Yasin Abbasi-Yadkori, Peter L. Bartlett, Kush Bhatia, Nevena Lazic, Csaba Szepesvári, Gellért Weisz
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction
ICML, 2019.
@inproceedings{ICML-2019-X,
booktitle = "{Proceedings of the 36th International Conference on Machine Learning}",
editor = "Yasin Abbasi-Yadkori and Peter L. Bartlett and Kush Bhatia and Nevena Lazic and Csaba Szepesvári and Gellért Weisz",
ee = "http://proceedings.mlr.press/v97/lazic19a.html",
pages = "3692--3702",
publisher = "{PMLR}",
title = "{POLITEX: Regret Bounds for Policy Iteration using Expert Prediction}",
year = 2019,
}