Sökning: onr:"swepub:oai:DiVA.org:kth-343694" >
Optimal exploration...
Optimal exploration strategies for finite horizon regret minimization in some adaptive control problems
-
- Colin, Kevin (författare)
- KTH,Reglerteknik
-
- Hjalmarsson, Håkan, 1962- (författare)
- KTH,Reglerteknik
-
- Bombois, Xavier (författare)
- Laboratoire Ampère, UMR CNRS 5005, Ecole Centrale de Lyon, Université de Lyon, France; Centre National de la Recherche Scientifique (CNRS), France
-
(creator_code:org_t)
- Elsevier BV, 2023
- 2023
- Engelska.
-
Ingår i: 22nd IFAC World Congress Yokohama, Japan, July 9-14, 2023. - : Elsevier BV. ; , s. 2564-2569
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://kth.diva-por... (primary) (Raw object)
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- In this work, we consider the problem of regret minimization in adaptive minimum variance and linear quadratic control problems. Regret minimization has been extensively studied in the literature for both types of adaptive control problems. Most of these works give results of the optimal rate of the regret in the asymptotic regime. In the minimum variance case, the optimal asymptotic rate for the regret is log(T) which can be reached without any additional external excitation. On the contrary, for most adaptive linear quadratic problems, it is necessary to add an external excitation in order to get the optimal asymptotic rate of √T. In this paper, we will actually show from a theoretical study, as well as, in simulations that when the control horizon is pre-specified a lower regret can be obtained with either no external excitation or a new exploration type termed immediate.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
Nyckelord
- adaptive control
- linear quadratic regulator
- linear systems
- minimum variance controller
- Regret minimization
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)