Deconstructing Off-Policy Ratios: Entropy-Normalized Trust Regions for Asynchronous Reinforcement Learning
Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data destabilizes optimization and can cause policy collapse. Existing methods gate tokens by ratio magnitude alone, applying one threshold at every position. We show that the ratio's natural scale is set by token entropy, so deviations from mid-trajectory weight updates stay within this scale and carry genuine exploration. We further identify an overlooked low-entropy regime that breaks this scaling, where a near-zero probability amplifies train--inference mismatch into noise far beyond what the local...
| Authors | Guanqun Zhao, Zijun Xie, Binbin Zheng et al. |
|---|---|
| Primary category | cs.AI |
| Published | 24 July 2026 |
| Last updated at source | 8 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.