Reinforcement Learning for Entanglement Swapping in Quantum Networks
Álvaro Troyano Olivas, Andrés Agustí Casado, Marco Pérez González, Javier Faba, Luis Miguel Robledo, Vicente Martín, Laura Ortíz · 2025
Current approaches for entanglement distribution networks face a largely untackled problem: precise timing and management of entanglement generation and swapping attempts is key in order to make entanglement distribution between any two nodes.To address this, we model a quantum network as two graphs, one containing the telecom fibers enabling physically the entanglement, and another containing the Bell pairs stored in its memories. Then, efficient entanglement distribution becomes a task of populating a mix of both graphs with a connection between one Alice and one Bob subject to constraints. Here, machine learning techniques are useful to find efficient policies through reinforcement learning. This way, we manage to consider inhomogeneous probabilities of generation and swapping, as well as complex networks beyond the chain scenario.