| 半Markov控制过程在平均准则下的优化算法 |
| |
| 引用本文： | 代桂平,殷保群,李衍杰,周亚平,奚宏生.半Markov控制过程在平均准则下的优化算法[J].中国科学技术大学学报,2005,35(2):202-207. |
| |
| 作者姓名： | 代桂平 殷保群 李衍杰 周亚平 奚宏生 |
| |
| 作者单位： | 1. 中国科学技术大学自动化系,安徽合肥,230027
2. 中国科学技术大学管理科学系,安徽合肥,230027 |
| |
| 基金项目： | 国家自然科学基金(60274012)，安徽省自然科学基金(01042308)资助项目. |
| |
| 摘 要： | 研究了一类半Markov控制过程(SMCP)在紧致行动集上关于无限水平平均代价准则的性能优化算法．利用等价Markov过程的方法，导出了SMCP的性能势公式和平均代价最优性方程，给出了求解最优或次最优平稳策略的策略迭代算法和数值迭代算法，并证明了算法的收敛性．最后给出了一个数值例子来说明算法的应用．
|
| 关 键 词： | 半Markov控制过程 紧致行动集 性能势 策略迭代 数值迭代 |
| 文章编号： | 0253-2778(2005)02-0202-06 |
| 修稿时间： | 2003年12月16 |
Optimization Algorithms for Semi-Markov Control Processes With Average Criteria |
| |
| DAI Gui-ping,YIN Bao-qun,LI Yan-Jie,ZHOU Ya-ping,XI Hong-sheng.Optimization Algorithms for Semi-Markov Control Processes With Average Criteria[J].Journal of University of Science and Technology of China,2005,35(2):202-207. |
| |
| Authors: | DAI Gui-ping YIN Bao-qun LI Yan-Jie ZHOU Ya-ping XI Hong-sheng |
| |
| Institution: | DAI Gui-ping 1,YIN Bao-qun 1,LI Yan-jie 1,ZHOU Ya-ping 2,XI Hong-sheng 1 |
| |
| Abstract: | Optimization algorithms are studied for a class of semi-Markov control processes (SMCPs) with infinite horizon average-cost criteria and compact action sets. By the equivalent Markov process, formulas of performance potentials and average-cost optimality equations for SMCPs are derived, and a policy iteration algorithm and a value iteration algorithm are proposed, which can lead to an optimal or suboptimal stationary policy in a finite number of iterations. The convergence of these algorithms is established, without the assumption of the corresponding iteration operator being an sp-contraction. A numerical example is provided to illustrate the application of the algorithms. |
| |
| Keywords: | semi-Markov control processes compact action set performance potentials policy iteration value iteration |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
