Application of an Off‐Policy Reinforcement Learning Algorithm for H∞${{H}_\infty }$ Control Design of Nonlinear Structural Systems With Completely Unknown Dynamics

ABSTRACT This paper proposes a model‐free and online off‐policy algorithm based on reinforcement learning (RL) for vibration attenuation of earthquake‐excited structures, through designing an optimal H∞${{H}_\infty }$ controller. This design relies on solving a two‐player zero‐sum game theory with a...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Earthquake engineering & structural dynamics Ročník 54; číslo 4; s. 1210 - 1228
Hlavní autori:	Amirmojahedi, M., Mojoodi, A., Shojaee, Saeed, Hamzehei‐Javaran, Saleh
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Bognor Regis Wiley Subscription Services, Inc 01.04.2025
Predmet:	Active damping Algorithms Civil engineering Control systems design Controllers Earthquakes Game theory H-infinity control H∞${{H}_\infty }$ control Machine learning Neural networks nonlinear building Nonlinear control Nonlinear systems online reinforcement learning Policies State feedback Strategy System dynamics two‐player zero‐sum game Vibration Zero sum games
ISSN:	0098-8847, 1096-9845
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!