@article{policyoptimizationwithstochasticmirror, title = {Policy Optimization with Stochastic Mirror Descent}, author = {Long Yang and Yu Zhang and Gang Zheng and Qian Zheng and Pengfei Li and Jianhang Huang and Jun Wen and Gang Pan}, year = {2019}, eprint = {1906.10462}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1906.10462v5}, }