Yu-Heng Hung, Ping-Chun Hsieh, Xi Liu 0011, P. R. Kumar 0001. Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021. pages 7874-7882, AAAI Press, 2021. [doi]
@inproceedings{HungH0021,
title = {Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits},
author = {Yu-Heng Hung and Ping-Chun Hsieh and Xi Liu 0011 and P. R. Kumar 0001},
year = {2021},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/16961},
researchr = {https://researchr.org/publication/HungH0021},
cites = {0},
citedby = {0},
pages = {7874-7882},
booktitle = {Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021},
publisher = {AAAI Press},
isbn = {978-1-57735-866-4},
}