← Back
ModelsAdvanced1950s

Reinforcement Learning

RL

Reinforcement learning teaches an AI through rewards and penalties as it tries different actions.

Explained simply

Reinforcement learning teaches an AI through rewards and penalties as it tries different actions.

1Take action
2Receive reward
3Update strategy
4Improve

At a glance

Category
Models
Difficulty
Advanced
Introduced
1950s

Real example

A game-playing AI receives a reward for winning and gradually learns better moves.

Why it matters

It gives you a clear way to understand where this idea fits in AI and how it affects the tools you use.

Timeline

Origins

The ideas behind Reinforcement Learning begin developing.

1950s

Reinforcement Learning becomes a recognised term or technique.

Wider use

Research and practical applications increase.

Modern AI

Reinforcement Learning becomes connected to newer AI systems and products.

Today

Reinforcement Learning remains relevant in the models area of AI.

Dates for broad concepts may describe the period when the idea emerged or became widely used, rather than one exact invention date.

Learn next

Simple infographic

A quick visual way to understand Reinforcement Learning.

1Take action
2Receive reward
3Update strategy
4Improve
1 of 6

Was this helpful?

Your feedback helps improve this explanation.