In this chapter, our final one, we will take a look at the current and future state of deep learning (DL) and deep reinforcement learning (DRL) for games. We take an honest and candid look to see whether these technologies are ready for prime-time commercial games or whether they are just novelties. Are we poised to see DRL agents beating human players at every game imaginable a few years from now? While that remains to be seen, and things are changing quickly, the question really is this: is DL ready for your game? It likely is a question you are asking yourself at this very moment, and it is hopefully one we will answer in this chapter.

This chapter will be a mix of hands-on exercises and general discussions with unfortunately no exercises. Well, there is one big exercise, but we will get to that shortly. Here is what we will cover in this chapter:

• The Unity Obstacle Tower challenge
• Deep Learning for your game?
• Building your game
• More foundations of learning

This chapter assumes you have covered numerous exercises in this book in order to understand the context. We will refer to those sections in order to remind the reader, but please don't jump to this chapter first.