Maris F. L. Galesloot

My affiliation is with the Department of Software Science (SWS) of the Institute for Computing and Information Sciences (iCIS), at Radboud University in Nijmegen, the Netherlands. My PhD is part of the European Laboratory for Learning and Intelligent Systems (ELLIS) PhD program.

There, I am supervised by promotor Prof. Dr. Nils Jansen and co-promotor Dr. Sebastian Junges, part of the AI-FM research group and member of the coordinator team of the ELLIS Unit Nijmegen.

My ELLIS co-supervisor is Prof. Dr. Nick Hawes from the GOALS research group of the Oxford Robotics Institute located at the University of Oxford in the United Kingdom. Hence, I spent 6-months as a PhD student at the University of Oxford between February and August 2025, during which I was an associate member of the MCR of Exeter College and supported by the European Lighthouse on Secure and Safe AI (ELSA).

My research interests revolve around sequential decision-making under uncertainty. More specifically, my PhD research specializes in (online) planning under uncertainty and model-based reinforcement learning with a touch of probabilistic verification for partially observable and uncertain environments. Such environments are typically modelled by (robust) extensions or (proper) subsets of partially observable Markov decision processes (POMDPs). My work focuses on developing scalable and robust algorithms and aims to combine the robustness of model-based approaches with the scalability of data-driven learning techniques.

News

Dec 20, 2025	Our paper, entitled Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learning, was accepted for publication at AAMAS 2026!
Sep 20, 2025	Our paper, entitled On Evaluating Policies for Robust POMDPs, was accepted for publication at NeurIPS 2025! Joint main authorship with Eline Bovy and Merlijn Krale.
Jul 11, 2025	Our paper, entitled Pessimistic Iterative Planning with RNNs for Robust POMDPs, was accepted for publication at ECAI 2025! An earlier version of the paper was presented at EWRL 2024.
May 26, 2025	Our paper, entitled Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs, was accepted for publication at IJCAI 2025!
Jan 15, 2024	My first paper, entitled Factored Online Planning in Many-Agent POMDPs has been accepted for publication at AAAI 2024!

Selected publications

AAMAS

Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learning

David Hudák, Maris F. L. Galesloot, Martin Tappler, and 3 more authors

In International Conference on Autonomous and Multiagent Systems, 2026

arXiv Bib Code

@inproceedings{Hudak2026Finite,
  author = {Hud{\'a}k, David and Galesloot, Maris F. L. and Tappler, Martin and Kure\v{c}ka, Martin and Jansen, Nils and \v{C}e\v{s}ka, Milan},
  title = {Finite-State Controllers for (Hidden-Model) {POMDP}s using Deep Reinforcement Learning},
  booktitle = {International Conference on Autonomous and Multiagent Systems},
  year = {2026},
}

NeurIPS

On Evaluating Policies for Robust POMDPs

Merlijn Krale, Eline M. Bovy, Maris F. L. Galesloot, and 2 more authors

In NeurIPS, 2025

(first three authors contributed equally)

Bib Code

@inproceedings{rpomdp,
  title = {On Evaluating Policies for Robust {POMDP}s},
  author = {Krale, Merlijn and Bovy, Eline M. and Galesloot, Maris F. L. and Sim{\~a}o, Thiago D. and Jansen, Nils},
  booktitle = {{NeurIPS}},
  note = {(first three authors contributed equally)},
  year = {2025},
}

IJCAI

Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs

Maris F. L. Galesloot, Roman Andriushchenko, Milan Češka, and 2 more authors

In IJCAI, 2025

arXiv Bib Code

@inproceedings{DBLP:conf/ijcai/GaleslootA0J025,
  author = {Galesloot, Maris F. L. and Andriushchenko, Roman and \v{C}e\v{s}ka, Milan and Junges, Sebastian and Jansen, Nils},
  title = {Robust Finite-Memory Policy Gradients for Hidden-Model {POMDP}s},
  booktitle = {{IJCAI}},
  pages = {8518--8526},
  publisher = {ijcai.org},
  year = {2025},
}

ECAI

Pessimistic Iterative Planning with RNNs for Robust POMDPs

Maris F. L. Galesloot, Marnix Suilen, Thiago D. Simão, and 4 more authors

In ECAI, 2025

arXiv Bib Code

@inproceedings{pip-rnn,
  title = {Pessimistic Iterative Planning with {RNN}s for Robust {POMDP}s},
  author = {Galesloot, Maris F. L. and Suilen, Marnix and Sim{\~a}o, Thiago D. and Carr, Steven and Spaan, Matthijs T. J. and Topcu, Ufuk and Jansen, Nils},
  booktitle = {{ECAI}},
  series = {Frontiers in Artificial Intelligence and Applications},
  year = {2025},
  volume = {413},
  pages = {4823--4831},
  publisher = {{IOS} Press},
}

AAAI

Factored Online Planning in Many-Agent POMDPs

Maris F. L. Galesloot, Thiago D. Simão, Sebastian Junges, and 1 more author

In AAAI, 2024

arXiv Bib Code

@inproceedings{DBLP:conf/aaai/GaleslootSJ024,
  author = {Galesloot, Maris F. L. and Sim{\~{a}}o, Thiago D. and Junges, Sebastian and Jansen, Nils},
  title = {Factored Online Planning in Many-Agent {POMDP}s},
  booktitle = {{AAAI}},
  pages = {17407--17415},
  publisher = {{AAAI} Press},
  year = {2024},
}