A new learning control based on the Lyapunov direct method

This paper illustrates a new learning control design using Lyapunov direct method. It has been shown that under the proposed learning control a class of nonlinear systems is always guaranteed to be be asymptotically stable with respect to the number of trials. The proposed control is also robust in the sense that the exact knowledge of the nonlinear dynamics is not required except for bounding functions on the magnitude.