Cooper Co Optimized Policy Reward

Joint optimization of policy and reward models in LLM reinforcement learning by leveraging rule-based reward precision and dynamically constructing training pairs to prevent reward hacking and improve performance.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 3303fb5bb3

Frequently asked questions

npx get-skill add adu2021/cooper-co-optimized-policy-reward