SOURCE-LINKED INTELLIGENCE

Latent Energy Action Planning with World Models

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Latent world models support efficient model predictive control from high-dimensional observations, yet optimizing a single learned latent objective can favor action sequences whose decoder-predicted terminal descriptor does not match the goal descriptor. We introduce Latent Energy Action Planning (LEAP), which treats the complete action horizon as a differentiable variable and optimizes it through a frozen LeWorldModel (LeWM). LEAP couples terminal latent goal matching with a terminal-window state energy. Low energy requires the predicted terminal latent to agree with the goal latent and the d

Read original source ↗ Open in workspace

recordType

paper

region

Global