Liam Plank | Trusted AI Group

PhD Student

TU Graz, Institute of Information Security

Liam Plank is a PhD student in the Trusted AI Group at TU Graz, supervised by Prof. Bettina Könighofer. His research focuses on ethical and safe sequential decision-making through neuro-symbolic AI. He is particularly interested in integrating symbolic approaches into subsymbolic systems to obtain formal guarantees, enhance interpretability, and improve the reliability of autonomous decision-making systems.

Research Interests

Safe and Norm-Compliant Reinforcement Learning
Applications of Safety Shielding