AI Agents 相关度: 8/10

Temporal Straightening for Latent Planning

Ying Wang, Oumayma Bounou, Gaoyue Zhou, Randall Balestriero, Tim G. J. Rudner, Yann LeCun, Mengye Ren
arXiv: 2603.12231v1 发布: 2026-03-12 更新: 2026-03-12

AI 摘要

该论文提出时间拉直方法,通过曲率正则化改进世界模型的潜在空间表示,提升基于梯度规划的稳定性和成功率。

主要贡献

  • 提出时间拉直方法,改进潜在空间表示
  • 使用曲率正则化鼓励局部拉直潜在轨迹
  • 提升了梯度规划的稳定性和成功率

方法论

联合学习编码器和预测器,使用曲率正则化减少潜在轨迹的曲率,使欧氏距离更好地近似测地距离,改善规划目标。

原文摘要

Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to planning and contain information irrelevant -- or even detrimental -- to planning. Inspired by the perceptual straightening hypothesis in human visual processing, we introduce temporal straightening to improve representation learning for latent planning. Using a curvature regularizer that encourages locally straightened latent trajectories, we jointly learn an encoder and a predictor. We show that reducing curvature this way makes the Euclidean distance in latent space a better proxy for the geodesic distance and improves the conditioning of the planning objective. We demonstrate empirically that temporal straightening makes gradient-based planning more stable and yields significantly higher success rates across a suite of goal-reaching tasks.

标签

潜在规划 世界模型 表征学习 强化学习

arXiv 分类

cs.LG