arXiv cs.AI
Reinforcement Learning with Visually Attributable On-Policy Self-Distillation
시각적 귀속이 가능한 온라인 정책 자기 증류를 활용한 강화학습
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.