Published in preprint, 2022
This paper introduces a Julia library of Machine Learning for Operations Research, as well as a new probabilistic approach.
Recommended citation: Guillaume Dalle, Léo Baty, Louis Bouvier, Axel Parmentier, "Learning with Combinatorial Optimization Layers: a Probabilistic Approach" https://arxiv.org/abs/2207.13513
Published in Transportation Science, 2023
This paper is the fruit of a partnership with Renault.
Recommended citation: Louis Bouvier, Guillaume Dalle, Axel Parmentier, Thibaut Vidal, "Solving a Continent-Scale Inventory Routing Problem at Renault" https://pubsonline.informs.org/doi/10.1287/trsc.2022.0342
Published in preprint, 2024
This preprint is about structured learning for combinatorial multistage stochastic optimization.
Recommended citation: Toni Greif, Louis Bouvier, Christoph M. Flath, Axel Parmentier, Sonja U. K. Rohmer, Thibaut Vidal, "Combinatorial Optimization and Machine Learning for Dynamic Inventory Routing" https://arxiv.org/abs/2402.04463
Published in Hal, 2024
This is the manuscript of my PhD thesis.
Recommended citation: Louis Bouvier, "Apprentissage structuré et optimisation combinatoire : contributions méthodologiques et routage d inventaire chez Renault". Mathématiques générales [math.GM]. École des Ponts ParisTech, 2024. https://pastel.hal.science/tel-04972042
Published in preprint, 2025
This paper introduces a new machine learning-based algorithm for contextual stochastic combinatorial optimization.
Recommended citation: Louis Bouvier, Thibault Prunet, Vincent Leclère, Axel Parmentier, "Primal-dual algorithm for contextual stochastic combinatorial optimization" https://arxiv.org/abs/2505.04757
Published in preprint, 2025
This paper introduces a novel actor-critic framework that embeds combinatorial optimization layers into the actor neural network.
Recommended citation: Heiko Hoppe, Léo Baty, Louis Bouvier, Axel Parmentier, Maximilian Schiffer, "Structured Reinforcement Learning for Combinatorial Decision-Making" https://arxiv.org/abs/2505.19053
Published:
We consider a large-scale multi-depot multi-commodity Inventory Routing Problem (IRP) to model the packaging return logistics of a major European car manufacturer. No algorithm is known to properly scale to our context. We propose a Large Neighborhood Search (LNS) based on common routing neighborhoods and two new ones: the reinsertion of a customer and a commodity in the IRP solution. We also try to bypass the heavy computations of the LNS leveraging recent ideas in Machine Learning for Operations Research in structured prediction.
Undergraduate course, Ecole des Ponts ParisTech, 2021
Teaching assistant in optimization for first-year engineering students.
Post-graduate course, Ecole des Ponts ParisTech, 2022
Teaching assistant (course + exercises + hackathon) in operations research for second-year engineering students.
Post-graduate course, Ecole des Ponts ParisTech, 2023
Teaching assistant (course + exercises + hackathon) in operations research for second-year engineering students.
Post-graduate course, Ecole des Ponts ParisTech, 2025
Co-organizer of the KIRO2025 hackathon with my colleagues Guillaume Dalle and Leo Baty. This hackathon gathered +100 students working on an industrial routing problem at Califrais for six hours.
Undergraduate course, Ecole des Ponts ParisTech, 2025
Teaching assistant in optimization for first-year engineering students.