@inproceedings{NEURIPS2021_096ffc29, author = {Zhang, Sheng and Zhang, Zhe and Maguluri, Siva Theja}, 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 = {1230--1242}, publisher = {Curran Associates, Inc.}, title = {Finite Sample Analysis of Average-Reward TD Learning and Q-Learning}, url = {https://proceedings.neurips.cc/paper_files/paper/2021/file/096ffc299200f51751b08da6d865ae95-Paper.pdf}, volume = {34}, year = {2021} }