In this long lecture we discuss what maximization bias is, when it comes to Q-Learning and how we can overcome this bias by using Double Learning. We go through a programming example to illustrate the concepts above.
You can find the code that we go through in this lecture in the link below:
github.com/JabrahTutorials/Re...
Негізгі бет Reinforcement Learning - Lecture 17 (Double Q Learning & Maximization Bias ~Programming in Python)
Пікірлер: 2