@inproceedings{NEURIPS2021_c1b8bf9e, author = {Luo, Haipeng and Wei, Chen-Yu and Lee, Chung-Wei}, booktitle = {Advances in Neural Information Processing Systems}, editor = {M. Ranzato and A. Beygelzimer and Y. Dauphin and P.S. Liang and J. Wortman Vaughan}, pages = {22931--22942}, publisher = {Curran Associates, Inc.}, title = {Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses}, url = {https://proceedings.neurips.cc/paper_files/paper/2021/file/c1b8bf9e071c0dabb899e7a27f353762-Paper.pdf}, volume = {34}, year = {2021} }