Papers

论文:将在线切换控制转化为带切换代价的专家问题

Online Switching Control as Learning with Experts

Why we picked it

这篇论文把控制领域的在线切换问题变成了学习理论里经典的专家问题来解,方法是基于 Hedge 算法加切换抑制,遗憾界达到最优阶 O(√(T log N))。做控制与在线学习交叉方向的研究者可以看看,归约思路和反事实代价的计算方式都值得借鉴。

arXiv 论文 2611.18352 研究离散时间非线性系统的在线切换控制问题:每一步从有限候选集中顺序选择一个控制器,在扰动和代价函数未知的情况下最小化累计代价。

Body

论文设定为全信息反馈场景,每次选择后可观测实际扰动效果与代价函数。核心方法是用历史数据计算反事实代价,把切换控制问题归约为带切换代价的专家问题,并在 Hedge 算法基础上加入切换抑制机制,提出自适应切换算法。

该算法达到 O(√(T log N)) 的期望遗憾(T 为时间范围,N 为候选控制器数量),与标准专家问题的最优遗憾阶一致,同时保证状态一致有界。

Original · arXiv cs.LG

Online Switching Control as Learning with Experts

This paper addresses the problem of online switching control for discrete-time nonlinear systems where a controller is sequentially selected from a finite set of candidates. The goal is to generate an adaptive sequence of controllers to minimize the cumulative cost under unknown disturbances and cost functions. Specifically, we consider a full-information feedback setting where realized disturbance effects and cost functions are available after each selection. Using counterfactual costs computed from historical data, we reduce the online switching control problem to the experts problem with switching costs. Then, we propose an adaptive switching algorithm based on the Hedge algorithm with a switching suppression mechanism. Notably, the proposed algorithm achieves an expected regret of $O(\sqrt{T\log N})$, where $T$ is the time horizon and $N$ is the number of candidate controllers, while ensuring uniform boundedness of the state. This matches the optimal regret order for the standard experts problem.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include online learning, regret bounds.

Source attribution: curated from arXiv cs.LG (@Masataka Nakamura, Kaito Ito, Hideaki Ishii).