With the current energy crisis, the study of different ways to reduce energy consumption has become a crucial topic in research. In many applications and, specifically, in the field of aeronautics, drag reduction has been studied in depth with different techniques such as active flow control. On the other hand, the increase of computational power has allowed in the recent years the use of machine learning algorithms to be applied in problems related with fluid mechanics. This is a perfect combination which is being exploit in different active flow control problems, for example [1, 2], where they applied deep reinforcement learning (DRL) techniques to obtain proper control strategies to reduce drag. We divide our work in two independent cases: two-dimensional wings and a turbulent boundary layer (TBL). The way the control is applied is the same in both problems: some jet actuators are placed in the boundaries of the problem in order to interfere with the incoming flow, thus influencing the wake and reducing drag. An artificial neural network is trained through a DRL agent that uses a proximal policy optimization to converge towards the most efficient control in termw of a given reward, i.e. drag or skin friction reduction. In both cases, we perform a parametric study of the Reynolds number, number of actuators and their position, and different reward functions. In the case of the airfoil, we also include different angles of attack. We analyze the different performances in terms of the percentage of drag or skin friction reduced for the case of the airfoil and TBL, respectively. Furthermore, the frequency response of the actions imposed compared with the baseline case without actuations is studied in depth. Also, a qualitative discussion of the different control strategies for each situation is detailed. [1] J. Rabault, M. Kuchta, A. Jensen, U. Réglade and N. Cerardi. Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control. Journal of Fluid Mechanics, Vol. 865, pp. 281-302, 2019. [2] T. Sonoda, Z. Liu, T. Itoh and Y. Hasegawa. Reinforcement learning of control strategies for reducing skin friction drag in a fully developed channel flow. arXiv:2206.15355, 2022.