Reinforcement-Learning-Based Robust Controller Design for Continuous-Time Uncertain Nonlinear Systems Subject to Input Constraints

• Published in: IEEE transactions on cybernetics Vol. 45; no. 7; pp. 1372 - 1385
• Main Authors: Liu, Derong, Yang, Xiong, Wang, Ding, Wei, Qinglai
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2015
• Subjects: Algorithm design and analysis; Approximate dynamic programming (ADP); Approximation algorithms; Artificial neural networks; neural networks (NNs); neuro-dynamic programming; Nonlinear systems; Optimal control; reinforcement learning (RL); Robust control; Robustness; nonlinear systems; neural networks (NNs); Approximate dynamic programming (ADP); optimal control; robust control; neuro-dynamic programming; reinforcement learning (RL)

The design of stabilizing controller for uncertain nonlinear systems with control constraints is a challenging problem. The constrained-input coupled with the inability to identify accurately the uncertainties motivates the design of stabilizing controller based on reinforcement-learning (RL) method...