Florent Delgrange

Florent Delgrange

Doctoral Researcher in Artificial Intelligence

AI Lab, Vrije Universiteit Brussel

Biography

I am a PhD student in the AI lab of the Vrije Universiteit Brussel (VUB), under the supervision of Ann Nowé (AI Lab, VUB) and Guillermo A. Pérez (Universiteit Antwerpen). My research interests lie in the fields of artificial intelligence and formal verification. More specifically, my PhD focuses on the formal verification of single- and multi-agent policies obtained through reinforcement learning. The end goal of my research is to provide end-users with reliable AI mechanisms.

Interests
  • Reinforcement learning
  • Multi-agent systems
  • Model checking and synthesis
  • Deep generative modeling
  • Planning under uncertainty and partial observability
Education
  • PhD in Computer Science

    Vrije Universiteit Brussel (VUB), Belgium

  • Master in Computer Science, 2018

    University of Mons (UMONS), Belgium

  • Bachelor in Computer Science, 2016

    UMONS, Belgium

Experience

 
 
 
 
 
AI Lab, Vrije Universiteit Brussel
Doctoral researcher
Dec 2019 – Present Brussels, Belgium
Formal verification of single- and multi-agent policies obtained through reinforcement learning.
 
 
 
 
 
RWTH Aachen University and UMONS
Scientific Researcher
RWTH Aachen University and UMONS
Sep 2018 – Aug 2019 Aachen, Germany and Mons, Belgium
Many-sided synthesis in stochastic systems.
 
 
 
 
 
Nokia Bell Labs
Data science intern
Sep 2017 – Nov 2017 Antwerp, Belgium
Trained machine learning models to detect, identify, and troubleshoot several impairments impacting DSL lines.
 
 
 
 
 
UMONS
Research intern
Aug 2016 – Sep 2016 Mons, Belgium
Introduction to research internship, in the software engineering lab. Development of a software tool for generating state machine visualizations from UML statechart specifications.

Publications

(2023). The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models. arXiv.

Cite Project DOI Preprint

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

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 URL Full Text

(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”.
UMONS & Université Polytechnique Hauts-de-France
Best MIMA Poster Award
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