Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

Group-based rollout sampling

Samples a group of rollouts for each prompt, with group size configurable by data source.

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.

Filed under post-training › reinforcement learning algorithm