@article{variancereducedpolicygradientapproaches, title = {Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs}, author = {Swetha Ganesh and Washim Uddin Mondal and Vaneet Aggarwal}, year = {2024}, eprint = {2404.02108}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.02108v2}, }