In this paper, we investigate some effects of errors in the initial conditions as a learning control algorithm is iteratively applied. We show that the pure error term in the learning control law can be positively utilized to improve the system performance, making it robust against varying initial conditions. For better performance in the face of variable initial conditions, we propose a method of ‘iterative learning control with multi-modal input’. In this proposed control method, an input is synthesized based on the state of initial condition. Numerical examples are given to show the effectiveness of the proposed learning control algorithm.