Overview

Bio

Herke van Hoof is currently assistant professor at the University of Amsterdam in the Netherlands, where he is part of the Amlab. He is interested in reinforcement learning with structured data and prior knowledge. Reinforcement learning is a very general framework, but this tends to result in extremely data-hungry algorithms. Exploiting structured prior knowledge, or using value function or policy parametrizations that respect known structural properties, is a promising avenue to learn more with less data. Examples of this line of work include reinforcement learning (RL) for combinatorial optimisation, RL with symbolic prior knowledge, and equivariant RL.  

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

  • David & Guillermo present their work at ICAPS (6/3/2024)

    Tomorrow, June 4th, David & Guillermo will present their work at ICAPS. The paper proposes a new way to learn sub-policies that can optimally solve complex tasks expressed in linear temporal logic, even in stochastic environments. They’d love to tell you all about it. Or read our paper here.

  • BeNeRL 2024 in Amsterdam on June 10th (4/19/2024)

    Together with Maryam Tavakol & Vincent Francois-Lavet, we are organizing the 2024 edition of the Belgian-Netherlands Reinforcement Learning Workshop (BeNeRL) in Amsterdam! It will take place on June 10th, and will be a free event thanks to generous support by the Ellis Unit Amsterdam and the NWO. Registration is required, though.
    More info & sign-up at the event website.

  • Masoud started as assistant professor at TU Delft (4/18/2024)

    After his postdoc, Masoud has recently started as assistant professor in the Multimedia Computing Group of TU Delft. Congratulations, Masoud!

An archive of news items can be found on the News page.

Highlighted publications
Kuric, D.; Infante, G.; Gómez, V.; Jonsson, A.; van Hoof, H.: Planning with a Learned Policy Basis to Optimally Solve Complex Tasks. In: International Conference on Automated Planning and Scheduling, 2024. (Type: Proceedings Article | Links | BibTeX)
Gagrani, Mukul; Rainone, Corrado; Yang, Yang; Teague, Harris; Jeon, Wonseok; Hoof, Herke; Zeng, Weiliang Will; Zappi, Piero; Lott, Christopher; Bondesan, Roberto: Neural Topological Ordering for Computation Graphs. In: Advances in Neural Information Processing Systems, 2022. (Type: Proceedings Article | Links | BibTeX)
Pol, Elise; Hoof, Herke; Oliehoek, Frans; Welling, Max: Multi-Agent MDP Homomorphic Networks. In: Proceedings of the International Conference on Learning Representations, 2022. (Type: Proceedings Article | Links | BibTeX)
Kool, Wouter; Hoof, Herke; Welling, Max: Estimating Gradients for Discrete Random Variables by Sampling without Replacement. In: International Conference on Learning Representations, 2020. (Type: Proceedings Article | Links | BibTeX)
Smith, M.; Hoof, H.; Pineau, J.: An Inference-Based Policy Gradient Method for Learning Options. In: International Conference on Machine Learning, pp. 4703-4712, 2018. (Type: Proceedings Article | Links | BibTeX)
Hoof, H. Van; Neumann, G.; Peters, J.: Non-parametric Policy Search with Limited Information Loss. In: Journal of Machine Learning Research, vol. 18, no. 73, pp. 1-46, 2017. (Type: Journal Article | Links | BibTeX)