Quentin Cappart

Since 2018, I am a postdoctoral fellow at Polytechnique Montréal in CIRRELT under the supervision of Prof. Louis-Martin Rousseau. I am also a research intern at ElementAI. My current research aims to integrate machine learning techniques into the field of discrete optimization. This research is funded by postdoctoral grants awarded by Ivado and Mitacs. Besides, I also collaborate with Prof. David Bergman (UConn).

I obtained my Ph.D. from UCLouvain in 2017 under the supervision of Prof. Pierre Schaus. I worked as a research assistant at ICTEAM until 2018. I also graduated from UCLouvain in 2014 with a Master’s degree in computer engineering and in 2018 with a second Master’s degree in management.
My research interests are quite broad. Instead of focusing on a particular method or paradigm, I am more interested in problem solving. I enjoy using all my knowledge to solve real and concrete challenges. I have particular affinities for problems related to operational research, optimisation, data science and machine learning.

2023

Marty T, François T, Tessier P, Gautier L, Cappart Q, Rousseau L-M, (2023), Learning a Generic Value-Selection Heuristic Inside a Generic Constraint Programming Solver, 29th International Conference on Principles and Practice of Constraint Programming LIPIcs, Volume 280, CP 2023.

Rudich I, Cappart Q, Rousseau L-M, (2023), Improved Peel-and-Bound: Methods for Generating Dual Bounds with Multivalued Decision Diagrams, Journal of Artificial Intelligence Research, 77:1489-1538.

Peyman K, Cappart Q, Chapados N, Pouya H, Rousseau L-M, (2023), Dynamic Routing and Wavelength Assignment with Deep Reinforcement Learning. INFORMS Journal on Optimization, 6(1): 1-18.

2022

Cappart Q, Bergman D, Rousseau L-M, Prémont-Schwartz I, Parjadis A. (2022). Improving Variable Orderings of Approximate Decision Diagrams using Reinforcement Learning. INFORMS Journal on computing. 34 (5). INFORMS.https://doi.org/10.1287/ijoc.2022.1194

Rudich I, Cappart Q, Rousseau L-M, (2022), Peel-And-Bound: Generating Stronger Relaxed Bounds with Multivalued Decision Diagrams. 28th International Conference on Principles and Practice of Constraint Programming (CP 2022). Volume 235. LIPICS.

Joshi CK, Cappart Q, Laurent T, Rousseau L-M, (2022), Learning the Travelling Salesperson Problem Requires Rethinking Generalization, Constraints, 27:70–98.

2021

Kafaei P, Cappart Q, Renaud M-A, Chapados N, Rousseau L-M, (2021), Graph neural networks and deep reinforcement learning for simultaneous beam orientation and trajectory optimization of Cyberknife, Physics in Medicine and Biology, 66(21). https://doi.org/10.1088/1361-6560/ac2bb5

*Parjadis A, Cappart Q, Rousseau L-M, and Bergman D, (2021), Improving Branch-and-Bound using Decision Diagrams and Reinforcement Learning, CPAIOR (International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research), LNTCS,volume 12735.

*Chalumeau F, *Coulon I, Cappart Q and Rousseau L-M, (2021), SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning, CPAIOR (International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research), LNTCS,volume 12735.

Kafaei P, Cappart Q, Renaud M-A, Chapados N, Rousseau L-M, (2021), Deep Q-learning for simultaneous Beam Orientation and trajectory optimization for Cyberknife. Physics and Medecine in Biology, 66(21).

Cappart Q, Moisan T, Rousseau L-M, Prémont-Schwarz I, Cire A, (2021), “Combining Reinforcement Learning and constraint programming combinatorial optimization”. AAAI 2020. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5): 3677-3687.

Joshi H-K, Cappart Q, Rousseau L-M, Laurent T, (2021), “Learning TSP Requires Rethinking Generalization”, International Conference on Principles and Practice of Constraint Programming – CP 2021.