People

Nils Jansen

I am interested in various aspects of dependability and safety in AI, intelligent decision-making under uncertainty, and safe reinforcement learning. A key aspect of my research is a thorough understanding of the (epistemic or aleatoric) uncertainty that may occur when AI systems operate in the real world.

• • artificial intelligence
• • planning under uncertainty
• • POMDPs
• • safe reinforcement learning
• • formal verification

Marcel Neuhausen

Having a strong background in computer vision, my research focuses on decision-making under the uncertainty inherent in visual perception. I am particularly interested in developing safe reinforcement learning agents that utilize object recognition to perceive their dynamic environment. My work aims to bridge the gap between perception and action by exploring how intelligent systems can make robust decisions despite uncertain perceptions, ensuring safety and reliability in real-world scenarios.

• • computer vision
• • safe reinforcement learning
• • decision-making under uncertainty

Thom Badings

My primary research interests are on the intersection between Engineering, Systems & Control, and Formal Verification. Currently, I am working on sequential decision making under uncertainty with correctness guarantees, with applications to autonomous and robotics systems, predictive maintenance, and electrical power systems.

• • systems and control
• • decision making under uncertainty
• • artificial intelligence
• • abstraction-based controller synthesis
• • predictive maintenance

Eline Bovy

My research interests are formal verification and decision-making problems. My current work focuses on uncertain partially observable Markov decision processes.

• • formal verification
• • decision making under uncertainty
• • POMDPs

Maris Galesloot

My primary research interests lie in sequential decision making in uncertain environments with partial observability. My work focuses on the intersection of a formal model-based approach and neural function approximation methods in reinforcement learning and aims to improve the scalability, applicability, and robustness of these algorithms in the real world.

• • model-based reinforcement learning
• • deep learning
• • online planning

Merlijn Krale

I am interested in model-based algorithms with strong theoretical foundations for complex decision-making processes. My current work focusses on partially-observable environments where agents have explicity control over their observations.

• • POMDPs
• • robustness
• • model abstractions

Christoph Schmidl

My research interests are safe reinforcement learning and formal verification applied to real-world scheduling problems. My current work focuses on robust scheduler learning with constrained interactions using reinforcement learning techniques applied to different shop types such as job shops and flow shops.

• • safe reinforcement learning
• • scheduling
• • robustness
• • AI
• • DevOps
• • formal verification
• • security

Marnix Suilen

My research interests are formal verification and learning in probabilistic systems such as (partially observable) Markov decision processes and variations that extend these models with uncertainty. Other interests include coalgebra (especially for probabilistic systems), (robust) convex optimization, and algorithms in general.

• • decision making under uncertainty
• • POMDPs
• • formal verification
• • artificial intelligence
• • offline reinforcement learning

Miriam Ackermann

My research interests include uncertainty quantification and reinforcement learning, with a particular focus on the potential for combining these two fields to enhance the safety of reinforcement learning.

• • artificial intelligence
• • neural networks
• • uncertainty quantification
• • safe reinforcement learning

Jule Schmidt

I am interested in methods that improve the generalizability and robustness of (Deep) Reinforcement Learning, with a particular focus on Causal RL. My research aims to enhance the reliability and safety of RL by integrating causal reasoning into the learning process.

• • reinforcement learning
• • deep learning
• • causality
• • safe reinforcement learning

Joshua Wendland

My research focuses on ensuring safety in Machine Learning applications. I've worked on off-policy evaluation in Reinforcement Learning, particularly in scenarios with incomplete datasets (missingness). Additionally, I've explored language model evaluation and contributed to policy-making in AI Governance. My interests span offline Reinforcement Learning, Robustness, the Alignment Problem, and Deep Learning.

• • robustness
• • offline reinforcement learning
• • safe reinforcement learning
• • alignment problem

Markel Zubia

I study the theoretical foundations of sequential decision-making under uncertainty. My research interests are broad and include complexity theory, formal verification, dynamical systems, automata theory, recursion theory, and reinforcement learning. I am particularly fascinated by cellular automata, as well as Turing-complete dynamical systems in general.

• • formal verification
• • safe reinforcement learning
• • robust MDPs
• • dynamical systems
• • cellular automata

Wietze Koops

ELLIS Excellence Fellow (2022 - 2024)

Next: PhD candidate at Lund University

I am interested in decision making problems from various perspectives. Currently, I am focussing on developing exact and approximate algorithms for solving Decentralized POMDPs. In general, I have broad interests including mathematics (in particular combinatorics, probability theory and optimization), operations research, machine learning and algorithms.

• • decision making
• • design of algorithms
• • probability theory
• • optimization
• • operations research
• • microeconomics
• • machine learning
• • decentralized POMDPs

Yannick Hogewind

ELLIS Excellence Fellow (2022 - 2023)

Next: Data Scientist at ABN AMRO

Thiago D. Simão

Postdoc (2022 - 2023)

Next: Assistant Professor at Eindhoven University of Technology

The motivation for my research revolves around making AI techniques more reliable, to enable their deployment in real-world applications. I focus on developing AI algorithms for scenarios with constrained interactions with an unknown environment.

• • decision making under uncertainty
• • safe reinforcement learning
• • offline reinforcement learning
• • probabilistic planning
• • AI

Dennis Gross

PhD (2019 - 2023)

Next: Postdoctoral Fellow at Simula Research Laboratory, Oslo

I am a PhD student at the department of software science at Radboud University, working on the formal verification of neural network classifiers and policies under supervision of dr. Nils Jansen, dr. Guillermo Alberto Perez, and prof. dr. Frits Vaandrager.

• • formal methods
• • machine learning

Zaharah A. Bukhsh

Postdoc (2020 - 2021)

Next: Assistant Professor at Eindhoven University of Technology

My research focus on developing tools and techniques to improve operational processes. The core research areas include business intelligence, business engineering and process engineering.

• • data-driven decision-making
• • predictive maintenance
• • deep reinforcement learning
• • business process monitoring and optimisation
• • self-supervised and transfer learning