Reward functions for reinforcement learning
Functions and rubrics that score a model's answers to train it with reinforcement learning.
Nobody has published here yet. Why not you?
What is a reward function?
A reward function scores a model's answer during reinforcement learning: the model learns to produce the answers that get the best score. It can be verifiable (code that checks a result), a rubric or the instructions for a judge model.
Guide: Rewards (RL) →