@article{atemporaldifferenceapproachtopolicy, title = {A Temporal-Difference Approach to Policy Gradient Estimation}, author = {Samuele Tosatto and Andrew Patterson and Martha White and A. Rupam Mahmood}, year = {2022}, eprint = {2202.02396}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2202.02396v4}, }