Multi-agent Reinforcement Learning Using Simulated Quantum Annealing

With quantum computers still under heavy development, already numerous quantum machine learning algorithms have been proposed for both gate-based quantum computers and quantum annealers. Recently, a quantum annealing version of a reinforcement learning algorithm for grid-traversal using one agent wa...

Descripción completa

Detalles Bibliográficos
Autores principales: Neumann, Niels M. P., de Heer, Paolo B. U. L., Chiscop, Irina, Phillipson, Frank
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7304685/
http://dx.doi.org/10.1007/978-3-030-50433-5_43
_version_ 1783548304496263168
author Neumann, Niels M. P.
de Heer, Paolo B. U. L.
Chiscop, Irina
Phillipson, Frank
author_facet Neumann, Niels M. P.
de Heer, Paolo B. U. L.
Chiscop, Irina
Phillipson, Frank
author_sort Neumann, Niels M. P.
collection PubMed
description With quantum computers still under heavy development, already numerous quantum machine learning algorithms have been proposed for both gate-based quantum computers and quantum annealers. Recently, a quantum annealing version of a reinforcement learning algorithm for grid-traversal using one agent was published. We extend this work based on quantum Boltzmann machines, by allowing for any number of agents. We show that the use of quantum annealing can improve the learning compared to classical methods. We do this both by means of actual quantum hardware and by simulated quantum annealing.
format Online
Article
Text
id pubmed-7304685
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-73046852020-06-22 Multi-agent Reinforcement Learning Using Simulated Quantum Annealing Neumann, Niels M. P. de Heer, Paolo B. U. L. Chiscop, Irina Phillipson, Frank Computational Science – ICCS 2020 Article With quantum computers still under heavy development, already numerous quantum machine learning algorithms have been proposed for both gate-based quantum computers and quantum annealers. Recently, a quantum annealing version of a reinforcement learning algorithm for grid-traversal using one agent was published. We extend this work based on quantum Boltzmann machines, by allowing for any number of agents. We show that the use of quantum annealing can improve the learning compared to classical methods. We do this both by means of actual quantum hardware and by simulated quantum annealing. 2020-05-25 /pmc/articles/PMC7304685/ http://dx.doi.org/10.1007/978-3-030-50433-5_43 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Neumann, Niels M. P.
de Heer, Paolo B. U. L.
Chiscop, Irina
Phillipson, Frank
Multi-agent Reinforcement Learning Using Simulated Quantum Annealing
title Multi-agent Reinforcement Learning Using Simulated Quantum Annealing
title_full Multi-agent Reinforcement Learning Using Simulated Quantum Annealing
title_fullStr Multi-agent Reinforcement Learning Using Simulated Quantum Annealing
title_full_unstemmed Multi-agent Reinforcement Learning Using Simulated Quantum Annealing
title_short Multi-agent Reinforcement Learning Using Simulated Quantum Annealing
title_sort multi-agent reinforcement learning using simulated quantum annealing
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7304685/
http://dx.doi.org/10.1007/978-3-030-50433-5_43
work_keys_str_mv AT neumannnielsmp multiagentreinforcementlearningusingsimulatedquantumannealing
AT deheerpaolobul multiagentreinforcementlearningusingsimulatedquantumannealing
AT chiscopirina multiagentreinforcementlearningusingsimulatedquantumannealing
AT phillipsonfrank multiagentreinforcementlearningusingsimulatedquantumannealing

Ejemplares similares