Mohammad Sadegh Talebi, Anders Jonsson, Odalric Maillard. Improved Exploration in Factored Average-Reward MDPs. In Arindam Banerjee 0001, Kenji Fukumizu, editors, The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, April 13-15, 2021, Virtual Event. Volume 130 of Proceedings of Machine Learning Research, pages 3988-3996, PMLR, 2021. [doi]
@inproceedings{TalebiJM21,
title = {Improved Exploration in Factored Average-Reward MDPs},
author = {Mohammad Sadegh Talebi and Anders Jonsson and Odalric Maillard},
year = {2021},
url = {http://proceedings.mlr.press/v130/sadegh-talebi21a.html},
researchr = {https://researchr.org/publication/TalebiJM21},
cites = {0},
citedby = {0},
pages = {3988-3996},
booktitle = {The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, April 13-15, 2021, Virtual Event},
editor = {Arindam Banerjee 0001 and Kenji Fukumizu},
volume = {130},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}