concept DRL in category reinforcement learning
This is an excerpt from Manning's book Grokking Deep Reinforcement Learning MEAP V14 epub.
A powerful recent approach to ML, called deep learning (DL), involves using multi-layered non-linear function approximation, typically neural networks. DL is not a separate branch of ML, so it’s not a different task than those described above. DL is a collection of techniques and methods for using neural networks to solve ML tasks, whether SL, UL, or RL. DRL is simply the use of DL to solve RL tasks.
Figure 1.3 Deep Learning is a powerful toolbox
The bottom line is that DRL is an approach to a problem. The field of AI defines the problem: Creating intelligent machines. One of the approaches to solving that problem is DRL. Throughout the book, you’ll find comparisons between RL and other ML approaches, but only in this chapter, you’ll find definitions and a historical overview of AI in general. It’s important to note that the field of RL includes the field of DRL, so while I make a distinction when necessary, when I refer to RL, remember that DRL is included.
In this book, we have surveyed a wide range of decision-making algorithms and reinforcement-learning agents; from the planning methods that you learned about in chapter 3 to the state-of-the-art deep reinforcement learning agents that we covered in the previous chapter. The focus of this book is to teach the ins-and-outs of the algorithms, and I think it does a pretty decent job at that. However, there is more to DRL than what we covered in this book, and I want you to have some direction going forward.