Back to papers
September 3, 2026cs.LGcs.AIcs.CL

Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPO

Hyun Bin Park, Du-Seong Chang
Read on arXivDownload PDF
Categories

cs.LG, cs.AI, cs.CL

Headroom-Drift Replay: A Primitive for | One9Founders