Intuition

A big chunk of machine learning is mathematics and reinforcement learning is no exception. Often we can lose track of what we are actually trying to solve and lose ourselves in the definitions and proofs. This chapter is inteded to give an intuitive introduction into the topic of reinforcement learning without any rigourous proofs. We would like to elicit excitement and passion and to show that under all those calculations lie simple but powerful ideas. Still, all the knowledge learned in this chapter is going to be useful for when we start dealing with math and programming.