Chapter 3. Deep Learning with PyTorch

In the previous chapter, we became familiar with open source libraries, which provided us with a collection of RL environments. However, recent developments in RL, especially its combination with deep learning (DL), now make it possible to solve much more complex and challenging problems than before. This is partly due to the development of DL methods and tools.

This chapter is dedicated to one such tool, which makes it possible to implement complex DL models in just a bunch of lines of Python code. The chapter doesn't pretend to be a complete DL manual, as the field is very wide and dynamic. The goal is to make you familiar with the PyTorch library specifics and implementation details, assuming that you're already familiar with DL fundamentals.

Compatibility note: All of the examples in this chapter were updated for the latest PyTorch 0.4.0, which has a number of changes compared with the previous 0.3.1 release. If you're using the old PyTorch, consider upgrading. Throughout this chapter, we will discuss the differences seen in the latest version.