DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wong, Wee Chin | ko |
dc.contributor.author | Lee, JayHyung | ko |
dc.date.accessioned | 2013-03-12T03:21:41Z | - |
dc.date.available | 2013-03-12T03:21:41Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2010 | - |
dc.identifier.citation | OPTIMAL CONTROL APPLICATIONS METHODS, v.31, no.4, pp.365 - 374 | - |
dc.identifier.issn | 0143-2087 | - |
dc.identifier.uri | http://hdl.handle.net/10203/101192 | - |
dc.description.abstract | Reinforcement learning where decision-making agents learn optimal policies through environmental interactions is an attractive paradigm for model-free, adaptive controller design. However, results for systems with continuous state and action variables are rare. In this paper, we present convergence results for optimal linear quadratic control of discrete-time linear stochastic systems. This work can be viewed as a generalization of a previous work on deterministic linear systems. Key differences between the algorithms for deterministic and stochastic systems are highlighted through examples. The usefulness of the algorithm is demonstrated through a nonlinear chemostat bioreactor case study Copyright (C) 2009 John Wiley & Sons, Ltd. | - |
dc.language | English | - |
dc.publisher | JOHN WILEY SONS LTD | - |
dc.subject | IDENTIFICATION | - |
dc.title | A reinforcement learning-based scheme for direct adaptive optimal control of linear stochastic systems | - |
dc.type | Article | - |
dc.identifier.wosid | 000280687600006 | - |
dc.identifier.scopusid | 2-s2.0-77955678039 | - |
dc.type.rims | ART | - |
dc.citation.volume | 31 | - |
dc.citation.issue | 4 | - |
dc.citation.beginningpage | 365 | - |
dc.citation.endingpage | 374 | - |
dc.citation.publicationname | OPTIMAL CONTROL APPLICATIONS METHODS | - |
dc.identifier.doi | 10.1002/oca.915 | - |
dc.contributor.localauthor | Lee, JayHyung | - |
dc.contributor.nonIdAuthor | Wong, Wee Chin | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | reinforcement learning | - |
dc.subject.keywordAuthor | linear systems | - |
dc.subject.keywordAuthor | stochastic adaptive optimal control | - |
dc.subject.keywordPlus | IDENTIFICATION | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.