EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL

A starting point.

Selected research in efficient ai. Read the full paper, including the methods, experiments, and reported results.

This work is included in a researcher’s reading path. A detailed editorial explanation is still being prepared. The complete manuscript is available in Full paper.

Source: EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL. The original manuscript contains the methods, experiments, figures, and references. An arXiv posting date may follow an earlier conference publication. Read the linked record for version history.