Abstarct: In this thesis, considering the importance of output voltage control in converters, an intelligent controller is designed using Q-Learning algorithm to control the output voltage of Buck , Boost and High Step-Up converters. Q-Learning algorithm is a model-free reinforcement learning algorithm for learning the value of an action in a specific state. It does not require a model of the environment and can solve problems related to random transitions and rewards without requiring adaptation. For this purpose, the governing equations of the converters are obtained first, and by linear modeling of the converters and by converting their equations into a linear quadratic tracking problem and solving it by the Q-Learning algorithm and simulation of the converter in the MATLAB software environment, it can be seen that the simulation results with Q-Learning algorithm have a good performance on solving converter equations. To show the efficiency and performance of the Q-Learning controller, the mentioned converters are also simulated with the fuzzy controller and the results are compared with the proposed method, the Q-Learning algorithm. Comparing the simulation results of the fuzzy controller and the Q-Learning algorithm shows that the proposed method, while being resistant to load and voltage changes, has a more suitable performance in terms of control criteria such as rise time, rise time, and ripple.