Revisiting Approximate Dynamic Programming and its Convergence

Value iteration-based approximate/adaptive dynamic programming (ADP) as an approximate solution to infinite-horizon optimal control problems with deterministic dynamics and continuous state and action spaces is investigated. The learning iterations are decomposed into an outer loop and an inner loop...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on cybernetics Jg. 44; H. 12; S. 2733 - 2743
1. Verfasser:	Heydari, Ali
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.12.2014 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Approximate dynamic programming Approximation Approximation methods Convergence Dynamic programming Equations Iterative methods Learning Mathematical analysis Mathematical model Mathematical models nonlinear control systems Optimal control Optimization Policies Vectors Approximate dynamic programming optimal control nonlinear control systems
ISSN:	2168-2267, 2168-2275, 2168-2275
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!