On the Complexity of the Policy Improvement Algorithm for Markov Decision Processes

On the Complexity of the Policy Improvement Algorithm for Markov Decision Processes
复制标题

马尔可夫决策过程的策略改进算法的复杂性

DOI:
--
复制
发表时间:
1994
影响因子:
2.1
通讯作者:
A. Condon
A. Condon
中科院分区:
计算机科学3区
文献类型:
--
作者:
Mary Melekopoglou;A. Condon

文献摘要

被引文献

相似文献

我们考虑马尔可夫决策过程的策略改进算法的复杂性。我们表明,该算法的四个变种在最坏的情况下需要指数时间。INFORMS Journal on Computing(ISSN 1091-9856)是1989年至1995年以ISSN 0899-1499的名义出版的ORSA Journal on Computing。
We consider the complexity of the policy improvement algorithm for Markov decision processes. We show that four variants of the algorithm require exponential time in the worst case. INFORMS Journal on Computing , ISSN 1091-9856, was published as ORSA Journal on Computing from 1989 to 1995 under ISSN 0899-1499.