Glossary
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 explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: Regularization · Next term: Reinforcement learning