I am a PhD student at the department of software science at Radboud University, working on the project Provably Correct Policies for Uncertain Partially Observable Markov Decision Processes under supervision of dr. Nils Jansen and prof. dr. Frits Vaandrager.

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.

You can reach me at m.suilen {AT} science.ru.nl

Publications

See also my DBLP or Google scholar profiles.

Accepted publications:
Thiago D. Simão, Marnix Suilen, Nils Jansen. Safe Policy Improvement for POMDPs via Finite-State Controllers. In AAAI 2023 (to appear).
PDF Marnix Suilen, Thiago D. Simão, David Parker, Nils Jansen. Robust Anytime Learning of Markov Decision Processes. In NeurIPS 2022 (to appear).
PDF Thom S. Badings, Arnd Hartmanns, Nils Jansen, Marnix Suilen. Balancing Wind and Batteries: Towards Predictive Verification of Smart Grids. In NASA Formal Methods Symposium 2021.
PDF Murat Cubuktepe, Nils Jansen, Sebastian Junges, Ahmadreza Marandi, Marnix Suilen, Ufuk Topcu. Robust Finite-State Controllers for Uncertain POMDPs. In AAAI 2021.
PDF Marnix Suilen, Nils Jansen, Murat Cubuktepe, Ufuk Topcu. Robust Policy Synthesis for Uncertain POMDPs via Convex Optimization. In IJCAI 2020.
Theses:
PDF Marnix Suilen, Entropy Guided Decision Making in Multiple-Environment Markov Decision Processes, 2020, master thesis, Radboud University Nijmegen.
PDF Marnix Suilen, Reachability properties for uncertain Markov decision processes, 2018, bachelor thesis, Radboud University Nijmegen.

Professional activities

Talks and Presentations

Decision-Making and Learning under Uncertainty. ROCKS 2022.
Anytime Learning and Verification of Uncertain Markov Decision Processes. LiVe 2022.
Unraveling Uncertainty in POMDPs. RWTH Aachen, Germany, 2021.
Robust Policies for Uncertain POMDPs. R4P 2021.
Robust Policies for Uncertain POMDPs. FUNCTION 2021.
Robust Policy Synthesis for Uncertain POMDPs via Convex Optimization. IJCAI 2020.

Teaching

As a lecturer:
Model Checking, spring 2022, lectures on bisimulations and POMDPs.

As a teaching assistant:
Mathematical Foundations of Computer Science Seminar, fall 2022.
Model Checking, spring 2022.
Mathematical Foundations of Computer Science Seminar, fall 2021.
Model Checking, spring 2021.
Model Checking, spring 2020.
Algorithms and Datastructures, fall 2019.
Algorithms and Datastructures, fall 2018.

Other

Student volunteer for FORMATS 2020, part of QONFEST 2020.