Multi-agent Reinforcement Learning Using Simulated Quantum Annealing

Niels M. P. Neumann; Paolo B. U. L. de Heer; Irina Chiscop; Frank Phillipson

doi:10.1007/978-3-030-50433-5_43

Multi-agent Reinforcement Learning Using Simulated Quantum Annealing

Niels M. P. Neumann^*, Paolo B. U. L. de Heer, Irina Chiscop, Frank Phillipson

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

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.

Original language	English
Title of host publication	Computational Science – ICCS 2020
Subtitle of host publication	20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part VI
Editors	Valeria V. Krzhizhanovskaya, Gábor Závodszky, Michael H. Lees, Jack J. Dongarra, Peter M.A. Sloot, Sérgio Brissos, Joao Teixeira
Publisher	Springer, Cham
Pages	562-575
Number of pages	14
ISBN (Electronic)	978-3-030-50433-5
ISBN (Print)	978-3-030-50432-8
DOIs	https://doi.org/10.1007/978-3-030-50433-5_43
Publication status	Published - 2020
Externally published	Yes

Publication series

Series	Lecture Notes in Computer Science
Volume	12142
ISSN	0302-9743

Keywords

multi-agent
reinforcement learning
quantum computing
d-wave
quantum annealing

Access to Document

10.1007/978-3-030-50433-5_43

Cite this

Neumann, N. M. P., Heer, P. B. U. L. D., Chiscop, I., & Phillipson, F. (2020). Multi-agent Reinforcement Learning Using Simulated Quantum Annealing. In V. V. Krzhizhanovskaya, G. Závodszky, M. H. Lees, J. J. Dongarra, P. M. A. Sloot, S. Brissos, & J. Teixeira (Eds.), Computational Science – ICCS 2020 : 20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part VI (pp. 562-575). Springer, Cham. https://doi.org/10.1007/978-3-030-50433-5_43

Neumann, Niels M. P. ; Heer, Paolo B. U. L. de ; Chiscop, Irina et al. / Multi-agent Reinforcement Learning Using Simulated Quantum Annealing. Computational Science – ICCS 2020 : 20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part VI. editor / Valeria V. Krzhizhanovskaya ; Gábor Závodszky ; Michael H. Lees ; Jack J. Dongarra ; Peter M.A. Sloot ; Sérgio Brissos ; Joao Teixeira. Springer, Cham, 2020. pp. 562-575 (Lecture Notes in Computer Science, Vol. 12142).

@inproceedings{99c1ef80881049cfb10ce67a767a17bf,

title = "Multi-agent Reinforcement Learning Using Simulated Quantum Annealing",

abstract = "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.",

keywords = "multi-agent, reinforcement learning, quantum computing, d-wave, quantum annealing",

author = "Neumann, {Niels M. P.} and Heer, {Paolo B. U. L. de} and Irina Chiscop and Frank Phillipson",

note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2020",

doi = "10.1007/978-3-030-50433-5_43",

language = "English",

isbn = "978-3-030-50432-8",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Cham",

pages = "562--575",

editor = "Krzhizhanovskaya, {Valeria V.} and G{\'a}bor Z{\'a}vodszky and Lees, {Michael H.} and Dongarra, {Jack J.} and Sloot, {Peter M.A. } and S{\'e}rgio Brissos and Joao Teixeira",

booktitle = "Computational Science – ICCS 2020",

address = "Switzerland",

}

Neumann, NMP, Heer, PBULD, Chiscop, I & Phillipson, F 2020, Multi-agent Reinforcement Learning Using Simulated Quantum Annealing. in VV Krzhizhanovskaya, G Závodszky, MH Lees, JJ Dongarra, PMA Sloot, S Brissos & J Teixeira (eds), Computational Science – ICCS 2020 : 20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part VI. Springer, Cham, Lecture Notes in Computer Science, vol. 12142, pp. 562-575. https://doi.org/10.1007/978-3-030-50433-5_43

Multi-agent Reinforcement Learning Using Simulated Quantum Annealing. / Neumann, Niels M. P.; Heer, Paolo B. U. L. de; Chiscop, Irina et al.
Computational Science – ICCS 2020 : 20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part VI. ed. / Valeria V. Krzhizhanovskaya; Gábor Závodszky; Michael H. Lees; Jack J. Dongarra; Peter M.A. Sloot; Sérgio Brissos; Joao Teixeira. Springer, Cham, 2020. p. 562-575 (Lecture Notes in Computer Science, Vol. 12142).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Multi-agent Reinforcement Learning Using Simulated Quantum Annealing

AU - Neumann, Niels M. P.

AU - Heer, Paolo B. U. L. de

AU - Chiscop, Irina

AU - Phillipson, Frank

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

KW - multi-agent

KW - reinforcement learning

KW - quantum computing

KW - d-wave

KW - quantum annealing

U2 - 10.1007/978-3-030-50433-5_43

DO - 10.1007/978-3-030-50433-5_43

M3 - Conference article in proceeding

SN - 978-3-030-50432-8

T3 - Lecture Notes in Computer Science

SP - 562

EP - 575

BT - Computational Science – ICCS 2020

A2 - Krzhizhanovskaya, Valeria V.

A2 - Závodszky, Gábor

A2 - Lees, Michael H.

A2 - Dongarra, Jack J.

A2 - Sloot, Peter M.A.

A2 - Brissos, Sérgio

A2 - Teixeira, Joao

PB - Springer, Cham

ER -

Neumann NMP, Heer PBULD, Chiscop I, Phillipson F. Multi-agent Reinforcement Learning Using Simulated Quantum Annealing. In Krzhizhanovskaya VV, Závodszky G, Lees MH, Dongarra JJ, Sloot PMA, Brissos S, Teixeira J, editors, Computational Science – ICCS 2020 : 20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part VI. Springer, Cham. 2020. p. 562-575. (Lecture Notes in Computer Science, Vol. 12142). doi: 10.1007/978-3-030-50433-5_43