1
Blockwise Policy-Drift Gating for On-Policy Distillation
On-Policy蒸馏中策略漂移的块级门控机制,为强化学习知识迁移提供新思路。
arXiv:2606.24084v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student policy using teacher signals computed on trajectories …