@article{policyoptimizationasonlinelearningwith, title = {Policy Optimization as Online Learning with Mediator Feedback}, author = {Alberto Maria Metelli and Matteo Papini and Pierluca D'Oro and Marcello Restelli}, year = {2020}, eprint = {2012.08225}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2012.08225v1}, }