@inproceedings{weightedimportancesamplingforoffpolicy, title = {Weighted importance sampling for off-policy learning with linear function approximation}, author = {A. Rupam Mahmood and Hado P. Van Hasselt and Richard S. Sutton}, year = {2014}, booktitle = {NeurIPS 2014 12}, url = {http://papers.nips.cc/paper/5249-weighted-importance-sampling-for-off-policy-learning-with-linear-function-approximation}, }