This chapter provides the theoretical background of the most prominent algorithms used throughout this book. First, the idea of reinforcement learning (RL) will be presented, followed by an introduction to Markov decision processes, which form the basis of each RL algorithm. Then, two RL algorithms, called Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), will be presented. TRPO provides the theory behind PPO, which is used for the placement task. This is followed by the description of a simulated annealing algorithm, which is used besides the PPO algorithm, for solving the placement task. At the end of this chapter, an introduction to the A* algorithm will be presented, which is needed for the routing task.