Mixture-of-Experts VLAにおける創発的な構成スキル
Emergent Compositional Skills in Mixture-of-Experts VLAs
専門家デモからロボットポリシーをエンドツーエンドで学習する際、Mixture-of-Expertsアーキテクチャを用いることで、タスク分解や階層構造を事前に定義せずとも、再利用可能で解釈可能なプリミティブが創発的に獲得されることを示した論文。
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: Shlok Shah, Rhiaan Jhaveri, Tharun Kumar Tiruppali Kalidoss, Chirayu Nimonkar, Ishaan Javali, Dhruv Shah
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
We consider the problem of learning compositional robot policies end-to-end from expert demonstrations, without any pre-specified notion of task decomposition or hierarchy. We ask whether a VLA trained with a simplified Mixture-of-Experts (MoE) action head can emergently learn to decompose tasks into reusable, interpretable primitives. We find that learned experts are heavily reused across tasks and consistently correspond to qualitatively distinct low-level behaviors, suggesting that the router implicitly learns to perform high-level sequencing while experts serve as compositional primitives. Our MoE matches the task performance of a monolithic baseline while demonstrating meaningful expert specialization, a step toward modular, interpretable robot policies that emerge from data alone.
