Entropy Guided Exploration

Stabilize RL training on reasoning tasks by performing entropy-guided rollouts from uncertain decision points, avoiding policy collapse and premature convergence. Increases fully correct trajectories on math reasoning while maintaining stable entropy throughout training.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 3591322ecd

Frequently asked questions

npx get-skill add adu2021/entropy-guided-exploration