Show simple item record

dc.contributor.authorAugust, Moritz
dc.contributor.authorHernández-Lobato, José Miguel
dc.date.accessioned2019-01-16T00:30:44Z
dc.date.available2019-01-16T00:30:44Z
dc.date.issued2018
dc.identifier.isbn978-3-030-02465-9
dc.identifier.issn0302-9743
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/288024
dc.description.abstractIn this work we introduce the application of black-box quantum control as an interesting rein- forcement learning problem to the machine learning community. We analyze the structure of the reinforcement learning problems arising in quantum physics and argue that agents parameterized by long short-term memory (LSTM) networks trained via stochastic policy gradients yield a general method to solving them. In this context we introduce a variant of the proximal policy optimization (PPO) algorithm called the memory proximal policy optimization (MPPO) which is based on this analysis. We then show how it can be applied to specific learning tasks and present results of nu- merical experiments showing that our method achieves state-of-the-art results for several learning tasks in quantum control with discrete and continouous control parameters.
dc.publisherhttps://link.springer.com/chapter/10.1007/978-3-030-02465-9_43#aboutcontent
dc.subjectcs.LG
dc.subjectcs.LG
dc.subjectquant-ph
dc.titleTaking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control
dc.typeConference Object
prism.endingPage693
prism.publicationNameISC High Performance 2018: High Performance Computing
prism.startingPage591
prism.volumeLNCS, volume 11203
dc.identifier.doi10.17863/CAM.35343
rioxxterms.versionofrecord10.1007/978-3-030-02465-9_43
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
dc.identifier.eissn1611-3349
rioxxterms.typeConference Paper/Proceeding/Abstract
cam.issuedOnline2019-01-25
pubs.conference-nameInternational Conference on High Performance Computing 2018
pubs.conference-start-date2018-06-24
cam.orpheus.successThu Nov 05 11:53:20 GMT 2020 - Embargo updated
cam.orpheus.counter12
pubs.conference-finish-date2018-06-28
rioxxterms.freetoread.startdate2020-01-25


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record