跳到正文
arXiv cs.AI· Kartik Pandit, Sourav Ganguly, Arnob Ghosh·· 2 小时前AI 评分37

面向安全控制器选择的免抵消约束 SquareCB 算法

Cancellation-Free Constrained SquareCB for Safe Controller Selection

AI 导读

一项研究针对约束上下文老虎机问题,改进了现有依赖拉格朗日乘子的在线回归约简方法,改为对 SquareCB 的成本使用修正权重:估计成本在预算内时权重为零,超出时取刚好拉回预算的大小。

正文 · 原文

View PDF HTML (experimental)

Abstract:We study constrained contextual bandits, in which a learner chooses one of $K$ actions in each round to minimize loss while keeping the expected cost of its play below a budget. Existing reductions to online regression weight the cost by a Lagrange multiplier learned from past constraint residuals, so slack in some rounds can offset violations in others. We instead run SquareCB proposed in \citep{foster2020beyond} with a rectified weight on the cost: it is zero when the estimated cost is within the budget, and otherwise just large enough to bring it back to the budget. Under realizability and Slater's condition with margin $\delta$, the algorithm attains regret $O(\sqrt{KT\,\mathrm{Reg}_{\mathsf{Sq}}(T)}/\delta)$ and cancellation-free violation $\sum_t(V_c^{p_t}-b)^+=O(\sqrt{KT\,\mathrm{Reg}_{\mathsf{Sq}}(T)})$, where $\mathrm{Reg}_{\mathsf{Sq}}$ is the error of the regression oracle. The same bounds hold when the budget must be met in every context, potentially adversarially chosen contexts. In controller selection for a safe-control-gym quadrotor and a BOPTEST building, the violation is 6 to 9 times lower than that of primal-dual and virtual-queue baselines, with a lower or comparable regret.
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
Cite as: arXiv:2611.21880 [cs.LG]
  (or arXiv:2611.21880v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.21880

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Kartik Pandit [view email]
[v1] Mon, 16 Nov 2026 20:47:19 UTC (43,991 KB)

来源:arXiv cs.AI · arxiv.org