@incollection{
BusLaz:12-009,
author={L. Bu{\c{s}}oniu and A. Lazaric and M. Ghavamzadeh and R. Munos and R.
Babu{\v{s}}ka and B. {D}e Schutter},
title={Least-squares methods for policy iteration},
booktitle={Reinforcement Learning: State-Of-The-Art},
series={Adaptation, Learning, and Optimization},
volume={12},
editor={M. Wiering and M. van Otterlo},
publisher={Springer},
address={Heidelberg, Germany},
pages={75--109},
year={2012},
doi={
10.1007/978-3-642-27645-3_3}
}