Alberto Maria Metelli, Matteo Papini, Pierluca D'Oro, Marcello Restelli. Policy Optimization as Online Learning with Mediator Feedback. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021. pages 8958-8966, AAAI Press, 2021. [doi]
@inproceedings{MetelliPDR21,
title = {Policy Optimization as Online Learning with Mediator Feedback},
author = {Alberto Maria Metelli and Matteo Papini and Pierluca D'Oro and Marcello Restelli},
year = {2021},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/17083},
researchr = {https://researchr.org/publication/MetelliPDR21},
cites = {0},
citedby = {0},
pages = {8958-8966},
booktitle = {Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021},
publisher = {AAAI Press},
isbn = {978-1-57735-866-4},
}