#artificial intelligence
Jun 2026
Rollout-Level Advantage-Prioritized Experience Replay for GRPO
A rollout-level replay buffer for GRPO is proposed that stores and samples individual rollouts rather than whole groups and bounds staleness through age eviction, and is the only condition with a positive margin over GRPO at every scale.
Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang et al.
· arXiv.org · 2 citations