning with Eligibility Traces: A Survey. Journal of Machine Learning Research, Journal of Machine Learning Research, 2014, 15 (1), pp.289-333. 〈hal-00921275〉



Consultations de la notice


Téléchargements de fichiers