Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

Group-wise policy optimization

A group-wise policy optimization algorithm for reinforcement-learning training; the evidence does not establish that it is GRPO.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reinforcement learning algorithm for the methods filed beside it.

Also called group-wise policy optimization algorithm.

Filed under post-training › reinforcement learning algorithm