Adaptive Dynamic Programming: Solltrajektorienfolgeregelung und Konvergenzbedingungen

In this work, discrete-time and continuous-time methods that integrate flexible reference trajectory representations into Adaptive Dynamic Programming approaches are presented and analyzed for the first time. Moreover, theoretical conditions on the system state are derived that ensure the persistent...

Volledige beschrijving

Bibliografische gegevens

Hoofdauteur:	Köpf, Florian
Formaat:	Online
Taal:	Duits
Gepubliceerd in:	KIT Scientific Publishing 2022
Onderwerpen:	Adaptive Dynamic Programming (ADP); Reinforcement Learning (RL); Persistent Excitation (PE); adaptive Optimalregelung; lernende Regler; KI; Adaptive Optimal Control; Learning-Based Control; AI thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
Online toegang:	OCN: 1367234043
Tags:	Voeg label toe Geen labels, Wees de eerste die dit record labelt!