SPREAD: 生涯模倣学習のための部分空間表現蒸留
SPREAD: Subspace Representation Distillation for Lifelong Imitation Learning
生涯模倣学習において、特異値分解を用いてタスク間のポリシー表現を低ランク部分空間で整列させ、幾何構造を保ちながら知識転移と忘却防止を実現する手法を提案した。
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: Kaushik Roy, Giovanni D'urso, Nicholas Lawrance, Brendan Tidd, Peyman Moghadam
分類: cs.LG, cs.RO
原文アブストラクト
A key challenge in lifelong imitation learning (LIL) is enabling agents to acquire new skills from expert demonstrations while retaining prior knowledge. This requires preserving the low-dimensional manifolds and geometric structures that underlie task representations across sequential learning. Existing distillation methods, which rely on L2-norm feature matching in raw feature space, are sensitive to noise and high-dimensional variability, often failing to preserve intrinsic task manifolds. To address this, we introduce SPREAD, a geometry-preserving framework that employs singular value decomposition (SVD) to align policy representations across tasks within low-rank subspaces. This alignment maintains the underlying geometry of multimodal features, facilitating stable transfer, robustness, and generalization. Additionally, we propose a confidence-guided distillation strategy that applies a Kullback-Leibler divergence loss restricted to the top-M most confident action samples, emphasizing reliable modes and improving optimization stability. Experiments on the LIBERO, lifelong imitation learning benchmark, show that SPREAD substantially improves knowledge transfer, mitigates catastrophic forgetting, and achieves state-of-the-art performance.
関連論文
- リプレイ不要の生涯模倣学習のための階層的二重ルーティング注意機構生涯学習/模倣学習
- 多モーダル潜在リプレイと段階的調整による生涯模倣学習生涯学習/模倣学習
