@article{multistepoffpolicylearningwithout, title = {Multi-step Off-policy Learning Without Importance Sampling Ratios}, author = {Ashique Rupam Mahmood and Huizhen Yu and Richard S. Sutton}, year = {2017}, eprint = {1702.03006}, archivePrefix = {arXiv}, url = {http://arxiv.org/abs/1702.03006v1}, }