Performance Evaluation of Direct Heuristic Dynamic Programming using Control-Theoretic Measures

Approximate dynamic programming (ADP) has been widely studied from several important perspectives: algorithm development, learning efficiency measured by success or failure statistics, convergence rate, and learning error bounds. Given that many learning benchmarks used in ADP or reinforcement learn...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of intelligent & robotic systems 2009-07, Vol.55 (2-3), p.177-201
Hauptverfasser:	Yang, Lei, Si, Jennie, Tsakalis, Konstantinos S., Rodriguez, Armando A.
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Benchmarks Control Controllers Design engineering Dynamic programming Dynamical systems Electrical Engineering Engineering Learning Mechanical Engineering Mechatronics Nonlinear dynamics Robotics Sensitivity analysis Studies
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!