This paper details the application of an online-learning algorithm to complement a baseline controller and improve the stabilization of a tilt-rotor VTOL UAV. The algorithm's structure and its response to various reference trajectories are presented, along with a discussion on parameter tuning and its associated effect. The online-learning algorithm enables the system to adapt to changes in the UAV's dynamics and external disturbances. Hardware in the loop (HIL) simulations were conducted to evaluate the algorithm's effectiveness in improving the stabilization of the UAV. The results demonstrate the importance of careful parameter selection and adjustment in optimizing the algorithm's performance.