Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. The purpose of reinforcement learning is for the agent to learn an optimal, or nearly- optimal, policy that maximizes the ”reward function” or other user-provided reinforcement signal that accumulates from the immediate rewards. In this area are existing a lot of algorithms that can be used for different types of tasks from playing computer games till autonomous driving and robotics. This paper describes and compares some of these methods to give more understanding about them and to show if the combination of them can make learning processes more successful. All comparisons between different methods were done based on real tests that show how the agents are developing themselves during the learning process.