Matteo Papini is an Assistant Professor (RTD-A) at Politecnico di Milano, Milan, Italy, in the Artificial Intelligence and Robotics Lab. His research is directed towards the development of intelligent systems, with a focus on the problem of sequential decision making under uncertainty, using the theory and algorithmic solutions of reinforcement learning. In 2021 he earned a PhD in Information Technology (cum laude) from Politecnico di Milano, Milan, Italy, under the supervision of Marcello Restelli, with a dissertation on safe policy optimization. In 2020 he worked as a student research intern at Facebook AI Research (now Meta). From 2021 to 2023 he was a postdoctoral researcher in the Artificial Intelligence and Machine Learning Research Group of Universitat Pompeu Fabra (UPF), Barcelona, Spain, in Gergely Neu’s team. He has authored more than 20 peer-reviewed conference papers, including publications at top artificial intelligence and and machine learning conferences such as NeurIPS (7 papers), ICML (5), COLT (2), AAAI (2) and IJCAI (2). Of these, one was awarded an oral presentation at NeurIPS 2018, which was only granted to the top 3% of the accepted papers. Moreover, he has published peer-reviewed manuscripts at renowned peer-reviewed machine learning journals: JMLR (1) and Springer’s Machine Learning (2). He is a member of ELLIS (European Laboratory for Learning and Intelligent Systems) since 2022. He has worked as a teaching assistant for several classes at Politecnico di Milano and for two international reinforcement learning summer schools. He has served as area chair for NeurIPS 2024 as is an action editor of TMLR since 2024. He served as a reviewer in the program committee of several conferences (NeurIPS, ICML, COLT, AAAI...) since 2019. In 2023, with Vincent Adam (UPF), he organized RLSS 2023 (Reinforcement Learning Summer School) in Barcelona. With Giulia Clerici (ELLIS Unit Milan) he is local chair of ALT 2025 (International Conference on Algorithmic Learning Theory) to be held in Milan.