elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Experimental quantum speed-up in reinforcement learning agents

Saggio, V. and Asenbeck, B. E. and Hamann, A. and Strömberg, T. and Schiansky, P. and Dunjko, V. and Friis, N. and Harris, N. C. and Hochberg, M. and Englund, D. and Wölk, Sabine Esther and Briegel, H. J. and Walther, P. (2021) Experimental quantum speed-up in reinforcement learning agents. Nature, 591 (7849), pp. 229-233. Nature Publishing Group. doi: 10.1038/s41586-021-03242-7. ISSN 0028-0836.

[img] PDF - Preprint version (submitted draft)
8MB
[img] PDF - Registered users only - Published version
2MB

Official URL: http://dx.doi.org/10.1038/s41586-021-03242-7

Abstract

As the field of artificial intelligence advances, the demand for algorithms that can learn quickly and efficiently increases. An important paradigm within artificial intelligence is reinforcement learning, where decision-making entities called agents interact with environments and learn by updating their behaviour on the basis of the obtained feedback. The crucial question for practical applications is how fast agents learn. Although various studies have made use of quantum mechanics to speed up the agent's decision-making process, a reduction in learning time has not yet been demonstrated. Here we present a reinforcement learning experiment in which the learning process of an agent is sped up by using a quantum communication channel with the environment. We further show that combining this scenario with classical communication enables the evaluation of this improvement and allows optimal control of the learning progress. We implement this learning protocol on a compact and fully tunable integrated nanophotonic processor. The device interfaces with telecommunication-wavelength photons and features a fast active-feedback mechanism, demonstrating the agent's systematic quantum advantage in a setup that could readily be integrated within future large-scale quantum communication networks.

Item URL in elib:https://elib.dlr.de/141373/
Document Type:Article
Title:Experimental quantum speed-up in reinforcement learning agents
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Saggio, V.UNSPECIFIEDUNSPECIFIED
Asenbeck, B. E.UNSPECIFIEDUNSPECIFIED
Hamann, A.UNSPECIFIEDUNSPECIFIED
Strömberg, T.UNSPECIFIEDUNSPECIFIED
Schiansky, P.UNSPECIFIEDUNSPECIFIED
Dunjko, V.UNSPECIFIEDUNSPECIFIED
Friis, N.UNSPECIFIEDUNSPECIFIED
Harris, N. C.UNSPECIFIEDUNSPECIFIED
Hochberg, M.UNSPECIFIEDUNSPECIFIED
Englund, D.UNSPECIFIEDUNSPECIFIED
Wölk, Sabine EstherSabine.Woelk (at) dlr.deUNSPECIFIED
Briegel, H. J.UNSPECIFIEDUNSPECIFIED
Walther, P.UNSPECIFIEDUNSPECIFIED
Date:March 2021
Journal or Publication Title:Nature
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:591
DOI :10.1038/s41586-021-03242-7
Page Range:pp. 229-233
Publisher:Nature Publishing Group
ISSN:0028-0836
Status:Published
Keywords:Quantum reinforcement learning
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:other
DLR - Research area:Raumfahrt
DLR - Program:R - no assignment
DLR - Research theme (Project):R - no assignment
Location: Ulm
Institutes and Institutions:Institute of Quantum Technologies > Theoretical Quantum Physics
Deposited By: Wölk, Sabine Esther
Deposited On:16 Mar 2021 14:45
Last Modified:16 Mar 2021 14:45

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.