Hide metadata

dc.date.accessioned2021-01-28T20:36:55Z
dc.date.created2020-12-27T19:36:22Z
dc.date.issued2021
dc.identifier.citationViquerat, Jonathan Rabault, Jean Kuhnle, Alexander Ghraieb, Hassan Larcher, Aurelien Hachem, Elie . DIRECT SHAPE OPTIMIZATION THROUGH DEEP REINFORCEMENT LEARNING. Journal of Computational Physics. 2020
dc.identifier.urihttp://hdl.handle.net/10852/82695
dc.description.abstractDeep Reinforcement Learning (DRL) has recently spread into a range of domains within physics and engineering, with multiple remarkable achievements. Still, much remains to be explored before the capabilities of these methods are well understood. In this paper, we present the first application of DRL to direct shape optimization. We show that, given adequate reward, an artificial neural network trained through DRL is able to generate optimal shapes on its own, without any prior knowledge and in a constrained time. While we choose here to apply this methodology to aerodynamics, the optimization process itself is agnostic to details of the use case, and thus our work paves the way to new generic shape optimization strategies both in fluid mechanics, and more generally in any domain where a relevant reward function can be defined.
dc.languageEN
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.titleDIRECT SHAPE OPTIMIZATION THROUGH DEEP REINFORCEMENT LEARNING
dc.typeJournal article
dc.creator.authorViquerat, Jonathan
dc.creator.authorRabault, Jean
dc.creator.authorKuhnle, Alexander
dc.creator.authorGhraieb, Hassan
dc.creator.authorLarcher, Aurelien
dc.creator.authorHachem, Elie
dc.date.embargoenddate2022-12-23
cristin.unitcode185,15,13,15
cristin.unitnameMekanikk
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode2
dc.identifier.cristin1863417
dc.identifier.bibliographiccitationinfo:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Journal of Computational Physics&rft.volume=&rft.spage=&rft.date=2020
dc.identifier.jtitleJournal of Computational Physics
dc.identifier.volume428
dc.identifier.doihttps://doi.org/10.1007/s13138-020-00173-0
dc.identifier.urnURN:NBN:no-85527
dc.type.documentTidsskriftartikkel
dc.type.peerreviewedPeer reviewed
dc.source.issn0021-9991
dc.identifier.fulltextFulltext https://www.duo.uio.no/bitstream/handle/10852/82695/2/1-s2.0-S0021999120308548-main.pdf
dc.type.versionAcceptedVersion
cristin.articleid110080
dc.relation.projectNFR/280625


Files in this item

Appears in the following Collection

Hide metadata

Attribution-NonCommercial-NoDerivatives 4.0 International
This item's license is: Attribution-NonCommercial-NoDerivatives 4.0 International