Le-Yi Pan

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

This work proposes RLCSD (Reinforcement Learning with Contrastive on-policy Self-Distillation), which mitigates this drift by contrasting the teacher-student gap under a correct hint against that under a wrong hint, suppressing style shifts induced by hints regardless of correctness and yielding a signal more concentra...