Avatar

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 (University of 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
  • 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

 
 
 
 
 

Doctoral researcher

AI Lab, Vrije Universiteit Brussel

Dec 2019 – Present Brussels, Belgium
Formal verification of single- and multi-agent policies obtained through reinforcement learning.
 
 
 
 
 

Doctoral researcher

RWTH Aachen University and UMONS

Sep 2018 – Aug 2019 Aachen, Germany and Mons, Belgium
Many-sided synthesis in stochastic systems.
 
 
 
 
 

Data science intern

Nokia Bell Labs

Sep 2017 – Nov 2017 Antwerpen, Belgium
Trained machine learning models to detect, identify, and troubleshoot several impairments impacting DSL lines.
 
 
 
 
 

Research intern

UMONS

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

(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.

PDF DOI

(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.

PDF DOI

Honors & Awards

Best Paper Award (CONCUR’19)

For the paper “Life is Random, Time is Not: Markov Decision Processes with Window Objectives”.

Best MIMA Poster Award

Best poster award in the category “Mathematics, Information technology, Modeling and Applications” at Mardi des Chercheurs 2019.

Best Master’s Thesis Award in Computer Science

For the thesis “Mutli-objective Synthesis in Markov Decision Processes”.

Attended Events

  • 2019: Took part in 8 international events
    • CONCUR’19 (conference, Amsterdam, The Netherlands).
    • LearnAut: Learning au Automata (LICS’19 workshop, SFU, Vancouver,Canada)
    • MoRe’19: Multi-objective Reasoning in Verification and Synthesis (LICS’19 workshop, SFU, Vancouver, Canada)
    • FMAI: Formal Methods and AI (workshop, IRISA Rennes, France)
    • SYNT Camp (ETAPS’19 workshop, Prague, Czech Republic)
    • LiVe: Learning in Verification (ETAPS’19 workshop, Prague, Czech Republic)
    • Theory and Algorithms in Graph and Stochastic Games (GameNet workshop, Mons, Belgium)
    • MdC’19: Mardi des Chercheurs (PhD Day, Mons, Belgium)
  • 2018: Took part in 5 international events
    • Highlights of logic, games and automata (conference, Berlin, Germany)
    • MOVEP: Modeling and verification of parallel processes (summer school, ENS Paris-Saclay, Cachan, France)
    • MoRe’18 (FLoC’18 workshop, University of Oxford, UK)
    • Logic and Learning (FoPSS’18 summer school, University of Oxford, UK)
    • Logic and Learning (workshop, The Alan Turing Institute, London, UK)