arXiv 2610.21601 · cs.LG · 2026-10-15
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Bingxi Hou, Guochao Jiang, Guofeng Quan, Weiqing Li, Wenfeng Feng, Guohua Liu, Yuewei Zhang
机构待核实
在最新榜 #70 本站收录于 2026-10-21
一句话要点
Waypoint-OPD 借助教师 RL 训练中途的检查点，只迁移前后一致的策略变化。
Waypoint-OPD uses an intermediate teacher checkpoint to transfer only consistent RL-induced policy shifts to the student.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：强化学习
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight ▲189
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches ▲152
- Sharpening Tax in Post-Training ▲111
- RULER: Instance-aware Rubric Rewards for SVG Generation ▲104
- TPPO: Tracking-Value PPO For Language Model Reasoning ▲96
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。