Adaptive Entanglement Routing with Deep Q-Networks in Quantum Networks
Lamarana Jallow, Majid Iqbal Khan
TL;DR
Entanglement routing in quantum networks faces stringent fidelity requirements and finite qubit resources. This work presents QuDQN, a reinforcement learning–based adaptive routing framework that uses a Deep Q-Network to select routes while accounting for topology, memory, and fidelity targets. Key contributions include a fidelity-aware reward design, a masked, Q-value-guided path selection mechanism, and stabilization via a target network, with extensive simulations showing superior performance over baselines and state-of-the-art methods. The results demonstrate strong scalability and resource efficiency, supporting practical deployment of quantum networks under dynamic demands.
Abstract
The quantum internet holds transformative potential for global communication by harnessing the principles of quantum information processing. Despite significant advancements in quantum communication technologies, the efficient distribution of critical resources, such as qubits, remains a persistent and unresolved challenge. Conventional approaches often fall short of achieving optimal resource allocation, underscoring the necessity for more effective solutions. This study proposes a novel reinforcement learning-based adaptive entanglement routing framework designed to enable resource allocation tailored to the specific demands of quantum applications. The introduced QuDQN model utilizes reinforcement learning to optimize the management of quantum networks, allocate resources efficiently, and enhance entanglement routing. The model integrates key considerations, including fidelity requirements, network topology, qubit capacity, and request demands.