Our Team
Marcello Restelli
Associate Professor
Marcello Restelli is Associate Professor of Computer Engineering at PoliMI. His main research interests are the design and analysis of reinforcement learning algorithms, with particular attention to their application to real-world problems. On these topics, he published over 150 papers and served as PC/SPC member and Area Chair of the top ML/AI conferences (NeurIPS, ICML, ICLR, AAAI, IJCAI, AISTATS). He was awarded the NeurIPS Reviewer Award in 2013 and in 2019, and the Outstanding Paper Award at ICML 2022. He is an Editorial Board Reviewer of JMLR. He is a board member of the National Phd Programme “Data Science and Computation”. He is also research manager of the Italian Observatory in Artificial Intelligence and he has been PI and co-PI of more than 25 research projects on machine learning and reinforcement learning funded by private or public institutions.
Francesco Trovò
Assistant Professor
Francesco Trovò is an assistant professor at the Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB) in the Artificial Intelligence and Robotics Laboratory (AIRLab) at Politecnico di Milano (PoliMi). He obtained the Ph.D. in Information Technology in March 2015 at Politecnico di Milano. He is co-founder of ML Cube S.r.l., an innovative start-up, providing cutting-edge solutions for machine learning systems and life-cycle-management optimization. His main research interests revolve around artificial intelligence and machine learning for sequential decision-making, in particular multi-armed bandit (MAB) for nonstationary settings. He is currently working on the application of such techniques in microeconomic environments. He is also interested in the application of automatic decision-making techniques to provide suggestions in the health field. He participates in research projects about machine learning for real-estate, e-commerce, advertising, and industry 4.0.
Alberto Maria Metelli
Assistant Professor
Alberto Maria Metelli is an Assistant Professor with the Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB) in the Artificial Intelligence and Robotics Laboratory (AIRLab) at Politecnico di Milano (PoliMi). He obtained the Ph.D. in Information Technology (cum Laude) in March 2021 at Politecnico di Milano defending a thesis about environment configuration in reinforcement learning, awarded the “Premio NeoDottori di Ricerca Marco Cadoli 2021” as the best Italian Ph.D. thesis in Artificial Intelligence (from AIxIA) and recently published in the book series “Frontiers in Artificial Intelligence and Applications” (FAIA). He is co-founder of ML Cube S.r.l., an innovative start-up, providing cutting-edge solutions for machine learning systems and life-cycle-management optimization. His main research interests revolve around artificial intelligence and machine learning for sequential decision-making, in particular reinforcement learning (RL). He is currently working on theoretical and algorithmic aspects of RL in configurable environments, off-policy RL, inverse RL, automated RL, and RL in structured environments. He participates in research projects about reinforcement learning for autonomous driving, for defense, and about machine learning for climate science. He is also interested in algorithms, optimization, statistics, probability, and recommendation systems.postdoctoral
Mirco Mutti
Postdoctoral researcher
Mirco Mutti is a Ph.D. candidate at Università di Bologna and Politecnico di Milano, where he works under the supervision of Marcello Restelli. His research focuses on theory and methods for pre-training reinforcement learning agents through unsupervised interactions.
- Email:mirco.mutti@polimi.it
Riccardo Poiani
PhD Student
Riccardo Poiani is a Ph.D. student in Information Technology at the Department of Electronics, Information and Bioengineering (DEIB) at Politecnico di Milano. He obtained an M.Sc. in Computer Science and Engineering at Politecnico di Milano while following the Honours Programme "Scientific Research in Information Technology" in the Artificial Intelligence and Robotics Laboratory (AIRLab) advised by Professor M. Restelli. His research focuses on Non-Stationary Reinforcement Learning, Multi-Fidelity Reinforcement Learning, and Transfer Learning in Reinforcement Learning.
Riccardo Zamboni
PhD Student
Riccardo Zamboni is a PhD student in Information Technology at the Department of Electonics, Information and Bioengineering (DEIB) of Politecnico di Milano, under the supervision of Professor M. Restelli. He obtained a M.Sc. in Automation and Control Engineering at Politecnico di Milano, advised by Professor M. Hayashibe (Tohoku University, Japan) and Professor F. D’Ercole (Politecnico di Milano, Italy). His research focuses on Distributed & Multi-Agent reinforcement learning, while studying its applications in the Industry 4.0 field throught a collaboration with Siemens (AT).
Vincenzo De Paola
PhD Student
Vincenzo De Paola is a Ph.D. student in Information Technology at the Department of Electronics, Information and Bioengineering (DEIB) at Politecnico di Milano. He obtained an M.Sc. in Automation and Control Engineering at Politecnico di Milano with a Master Thesis on an Industry4.0 Project of a Mechanical Servo Press. Actually working as Siemens Employee his research focuses on the application of AI in the Manufacturing Industries on theme of Safe and Deterministic Reinforcement Learning .
Amarildo Likmeta
PhD Student
Amarildo Likmeta is a Ph.D. candidate at Università di Bologna and Politecnico di Milano, working under the supervision of Marcello Restelli on the intersection of Reinforcement Learning and Online Planning, with a focus on exploration and real-life applications.
Alessio Russo
PhD Student
Alessio Russo is a Ph.D. Fellow at Politecnico di Milano supervised by Prof. Marcello Restelli. He obtained a Master’s degree in Computer Science and Engineering defending the thesis “Towards Making Importance Sampling Practical” advised by Prof. M. Restelli. He is a member of the AI research group of the spin-off MLCube. His main research areas include Non-Stationary environments with a focus on the identification of changes in streaming data, and Transfer Learning in Reinforcement Learning.
- Email:alessio.russo@polimi.it
Paolo Bonetti
PhD Student
Paolo Bonetti is a Ph.D. candidate in Information Technology at the Department of Electronics, Information and Bioengineering (DEIB) of Politecnico di Milano since November 2021. In 2020 he obtained the master’s degree in Mathematical Engineering in the Applied Statistics track. From 2020 to 2021 he worked as data consultant. His research focuses on Machine Learning for spatio-temporal data, with a particular interest on feature selection, dimensionality reduction and causal discovery.
- Email:paolo.bonetti@polimi.it
Davide Salaorni
PhD Student
Davide Salaorni is a Ph.D. student in Information Technology at the Department of Electronics, Information, and Bioengineering (DEIB) of Politecnico di Milano. He achieved his M. Sc. in Computer Science and Engineering defending the thesis “Optimal real-time control of water distribution systems undergoing cyber-attacks: a reinforcement learning approach" in collaboration with Singapore University of Technology and Design (SUTD). His research aims to integrate Reinforcement Learning techniques within Smart Grid environments and Battery Energy Storage Systems.
Marco Mussi
PhD Student
Alberto Maria Metelli is an Assistant Professor with the Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB) in the Artificial Intelligence and Robotics Laboratory (AIRLab) at Politecnico di Milano (PoliMi). He obtained the Ph.D. in Information Technology (cum Laude) in March 2021 at Politecnico di Milano defending a thesis about environment configuration in reinforcement learning, awarded the “Premio NeoDottori di Ricerca Marco Cadoli 2021” as the best Italian Ph.D. thesis in Artificial Intelligence (from AIxIA) and recently published in the book series “Frontiers in Artificial Intelligence and Applications” (FAIA). He is co-founder of ML Cube S.r.l., an innovative start-up, providing cutting-edge solutions for machine learning systems and life-cycle-management optimization. His main research interests revolve around artificial intelligence and machine learning for sequential decision-making, in particular reinforcement learning (RL). He is currently working on theoretical and algorithmic aspects of RL in configurable environments, off-policy RL, inverse RL, automated RL, and RL in structured environments. He participates in research projects about reinforcement learning for autonomous driving, for defense, and about machine learning for climate science. He is also interested in algorithms, optimization, statistics, probability, and recommendation systems.postdoctoral
Gianluca Drappo
PhD Student
Gianluca Drappo is a Ph.D. student in Information Technology at the Department of Electonics, Information and Bioengineering (DEIB) of Politecnico di Milano. He received his Master's degree in Computer Science and Engineering at Politecnico di Milano, defending the thesis "Gradient-based approach to inverse reinforcement learning by observing a not-expert demonstrator". His current research focuses on Hierarchical Reinforcement Learning.
Davide Maran
PhD Student
Davide Maran is a PhD student in Information Technology at the Department of Electronics, Information and Bioengineering (DEIB) of Politecnico di Milano. He received he's master degree in Mathematical Engineering in december 2021, and was Research Fellow in DEIB up to October 2022. Now: working on theoretical aspects of Reinforcement Learning (in particular imitation learning and bandits) and Representation Learning.
- Email:davide.maran@polimi.it
Gianmarco Tedeschi
PhD Student
Gianmarco Tedeschi is a Ph.D. student in Information Technology at the Department of Electronics, Information, and Bioengineering (DEIB) of Politecnico di Milano. He achieved his master's degree in Computer Science and Engineering in December 2022 with a master's thesis on an Industry 4.0 project of an automated construction plant advised by Professor M. Restelli. His research focuses on applying reinforcement learning methods in industrial scenarios.
Former Team Members
Alessandro Lazaric
Research scientist @ Meta AI
Matteo Pirotta
Research scientist @ Meta AI
Carlo D'Eramo
Professor @ U of Würzburg
Davide Tateo
Postdoc @ TU Darmstadt
Andrea Tirinzoni
Postdoc @ Meta AI
Matteo Papini
Postdoc @ UPF
Luca Sabbioni
AI specialist @ ML cube
Giorgia Ramponi
Postdoc@ ETH Zurich
Pierre Liotet
AI specialist @ ML cube
Lorenzo Bisi
AI specialist @ ML cube