State-of-the-Art Deep Learning Models in TensorFlow: Modern Machine Learning in the Google Colab Ecosystem

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2021

D. PaperState-of-the-Art Deep Learning Models in TensorFlowhttps://doi.org/10.1007/978-1-4842-7341-8_14

14. An Introduction to Reinforcement Learning

David Paper¹  

(1)

Logan, UT, USA

 

Reinforcement learning (RL) is an area of machine learning that focuses on teaching intelligent agents how to take actions in an environment in order to maximize cumulative reward. Cumulative reward in RL is the sum of all rewards as a function of the number of training steps.

We train machine learning (ML) models by using rewards and punishments. When an agent makes a correct decision, we reward it with a positive point. With a wrong decision, we punish it with a negative point. ...