We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Reinforcement learning event-triggered output feedback control for uncertain nonlinear discrete systems.
- Authors
Ren, Jianwei; Li, Ping; Song, Zhibao
- Abstract
In this paper, a novel reinforcement learning (RL)-based event-triggered (ET) output feedback control algorithm is proposed for a class of uncertain strict-feedback nonlinear discrete-time systems. In contrast to traditional RL-based control methods, we proposed an ET output feedback controller based on the backstepping technique, where the transmission cost can be efficiently conserved. Then, in light of the radial basis function (RBF) neural network (NN), various critic NNs are constructed to approximate the critic functions in each step. Furthermore, with the backing of the proposed ET mechanism, a sampled output feedback controller is addressed to guarantee that the tracking errors and all signals of the closed-loop system are semi-global uniformly ultimately bounded (SGUUB). Finally, a simulation example is presented to demonstrate the effectiveness of the control strategy.
- Subjects
ADAPTIVE control systems; DISCRETE systems; REINFORCEMENT learning; NONLINEAR systems; BACKSTEPPING control method; RADIAL basis functions; PSYCHOLOGICAL feedback
- Publication
Transactions of the Institute of Measurement & Control, 2024, Vol 46, Issue 8, p1467
- ISSN
0142-3312
- Publication type
Article
- DOI
10.1177/01423312231196639