Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

RL for calibration with proper scoring rules

Trains calibration using reinforcement learning against proper scoring rules on resolved questions.

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