Rethinking Relative Policy Differences Transfer of On-Policy Distillation
On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on the teacher being substantially more capable than the target. Recent work relaxes this requirement by transferring the relative policy difference between an expert and a...
Rong Wu, Dao-Cheng Fu, Yu Yang et al.
· 0 citations