Article

Latent Projection for Latent Planning: Improving World-Model Planning Costs with Latent-Space Projection

The paper proposes Latent Projection for Latent Planning, noting that planning costs in latent world models are often taken as the ℓ2 distance between the predicted terminal latent and the goal latent, while the latent itself contains noise whose source is precisely the regularizer used during training to prevent collapse.

Part of the event: Uncertainty Projection Improves Cost Computation for Latent Space Planning

This page provides a summary and source link only.