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

arXiv:2602.04417 · cs.LG, cs.AI · Submitted 2026-02-04 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-02-04

Updated: 2026-11-19

Terminology

Related papers