行動チャンク型模倣学習におけるマルチモーダル失敗の理解
Understanding Multimodal Failure in Action-Chunking Behavioral Cloning
行動チャンク型ポリシーで同じ観察に複数の正解行動がある場合の失敗メカニズムを分析し、潜在変数型と生成型の各パラメータ化の特性を明らかにした。
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: Lorenzo Mazza, Massimiliano Datres, Ariel Rodriguez, Sebastian Bodenstedt, Gitta Kutyniok, Stefanie Speidel
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Behavioral cloning becomes difficult when the same observation admits several valid actions. We study this problem for action-chunking policies and show that different multimodal parameterizations fail in different ways. For latent-variable policies, posterior-prior regularization makes deployment-time sampling more reliable, but excessive regularization removes the action-conditioned information needed to distinguish demonstrated modes. Reducing this regularization can preserve mode information, but then success depends on whether the prior covers the relevant latent regions. For action-space generative policies, multimodality is constrained by the smoothness of the base-to-action transport: a map with small Lipschitz constant cannot assign substantial probability to many well-separated modes. Covering many modes therefore requires either sharp transitions in base space or off-support bridge regions in action space. Experiments on synthetic multimodal tasks and robotic simulation benchmarks support these mechanisms.
