Groups

Projects 2026

1. Team: Ferid Kendić & Tiemen Ykema
   Topic: Safe RL
   Paper: CRAX: Fast Safe Reinforcement Learning Benchmarking

2. Team: Ian de Haan & Iwan Steenhoff
   Topic: Model-based RL
   Paper: R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation

3. Team: Jip Raven & Olaf Tijs
   Topic: Evolutionary RL
   Paper: Evolution Strategies at the Hyperscale

4. Team: Coen Buller & Mario Magalini
   Topic: Multi-agent RL
   Paper: SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas

5. Team: Emma Bouwman & Alexa van Thiel
   Topic: RL for computer vision
   Paper: Experimental design for MRI by greedy policy search

6. Team: Luc van Driel, Rwik Kamilya & Jasper Scheel
   Topic: RL for chemistry
   Paper: Reinforcement Learning for Minimum-Energy Path Discovery

7. Team: Matiss Kalnare & Valeria Rezan
   Topic: Evolutionary RL
   Paper: Evolution Strategies at the Hyperscale

8. Team: Xing He & Ahmad Baasim Husain
   Topic: Model-based RL
   Paper: A KL-Regularization Framework for Learning to Plan with Adaptive Priors

9. Team: Avan Salman & Maarten Verhoeff
   Topic: RL for (sequential) generative models
   Paper: Generative Flow Networks as Entropy-Regularized RL

10. Team: Nitin Raju & Roshun Sai
    Topic: Graph-based RL
    Paper: Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case