works on
large language models 1meta-learning 1policy optimization 1reinforcement learning from human feedback 1reward shaping 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Meta-Learned Reward Shaping for Reinforcement Learning from Human Feedback

Yunpeng Chu

The paper proposes MeRLa, a meta‑learning framework that learns task‑specific reward shaping functions to improve reinforcement learning from human feedback for large language mode…