Quantum Computing promises to solve computational problems much faster than any classical computer, also unlocking solutions to challenges which can not be approached with classical processors in any useful amount of time. In this thesis we want to combine the power of reinforcement learning with quantum computing: the goal is to train an agent to design a quantum circuit which transforms an initial state vector associated to a quantum system into a target state of interest. We proceed by introducing the principles of Reinforcement Learning, Quantum Mechanics and Quantum Computation. Then, we provide a detailed description of the algorithm constructed and the results obtained.