Online learning control based on projected gradient temporal difference and advanced heuristic dynamic programming

Jian Fu, Sujuan Wei, Haibo He, Shengyong Wang. Online learning control based on projected gradient temporal difference and advanced heuristic dynamic programming. In 2014 International Joint Conference on Neural Networks, IJCNN 2014, Beijing, China, July 6-11, 2014. pages 3649-3656, IEEE, 2014. [doi]

Abstract

Abstract is missing.