METELLI, Alberto Maria; PAPINI, Matteo; D’ORO, Pierluca; RESTELLI, Marcello. Policy Optimization as Online Learning with Mediator Feedback. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 35, n. 10, p. 8958–8966, 2021. DOI: 10.1609/aaai.v35i10.17083. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/17083. Acesso em: 26 may. 2026.