Francesco Belardinelli

Francesco Belardinelli is an Associate Professor in the Department of Computing at Imperial College London. His research focuses on Safe AI, primarily through the application of formal methods. His main areas of interest include Safe Reinforcement Learning, Logic-based Languages for Artificial Intelligence, the Specification and Verification of Multi-agent Systems, and Strategic Reasoning under Imperfect Information. He is co-director of the CDT in Safe and Trusted AI and is currently developing an EPSRC project on an Abstraction-based Technique for Safe Reinforcement Learning. He also supervises PhD students and is involved in outreach activities.

Francesco Belardinelli is a researcher at Imperial College London, specializing in Artificial Intelligence, Logic, and Formal Methods. His work focuses on the verification of complex systems, particularly multi-agent systems, artifact-centric systems, and strategic reasoning. He explores the intersection of logic and AI, addressing challenges in knowledge, time, and strategy. His research includes the development of abstraction techniques, epistemic logics, and methods for verifying strategic properties in systems with imperfect information. Belardinelli's contributions span both theoretical and applied aspects of formal verification, with an emphasis on ensuring correctness in AI-driven environments.