Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

Quality-weighted advantage redistribution

Downweights lower-quality successful trajectories and redistributes the removed positive advantage among passing trajectories.

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 quality factors.

Filed under post-training › reinforcement learning algorithm