#policy-gradient

1 articles

01 ·Inference & Serving·★ MEMBER·PAPER·11 min read Paper Walkthrough: On-Policy Reverse Distillation — Borrowing a Weak Teacher's Direction, Not Its Answers OPRD takes the policy change a weak teacher acquired during post-training and uses it only as a direction to amplify the student's own policy gradient — never as an optimization target. A ground-up walkthrough.