Sébastien Gros, Mario Zanon. Bias Correction in Reinforcement Learning via the Deterministic Policy Gradient Method for MPC-Based Policies. In 2021 American Control Conference, ACC 2021, New Orleans, LA, USA, May 25-28, 2021. pages 2543-2548, IEEE, 2021. [doi]
@inproceedings{GrosZ21a,
title = {Bias Correction in Reinforcement Learning via the Deterministic Policy Gradient Method for MPC-Based Policies},
author = {Sébastien Gros and Mario Zanon},
year = {2021},
doi = {10.23919/ACC50511.2021.9483016},
url = {https://doi.org/10.23919/ACC50511.2021.9483016},
researchr = {https://researchr.org/publication/GrosZ21a},
cites = {0},
citedby = {0},
pages = {2543-2548},
booktitle = {2021 American Control Conference, ACC 2021, New Orleans, LA, USA, May 25-28, 2021},
publisher = {IEEE},
isbn = {978-1-6654-4197-1},
}