2 papers
cs.RO2026
Can Vision-Language-Action Models Learn from Real-World Data Continually without Forgetting?
Jiarun Zhu, Yijun Hong, Xiaoquan Sun +7
Vision-Language-Action (VLA) models provide a promising foundation for general-purpose robotics, yet their real-world deployment demands the ability to continually acquire new skil…
cs.LG2026
Continual Policy Distillation from Distributed Reinforcement Learning Teachers
Yuxuan Li, Qijun He, Mingqi Yuan +3
Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. Thi…