Lucian Busoniu, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos, Robert Babuska, Bart De Schutter. Least-Squares Methods for Policy Iteration. In Marco Wiering, Martijn Van Otterlo, editors, Reinforcement Learning. Volume 12 of Adaptation, Learning, and Optimization, pages 75-109, Springer, 2012. [doi]
@incollection{BusoniuLGMBS12, title = {Least-Squares Methods for Policy Iteration}, author = {Lucian Busoniu and Alessandro Lazaric and Mohammad Ghavamzadeh and Rémi Munos and Robert Babuska and Bart De Schutter}, year = {2012}, doi = {10.1007/978-3-642-27645-3_3}, url = {https://doi.org/10.1007/978-3-642-27645-3_3}, researchr = {https://researchr.org/publication/BusoniuLGMBS12}, cites = {0}, citedby = {0}, pages = {75-109}, booktitle = {Reinforcement Learning}, editor = {Marco Wiering and Martijn Van Otterlo}, volume = {12}, series = {Adaptation, Learning, and Optimization}, publisher = {Springer}, isbn = {978-3-642-27644-6}, }