Akshay Mete, Rahul Singh, Xi Liu, P. R. Kumar 0001. Reward Biased Maximum Likelihood Estimation for Reinforcement Learning. In Ali Jadbabaie, John Lygeros, George J. Pappas, Pablo A. Parrilo, Benjamin Recht, Claire J. Tomlin, Melanie N. Zeilinger, editors, Proceedings of the 3rd Annual Conference on Learning for Dynamics and Control, L4DC 2021, 7-8 June 2021, Virtual Event, Switzerland. Volume 144 of Proceedings of Machine Learning Research, pages 815-827, PMLR, 2021. [doi]
@inproceedings{MeteSL021,
title = {Reward Biased Maximum Likelihood Estimation for Reinforcement Learning},
author = {Akshay Mete and Rahul Singh and Xi Liu and P. R. Kumar 0001},
year = {2021},
url = {http://proceedings.mlr.press/v144/mete21a.html},
researchr = {https://researchr.org/publication/MeteSL021},
cites = {0},
citedby = {0},
pages = {815-827},
booktitle = {Proceedings of the 3rd Annual Conference on Learning for Dynamics and Control, L4DC 2021, 7-8 June 2021, Virtual Event, Switzerland},
editor = {Ali Jadbabaie and John Lygeros and George J. Pappas and Pablo A. Parrilo and Benjamin Recht and Claire J. Tomlin and Melanie N. Zeilinger},
volume = {144},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}