期刊文献+

基于Q学习的供应链分销系统最优订货策略研究 被引量:2

Optimum Order Strategies for Distribution System of Supply Chain Based on Q-learning
下载PDF
导出
摘要 研究由一个制造商和多个分销商组成的分销系统的最优订货策略问题.在外部顾客需求不断变化的情况下,以不断提高分销系统双方合作绩效为目标,基于Q学习算法来确定每个分销商的最优订货批量.实例结果表明,在外部需求不断变化的条件下,该算法能简便地解决供应链企业分销系统合作中的最优订货批量问题. The optimum order strategies for the distribution system consisting of a single manufacturer and multidistributors in the supply chain management is discussed. In the case of the varying demand of customers, and with an aim at improving the cooperative performance of the distribution system, the optimum order batch of each distributor is determined based on the Q -learning algorithm. An example shows that this algorithm can simply solve the problem of the optimum order batch in the distribution system in the case of external ongoing changes in demand.
出处 《控制与决策》 EI CSCD 北大核心 2005年第12期1404-1407,共4页 Control and Decision
基金 陕西省自然科学基金项目(04JK263)
关键词 供应链管理 分销系统 Q学习算法 最优订货批量 Supply chain management Distribution system Q-learning algorithm Optimum order batch
  • 相关文献

参考文献10

二级参考文献46

  • 1PR科恩 周少柏等(译).人工智能手册(第三卷)[M].科学出版社,1991..
  • 2钱颂迪.运筹学(第2版)[M].北京:清华大学出版社,1990..
  • 3Sutton R S,Barto A G. Reimforcement learning: an introduction[M] .MA:MIT Press, 1998.
  • 4Brown X T. Low power wireless communication via reinforcement learning[A]. In: Advances in Neural Information Processing Systems[C] .MIT press,2000(12):893 ~ 899.
  • 5Mataric M J. Cetting humanoids to move and imitate[J].IEEE Intelligent Systems,2000(7): 18 ~ 24.
  • 6Mill' an R, Posenato D, Dedieu E. Continuous - Action Qlearning[ J]. Machine Learning,2002(49):247 ~ 265.
  • 7Shapiro D. Value - driven agents[ D]. Ph. D. thesis, Stanford University, 2001.
  • 8Rennie J, McCallum A. Using reinforcement leaming to spider the web efficiently[A]. In: Pwroc of International Conference on Machine Learning (ICML)[C] .1999.
  • 9Sutton R S. Open theoretical questions in reinforcement leaming[A]. In:Proc of EuroCOLT'99[ C] .1999,11 ~ 17.
  • 10Barto A G, Mahadevan S. Recent advances in hierarchical reinforcement learning [ J ]. Special Issue on Reinforcement Learning, Discrete Event Systems,2003,23(4): 197 ~ 223.

共引文献79

同被引文献26

引证文献2

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部