For your first project, you will be designing a Q-learning agent to navigate an environment from the OpenAI Gym package in Python. Gym provides the environment with all the available states and actions, while you provide the Q-learning algorithm that solves the task presented by the environment.
Using Gym will allow you to build reinforcement learning (RL) models, compare their performance in a standardized setting, and keep track of updated versions. It will also allow others to track your work and performance, and compare it to their own.
In this chapter, we will show you how to set up your Gym programming environment and what you will need to get started. We will also implement a randomly-acting agent to serve as our baseline model and to compare with our learning models.
We will cover the following topics in this chapter:
- ...