Francesco Belardinelli

Francesco Belardinelli is a Senior Lecturer in the Department of Computing at Imperial College London, part of the Faculty of Engineering. He co-directs the UKRI Centre for Doctoral Training (CDT) in Safe and Trusted AI and leads the EPSRC-funded project 'An Abstraction-based Technique for Safe Reinforcement Learning'. His research focuses on Safe AI, formal methods, and strategic reasoning in multi-agent systems under imperfect information. He holds a PhD and undergraduate degrees from Scuola Normale Superiore, Italy.

Belardinelli's work bridges formal verification techniques with AI systems, particularly in ensuring safety in reinforcement learning and multi-agent dynamics. He has secured grants including EPSRC NIA, ANR projects (e.g., AGAPE, SVeDaS), and Marie Curie Fellowships. He supervises multiple PhD and postdoctoral researchers in areas like safe RL, formal methods, and multi-agent systems.

His educational contributions include courses on logical aspects of AI and scientific research methodologies. He organizes events like the FMAI Seminar series and chairs international conferences (e.g., AAMAS 2021 workshop). His outreach activities include invited talks on topics like safety-aware RL and epistemic logic.