Uncertainty
PETS combines probabilistic dynamics models in an ensemble and samples trajectories to carry uncertainty into planning. A single predicted trajectory can hide the range of plausible outcomes.
Why it matters
Decisions should account for uncertainty in predictions. Any displayed range needs a stated method and does not automatically constitute a calibrated guarantee.
Relationships
informsUncertainty → World model
WML · World Model Laboratory
Explore the connection between perception, prediction, planning, and action studied in WFM through experiments in WML. Compare predictions with simulated outcomes in interactive physics scenes, then explore a different action from the same decision point.
Educational simulation: WML uses simplified predictors; it does not validate the performance of learned foundation world models or transfer to the real world.
Open the experiment in WML