通过可扩展的符号化技能模块，实现长期模仿学习中旧技能不遗忘、新技能易获取。
T2S: Tokenized Skill Scaling for Lifelong Imitation Learning
- 用可学习的符号令牌替代传统参数，通过跨注意力机制提升模型扩展性。
- 在三个LIBERO任务中平均遗忘率仅1.0%，新增任务仅需8.0%参数量。
- 支持跨任务知识迁移，平均前向转移性能达77.7%，适合持续学习场景。
长期模仿学习的核心挑战在于平衡旧技能的灾难性遗忘与新技能的学习容量。现有方法多孤立处理二者，忽视其内在关联。本文提出统一框架Tokenized Skill Scaling（T2S），通过将模型参数符号化，将传统Transformer的线性参数映射转化为输入与可学习令牌间的交叉注意力，从而实现通过新增令牌轻松扩展模型。同时引入语言引导的技能扩展机制，实现跨任务知识高效迁移，避免参数线性增长。在多个任务上的实验表明：T2S在三个LIBERO任务套件中平均非破坏性遗忘率仅为1.0%，在长期任务中平均仅需8.0%的可训练令牌即可实现新技能扩展，并在跨任务迁移中达到平均77.7%的前向转移性能，为长期模仿学习提供了有效解决方案。
原文摘要 · Abstract (English)
The main challenge in lifelong imitation learning lies in the balance between mitigating catastrophic forgetting of previous skills while maintaining sufficient capacity for acquiring new ones. However, current approaches typically address these aspects in isolation, overlooking their internal correlation in lifelong skill acquisition. We address this limitation with a unified framework named Tokenized Skill Scaling (T2S). Specifically, by tokenizing the model parameters, the linear parameter mapping of the traditional transformer is transformed into cross-attention between input and learnable tokens, thereby enhancing model scalability through the easy extension of new tokens. Additionally, we introduce language-guided skill scaling to transfer knowledge across tasks efficiently and avoid linearly growing parameters. Extensive experiments across diverse tasks demonstrate that T2S: 1) effectively prevents catastrophic forgetting (achieving an average NBT of 1.0% across the three LIBERO task suites), 2) excels in new skill scaling with minimal increases in trainable parameters (needing only 8.0% trainable tokens in an average of lifelong tasks), and 3) enables efficient knowledge transfer between tasks (achieving an average FWT of 77.7% across the three LIBERO task suites), offering a promising solution for lifelong imitation learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。