arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.06502math.OC
收藏

再论凸分析方法:平均费用随机控制中确定性策略的进一步最优性结果和性能

Convex Analytic Method Revisited: Further Optimality Results and Performance of Deterministic Policies in Average Cost Stochastic Control

Ari Arapostathis, Serdar Yüksel

摘要:

凸分析方法已被证明是研究无限期平均费用最优随机控制问题的一种非常通用的方法。在本文中,我们重新审视凸分析方法,并作出了三个主要贡献:(i)我们提出了一个存在性结果的控制马尔可夫模型,缺乏弱连续性的过渡核,但在每个固定的状态变量的行动变量是强连续的。(ii)对于标准Borel空间中的平均成本随机控制问题,虽然现有的结果建立了固定(可能是随机的)政策的最优性,但很少有结果可用于确定性策略的最优性。我们回顾现有的结果,并提出进一步的条件下,平均成本最优随机控制问题承认最优解是确定性平稳。(iii)我们建立的条件下,固定的确定性(和量化)的政策下的性能是密集的随机平稳策略下的性能值的集合。

英文摘要:

The convex analytic method has proved to be a very versatile method for the study of infinite horizon average cost optimal stochastic control problems. In this paper, we revisit the convex analytic method and make three primary contributions: (i) We present an existence result for controlled Markov models that lack weak continuity of the transition kernel but are strongly continuous in the action variable for every fixed state variable. (ii) For average cost stochastic control problems in standard Borel spaces, while existing results establish the optimality of stationary (possibly randomized) policies, few results are available on the optimality of deterministic policies. We review existing results and present further conditions under which an average cost optimal stochastic control problem admits optimal solutions that are deterministic stationary. (iii) We establish conditions under which the performance under stationary deterministic (and also quantized) policies is dense in the set of performance values under randomized stationary policies.

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。

↑