MARKOV DECISION PROCESSES WITH RANDOM HORIZON

MARKOV DECISION PROCESSES WITH RANDOM HORIZON
复制标题

具有随机视野的马尔可夫决策过程

DOI:
--
复制
发表时间:
1996
期刊:
影响因子:
--
通讯作者:
Masao Mori
Masao Mori
中科院分区:
--
文献类型:
--
作者:
Tetsuo Iida;Masao Mori

文献摘要

被引文献

相似文献

在本文中,我们制定马尔可夫决策过程与随机地平线(MDPRH)。我们给出了MDPN的最优性方程,但是可能不存在最优的平稳策略!或者是过程的最优平稳策略。当MDPRH具有无限支持的规划水平的概率分布时!我们展示了收费公路规划地平线定理。然后,我们评估滚动策略,并开发一个算法,获得最佳的第一阶段的决定。最后,对一个简单的库存模型进行了数值实验,以了解这一现象。
In this paper we formulate Markov Decision Processes with Random Horizon (MDPRH). We show the optimality equation for the MDPN, however there may not exist optimal stationary strategies! or €-optim stationary strategies for the processes. When the MDPRH has the probability distribution for the planning horizon with infinite support! we show Turnpike Planning Horizon Theorem. Then we evaluate rolling strategies and develop an algorithm obtaining an optimal first stage decision. Finally, some numerical experiments on a simple inventory mode1 are done to understand the phenome~a.