论文标题
在网络控制系统中学习
Learning in Networked Control Systems
论文作者
论文摘要
我们为网络控制系统（NCS）设计自适应控制器（学习规则），其中包含控制信息的数据包在有损的无线通道上传输。 We propose Upper Confidence Bounds for Networked Control Systems (UCB-NCS), a learning rule that maintains confidence intervals for the estimates of plant parameters $(A_{(\star)},B_{(\star)})$, and channel reliability $p_{(\star)}$, and utilizes the principle of optimism in the face of uncertainty while making control decisions.我们通过分析$（a _ {（\ star）}，b _ {（\ star）}，p _ {（\ star）}）$时，为UCB-NC提供了非反应性绩效保证，即从场景中的性能差距。我们表明，遗憾的可能性很高，可以将遗憾作为$ \ tilde {o} \ left（c \ sqrt {t} \ right）$ \ footNote {在这里$ \ tilde {o} $ hides boogarithmic factor。}，其中$ t $ t $是$ c $ c $ co $ ristions and comptiment and Is comptiment and Is Is Is Is Is Is Is Is Is Is Is Is Is Is Issive。
We design adaptive controller (learning rule) for a networked control system (NCS) in which data packets containing control information are transmitted across a lossy wireless channel. We propose Upper Confidence Bounds for Networked Control Systems (UCB-NCS), a learning rule that maintains confidence intervals for the estimates of plant parameters $(A_{(\star)},B_{(\star)})$, and channel reliability $p_{(\star)}$, and utilizes the principle of optimism in the face of uncertainty while making control decisions. We provide non-asymptotic performance guarantees for UCB-NCS by analyzing its "regret", i.e., performance gap from the scenario when $(A_{(\star)},B_{(\star)},p_{(\star)})$ are known to the controller. We show that with a high probability the regret can be upper-bounded as $\tilde{O}\left(C\sqrt{T}\right)$\footnote{Here $\tilde{O}$ hides logarithmic factors.}, where $T$ is the operating time horizon of the system, and $C$ is a problem dependent constant.
