What is Reinforcement Learning?

What You'll Learn

Define reinforcement learning and distinguish it from supervised and unsupervised learning
Understand the core idea: learning from interaction and consequences
See real-world examples of RL in action, from games to LLMs
Know the key milestones in RL’s history

Chapter Overview

Every time you teach a dog a trick, you’re doing reinforcement learning. Every time you learn which route to work avoids traffic, you’re doing reinforcement learning. It’s perhaps the most natural form of learning—and also one of the most powerful approaches in artificial intelligence.

In this chapter, we’ll explore what makes RL unique, see it in action across many domains, and trace its journey from theoretical foundations to powering today’s most impressive AI systems.

In this chapter:

The Core Idea

Learning from interaction: how RL differs from supervised and unsupervised learning

RL in the Wild

Real-world examples from everyday decisions to LLMs and game-playing AI

A Brief History

From Bellman to ChatGPT: the milestones that shaped reinforcement learning

💡Start Here

New to RL? Begin with The Core Idea to understand what makes reinforcement learning unique, then continue through the sections in order.

Next ChapterThe RL Framework→