DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Donghwan | ko |
dc.date.accessioned | 2022-10-14T01:00:09Z | - |
dc.date.available | 2022-10-14T01:00:09Z | - |
dc.date.created | 2022-10-13 | - |
dc.date.created | 2022-10-13 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON AUTOMATIC CONTROL, v.67, no.10, pp.5661 - 5668 | - |
dc.identifier.issn | 0018-9286 | - |
dc.identifier.uri | http://hdl.handle.net/10203/298942 | - |
dc.description.abstract | The goal of this article is to investigate new and simple convergence analysis of dynamic programming for the linear–quadratic regulator problem of discrete-time linear time-invariant systems. In particular, bounds on errors are given in terms of both matrix inequalities and matrix norm. Under a mild assumption on the initial parameter, we prove that the Q -value iteration exponentially converges to the optimal solution. Moreover, a global asymptotic convergence is also presented. These results are then extended to the policy iteration. We prove that in contrast to the Q -value iteration, the policy iteration always converges exponentially fast. An example is given to illustrate the results. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Convergence of Dynamic Programming on the Semidefinite Cone for Discrete-Time Infinite-Horizon LQR | - |
dc.type | Article | - |
dc.identifier.wosid | 000861438100065 | - |
dc.identifier.scopusid | 2-s2.0-85132768642 | - |
dc.type.rims | ART | - |
dc.citation.volume | 67 | - |
dc.citation.issue | 10 | - |
dc.citation.beginningpage | 5661 | - |
dc.citation.endingpage | 5668 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON AUTOMATIC CONTROL | - |
dc.identifier.doi | 10.1109/TAC.2022.3181752 | - |
dc.contributor.localauthor | Lee, Donghwan | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Convergence | - |
dc.subject.keywordAuthor | dynamic programming | - |
dc.subject.keywordAuthor | linear time-invariant (LTI) system | - |
dc.subject.keywordAuthor | optimal control | - |
dc.subject.keywordAuthor | reinforcement learning | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.