@article{regretanalysisofpolicygradientalgorithm, title = {Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes}, author = {Qinbo Bai and Washim Uddin Mondal and Vaneet Aggarwal}, year = {2023}, eprint = {2309.01922}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2309.01922v3}, }