预训练视觉-语言-动作模型在持续学习中出人意料地表现出遗忘抵抗性
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
AI总结：
研究发现预训练的视觉-语言-动作模型在持续学习中表现出较强的遗忘抵抗性，简单经验回放在这些模型上效果显著，即使数据量小也能实现零遗忘。
摘要：
持续学习是机器人策略学习中的长期挑战，其中策略必须在时间推移中获取新技能而不灾难性遗忘之前学到的内容。尽管先前工作已广泛研究了在相对较小的行为克隆（BC）策略模型上持续学习，但其在现代大规模预训练视觉-语言-动作（VLA）模型中的行为仍不为人知。在本工作中，我们发现预训练的VLA模型比从头开始训练的小型策略模型在持续学习中表现出更强烈的遗忘抵抗性。简单的经验回放（ER）在VLA上出人意料地有效，有时即使使用小的回放数据量也能实现零遗忘。我们的分析揭示了预训练在下游持续学习性能中的关键作用：大型预训练模型在使用小的回放缓冲区大小时能够减轻遗忘，同时保持强大的前向学习能力。此外，我们发现VLA在学习新任务时尽管性能下降，仍能保留先前任务的相关知识。这种知识保留使得通过微调能够快速恢复看似遗忘的技能。这些见解表明，大规模预训练从根本上改变了持续学习的动力学，使模型能够通过简单的回放持续获取新技能。代码和更多信息可在https://continual-vlas.github.io/forget-me-not/上找到。
英文摘要：
Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual learning in relatively small behavior cloning (BC) policy models trained from scratch, its behavior in modern large-scale pretrained Vision-Language-Action (VLA) models remains underexplored. In this work, we found that pretrained VLAs are remarkably resistant to forgetting compared with smaller policy models trained from scratch. Simple Experience Replay (ER) works surprisingly well on VLAs, sometimes achieving zero forgetting even with a small replay data size. Our analysis reveals that pretraining plays a critical role in downstream continual learning performance: large pretrained models mitigate forgetting with a small replay buffer size while maintaining strong forward learning capabilities. Furthermore, we found that VLAs can retain relevant knowledge from prior tasks despite performance degradation during learning new tasks. This knowledge retention enables rapid recovery of seemingly forgotten skills through finetuning. Together, these insights imply that large-scale pretraining fundamentally changes the dynamics of continual learning, enabling models to continually acquire new skills over time with simple replay. Code and more information can be found at https://continual-vlas.github.io/forget-me-not/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
