@inproceedings{NEURIPS2021_1bf2efbb, author = {Chatterji, Niladri and Pacchiano, Aldo and Bartlett, Peter and Jordan, Michael}, 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 = {3401--3412}, publisher = {Curran Associates, Inc.}, title = {On the Theory of Reinforcement Learning with Once-per-Episode Feedback}, url = {https://proceedings.neurips.cc/paper_files/paper/2021/file/1bf2efbbe0c49b9f567c2e40f645279a-Paper.pdf}, volume = {34}, year = {2021} }