Florent Delgrange

Florent Delgrange

Post-doctoral Researcher in Computer Science

AI Lab, Vrije Universiteit Brussel

Biography

I am a post-doctoral researcher at the AI Lab of Vrije Universiteit Brussel (VUB). My research focuses on artificial intelligence and formal verification. Specifically, I work on theoretical aspects of reinforcement learning (RL), representation learning in RL, model-checking and synthesis in stochastic systems, and decision-making under uncertainty and partial observability. The end goal of my research is to provide end-users with reliable AI mechanisms. I am also the lecturer for the course Theory of Computation, which I teach at the VUB.

Before, I did a joint PhD within the VUB and the University of Antwerp under the supervision of Ann Nowé and Guillermo A. Pérez. My thesis focused on enabling the formal verification of deep RL policies (you can find the dissertation here).

News Feed

  • My PhD thesis dissertation, entitled Activating Formal Verification of Deep Reinforcement Learning Policies by Model Checking Bisimilar Latent Space Models is available here!
Interests
  • Reinforcement learning
  • Model checking and synthesis
  • Representation learning in RL
  • Multi-objective decision making
  • Decision-making under uncertainty and partial observability
  • Deep generative modeling
Education
  • Doctor of Science, Computer Science, 2024

    Vrije Universiteit Brussel (VUB) and University of Antwerp, Belgium

  • Master in Computer Science, 2018

    University of Mons (UMONS), Belgium

  • Bachelor in Computer Science, 2016

    UMONS, Belgium

Publications

(2024). Controller Synthesis from Deep Reinforcement Learning Policies. Seventeenth European Workshop on Reinforcement Learning.

Cite EWRL 2024 MODeM 2024

(2023). The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models. The Twelfth International Conference on Learning Representations, ICLR 2024.

Cite Project PDF

(2023). WAE-PCN: Wasserstein-autoencoded Pareto Conditioned Networks. Proceedings of the Adaptive and Learning Agents Workshop (ALA 2023).

Cite PDF Workshop Page

(2023). Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees. The Eleventh International Conference on Learning Representations, ICLR 2023.

Cite Code Project URL PDF

(2022). Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes. Proceedings of the AAAI Conference on Artificial Intelligence Vol. 36 No. 6: AAAI-22 Technical Tracks 6, 6497-6505.

Cite Code Project DOI URL Extended Abstract Technical Report

(2022). A Framework for Flexibly Guiding Learning Agents. Neural Computing and Applications, Special Issue on Adaptive and Learning Agents 2021.

Cite DOI

(2020). Life is Random, Time is Not: Markov Decision Processes with Window Objectives. Logical Methods in Computer Science, December 14, 2020, Volume 16, Issue 4.

Cite URL PDF DOI

(2020). Simple Strategies in Multi-Objective MDPs. Tools and Algorithms for the Construction and Analysis of Systems - 26th International Conference, TACAS 2020, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2020, Dublin, Ireland, April 25-30, 2020, Proceedings, Part I.

Cite DOI PDF

(2019). Life Is Random, Time Is Not: Markov Decision Processes with Window Objectives. 30th International Conference on Concurrency Theory, CONCUR 2019, August 27-30, 2019, Amsterdam, the Netherlands.

Cite DOI PDF

Honors & Awards

The 30th International Conference on Concurrency Theory
Best Paper Award (CONCUR'19)
For the paper “Life is Random, Time is Not: Markov Decision Processes with Window Objectives”.
Best poster award in the category “Mathematics, Information technology, Modeling and Applications” at Mardi des Chercheurs 2019.
UMONS
Best Master’s Thesis Award in Computer Science
For the thesis “Multi-objective Synthesis in Markov Decision Processes”.

Contact

  • Pleinlaan 9, Artificial Intelligence Lab, Vrije Universiteit Brussel, Brussels, B-1050
  • Building 9, 3rd floor