Kang Mingu

The work shows that isotropic Gaussian regularization (SIGReg) can make Euclidean latent planning cost rank feasible outcomes differently from the task cost, and introduces AnisoWM with ΛReg, which learns a diagonal covariance target under fixed-trace and anisotropy constraints while leaving the prediction objective and Euclidean planner unchanged, improving planning success over LeWM in all four visual control environments (TwoRoom, Reacher, PushT, Cube) and yielding better agreement between latent costs and task outcomes.

The work shows that isotropic Gaussian regularization (SIGReg) can make Euclidean latent planning cost rank feasible outcomes differently from the task cost, and introduces AnisoWM with ΛReg, which learns a diagonal covariance target under fixed-trace and anisotropy constraints while leaving the prediction objective and Euclidean planner unchanged, improving planning success over LeWM in all four visual control environments (TwoRoom, Reacher, PushT, Cube) and yielding better agreement between latent costs and task outcomes.