SOURCE-LINKED INTELLIGENCE
Trajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers
Offline on-policy distillation gains efficiency by collecting student trajectories and teacher supervision once and reusing them throughout optimization. The same reuse makes imperfect supervision persistent. Since even strong teachers can fail, we ask \emph{what remains learnable from imperfect teacher supervision?} Teacher failure is only a coarse problem-level signal and does not imply that all supervision along the associated student trajectory is unhelpful. A natural alternative is to estimate teacher recoverability along the trajectory, but repeated continuations largely erase the effici
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-16T08:41:16.000Z
First collected: 2026-09-20T08:01:03.945Z. This is not the publication date.