@article{qpropsampleefficientpolicygradientwith, title = {Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic}, author = {Shixiang Gu and Timothy Lillicrap and Zoubin Ghahramani and Richard E. Turner and Sergey Levine}, year = {2016}, eprint = {1611.02247}, archivePrefix = {arXiv}, url = {http://arxiv.org/abs/1611.02247v3}, }