Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

GRPO with masked importance sampling

Combines GRPO with masked importance sampling to account for differences between training and rollout policies.

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