In this study, a data-driven optimisation solution for operational index control for a class of industrial processes is presented. First, the operational index control problem is formulated as an optimal tracking control problem. Then, an augmented system composed of the device loop dynamics and operational indices dynamics is constructed on two different time scales. Since, finding mathematical model of the operational indices dynamics is difficult, in contrast to most existing operational optimisation and control methods that use a mathematical model of the operational indices dynamics, a reinforcement learning algorithm based on actor-critic structure is employed to provide a data-driven optimisation control method to select optimal process setpoints so that the operational indices can track desired values. This solution does not require complete knowledge of the industrial process dynamics. Moreover, complicated system identification of the dynamics of the operational indices is not required. The effectiveness of the proposed method is demonstrated by experimental results that are carried out on a hardware-in-the-loop emulation system for a mineral grinding process.