Deep Reinforcement Learning for Optimizing Quantum-Memory Based Quantum-Repeaters

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: Rath, Anshul, Chaphekar, Atharva, Kohli, Raghav
Format: Recurso digital
Language:English
Published: Zenodo 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901692545499136
author Rath, Anshul
Chaphekar, Atharva
Kohli, Raghav
author_facet Rath, Anshul
Chaphekar, Atharva
Kohli, Raghav
contents <p dir="auto">This repository implements a memory-based quantum repeater as a Gymnasium environment formulated as a Markov decision process. A deep reinforcement learning agent based on the Proximal Policy Optimization (PPO) algorithm is trained to dynamically control memory discard and entanglement swapping decisions. The learned policies are evaluated based on their ability to optimize the secret key rate in quantum key distribution tasks and are compared against static memory cutoff baseline strategies.</p> <p dir="auto">This work is inspired by the reinforcement learning agents developed in the repository: <a href="https://github.com/SimonReiss/Master-Thesis">https://github.com/SimonReiss/Master-Thesis</a> and the method outlined in the paper: <a href="https://doi.org/10.1103/PhysRevA.108.012406" rel="nofollow">https://doi.org/10.1103/PhysRevA.108.012406</a></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18249278
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Deep Reinforcement Learning for Optimizing Quantum-Memory Based Quantum-Repeaters
Rath, Anshul
Chaphekar, Atharva
Kohli, Raghav
Quantum Computing
<p dir="auto">This repository implements a memory-based quantum repeater as a Gymnasium environment formulated as a Markov decision process. A deep reinforcement learning agent based on the Proximal Policy Optimization (PPO) algorithm is trained to dynamically control memory discard and entanglement swapping decisions. The learned policies are evaluated based on their ability to optimize the secret key rate in quantum key distribution tasks and are compared against static memory cutoff baseline strategies.</p> <p dir="auto">This work is inspired by the reinforcement learning agents developed in the repository: <a href="https://github.com/SimonReiss/Master-Thesis">https://github.com/SimonReiss/Master-Thesis</a> and the method outlined in the paper: <a href="https://doi.org/10.1103/PhysRevA.108.012406" rel="nofollow">https://doi.org/10.1103/PhysRevA.108.012406</a></p>
title Deep Reinforcement Learning for Optimizing Quantum-Memory Based Quantum-Repeaters
topic Quantum Computing
url https://doi.org/10.5281/zenodo.18249278