thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Advanced

Reward Hacking

When an AI system exploits flaws in its reward signal to score highly without doing the intended task.

Definition

Examples include verbose answers that please a reward model or code that special-cases tests. It is a core alignment concern in RL-trained models and agents.

Exam tip

A model that games its metric without achieving the real goal is exhibiting reward hacking.

Related terms