Francesco De Lellis
POSTDOC
Contacts
Department of Electrical Engineering and Information Technology
University of Naples Federico II
Via Claudio 21, 80125, Naples, Italy
Telephone: +390817683607
Email: francesco.delellis@unina.it; francesco.delellis.93@gmail.com
Short Bio
Francesco De Lellis obtained his master degree in Automation Engineering at the University of Naples Federico II in October 2019. His master thesis focused on the development of model-based control-tutored reinforcement learning providing a solution of the herding problem.
Francesco also obtained his Ph.D. in Information Technology and Electrical Engineering at the University of Naples Federico II in May 2023. During his Ph.D. project Francesco has been advised by the prof.s Mario di Bernardo, Giovanni Russo and Mirco Musolesi. The core of Francesco's research deals with the application of non linear control theory and reinforcement learning for the development of new methodologies for the control of multi-agent complex systems.
Under the alias Redoken, Francesco is also an electronic music producer. He relased many tunes with well established record label such as Artist Intelligent Agency, DubstepGutter, Stereofox, Riddim Network and many more.
Publications
F. De Lellis, M. Coraggio, N. C. Foster, R. Villa, C. Becchio, M. di Bernardo, “Data-driven architecture to encode information in the kinematics of robots and artificial avatars”, submitted to IEEE Control Systems Letters and IEEE Conference on Decision and Control (CDC) , 2024, arxiv:2403.065571
S. M. Brancato, D. Salzano, F. De Lellis, D. Fiore, G. Russo, M. di Bernardo, "In vivo learning-based control of microbial populations density in bioreactors", accepted for presentation to Learning 4 Dynamics and Control, 2024, arXiv:2312.09773.
F. De Lellis, M. Coraggio, G. Russo, M. Musolesi, M. di Bernardo, "Guaranteeing Control Performance via Reward Shaping in Reinforcement Learning", accepted for publication to IEEE Transactions on Control Systems Technology, 2024, arXiv:2311.10026.
F. De Lellis, M. Coraggio, G. Russo, M. Musolesi, M. di Bernardo, "CT-DQN: Control-Tutored Deep Reinforcement Learning", Learning for Dynamics and Control Conference (L4DC), Proceedings of Machine Learning Research (PMLR), 211, pp. 941-953, 2023.
S. M. Brancato, F. De Lellis, D. Salzano, G. Russo, M. di Bernardo, "External control of genetic toggle switch via Reinforcement Learning", European Control Conference (ECC), pp. 1-6, 2023.
F. De Lellis, M. Coraggio, G. Russo, M. Musolesi, M. di Bernardo "Control-Tutored Reinforcement Learning: Towards the Integration of Data-Driven and Model Based Control", Learning for Dynamics and Control Conference (L4DC), Proceedings of Machine Learning Research (PMLR), 168, pp. 1048-1059, 2022.
M. Coraggio, S. Xie, F. De Lellis, G. Russo, M. di Bernardo, "Intermittent non-pharmaceutical strategies to mitigate the COVID-19 epidemic in a network model of Italy via constrained optimization", Conference on Decision and Control (CDC), pp. 3538-3543, 2021.
F. De Lellis, F. Auletta, G. Russo, P. De Lellis, M. di Bernardo, "An Application of Control-Tutored Reinforcement Learning to the Herding Problem", IEEE International Workshop on Cellular Nanoscale Networks and their Applications, pp. 1-4, 2021.
F. De Lellis, G. Russo, M. di Bernardo, "Tutoring Reinforcement Learning via Feedback Control", European Control Conference (ECC), pp. 580-585, 2021.
F. Della Rossa, D. Salzano, A. Di Meglio, F. De Lellis, M. Coraggio, C. Calabrese, A. Guarino, R. Cardona-Rivera, P. De Lellis, D. Liuzza, F. Lo Iudice, G. Russo, M. di Bernardo, "A network model of Italy shows that intermittent regional strategies can alleviate the COVID-19 epidemic", Nature Communications, 11, 5106, 2020.