Briefly

I am a PhD Student, working on Reinforcement Learning under the supervision of Prof. Marcello Restelli, at the Department of Electronics, Informatics and Bio-engineering (DEIB) of Politecnico di Milano.

Research Interests

My main research interests focus on Reinforcement Learning (RL), and more specifically Multi-Agent Reinfocement Learning (MARL). Generally, I am investigating on the role of information in defining the frontiers between single-agent and multi-agent problems with the long term goal of passing over the existing (and often limiting) common frameworks, like Centralized Training Decentralized Execution (as for Chapter 9.1 of this nice book) and data abundance. My aim is to develop a theoretical understanding of how single-agent methods can be distributed through communication, without paying too much in terms of RL performance. (un)Fortunately, little has changed since Laurer & Riedmiller (2000). Currently, I am focusing on how to learn purely explorative policies in multi-agent settings and on how to design scalable offline algorithms based on information-sharing.

Industrial Collaborations

I am passionate about applying RL to challenging tasks and looking for new ways towards principled MARL for real-world applications. In particular, I am currently collaborating with Siemens AT on applying scalable MARL techniques for Industry 4.0.

Teaching Activities

In the Academic Years 2022-2023 & 2023-2024 I have been working as Teaching Assistant for the Course of Informatics by Prof. A. Marchesi.

In the Academic Year 2022-2023 I did some Tutoring Activities for the Master in Data Science & AI held by Cefriel.

Work Experience

Between 2019 and 2022 I worked first as a R&D Control Engineer for e-Novia, then briefly as an Embedded SW Engineer for Kalpa, and finally as a Research Scholar at DEIB working on Distributed Methods for Industry 4.0.

Education

In October 2019, I received my Master of Science in Automation and Control Engineering at Politecnico di Milano (with honors), defending the thesis “Introducing a proprio-ceptive feedback in the bio-inspired Tegotae control approach : enhanced learning and energy efficiency”, under the supervision of Prof. Fabio Dercole and Prof. Mitsuhiro Hayashibe, which resulted from a visiting research program at the Neuro-Robotics Laboratory of Tohoku Univesity.

In July 2017, I obtained a Bachelor of Mechatronics Engineering from University of Trento (with honors), defending a thesis on Mathematical Control Theory (in Italian, unfortunately).

Credits

You can have a look at my full CV here. It might not be updated very often.

Feel free to contact me by e-mail, I am always open to collaborations!