Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Conference on Quantum Communications, Networking, and Computing (QCNC)

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

Published Mar 31, 2025• 3 citations
Publisher

Abstract

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.

DOI
10.1109/qcnc64685.2025.00051

Related papers

Quantum Virtual Link Generation via Reinforcement Learning

Ramón Aparicio-Pardo, Antoine Cousson, Redha A. Alliche

Quantum networks make use of the quantum entanglement as building block. When two qubits are entangled, their state changes exhibit non-classical correlations used to design new applications not possible with classical communication, such us quantum key distribution or distributed quantum computation. Unfortunately, quantum entanglement is a probabilistic process strongly dependent on the features of involved devices (optical fibers, lasers, quantum memories, …). The management decisions (i.e., the control policy) to set up and keep the entanglement as long as possible with the highest quality constitutes a stochastic control problem. This process can be modelled as Markov Decision Process (MDP) and solved via the Reinforcement Learning (RL) framework (a form of Machine Learning). In this work, we apply this RL framework to learn an entanglement management policy outperforming the State-of-the-Art policy when models characterising precisely the involved quantum devices are not known.

International Conference on Transparent Optical Networks•Jul 2, 2023•0 citations

A Reinforcement Learning Model for Quantum Network Data Aggregation and Analysis

Quantum Entanglement and Quantum swapping are major research areas nowadays.Remote quantum entanglement is used in many applications like secure communication, secret sharing, data aggregation, and precision sensing.In data aggregation applications, every sensor node captures data and communicates to the central node.Efficient Data aggregation depends on whether the local information or global quantum network information is used for constructing the aggregation schedules.In addition, Quantum networks suffer from lossy optical links and with limited resources such as quantum memories, edge capacities.Computation of optimal schedules deals with large quantities of data and complex time-consuming calculations.However, the quantum memories cannot hold the qubits for a longer time as the stored qubit completely decoheres an infinite amount of time.Hence, there is a necessity for finding new data aggregation scheduling protocols, which use optimal channel capacity and optimal size of memory for improving the network throughput.This paper uses a reinforcement-learning technique that considers entanglement pairing and swapping the success probability of nodes with their neighbors while finding an optimal scheduling policy.The proposed method uses local network information for constructing optimal data aggregation schedules by prior sharing the maximally entangled qubit pairs between the nodes through optimal usage of the processes, channel capacity, and memory at the intermediate nodes.Experiments show that our proposed method can maximize the network throughput.

Journal of System and Management Sciences•Feb 20, 2022•5 citations

Reinforcement Learning for Entanglement Distribution in Quantum Networks

Andrés Agustí, Álvaro Troyano Olivas, Javier Faba +3 more

Distributing entanglement efficiently across quantum networks remains a major challenge, primarily due to the intricate timing and coordination required for entanglement generation and swapping. Orchestrating these operations with precision is key to achieving efficient and reliable entanglement distribution while hardware performance is improved.

Workshop on Quantum Networks and Distributed Quantum Computing (QuNet)•Aug 19, 2025•0 citations

Fast and reliable entanglement distribution with quantum repeaters: Principles for improving protocols using reinforcement learning

Stav Haldar, Pratik J. Barge, Sumeet Khatri +1 more

Tomorrow's quantum technologies for communication, sensing, and distributed computing will rely on networks with entanglement shared between spatially separated nodes. The authors provide improved protocols and policies for entanglement distribution along a chain of nodes, accounting for practical limitations such as photon losses, nonideal measurements, and quantum memories with short coherence times. These policies feature dynamic, state-dependent memory cutoffs and collaboration between nodes, all of which are quantified. Nesting policies for small repeater chains yields policies for large chains that improve upon a swap-as-soon-as-possible approach, and thus pave the way to scaling up.

arXiv:2303.00777•Physical Review Applied•Feb 21, 2024•28 citations

Optimising entanglement distribution policies under classical communication constraints assisted by reinforcement learning

Jan Li, Tim J. Coopmans, Patrick Emonts +3 more

Abstract Quantum repeaters play a crucial role in the effective distribution of entanglement over long distances. The nearest-future type of quantum repeater requires two operations: entanglement generation across neighbouring repeaters and entanglement swapping to promote short-range entanglement to long-range. For many hardware setups, these actions are probabilistic, leading to longer distribution times and incurred errors. Significant efforts have been vested in finding the optimal entanglement-distribution policy, i.e. the protocol specifying when a network node needs to generate or swap entanglement, such that the expected time to distribute long-distance entanglement is minimal. This problem is even more intricate in more realistic scenarios, especially when classical communication delays are taken into account. In this work, we formulate our problem as a Markov decision problem and use reinforcement learning (RL) to optimise over centralised strategies, where one designated node instructs other nodes which actions to perform. Contrary to most RL models, ours can be readily interpreted. Additionally, we introduce and evaluate a fixed local policy, the ‘predictive swap-asap’ policy, where nodes only coordinate with nearest neighbours. Compared to the straightforward generalisation of the common swap-asap policy to the scenario with classical communication effects, the ‘wait-for-broadcast swap-asap’ policy, both of the aforementioned entanglement-delivery policies are faster at high success probabilities. Our work showcases the merit of considering policies acting with incomplete information in the realistic case when classical communication effects are significant.

arXiv:2412.06938•Machine Learning Science and Technology•Jul 11, 2025•1 citation

Entangled Resource Allocation Algorithm for Quantum Networks

Jincheng Zhang

This paper presents a novel algorithm for optimizing the allocation of entangled resources within quantum networks. The core of the approach lies in employing a reinforcement learning (RL) framework to dynamically manage and distribute entanglement, addressing the inherent challenges of maximizing utilization and enhancing quantum communication efficiency. Unlike traditional static allocation methods, the proposed RL agent learns optimal allocation strategies through iterative interaction with a simulated quantum network environment. The algorithm considers factors such as node connectivity, qubit availability, and communication delays to minimize resource wastage and improve overall network performance. The key performance indicator (KPI) is the entanglement fidelity between communicating nodes. The developed algorithm offers a promising pathway towards realizing the full potential of quantum networks by intelligently managing their most valuable asset: entanglement. The primary goal is to achieve higher fidelity entanglement distribution and improved communication rates. The effectiveness of the algorithm is evaluated through simulations, demonstrating its ability to outperform existing allocation schemes in various network topologies and operational scenarios.

•Aug 31, 2026•0 citations
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.
Quantum networks make use of the quantum entanglement as building block. When two qubits are entangled, their state changes exhibit non-classical correlations used to design new applications not possible with classical communication, such us quantum key distribution or distributed quantum computation. Unfortunately, quantum entanglement is a probabilistic process strongly dependent on the features of involved devices (optical fibers, lasers, quantum memories, …). The management decisions (i.e., the control policy) to set up and keep the entanglement as long as possible with the highest quality constitutes a stochastic control problem. This process can be modelled as Markov Decision Process (MDP) and solved via the Reinforcement Learning (RL) framework (a form of Machine Learning). In this work, we apply this RL framework to learn an entanglement management policy outperforming the State-of-the-Art policy when models characterising precisely the involved quantum devices are not known.
Quantum Entanglement and Quantum swapping are major research areas nowadays.Remote quantum entanglement is used in many applications like secure communication, secret sharing, data aggregation, and precision sensing.In data aggregation applications, every sensor node captures data and communicates to the central node.Efficient Data aggregation depends on whether the local information or global quantum network information is used for constructing the aggregation schedules.In addition, Quantum networks suffer from lossy optical links and with limited resources such as quantum memories, edge capacities.Computation of optimal schedules deals with large quantities of data and complex time-consuming calculations.However, the quantum memories cannot hold the qubits for a longer time as the stored qubit completely decoheres an infinite amount of time.Hence, there is a necessity for finding new data aggregation scheduling protocols, which use optimal channel capacity and optimal size of memory for improving the network throughput.This paper uses a reinforcement-learning technique that considers entanglement pairing and swapping the success probability of nodes with their neighbors while finding an optimal scheduling policy.The proposed method uses local network information for constructing optimal data aggregation schedules by prior sharing the maximally entangled qubit pairs between the nodes through optimal usage of the processes, channel capacity, and memory at the intermediate nodes.Experiments show that our proposed method can maximize the network throughput.
Tomorrow's quantum technologies for communication, sensing, and distributed computing will rely on networks with entanglement shared between spatially separated nodes. The authors provide improved protocols and policies for entanglement distribution along a chain of nodes, accounting for practical limitations such as photon losses, nonideal measurements, and quantum memories with short coherence times. These policies feature dynamic, state-dependent memory cutoffs and collaboration between nodes, all of which are quantified. Nesting policies for small repeater chains yields policies for large chains that improve upon a swap-as-soon-as-possible approach, and thus pave the way to scaling up.
Abstract Quantum repeaters play a crucial role in the effective distribution of entanglement over long distances. The nearest-future type of quantum repeater requires two operations: entanglement generation across neighbouring repeaters and entanglement swapping to promote short-range entanglement to long-range. For many hardware setups, these actions are probabilistic, leading to longer distribution times and incurred errors. Significant efforts have been vested in finding the optimal entanglement-distribution policy, i.e. the protocol specifying when a network node needs to generate or swap entanglement, such that the expected time to distribute long-distance entanglement is minimal. This problem is even more intricate in more realistic scenarios, especially when classical communication delays are taken into account. In this work, we formulate our problem as a Markov decision problem and use reinforcement learning (RL) to optimise over centralised strategies, where one designated node instructs other nodes which actions to perform. Contrary to most RL models, ours can be readily interpreted. Additionally, we introduce and evaluate a fixed local policy, the ‘predictive swap-asap’ policy, where nodes only coordinate with nearest neighbours. Compared to the straightforward generalisation of the common swap-asap policy to the scenario with classical communication effects, the ‘wait-for-broadcast swap-asap’ policy, both of the aforementioned entanglement-delivery policies are faster at high success probabilities. Our work showcases the merit of considering policies acting with incomplete information in the realistic case when classical communication effects are significant.
This paper presents a novel algorithm for optimizing the allocation of entangled resources within quantum networks. The core of the approach lies in employing a reinforcement learning (RL) framework to dynamically manage and distribute entanglement, addressing the inherent challenges of maximizing utilization and enhancing quantum communication efficiency. Unlike traditional static allocation methods, the proposed RL agent learns optimal allocation strategies through iterative interaction with a simulated quantum network environment. The algorithm considers factors such as node connectivity, qubit availability, and communication delays to minimize resource wastage and improve overall network performance. The key performance indicator (KPI) is the entanglement fidelity between communicating nodes. The developed algorithm offers a promising pathway towards realizing the full potential of quantum networks by intelligently managing their most valuable asset: entanglement. The primary goal is to achieve higher fidelity entanglement distribution and improved communication rates. The effectiveness of the algorithm is evaluated through simulations, demonstrating its ability to outperform existing allocation schemes in various network topologies and operational scenarios.