Ian Osband, Benjamin Van Roy
Why is Posterior Sampling Better than Optimism for Reinforcement Learning?
ICML, 2017.
@inproceedings{ICML-2017-OsbandR,
author = "Ian Osband and Benjamin Van Roy",
booktitle = "{Proceedings of the 34th International Conference on Machine Learning}",
ee = "http://proceedings.mlr.press/v70/osband17a.html",
pages = "2701--2710",
publisher = "{PMLR}",
title = "{Why is Posterior Sampling Better than Optimism for Reinforcement Learning?}",
year = 2017,
}