Research

See my researchgate profile here

Research interests

Reinforcement Learning, Machine Learning, AI Safety

Conference Papers

  • Matteo Papini, Alberto Maria Metelli, Lorenzo Lupo, Marcello Restelli; Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4989-4999, 2019. [bibtex][more]

  • Alberto Metelli, Matteo Papini, Francesco Faccio, Marcello Restelli; “Policy Optimization via Importance Sampling”; NeurIPS 2018 [bibtex][more]

  • Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta, Marcello Restelli; “Stochastic Variance-Reduced Policy Gradient”; Proceedings of the 35th International Conference on Machine Learning, PMLR 80:4026-4035, 2018. [bibtex][more]

  • Matteo Papini, Matteo Pirotta, Marcello Restelli; “Adaptive batch size for safe policy gradients”; Advances in Neural Information Processing Systems, pp. 3591-3600, 2017 [bibtex][more]

Workshop Papers

  • Matteo Papini, Andrea Battistello, Marcello Restelli; “Safely Exploring Policy Gradient”; 14th European Workshop on Reinforcement Learning, Lille, France, 2018 [more]

image-title-here