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.

翻译：学习良好的表示对于基于世界模型的潜在规划至关重要。尽管预训练的视觉编码器能够生成强语义的视觉特征，但这些特征并非为规划任务定制，且包含与规划无关甚至有害的信息。受人类视觉处理中感知拉直假说的启发，我们引入时序拉直技术以改进潜在规划的表示学习。通过采用鼓励局部拉直潜在轨迹的曲率正则化器，我们联合学习编码器与预测器。研究表明，通过这种方式降低曲率可使潜在空间中的欧氏距离更好地替代测地距离，并改善规划目标的条件性。实验证明，时序拉直使基于梯度的规划更加稳定，并在一系列目标达成任务中显著提高了成功率。