Anna Harutyunyan, Marc G. Bellemare, Tom Stepleton, Rémi Munos. Q(λ) with Off-Policy Corrections. In Ronald Ortner, Hans-Ulrich Simon, Sandra Zilles, editors, Algorithmic Learning Theory - 27th International Conference, ALT 2016, Bari, Italy, October 19-21, 2016, Proceedings. Volume 9925 of Lecture Notes in Computer Science, pages 305-320, 2016. [doi]
@inproceedings{HarutyunyanBSM16, title = {Q(λ) with Off-Policy Corrections}, author = {Anna Harutyunyan and Marc G. Bellemare and Tom Stepleton and Rémi Munos}, year = {2016}, doi = {10.1007/978-3-319-46379-7_21}, url = {http://dx.doi.org/10.1007/978-3-319-46379-7_21}, researchr = {https://researchr.org/publication/HarutyunyanBSM16}, cites = {0}, citedby = {0}, pages = {305-320}, booktitle = {Algorithmic Learning Theory - 27th International Conference, ALT 2016, Bari, Italy, October 19-21, 2016, Proceedings}, editor = {Ronald Ortner and Hans-Ulrich Simon and Sandra Zilles}, volume = {9925}, series = {Lecture Notes in Computer Science}, isbn = {978-3-319-46378-0}, }