Please use this identifier to cite or link to this item: https://scidar.kg.ac.rs/handle/123456789/13467
Full metadata record
DC FieldValueLanguage
dc.rights.licenserestrictedAccess-
dc.contributor.authorXin X.-
dc.contributor.authorTu Y.-
dc.contributor.authorStojanović, Vladimir-
dc.contributor.authorWang H.-
dc.contributor.authorShi K.-
dc.contributor.authorHe Z.-
dc.contributor.authorpan, sudip-
dc.date.accessioned2021-09-24T22:41:26Z-
dc.date.available2021-09-24T22:41:26Z-
dc.date.issued2022-
dc.identifier.issn0096-3003-
dc.identifier.urihttps://scidar.kg.ac.rs/handle/123456789/13467-
dc.description.abstractIn this paper, a novel online mode-free integral reinforcement learning algorithm is proposed to solve the multiplayer non-zero sum games. We first collect and learn the subsystems information of states and inputs; then we use the online learning to compute the corresponding N coupled algebraic Riccati equations. The policy iterative algorithm proposed in this paper can solve the coupled algebraic Riccati equations corresponding to the multiplayer non-zero sum games. Finally, the effectiveness and feasibility of the design method of this paper is proved by simulation example with three players.-
dc.rightsinfo:eu-repo/semantics/restrictedAccess-
dc.sourceApplied Mathematics and Computation-
dc.titleOnline reinforcement learning multiplayer non-zero sum games of continuous-time Markov jump linear systems-
dc.typearticle-
dc.identifier.doi10.1016/j.amc.2021.126537-
dc.identifier.scopus2-s2.0-85112302552-
Appears in Collections:Faculty of Mechanical and Civil Engineering, Kraljevo

Page views(s)

481

Downloads(s)

7

Files in This Item:
File Description SizeFormat 
PaperMissing.pdf
  Restricted Access
29.86 kBAdobe PDFThumbnail
View/Open


Items in SCIDAR are protected by copyright, with all rights reserved, unless otherwise indicated.