@inproceedings{variancereducedoffpolicytdclearningnon, title = {Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis}, author = {Shaocong Ma and Yi Zhou and Shaofeng Zou}, year = {2020}, booktitle = {NeurIPS 2020 12}, eprint = {2010.13272}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2010.13272v4}, }