Pierre Ménard, Omar Darwiche Domingues, Xuedong Shang, Michal Valko. UCB Momentum Q-learning: Correcting the bias without forgetting. 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 7609-7618, PMLR, 2021. [doi]
@inproceedings{MenardDSV21,
title = {UCB Momentum Q-learning: Correcting the bias without forgetting},
author = {Pierre Ménard and Omar Darwiche Domingues and Xuedong Shang and Michal Valko},
year = {2021},
url = {http://proceedings.mlr.press/v139/menard21b.html},
researchr = {https://researchr.org/publication/MenardDSV21},
cites = {0},
citedby = {0},
pages = {7609-7618},
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},
}