GRPO
Group relative policy optimisation — a reinforcement-learning method that compares a group of sampled answers rather than learning a separate reward model.
By Lattice editorial · Entry last reviewed · method
What it implies
Useful when you have a verifiable reward, a checker or a test, rather than human preference. It sidesteps reward-model training, which is the expensive and fragile part, and is why it shows up in reasoning-model post-training.