Learning Stochastic Optimal Policies via Gradient Descent

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 187
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorMassaroli, Stefanoko
dc.contributor.authorPoli, Michaelko
dc.contributor.authorPeluchetti, Stefanoko
dc.contributor.authorPark, Jinkyooko
dc.contributor.authorYamashita, Atsushiko
dc.contributor.authorAsama, Hajimeko
dc.date.accessioned2021-07-29T01:50:04Z-
dc.date.available2021-07-29T01:50:04Z-
dc.date.created2021-07-29-
dc.date.issued2022-
dc.identifier.citationIEEE CONTROL SYSTEMS LETTERS, v.6, pp.1094 - 1099-
dc.identifier.issn2475-1456-
dc.identifier.urihttp://hdl.handle.net/10203/286888-
dc.description.abstractWe systematically develop a learning-based treatment of stochastic optimal control (SOC), relying on direct optimization of parametric control policies. We propose a derivation of adjoint sensitivity results for stochastic differential equations through direct application of variational calculus. Then, given an objective function for a predetermined task specifying the desiderata for the controller, we optimize their parameters via iterative gradient descent methods. In doing so, we extend the range of applicability of classical SOC techniques, often requiring strict assumptions on the functional form of system and control. We verify the performance of the proposed approach on a continuous-time, finite horizon portfolio optimization with proportional transaction costs.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.titleLearning Stochastic Optimal Policies via Gradient Descent-
dc.typeArticle-
dc.identifier.scopusid2-s2.0-85107388968-
dc.type.rimsART-
dc.citation.volume6-
dc.citation.beginningpage1094-
dc.citation.endingpage1099-
dc.citation.publicationnameIEEE CONTROL SYSTEMS LETTERS-
dc.identifier.doi10.1109/LCSYS.2021.3086672-
dc.contributor.localauthorPark, Jinkyoo-
dc.contributor.nonIdAuthorMassaroli, Stefano-
dc.contributor.nonIdAuthorPoli, Michael-
dc.contributor.nonIdAuthorPeluchetti, Stefano-
dc.contributor.nonIdAuthorYamashita, Atsushi-
dc.contributor.nonIdAuthorAsama, Hajime-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorOptimal control-
dc.subject.keywordAuthorIndium tin oxide-
dc.subject.keywordAuthorStochastic processes-
dc.subject.keywordAuthorProcess control-
dc.subject.keywordAuthorOptimization-
dc.subject.keywordAuthorNeural networks-
dc.subject.keywordAuthorNoise measurement-
dc.subject.keywordAuthorOptimal control-
dc.subject.keywordAuthorstochastic processes-
dc.subject.keywordAuthormachine learning-
Appears in Collection
IE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0