Jul 2026
β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
This work introduces $\beta$-OPSD and derives its optimal policy as a geometric interpolation between the reference policy and the privileged teacher, and provides a principled route from self-distillation to policy optimization and back without sacrificing the efficiency that makes OPSD practical.
Jiawei Xu, Minghui Liu, Juzheng Zhang et al.
· arXiv.org · 1 citation