SOURCE-LINKED INTELLIGENCE

Learning Manipulation-Sufficient Representations via Outcome Bottlenecks

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Networked manipulation endpoints couple perception to actuation across compute- and bandwidth-limited links, yet commonly exchange dense geometric states optimized for fidelity rather than action outcomes. A stochastic representation is learned with a policy-free, action-conditioned outcome bottleneck: marginal outcome log-loss supplies distortion and a KL term regularizes rate. The construction is motivated by the minimal statistic that preserves the outcome distribution of every admissible action, while the implemented finite model is evaluated as a rate-regularized mixture predictor. The sa

Read original source ↗ Open in workspace

recordType

paper

region

Global