@inproceedings{NEURIPS2021_8ec2ba5e, author = {Liu, Tao and Zhou, Ruida and Kalathil, Dileep and Kumar, Panganamala and Tian, Chao}, 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 = {17183--17193}, publisher = {Curran Associates, Inc.}, title = {Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs}, url = {https://proceedings.neurips.cc/paper_files/paper/2021/file/8ec2ba5e96ec1c050bc631abda80f269-Paper.pdf}, volume = {34}, year = {2021} }