T2S: 生涯模倣学習のためのトークン化スキルスケーリング
T2S: Tokenized Skill Scaling for Lifelong Imitation Learning
モデルパラメータをトークン化し、言語ガイド付きでスキルを拡張することで、破滅的忘却を防ぎつつ新しいスキルを効率的に学習する生涯模倣学習フレームワークを提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Hongquan Zhang, Jingyu Gong, Zhizhong Zhang, Xin Tan, Yanyun Qu, Yuan Xie
分類: cs.LG, cs.RO
原文アブストラクト
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.
