未知线性动力学的近似最优不可知控制
Almost Optimal Agnostic Control of Unknown Linear Dynamics
AI总结:
该研究针对依赖未知参数$a$的线性动力学控制问题,分析三类控制变体的最优性判定标准,给出贝叶斯和有界不可知控制的最优策略,以及完全不可知控制的近似最优策略。
摘要:
我们研究一个基础动力学依赖于未知且需学习的参数$a$的简单控制问题,探讨该问题的三类变体:贝叶斯控制(我们对$a$持有先验信念)、有界不可知控制(对$a$无先验信念,但假设$a$属于一个有界集合)以及完全不可知控制(允许$a$为任意实数,且我们对其无任何先验信念)。在贝叶斯变体中,使某一期望成本最小化的控制策略即为最优策略;在不可知变体中,使被称为最坏情况悔值的量最小化的控制策略为最优策略。针对上述贝叶斯变体和有界不可知变体,我们给出了最优控制策略;针对完全不可知变体,我们给出了近似最优控制策略——即对任意$\boldsymbol{\u03b5>0}$,我们都能给出一种将最坏情况悔值最小化至乘性因子$(1+\u03b5)$范围内的策略。
英文摘要:
We consider a simple control problem in which the underlying dynamics depend on a parameter $a$ that is unknown and must be learned. We study three variants of the control problem: Bayesian control, in which we have a prior belief about $a$; bounded agnostic control, in which we have no prior belief about $a$ but we assume that $a$ belongs to a bounded set; and fully agnostic control, in which $a$ is allowed to be an arbitrary real number about which we have no prior belief. In the Bayesian variant, a control strategy is optimal if it minimizes a certain expected cost. In the agnostic variants, a control strategy is optimal if it minimizes a quantity called the worst-case regret. For the Bayesian and bounded agnostic variants above, we produce optimal control strategies. For the fully agnostic variant, we produce almost optimal control strategies, i.e., for any $\varepsilon>0$ we produce a strategy that minimizes the worst-case regret to within a multiplicative factor of $(1+\varepsilon)$.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。