AI RESEARCH
Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
arXiv CS.LG
•
ArXi:2603.11653v1 Announce Type: new Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual learning suggests that naive Sequential Fine-Tuning (Seq. FT) leads to catastrophic forgetting, necessitating complex CRL strategies. In this work, we take a step back and conduct a systematic study of CRL for large pretrained VLAs across three models and five challenging lifelong RL benchmarks.