Learning to Build Solutions in Stochastic Matching Problems Using Flows (Student Abstract)

Authors

  • William St-Arnaud Université de Montréal Mila
  • Margarida Carvalho Université de Montréal
  • Golnoosh Farnadi Université de Montréal McGill University Mila

DOI:

https://doi.org/10.1609/aaai.v38i21.30515

Keywords:

Machine Learning, Markov Decision Processes, Reinforcement Learning, Applications Of AI

Abstract

Generative Flow Networks, known as GFlowNets, have been introduced in recent times, presenting an exciting possibility for neural networks to model distributions across various data structures. In this paper, we broaden their applicability to encompass scenarios where the data structures are optimal solutions of a combinatorial problem. Concretely, we propose the use of GFlowNets to learn the distribution of optimal solutions for kidney exchange problems (KEPs), a generalized form of matching problems involving cycles.

Published

2024-03-24

How to Cite

St-Arnaud, W., Carvalho, M., & Farnadi, G. (2024). Learning to Build Solutions in Stochastic Matching Problems Using Flows (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23659-23660. https://doi.org/10.1609/aaai.v38i21.30515