Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO
Jiahua Yang, Zhiwei Yang, Xianpeng Zhang +7
Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance gains. However, these methods…
cs.AI2026
Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning
Wenhao Zhang, Yibo Xie, Rui Wang +9
Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models. Reusing each rollout batch for additional learner updates amort…