Benutzer: Gast  Login
Titel:

Model-free Incremental Adaptive Dynamic Programming based Approximate Robust Optimal Regulation

Dokumenttyp:
Zeitschriftenaufsatz
Autor(en):
Li, Cong; Wang, Yongchao; Liu, Fangzhou; Liu, Qingchen; Buss, Martin
Abstract:
This article presents a new formulation for model-free robust optimal regulation of continuous-time nonlinear systems. The proposed reinforcement learning based approach, referred to as incremental adaptive dynamic programming (IADP), utilizes measured input-state data to allow the design of the approximate optimal incremental control strategy, stabilizing the controlled system incrementally under model uncertainties, environmental disturbances, and input saturation. By leveraging the time delay...     »
Stichworte:
incremental adaptive dynamic programming, reinforcement learning, robust optimal regulation, time delay estimation
Zeitschriftentitel:
International Journal of Robust and Nonlinear Control
Jahr:
2022
Band / Volume:
32
Heft / Issue:
5
Seitenangaben Beitrag:
2662-2682
Reviewed:
ja
Sprache:
en
Volltext / DOI:
doi:10.1002/rnc.5964
WWW:
https://onlinelibrary.wiley.com/doi/abs/10.1002/rnc.5964
Semester:
WS 21-22
 BibTeX