Anthony DiGiovanni, Ambuj Tewari. Thompson sampling for Markov games with piecewise stationary opponent policies. In Cassio P. de Campos, Marloes H. Maathuis, Erik Quaeghebeur, editors, Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI 2021, Virtual Event, 27-30 July 2021. Volume 161 of Proceedings of Machine Learning Research, pages 738-748, AUAI Press, 2021. [doi]
@inproceedings{DiGiovanniT21,
title = {Thompson sampling for Markov games with piecewise stationary opponent policies},
author = {Anthony DiGiovanni and Ambuj Tewari},
year = {2021},
url = {https://proceedings.mlr.press/v161/digiovanni21a.html},
researchr = {https://researchr.org/publication/DiGiovanniT21},
cites = {0},
citedby = {0},
pages = {738-748},
booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI 2021, Virtual Event, 27-30 July 2021},
editor = {Cassio P. de Campos and Marloes H. Maathuis and Erik Quaeghebeur},
volume = {161},
series = {Proceedings of Machine Learning Research},
publisher = {AUAI Press},
}