The unknown multi-motor driven load systems are addressed in this paper with game theory and adaptive dynamic programming. The neural network (NN) is used to approximate the unknown dynamics. Based on the approximated dynamics, define the optimal performance index and design the optimal tracking controls. The adaptive dynamic programming based tracking controls are divided as steady-state controls and optimal feedback controls. Steady-state controls can be obtained with the

tracking commands and load dynamics directly. The optimal feedback controls are obtained with an approximate dynamic programming algorithm, which can research the saddle point and make the performance index be minimized. The convergence of the NN weights is analyzed, and the stability of the load system is proved. Finally, a simulation is provided to illustrate the effectiveness of the methods, which can optimize the load performance.