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 Model

A model trained to score outputs according to human or AI preferences, used to guide RL fine-tuning.

Definition

Reward models are trained on pairwise comparisons of responses and output a scalar score. Their flaws can be exploited by the policy, a form of reward hacking.

Exam tip

In RLHF the reward model is trained on human preference comparisons, not on labeled correct answers.

Related terms