HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime 事件

HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime arXiv:2605.30201v1 Announce Type: cross Abstract: We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contain more responses with negative advantages than those with positive advantages, while response-level length normalization ties the magnitude of the update to the length of the output. We propose Hysteret