Author

Keye Zheng

h-index 1 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

CLOOPD: Closing the Learner Loop in On-Policy Distillation

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 framewor...

Keye Zheng, Han-Yu Li, Zhan Cheng et al. · 0 citations