Mridul Agarwal, Qinbo Bai, Vaneet Aggarwal. Concave Utility Reinforcement Learning with Zero-Constraint Violations. Trans. Mach. Learn. Res., 2022, 2022. [doi]
@article{AgarwalBA22-0,
title = {Concave Utility Reinforcement Learning with Zero-Constraint Violations},
author = {Mridul Agarwal and Qinbo Bai and Vaneet Aggarwal},
year = {2022},
url = {https://openreview.net/forum?id=WXVkgkPXRk},
researchr = {https://researchr.org/publication/AgarwalBA22-0},
cites = {0},
citedby = {0},
journal = {Trans. Mach. Learn. Res.},
volume = {2022},
}