Abstract

The research covers a wide range of topics, including multi-armed bandits, multi-agent reinforcement learning, inverse reinforcement learning, and deep RL, as well as recent directions such as risk-aware, preference-based, and unsupervised RL. Particular attention is given to realistic settings characterized by continuous action spaces, partial observability, non-stationarity, and safety constraints.
A key aspect of this research is integrating methodological advances with real-world applications. Several industrial collaborations are considered, spanning domains such as dynamic pricing, online advertising, finance, energy, manufacturing, and autonomous systems, where RL techniques must address practical constraints and ensure reliable performance.
The talk concludes with an overview of current challenges and future directions to improve the robustness, scalability, and applicability of reinforcement learning in complex real-world environments.

Bio

Marcello Restelli is a Full Professor at the Department of Electronics, Information and Bioengineering at Politecnico di Milano, where he coordinates the Real-Life Reinforcement Learning Research Lab (RL3). He is the author of more than 200 international scientific publications, primarily focused on the study and development of new reinforcement learning techniques. His research results are applied to real-world problems through numerous industrial collaborations in diverse sectors, including finance, e-commerce, Industry 4.0, and automotive.
He is an ELLIS Fellow and serves as the research lead for the Artificial Intelligence Observatory of Politecnico di Milano. In 2020, he co-founded ML cube, a spin-off of Politecnico di Milano, where he is currently scientific advisor.

Host

Loris Roveda, Associate Professor in Integrated Intelligence for Robotics, Intelligent Control Area for Systems and Network