Skip to main content
Search

# Task-level performance funnels

1 related articles

Subscribe to updates
  1. arXiv

    Flow-matching robot policies get a task-progress check: physics rollouts lift PushT success from 31.3% to 88.5%

    Generative manipulation policies can produce plausible action chunks that still stall or undo earlier progress. An inference-time refinement method for flow-matching policies evaluates candidate chunks through parallel physics-based rollouts and requires each chunk to satisfy a task-performance funnel with terminal contraction, so repeated execution drives task error toward zero. On PushT and three-cube stacking, refinement raises success from 31.3% to 88.5% and from 77.0% to 86.0%; on PushT, a learned funnel lowers the mean maximum drawdown of achieved progress by 19% relative to constraining only each chunk's endpoint, at a similar success rate.

You’re all caught up