Matthias Grilz

Matthias Grilz is a PhD student in the Trusted AI Group at TU Graz, supervised by Prof. Bettina Könighofer. His work focuses on safe (constrained) reinforcement learning, as well as the combination of normative reasoning systems with reinforcement learning and probabilistic model checking. In particular, he extends probabilistic model checkers and develops safe reinforcement learning frameworks.

Research Interests

• Safe reinforcement learning
• Formal safety analysis based on normative reasoning
• Fairness in artificial intelligence