论文标题
竞争性控制和延迟不完美的信息
Competitive Control with Delayed Imperfect Information
论文作者
论文摘要
本文研究了不完美的信息在在线控制中的影响，并通过对抗性干扰。特别是，我们考虑了未来干扰的状态反馈和不精确的预测。我们引入了一种贪婪，近视政策，与离线最佳政策相比，持续的竞争比率持续。我们还通过表明我们的竞争比率在对抗性环境中的贪婪，近视政策匹配（最高较低阶段）在随机设置中的下限来分析在线控制的基本限制。
This paper studies the impact of imperfect information in online control with adversarial disturbances. In particular, we consider both delayed state feedback and inexact predictions of future disturbances. We introduce a greedy, myopic policy that yields a constant competitive ratio against the offline optimal policy. We also analyze the fundamental limits of online control with limited information by showing that our competitive ratio bounds for the greedy, myopic policy in the adversarial setting match (up to lower-order terms) lower bounds in the stochastic setting.
