Dohyeong Kim, Songhwai Oh. Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value At Risk. IEEE Robotics and Automation Letters, 7(3):7644-7651, 2022. [doi]
@article{KimO22a,
title = {Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value At Risk},
author = {Dohyeong Kim and Songhwai Oh},
year = {2022},
doi = {10.1109/LRA.2022.3184793},
url = {https://doi.org/10.1109/LRA.2022.3184793},
researchr = {https://researchr.org/publication/KimO22a},
cites = {0},
citedby = {0},
journal = {IEEE Robotics and Automation Letters},
volume = {7},
number = {3},
pages = {7644-7651},
}