The program was build with the intention to learn about the fundamentals of reinforcement learning. The point is to learn how to most efficiently take a client from point A to point B. The main idea behind reinforcement learning is trial and error, the agent interacts with the environment and based on how it accomplished a task, it will get a reward. The objective is to maximize the expected reward by playing over and over again and learning the most optimal way.The central function in Q-learning is a Q function. Basically, it is a sum of expected rewards over time.