@article{softmaxpolicygradientmethodscantake, title = {Softmax Policy Gradient Methods Can Take Exponential Time to Converge}, author = {Gen Li and Yuting Wei and Yuejie Chi and Yuxin Chen}, year = {2021}, eprint = {2102.11270}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2102.11270v3}, }