Gi-Soo Kim, Myunghee Cho Paik. Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model. In Kamalika Chaudhuri, Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA. Volume 97 of Proceedings of Machine Learning Research, pages 3389-3397, PMLR, 2019. [doi]
@inproceedings{KimP19-3,
title = {Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model},
author = {Gi-Soo Kim and Myunghee Cho Paik},
year = {2019},
url = {http://proceedings.mlr.press/v97/kim19d.html},
researchr = {https://researchr.org/publication/KimP19-3},
cites = {0},
citedby = {0},
pages = {3389-3397},
booktitle = {Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA},
editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov},
volume = {97},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}