Discretizing the Continues Features in Reinforcement Learning

How to convert infinite variables to a discrete space using tile coding and Python

Photo by Ehud Neuhaus on Unsplash

This article is a continuation of the Reinforcement Learning series. To recap, visit these articles:

First Steps in the World Of Reinforcement Learning using Python

Temporal Differences with Python — First Sample-Based Reinforcement Learning Algorithm

The Values of Actions in Reinforcement Learning using Q-learning

The last article about Q-Learning explored the concept of assigning a number to a state action pair:

The states used were states that can be listed and written into a table. For example, we indexed all the available positions in a maze that our agent can be in. Even in a…