SOURCE-LINKED INTELLIGENCE

Geometric Distributional Control: Learning Progress with Partial Structural Knowledge

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Real-time control often sits between two limiting regimes. Predictive optimization and model-based control are powerful when dynamics, parameters, objectives, and online planning models are specified; reinforcement learning can relax this requirement, but must infer long-horizon value signals from sequential data and interaction, making training slow, high-variance, and hard to scale in large action spaces. This middle regime is common in systems including autonomous driving, warehouse robotics, traffic control, and delivery drones: partial geometry, physics, rules, or constraints are known, y

Read original source ↗ Open in workspace

recordType

paper

region

Global