Toward a Scalable Upper Bound for a CVaR-LQ Problem

Toward a Scalable Upper Bound for a CVaR-LQ Problem
复制标题

DOI:
10.1109/lcsys.2021.3086842
复制
发表时间:
2021-03
影响因子:
3
通讯作者:
Margaret P. Chapman;Laurent Lessard
Margaret P. Chapman;Laurent Lessard
中科院分区:
--
文献类型:
--
作者:
Margaret P. Chapman;Laurent Lessard

文献摘要

被引文献

相似文献

我们研究了一个离散有限时间范围的线性二次最优控制问题,其中成本是通过条件风险值(CVaR)来评估的。我们逐步推导出一种可伸缩的动态规划方法来求解该问题的最优值函数的上界。这种动态规划产生了一种新颖的、可调的风险规避控制策略,我们将其与现有的最先进的方法进行了比较。
We study a linear-quadratic, optimal control problem on a discrete, finite time horizon with distributional ambiguity, in which the cost is assessed via Conditional Value-at-Risk (CVaR). We take steps toward deriving a scalable dynamic programming approach to upper-bound the optimal value function for this problem. This dynamic program yields a novel, tunable risk-averse control policy, which we compare to existing state-of-the-art methods.