<p>This study presents an online adaptive dynamic programming-based controller for the variable-speed wind turbine system. The controller’s primary objective is to enable the wind turbine to effectively track the maximum power point under unknown and varying conditions. The control system consists of two main components: the adaptive optimal control component and the high-order disturbance observer-based adaptive control component. The adaptive optimal control component leverages an online adaptive dynamic programming technique, a reinforcement learning algorithm, to achieve optimal performance for the nonlinear system. Meanwhile, the high-order disturbance observer accurately estimates system uncertainties and external disturbances. These estimated disturbances are integrated into the adaptive control module to compensate for the system’s disturbances effectively. As a result, the system maintains optimal performance despite the presence of unknown disturbances. Additionally, the convergence of adaptive rules and the stability of the entire system are rigorously ensured through Lyapunov theory. Ultimately, comparative simulations are conducted in order to validate the merits of the proposed control method in comparison to existing works.</p>