In this issue:

• we explain what Q-Learning models are; 

• we explore how Google SEED RL architecture enables highly scalable RL tasks; 

• we discuss Facebook’s ReAgent that is used for building reinforcement learning systems. 

Give a gift subscription

💡 ML Concept of the Day: What is Q-Learning?

Continuing our series in reinforcement learning (RL), today we would like to explore one o…