Latent Energy Action Planning with World Models
Classification
View four quadrants- Major category
- WAMs
- Quadrant
- Outside quadrants
- Architecture
- Pending verification
- Prediction paradigm
- Other mechanisms
- Subcategories
- Latent prediction & JEPA
- Source review status
- Not assigned
Category review. The planner differentiates goal costs through frozen action-conditioned latent dynamics, refines bounded action sequences, executes them and replans; the paper is a specific model-based control method. The described action mechanism is external planning, model-assisted policy optimization, geometric tracking, or video-conditioned control; the source does not establish joint future/action generation or an IDM action decoder. Reading evidence
Contribution
LEAP refines an action horizon through frozen LeWorldModel dynamics, combining latent-goal matching with a learned decoder’s terminal-state error. A trained proposal initializes search; projection bounds executed controls. Four-domain mean success rises from 77.5% to 94.8% against matched LeWM+CEM. The narrower energy ablation improves from 91.0% to 96.5%, separating the extra objective’s contribution from the complete planner change. Numerical goal descriptors and trustworthy learned rollouts remain prerequisites (e-energy, e-proposal, e-optimization, e-main, e-ablation, e-limits).
Abstract
An abstract has not been added yet.
Affiliations
Department of Computer Science, Purdue University, USA