FlashREINFORCE: Critic-Free Single-Rollout Asynchronous RL for Agentic Language Models
Jian Hu, Yifan Zhang, Hao Zhang, Binfeng Xu, Shaokun Zhang, Hongqing Peng, Zhiding Yu, Pavlo Molchanov 等 10 位作者
原文摘要
Asynchronous reinforcement learning suits long-horizon agents with irregular rollout times, but group-relative updates require repeated rollouts of each prompt. However, group-based sampling limits prompt coverage at a fixed rollout budget and introduces group synchronization barriers. One rollout per prompt avoids these constraints but requires learning from stale, variable-length trajectories without a sibling baseline. We present FlashREINFORCE, to our knowledge the first critic-free single-rollout framework that scales to long asynchronous training and large models. It combines One-Batch REINFORCE, a Sequence Trust Region, and Sample-Mean Optimization, which provide prompt coverage and batch centering while controlling policy drift and length-amplified negative updates. Each component is easy to implement, and the result is their combination: a batch-mean baseline is stable under sample-mean loss, and each common alternative degrades or collapses training. FlashREINFORCE remains stable through 6,000 updates on DeepSeek-R1-Distill-Qwen-1.5B at policy lag four, and through 1,450 on the 30B MoE Qwen3-30B-A3B at lag eight. Under identical loss, data, and lag it matches a strengthened group-relative baseline within 0.5 points, and with half the rollouts exceeds published synchronous baselines on Qwen2.5-Math-1.5B (38.0 versus 36.3 five-benchmark mean). On Qwen2.5-7B-Instruct it maintains tool use where GRPO stops calling tools and achieves 98.3%/96.5% seen/unseen ALFWorld success.
cs.CL · cs.LG