@InCollection{Supelec725,
author = {Bruno Scherrer and Matthieu Geist},
title = {Recursive Least-Squares Learning with Eligibility Traces},
year = {2011},
booktitle = {Proceedings of the European Workshop on Machine Learning (EWRL 2011)},
publisher = {Springer Verlag - Heidelberg Berlin},
pages = {12 pages},
month = {september},
series = {Lecture Notes in Computer Science (LNCS)},
address = {Athens (Greece)},
url = {http://www.metz.supelec.fr//metz/personnel/geist_mat/pdfs/supelec725.pdf},
abstract = {In the framework of Markov Decision Processes, we consider 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 describe a systematic approach for adapting \emph{on-policy} learning least squares algorithms of the literature (LSTD, LSPE, FPKF and GPTD/KTD) to \emph{off-policy} learning \emph{with eligibility traces}. This leads to two known algorithms, LSTD($\lambda$)/LSPE($\lambda$) and suggests new extensions of FPKF and GPTD/KTD. We describe their recursive implementation, discuss their convergence properties, and illustrate their behavior experimentally. Overall, our study suggests that the state-of-art LSTD($\lambda$) remains the best least-squares algorithm.}
}