AI Glossary Term

What is Reward Model?

Definition

A model that scores outputs based on preference signals, often used in RLHF pipelines.

Related terms

Reinforcement Learning from Human Feedback (RLHF)

A training method that uses human preference signals to shape model behavior.

Reinforcement Learning

Training by reward signals where an agent learns actions that maximize long-term return.

Trusted reference labels used to train or evaluate model outputs.

DPO (Direct Preference Optimization)

A training method that fine-tunes models directly on preference pairs without needing a separate reward model.

An intermediate training phase between pretraining and post-training, often used for capability or domain adjustments.

A software system that can observe, reason, and take actions to achieve a goal, often using tools and memory.

Learn more in our free guides

AI Models Explained Model Collapse Model Lifecycle Model Context Protocol

Browse the full AI Glossary Explore all free AI guides