LePlanner: An Iterative Amortized Controller For World Models
World models trained with joint-embedding predictive architectures learn compact, structured latent representations from physical interaction, yet planning in these latent spaces typically relies on one of two costly approaches. Search-based planners such as CEM, MPPI, and iCEM optimize action sequences through many pr...
Saksham Bansal, Om Naphade, Chayan Aggarwal et al.
· 0 citations