arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2002.11578math.OC
收藏

具有动态学习的最优控制:一个玩具问题

Optimal control with learning on the fly: a toy problem

Charles L. Fefferman, Bernat Guillen Pegueroles, Clarence W. Rowley, Melanie Weber

摘要:

我们表现出最优控制策略的一个简单的玩具问题,其中的基本动态依赖于一个参数,最初是未知的,必须学习。我们考虑一个费用函数提出了在有限的时间间隔,在对比以前的工作,认为渐近的时间范围趋于无穷大。我们研究了几个不同版本的问题,包括贝叶斯控制,我们假设一个先验分布的未知参数;和“不可知”的控制,我们假设没有关于未知参数。对于不可知论的问题,我们比较我们的表现与对手谁知道参数的值。这种比较产生了几个概念的“遗憾”,我们得到的策略,最大限度地减少“最坏情况下的遗憾”所产生的最不利的选择的未知参数。在每种情况下,最优策略都是贝叶斯策略或贝叶斯策略的极限。

英文摘要:

We exhibit optimal control strategies for a simple toy problem in which the underlying dynamics depend on a parameter that is initially unknown and must be learned. We consider a cost function posed over a finite time interval, in contrast to much previous work that considers asymptotics as the time horizon tends to infinity. We study several different versions of the problem, including Bayesian control, in which we assume a prior distribution on the unknown parameter; and "agnostic" control, in which we assume nothing about the unknown parameter. For the agnostic problems, we compare our performance with that of an opponent who knows the value of the parameter. This comparison gives rise to several notions of "regret," and we obtain strategies that minimize the "worst-case regret" arising from the most unfavorable choice of the unknown parameter. In every case, the optimal strategy turns out to be a Bayesian strategy or a limit of Bayesian strategies.

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。

↑