JEPA世界モデルによる物理プランニングの成功要因の解明
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
JEPA型世界モデルを用いたプランニングにおいて、モデル構造・学習目的・プランニングアルゴリズムが成功に与える影響を体系的に調査し、ナビゲーションとマニピュレーションで既存手法を上回るモデルを提案した。
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: Basile Terver, Tsung-Yen Yang, Jean Ponce, Adrien Bardes, Yann LeCun
分類: cs.AI, cs.LG, cs.RO, stat.ML
原文アブストラクト
A long-standing challenge in AI is to develop agents capable of solving a wide range of physical tasks and generalizing to new, unseen tasks and environments. A popular recent approach involves training a world model from state-action trajectories and subsequently use it with a planning algorithm to solve new tasks. Planning is commonly performed in the input space, but a recent family of methods has introduced planning algorithms that optimize in the learned representation space of the world model, with the promise that abstracting irrelevant details yields more efficient planning. In this work, we characterize models from this family as JEPA-WMs and investigate the technical choices that make algorithms from this class work. We propose a comprehensive study of several key components with the objective of finding the optimal approach within the family. We conducted experiments using both simulated environments and real-world robotic data, and studied how the model architecture, the training objective, and the planning algorithm affect planning success. We combine our findings to propose a model that outperforms two established baselines, DINO-WM and V-JEPA-2-AC, in both navigation and manipulation tasks. Code, data and checkpoints are available at https://github.com/facebookresearch/jepa-wms.
