階層的潜在行動モデル
Hierarchical Latent Action Model
長期的な時間構造を捉えるため、事前学習済みの潜在行動モデルを低レベル抽出器として用い、潜在行動系列を高レベルの潜在スキルに集約する階層的潜在行動モデルHiLAM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: Hanjung Kim, Lerrel Pinto, Seon Joo Kim
分類: cs.RO
原文アブストラクト
Latent Action Models (LAMs) enable learning from actionless data for applications ranging from robotic control to interactive world models. However, existing LAMs typically focus on short-horizon frame transitions and capture low-level motion while overlooking longer-term temporal structure. In contrast, actionless videos often contain temporally extended and high-level skills. We present HiLAM, a hierarchical latent action model that discovers latent skills by modeling long-term temporal information. To capture these dependencies across long horizons, we utilize a pretrained LAM as a low-level extractor. This architecture aggregates latent action sequences, which contain the underlying dynamic patterns of the video, into high-level latent skills. Our experiments demonstrate that HiLAM improves over the baseline and exhibits robust dynamic skill discovery.
