← 研踪 PaperTrailarXiv:2611.19660 · v1
PSK: A Matrix-Free Single-Loop Method for K-Level Physics-Based Control
首次提交 2026-11-15 07:09
版本更新 2026-11-15 07:09
雷达观测 2026-11-17 12:06
摘要
Physics-based control is central to robot learning, but differentiating through implicit physics steps typically requires Hessian or Karush--Kuhn--Tucker (KKT) linear solves; we ask whether gradient steps suffice. Each simulation step minimizes an energy under many contact and collision constraints. Without constraints, we view control over steps as -level optimization with strongly convex lower levels, recast as one min--max problem. Our Penalized Single-loop -level method (PSK) uses only gradients and a projection, updates all levels in parallel, and reaches an -stationary control in iterations, with a -independent exponent but a -dependent constant. Contact-rich constraints, however, typically violate a constraint qualification (CQ). We replace each constraint by a smooth wall that acts on a band of constant width. Under mild assumptions that need no CQ, every exact solution of the banded lower levels is then feasible and banded Fritz--John, and PSK keeps the complexity. Without a CQ that is uniform in the band width, however, a shrinking band loses the -independent exponent: with width and fixed , deterministic zero-respecting methods need calls on a hard instance whose control dimension grows with . We prove our assumptions for smoothed kinematic and dynamic multi-robot navigation among segment obstacles. In navigation experiments, PSK, tuned per case, reaches every goal with sixteen levels and, at equal time, reaches a lower loss than tuned unrolling in 17 of 18 cases, while implicit differentiation is lower in 10.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-15 07:09 · 最新观测版本
PSK: A Matrix-Free Single-Loop Method for K-Level Physics-Based Control
Physics-based control is central to robot learning, but differentiating through implicit physics steps typically requires Hessian or Karush--Kuhn--Tucker (KKT) linear solves; we ask whether gradient steps suffice. Each simulation step minimizes an energy under many contact and collision constraints. Without constraints, we view control over steps as -level optimization with strongly convex lower levels, recast as one min--max problem. Our Penalized Single-loop -level method (PSK) uses only gradients and a projection, updates all levels in parallel, and reaches an -stationary control in iterations, with a -independent exponent but a -dependent constant. Contact-rich constraints, however, typically violate a constraint qualification (CQ). We replace each constraint by a smooth wall that acts on a band of constant width. Under mild assumptions that need no CQ, every exact solution of the banded lower levels is then feasible and banded Fritz--John, and PSK keeps the complexity. Without a CQ that is uniform in the band width, however, a shrinking band loses the -independent exponent: with width and fixed , deterministic zero-respecting methods need calls on a hard instance whose control dimension grows with . We prove our assumptions for smoothed kinematic and dynamic multi-robot navigation among segment obstacles. In navigation experiments, PSK, tuned per case, reaches every goal with sixteen levels and, at equal time, reaches a lower loss than tuned unrolling in 17 of 18 cases, while implicit differentiation is lower in 10.
查看此版本解读 →查看此版本原文 ↗