探索を超えた潜在幾何学:ワールドモデルにおける計画の償却
Latent Geometry Beyond Search: Amortizing Planning in World Models
滑らかで一様な潜在空間を持つ事前学習済みワールドモデルにおいて、反復的なオンライン探索を軽量な目標条件付き逆動力学モデル(GC-IDM)に置き換え、計画を償却する手法を提案。4つのベンチマークでCEM等と同等以上の性能を維持しつつ、計算コストを100〜130倍削減した。
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: Hoang Nguyen, Xiaohao Xu, Xiaonan Huang
分類: cs.RO, cs.LG
原文アブストラクト
Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these spaces remains challenging. This raises a central question: when does a learned representation simplify control, rather than merely enabling prediction? We study this question in a pretrained LeWorldModel, whose latent geometry is regularized for smoothness and uniformity. Our key insight is that, under such geometry, planning can be amortized into a latent inverse-dynamics mapping instead of requiring online search. We therefore replace iterative planning with a lightweight Goal-Conditioned Inverse Dynamics Model (GC-IDM) that maps the current latent state, goal latent state, and remaining horizon directly to the next action. Empirically, across four benchmark environments spanning navigation, contact-rich manipulation, and continuous control, our controller matches or exceeds CEM in seven of eight environment-protocol settings while reducing per-decision cost by 100-130x. A broader sweep over test-time planners (CEM, MPPI, iCEM, and gradient-based methods) shows that this result is not specific to a particular optimizer. These findings suggest that much of the structure recovered by test-time planning is already locally encoded in the latent representation. More broadly, our results indicate that sufficiently structured latent spaces can shift part of the planning burden from online optimization to learned inference. Our code is publicly available at https://github.com/hdnndh/Latent-Geometry-Beyond-Search-Amortizing-Planning-in-World-Models .
関連論文
- 潜在エネルギー行動計画とワールドモデル計画/ワールドモデル
