Data-Free Continual Learning for World Action Model with Rectified Generative Replay
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
World action models (WAMs) built on pretrained video generation models adapt quickly to new robotic tasks, but they forget previously learned tasks under sequential fine-tuning. Experience replay (ER) mitigates such forgetting by rehearsing data of previous tasks, yet this data is often unavailable in robotics, where a policy is deployed as weights only and its training data is not shared along with it.
초록에서 가져왔습니다. 요약을 준비 중입니다.
이 논문은 라이선스상 전문을 게재할 수 없어 요약과 원문 링크만 제공합니다.