Paulo Heredia, Shaoshuai Mou. Finite-Sample Analysis of Multi-Agent Policy Evaluation with Kernelized Gradient Temporal Difference. In 59th IEEE Conference on Decision and Control, CDC 2020, Jeju Island, South Korea, December 14-18, 2020. pages 5647-5652, IEEE, 2020. [doi]
@inproceedings{HerediaM20,
title = {Finite-Sample Analysis of Multi-Agent Policy Evaluation with Kernelized Gradient Temporal Difference},
author = {Paulo Heredia and Shaoshuai Mou},
year = {2020},
doi = {10.1109/CDC42340.2020.9303966},
url = {https://doi.org/10.1109/CDC42340.2020.9303966},
researchr = {https://researchr.org/publication/HerediaM20},
cites = {0},
citedby = {0},
pages = {5647-5652},
booktitle = {59th IEEE Conference on Decision and Control, CDC 2020, Jeju Island, South Korea, December 14-18, 2020},
publisher = {IEEE},
isbn = {978-1-7281-7447-1},
}