@inproceedings{metelli2021policya,
  author = {Metelli, Alberto Maria and Papini, Matteo and D'Oro, Pierluca and Restelli, Marcello},
  title = {Policy Optimization as Online Learning with Mediator Feedback},
  booktitle = {{AAAI} Conference on Artificial Intelligence ({AAAI})},
  publisher = {{AAAI} Press},
  year = {2021},
  volume = {35},
  pages = {8958--8966},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/17083}
}