# What is REINFORCE? Definition and meaning

A Monte Carlo policy-gradient algorithm that increases the probability of actions in proportion to the return that followed them.

## Definition

**REINFORCE**: A Monte Carlo policy-gradient algorithm that increases the probability of actions in proportion to the return that followed them.

In short: The basic policy-gradient method.

## When it is used

Teaching and baseline use, and the core idea behind many policy-optimization methods.

## Learn more

The full guide to **[REINFORCE](/tools/reinforce)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Regularization](/glossary/regularization) · Next term: [Reinforcement learning](/glossary/reinforcement-learning)
