Matches in SemOpenAlex for { <https://semopenalex.org/work/W3045747378> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3045747378 abstract "Computing optimal feedback controls for nonlinear systems generally requires solving Hamilton-Jacobi-Bellman (HJB) equations, which, in high dimensions, are notoriously difficult. Existing strategies often rely on specific, restrictive problem structures, or are valid only locally around some nominal trajectory. In this paper, we propose a data-driven method to approximate semi-global solutions to HJB equations for general high-dimensional nonlinear systems and compute optimal feedback controls in real-time. To accomplish this, we model solutions to HJB equations with neural networks (NNs) trained on data generated without discretizing the state space. Training is made more effective and data-efficient by leveraging the known problem structure and using the partially-trained NN to aid in further data generation. We demonstrate the effectiveness of our method by learning solutions to HJB equations for nonlinear systems of dimension up to 30 arising from the stabilization of a Burgers'-type partial differential equation. The trained NNs are then used for real-time optimal feedback control of these systems." @default.
- W3045747378 created "2020-08-03" @default.
- W3045747378 creator A5023374462 @default.
- W3045747378 creator A5069454917 @default.
- W3045747378 creator A5074368108 @default.
- W3045747378 date "2020-07-01" @default.
- W3045747378 modified "2023-09-24" @default.
- W3045747378 title "A Causality-Free Neural Network Method for High-Dimensional Hamilton-Jacobi-Bellman Equations" @default.
- W3045747378 cites W124620454 @default.
- W3045747378 cites W1490180844 @default.
- W3045747378 cites W1966419611 @default.
- W3045747378 cites W1974854353 @default.
- W3045747378 cites W1982019931 @default.
- W3045747378 cites W2010142289 @default.
- W3045747378 cites W2108984317 @default.
- W3045747378 cites W2749028154 @default.
- W3045747378 cites W2767915842 @default.
- W3045747378 cites W2803629276 @default.
- W3045747378 cites W2899283552 @default.
- W3045747378 cites W2963395620 @default.
- W3045747378 cites W2964179106 @default.
- W3045747378 cites W3098623180 @default.
- W3045747378 cites W3101159108 @default.
- W3045747378 cites W3104543508 @default.
- W3045747378 cites W4210840654 @default.
- W3045747378 doi "https://doi.org/10.23919/acc45564.2020.9147270" @default.
- W3045747378 hasPublicationYear "2020" @default.
- W3045747378 type Work @default.
- W3045747378 sameAs 3045747378 @default.
- W3045747378 citedByCount "9" @default.
- W3045747378 countsByYear W30457473782021 @default.
- W3045747378 countsByYear W30457473782022 @default.
- W3045747378 countsByYear W30457473782023 @default.
- W3045747378 crossrefType "proceedings-article" @default.
- W3045747378 hasAuthorship W3045747378A5023374462 @default.
- W3045747378 hasAuthorship W3045747378A5069454917 @default.
- W3045747378 hasAuthorship W3045747378A5074368108 @default.
- W3045747378 hasBestOaLocation W30457473782 @default.
- W3045747378 hasConcept C121332964 @default.
- W3045747378 hasConcept C126255220 @default.
- W3045747378 hasConcept C134306372 @default.
- W3045747378 hasConcept C154945302 @default.
- W3045747378 hasConcept C158622935 @default.
- W3045747378 hasConcept C196978813 @default.
- W3045747378 hasConcept C202444582 @default.
- W3045747378 hasConcept C2775924081 @default.
- W3045747378 hasConcept C28826006 @default.
- W3045747378 hasConcept C33676613 @default.
- W3045747378 hasConcept C33923547 @default.
- W3045747378 hasConcept C41008148 @default.
- W3045747378 hasConcept C47446073 @default.
- W3045747378 hasConcept C50644808 @default.
- W3045747378 hasConcept C62520636 @default.
- W3045747378 hasConcept C73000952 @default.
- W3045747378 hasConcept C91575142 @default.
- W3045747378 hasConcept C93779851 @default.
- W3045747378 hasConceptScore W3045747378C121332964 @default.
- W3045747378 hasConceptScore W3045747378C126255220 @default.
- W3045747378 hasConceptScore W3045747378C134306372 @default.
- W3045747378 hasConceptScore W3045747378C154945302 @default.
- W3045747378 hasConceptScore W3045747378C158622935 @default.
- W3045747378 hasConceptScore W3045747378C196978813 @default.
- W3045747378 hasConceptScore W3045747378C202444582 @default.
- W3045747378 hasConceptScore W3045747378C2775924081 @default.
- W3045747378 hasConceptScore W3045747378C28826006 @default.
- W3045747378 hasConceptScore W3045747378C33676613 @default.
- W3045747378 hasConceptScore W3045747378C33923547 @default.
- W3045747378 hasConceptScore W3045747378C41008148 @default.
- W3045747378 hasConceptScore W3045747378C47446073 @default.
- W3045747378 hasConceptScore W3045747378C50644808 @default.
- W3045747378 hasConceptScore W3045747378C62520636 @default.
- W3045747378 hasConceptScore W3045747378C73000952 @default.
- W3045747378 hasConceptScore W3045747378C91575142 @default.
- W3045747378 hasConceptScore W3045747378C93779851 @default.
- W3045747378 hasLocation W30457473781 @default.
- W3045747378 hasLocation W30457473782 @default.
- W3045747378 hasOpenAccess W3045747378 @default.
- W3045747378 hasPrimaryLocation W30457473781 @default.
- W3045747378 hasRelatedWork W1999569317 @default.
- W3045747378 hasRelatedWork W2034288315 @default.
- W3045747378 hasRelatedWork W2088468004 @default.
- W3045747378 hasRelatedWork W2766341587 @default.
- W3045747378 hasRelatedWork W3146391492 @default.
- W3045747378 hasRelatedWork W3200204621 @default.
- W3045747378 hasRelatedWork W3202879871 @default.
- W3045747378 hasRelatedWork W4286979945 @default.
- W3045747378 hasRelatedWork W4288024825 @default.
- W3045747378 hasRelatedWork W4377134191 @default.
- W3045747378 isParatext "false" @default.
- W3045747378 isRetracted "false" @default.
- W3045747378 magId "3045747378" @default.
- W3045747378 workType "article" @default.