Akshay Mete, Rahul Singh 0001, P. R. Kumar 0001. The Reward Biased Method: An Optimism based Approach for Reinforcement Learning. In 59th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2023, Monticello, IL, USA, September 26-29, 2023. pages 1-7, IEEE, 2023. [doi]
@inproceedings{MeteSK23,
title = {The Reward Biased Method: An Optimism based Approach for Reinforcement Learning},
author = {Akshay Mete and Rahul Singh 0001 and P. R. Kumar 0001},
year = {2023},
doi = {10.1109/Allerton58177.2023.10313396},
url = {https://doi.org/10.1109/Allerton58177.2023.10313396},
researchr = {https://researchr.org/publication/MeteSK23},
cites = {0},
citedby = {0},
pages = {1-7},
booktitle = {59th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2023, Monticello, IL, USA, September 26-29, 2023},
publisher = {IEEE},
isbn = {979-8-3503-2814-1},
}