Matteo Papini

Matteo Papini is an Assistant Professor at Politecnico di Milano, affiliated with the Department of Electronics, Information, and Bioengineering. He is a member of the Artificial Intelligence and Robotics Lab and an active researcher in reinforcement learning. His work focuses on sequential decision-making under uncertainty, policy optimization, and safe exploration.

• Education: PhD in Information Technology (cum laude, 2021) from Politecnico di Milano; M.Sc. and B.Sc. in Computer Engineering from the same institution.

Research Interests:

• Reinforcement Learning
• Policy Gradient Methods
• Contextual Bandits
• Safe and Efficient Exploration

Key Awards: NeurIPS 2018 Oral Presentation, Juan de la Cierva-Formación Grant, and multiple travel awards. He has authored over 20 peer-reviewed papers in top conferences like NeurIPS, ICML, and COLT.

Teaching: Currently teaching Algorithms and Advanced Deep Learning. Served as a Teaching Assistant for multiple AI and machine learning courses.

Service: Local Co-chair of ALT 2025, Area Chair for NeurIPS and ICML, and Action Editor for TMLR.

Labs/Teams: Member of the Artificial Intelligence and Robotics Lab at Politecnico di Milano and part of the ELLIS network.