Max Simchowitz, Kevin G. Jamieson. Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alché-Buc, Edward A. Fox, Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada. pages 1151-1160, 2019. [doi]
@inproceedings{SimchowitzJ19,
title = {Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs},
author = {Max Simchowitz and Kevin G. Jamieson},
year = {2019},
url = {http://papers.nips.cc/paper/8399-non-asymptotic-gap-dependent-regret-bounds-for-tabular-mdps},
researchr = {https://researchr.org/publication/SimchowitzJ19},
cites = {0},
citedby = {0},
pages = {1151-1160},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada},
editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alché-Buc and Edward A. Fox and Roman Garnett},
}