2019 | OriginalPaper | Chapter
5. Custom OpenAI Reinforcement Learning Environments
Published in:
Applied Reinforcement Learning with Python
Abstract
For our final chapter, we will be focusing on Open AI’s gym package, but more importantly trying to understand how we can create our own custom environments so we can tackle more than the typical use cases. Most of this chapter will focus around what I would suggest regarding programming practices for Open AI as well as recommendations on how I would generally write most of this software. Finally, after we have completed creating an environment, we will move on to focusing on solving the problem. For this instance, we will focus on trying to create and solve a new video game.
