残差潜在アクションによる視覚特徴ベース世界モデルの学習
Learning Visual Feature-Based World Models via Residual Latent Action
視覚特徴ベースの世界モデルにおいて、DINO残差から学習可能な新しい潜在アクション表現（RLA）を導入し、フローマッチングで予測することで、既存手法より高速かつ高精度な未来予測を実現した。さらに、ロボット学習への応用として、アクションなし動画からの行動学習や、オフライン動画のみで学習する視覚RLフレームワークを開発した。
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: Xinyu Zhang, Zhengtong Xu, Yutian Tao, Yeping Wang, Yu She, Abdeslam Boularias
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
World models predict future transitions from observations and actions. Existing works predominantly focus on image generation only. Visual feature-based world models, on the other hand, predict future visual features instead of raw video pixels, offering a promising alternative that is more efficient and less prone to hallucination. However, current feature-based approaches rely on direct regression, which leads to blurry or collapsed predictions in complex interactions, while generative modeling in high-dimensional feature spaces still remains challenging. In this work, we discover that a new type of latent action representation, which we refer to as *Residual Latent Action* (RLA), can be easily learned from DINO residuals. We also show that RLA is predictive, generalizable, and encodes temporal progression. Building on RLA, we propose *RLA World Model* (RLA-WM), which predicts RLA values via flow matching. RLA-WM outperforms both state-of-the-art feature-based and video-diffusion world models on simulation and real-world datasets, while being orders of magnitude faster than video diffusion. Furthermore, we develop two robot learning techniques that use RLA-WM to improve policy learning. The first one is a minimalist world action model with RLA that learns from actionless demonstration videos. The second one is the first visual RL framework trained entirely inside a world model learned from offline videos only, using a video-aligned reward and no online interactions or handcrafted rewards. Project page: https://mlzxy.github.io/rla-wm
