Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems

Simple item page
dc.contributor.authorGu, Fangdaen
dc.contributor.authorYin, Heen
dc.contributor.authorEl Ghaoui, Laurenten
dc.contributor.authorArcak, Muraten
dc.contributor.authorSeiler, Peteren
dc.contributor.authorJin, Mingen
dc.date.accessioned2022-02-27T00:17:34Zen
dc.date.available2022-02-27T00:17:34Zen
dc.date.issued2022en
dc.date.updated2022-02-27T00:17:30Zen
dc.description.abstractNeural network controllers have become popular in control tasks thanks to their flexibility and expressivity. Stability is a crucial property for safety-critical dynamical systems, while stabilization of partially observed systems, in many cases, requires controllers to retain and process long-term memories of the past. We consider the important class of recurrent neural networks (RNN) as dynamic controllers for nonlinear uncertain partially-observed systems, and derive convex stability conditions based on integral quadratic constraints, S-lemma and sequential convexification. To ensure stability during the learning and control process, we propose a projected policy gradient method that iteratively enforces the stability conditions in the reparametrized space taking advantage of mild additional information on system dynamics. Numerical experiments show that our method learns stabilizing controllers while using fewer samples and achieving higher final performance compared with policy gradient.en
dc.description.notesYes, full paper (Peer reviewed?)en
dc.description.versionAccepted versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.orcidJin, Ming [0000-0001-7909-4545]en
dc.identifier.urihttp://hdl.handle.net/10919/108885en
dc.language.isoenen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.titleRecurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systemsen
dc.typeConference proceedingen
dc.type.dcmitypeTexten
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/Engineeringen
pubs.organisational-group/Virginia Tech/Engineering/Electrical and Computer Engineeringen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Engineering/COE T&R Facultyen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
PPG_2022.pdf
Size:
5.48 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download
Collections
All Faculty Deposits
Scholarly Works, Electrical and Computer Engineering