zbMATH — the first resource for mathematics

Neural network-based adaptive optimal controller – a continuous-time formulation. (English) Zbl 1155.49033
Huang, De-Shuang (ed.) et al., Advanced intelligent computing theories and applications. With aspects of contemporary intelligent computing techniques. 4th international conference on intelligent computing, ICIC 2008 Shanghai, China, September 15–18, 2008. Proceedings. Berlin: Springer (ISBN 978-3-540-85929-1/pbk). Communications in Computer and Information Science 15, 276-285 (2008).
Summary: We present a new online adaptive control scheme, for partially unknown nonlinear systems, which converges to the optimal state-feedback control solution for affine in the input nonlinear systems. The main features of the algorithm map on the characteristics of the rewards-based decision making process in the mammal brain.
The derivation of the optimal adaptive control algorithm is presented in a continuous-time framework. The optimal control solution will be obtained in a direct fashion, without system identification. The algorithm is an online approach to policy iterations based on an adaptive critic structure to find an approximate solution to the state feedback, infinite-horizon, optimal control problem.
For the entire collection see [Zbl 1148.68003].

49N90 Applications of optimal control and differential games
90C39 Dynamic programming
93C40 Adaptive control/observation systems
92B20 Neural networks for/in biological studies, artificial life and related topics