Mathias Jackermeier

Mathias Jackermeier is a doctoral student and Stipendiary Lecturer in Computer Science at the University of Oxford. He is affiliated with the Department of Computer Science and the AIMS CDT (Autonomous Intelligent Machines and Systems) Centre for Doctoral Training. His research focuses on reinforcement learning, with an emphasis on developing methods for agents to learn from high-level specifications like Linear Temporal Logic (LTL) while ensuring safety constraints.

Education:

• PhD in Machine Learning (AIMS CDT), 2022-2026, University of Oxford
• MSc in Computer Science, 2020-2022, University of Oxford
• BSc in Informatics, 2016-2020, Technical University of Munich

Research Interests: Reinforcement Learning, Formal Methods, Decision Trees, Explainable AI, and Knowledge Representation. He actively explores integrating logical formalisms like LTL with machine learning frameworks to enhance task generalization and safety in autonomous systems.

Recent Activities: In 2025, he joined QuantCo as a Deep Learning Intern and became a Stipendiary Lecturer at St Hugh’s College, Oxford. His work includes notable contributions such as DeepLTL (ICLR 2025) and dtControl for explainable controller representation.

Publications: His research spans multi-task RL, formal logic embeddings, and decision tree algorithms for control systems. GitHub repositories like deep-ltl showcase his technical contributions.