no code implementations • 5 Feb 2024 • Jiaqi Liang, Sanjay Dominik Jena, Defeng Liu, Andrea Lodi
Our work offers practical insights for operators and enriches the integration of reinforcement learning into dynamic rebalancing problems, paving the way for more intelligent and robust urban mobility solutions.
no code implementations • 22 Dec 2022 • Defeng Liu, Vincent Perreault, Alain Hertz, Andrea Lodi
Then, the key of the proposed methodology is to generate promising neighbors by selecting a proper subset of variables that contains a descent of the objective in the solution space.
no code implementations • 4 Jun 2022 • Warley Almeida Silva, Federico Bobbio, Flore Caye, Defeng Liu, Justine Pepin, Carl Perreault-Lafleur, William St-Arnaud
Our Branch-and-Bound algorithm is effective on a small portion of the training data set, and it manages to find an incumbent feasible solution for an instance that we could not solve with the Diving heuristics.
1 code implementation • 3 Dec 2021 • Defeng Liu, Matteo Fischetti, Andrea Lodi
In this work, we study the relation between the size of the search neighborhood and the behavior of the underlying LB algorithm, and we devise a leaning based framework for predicting the best size for the specific instance to be solved.
no code implementations • 16 Oct 2019 • Defeng Liu, Andrea Lodi, Mathieu Tanneau
As a first building block of the learning framework, we propose an on-policy imitation learning scheme that mimics the elimination ordering provided by the (classical) minimum degree rule.