SOURCE-LINKED INTELLIGENCE

CLOOPD: Closing the Learner Loop in On-Policy Distillation

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

On-policy distillation (OPD) pays twice for each fresh batch: the student generates trajectories and a stronger teacher scores them. Existing methods improve which trajectories are scored and how the teacher signal is constructed, but usually consume it with one actor update. We introduce CLOOPD, a closed-loop framework separating teacher-signal acquisition from student-side realization. CLOOPD selects an adaptive $α$ waypoint inside a KL envelope, freezes the scored batch and its advantages, re-forwards the student after each actor pass, measures realization, and allocates actor work under a

Read original source ↗ Open in workspace

recordType

paper

region

Global