A Neural-Reinforcement-Learning-Based Guaranteed Cost Control for Perturbed Tracking Systems

• Published in: IEEE transactions on artificial intelligence Vol. 5; no. 6; pp. 3205 - 3217
• Main Authors: Zhong, Xiangnan, Ni, Zhen
• Format: Journal Article
• Language: English
• Published: IEEE 01.06.2024
• Subjects: Cost function; Costs; Guaranteed cost control; Learning systems; matched and mismatched perturbations; neural networks; Perturbation methods; Reinforcement learning; Symmetric matrices; tracking control; Uncertainty

Artificial intelligence (AI)-based learning control plays a critical role in the evolution of intelligent control, particularly for complex network systems. Traditional intelligent control methods assume the agent can learn from safe data in the tasks. However, many application scenarios exist pertu...