Summary
In this chapter, you've implemented a Q-learning solution to a business problem. You had to find the best route to a certain location in your warehouse. Not only have you done that, but you've also implemented additional code that allowed your AI to make as many intermediary stops as you wanted. Based on the obtained rewards, your AI was able to find the best route going through these stops. That was Q-learning for warehouse robots. Now, let's move on to deep Q-learning!