Reinforcement Learning-Based Optimal Stabilization for Unknown Nonlinear Systems Subject to Inputs With Uncertain Constraints

• Published in: IEEE transaction on neural networks and learning systems Vol. 31; no. 10; pp. 4330 - 4340
• Main Authors: Zhao, Bo, Liu, Derong, Luo, Chaomin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Actuators; Adaptive dynamic programming (ADP); Algorithms; Artificial neural networks; Control algorithms; Control theory; Distance learning; Feedback control; Feedforward control; Feedforward systems; Learning; Machine learning; Neural networks; neural networks (NNs); Nonlinear systems; Observers; Optimal control; Reinforcement; reinforcement learning (RL); Saturation; Stability analysis; System dynamics; uncertain input constraints; unknown nonlinear systems

This article presents a novel reinforcement learning strategy that addresses an optimal stabilizing problem for unknown nonlinear systems subject to uncertain input constraints. The control algorithm is composed of two parts, i.e., online learning optimal control for the nominal system and feedforwa...