Permanent magnet synchronous generator (PMSG) based wind energy conversion system (WECS) also known as Type 4-WECS has many advantages over other types of WECS. One of the advantages is full variable speed operation for low wind speed. With the MPPT control, most wind turbines try to follow optimal rotational speed for maximum possible power capture. However, due to rotor inertia, tracking loss is inevitable, which causes decreased power production. This study investigates the use of inertia in the rotational masses of the WT for increased power production. The idea is to use the rotor inertia of the large-scale wind turbine (VSWT) to temporarily retain the rotational speed at a higher value for a short time rather than following optimal rotational speed in a variable speed region. As a result, the wind turbine can capture more power. The optimal tip speed ratio (TSR) method is used as the main MPPT control method, and additional Reinforcement Learning (RL) algorithm-based reference rotational readjustment was used for the purpose mentioned above. The simulation studies have been conducted in Matlab/Simulink ® software and it showed that power production of wind turbines has increased slightly than the standard method.