# What is DDPG? Definition and meaning

An off-policy actor-critic algorithm that learns a deterministic policy over continuous action spaces.

## Definition

**DDPG**: An off-policy actor-critic algorithm that learns a deterministic policy over continuous action spaces.

In short: Deep deterministic policy gradient for continuous actions.

## When it is used

Early continuous-control problems; now mostly replaced by TD3 and SAC.

## Learn more

The full guide to **[DDPG](/tools/ddpg)** 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: [DDIM](/glossary/ddim) · Next term: [DDPM](/glossary/ddpm)
