Bio
Herke van Hoof is currently associate professor at the University of Amsterdam in the Netherlands, where he is part of the Amlab. He is interested in modular reinforcement learning. Reinforcement learning is a very general framework, but this tends to result in extremely data-hungry algorithms. Exploiting modular structures, including hierarchical structures, allows sharing information between tasks and exploiting prior knowledge, to learn more with less data.
Before joining the University of Amsterdam, Herke van Hoof was a postdoc at McGill University in Montreal, Canada, where he worked with Professors Joelle Pineau, Dave Meger, and Gregory Dudek. He obtained his PhD at TU Darmstadt, Germany, under the supervision of Professor Jan Peters, where he graduated in November 2016. Herke got his bachelor and master degrees in Artificial Intelligence at the University of Groningen in the Netherlands.
Recent news
- Masoud’s paper accepted (8/21/2026)
Masoud Mansoury’s paper on The Unfairness of Multifactorial Bias in Recommendation has been accepted in the ACM Transactions on Information Systems and is now available here. Congratulations, Mansoud!
- Three workshop papers accepted (7/13/2026)
Adi Watzman‘s paper Toward Iterative Safe Policy Improvement (with co-authors Floris den Hengst and Thiago Dias Simão) was accepted to the UAI workshop on Safe AI.
Two UvA master students had papers accepted to the European Workshop on Reinforcement learning: Eduardo Terres Caballero the paper A Goal-Set Characterization of Task Composition in the Boolean Task Algebra and Oscar Miró López Feliu the paper Correcting Within-Group Self-Selection Bias in Prioritized Replay.
Congratulations!
- Paper Matthew accepted at ICLR (2/18/2026)
Matthew’s paper Gradient-Based Program Synthesis with Neurally Interpreted Languages, with Clément Bonnet and Levi Lelis, was accepted to ICLR! Congrats, Matthew!
An archive of news items can be found on the News page.
Highlighted publications
| : Gradient-Based Program Synthesis with Neurally Interpreted Languages. In: Proceedings of the International Conference on Learning Representations, 2026. |
| : Planning with a Learned Policy Basis to Optimally Solve Complex Tasks. In: International Conference on Automated Planning and Scheduling, 2024. |
| : Neural Topological Ordering for Computation Graphs. In: Advances in Neural Information Processing Systems, 2022. |
| : Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement. In: International Conference on Machine Learning, pp. 3499–3508, 2019. |
| : Non-parametric Policy Search with Limited Information Loss. In: Journal of Machine Learning Research, vol. 18, no. 73, pp. 1-46, 2017. |