@article{proximalgradienttemporaldifference, title = {Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity}, author = {Bo Liu and Ian Gemp and Mohammad Ghavamzadeh and Ji Liu and Sridhar Mahadevan and Marek Petrik}, year = {2020}, eprint = {2006.03976}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2006.03976v1}, }