Aymen Al Marjani, Alexandre Proutière. Adaptive Sampling for Best Policy Identification in Markov Decision Processes. In Marina Meila, Tong Zhang 0001, editors, Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. Volume 139 of Proceedings of Machine Learning Research, pages 7459-7468, PMLR, 2021. [doi]
@inproceedings{MarjaniP21,
title = {Adaptive Sampling for Best Policy Identification in Markov Decision Processes},
author = {Aymen Al Marjani and Alexandre Proutière},
year = {2021},
url = {http://proceedings.mlr.press/v139/marjani21a.html},
researchr = {https://researchr.org/publication/MarjaniP21},
cites = {0},
citedby = {0},
pages = {7459-7468},
booktitle = {Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event},
editor = {Marina Meila and Tong Zhang 0001},
volume = {139},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}