@article{adaptivetrustregionpolicyoptimization, title = {Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs}, author = {Lior Shani and Yonathan Efroni and Shie Mannor}, year = {2019}, eprint = {1909.02769}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1909.02769v2}, }