Asymptotic dynamic programming: preliminary concepts and results
Richard E. Saeks, Chadwick J. Cox, Karl Mathia, Alianna J. Maren · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
A formal setting for the development of adaptive critic techniques is established in a nonlinear dynamical systems setting and some preliminary stability and suboptimality theorems are developed. Two alternative versions of the theory are developed, one with a known plant and one with an initial unknown plant which must be identified online.