arXiv 2609.35259 · cs.LG · 2026-09-28
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
Julianna Piskorz, Antonin Berthon, Mihaela van der Schaar
University of Cambridge
在最新榜 #77 本站收录于 2026-10-21
一句话要点
在受控实验中分离 on-policy 与 off-policy 蒸馏的作用，发现结论比“on-policy 总更好”复杂。
A controlled study isolating on- vs off-policy rollouts in distillation, finding a more nuanced picture than 'on-policy is always better'.
阅读 arXiv 原文 PDF Hugging Face 讨论 项目页
主题与学科
同主题：高效训练与推理
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲251
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
- TokenRouter: Efficient Serving System for Token-Level LLM Routing ▲143
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。