首页> 外文会议>17th Anniversary of the International Simulatros Conference, Apr 16-20, 2000, Washington, D.C. >APPLICATION OF SIMULATION AND NEURODYNAMIC PROGRAMMING TO OPTIMAL PORTFOLIO SELECTION
【24h】

APPLICATION OF SIMULATION AND NEURODYNAMIC PROGRAMMING TO OPTIMAL PORTFOLIO SELECTION

机译:模拟和神经动力学程序设计在最优组合选择中的应用

获取原文
获取原文并翻译 | 示例

摘要

The article is devoted to the application of simulation to optimal control generation process for systems without given mathematical models of their dynamics. We show an algorithm, called Q-learning, introduced in the last decade and still intensively being developed. With this algorithm, it is possible to calculate optimal control policy on the basis of simulation. Some results of a successful attempt of the application of Q-learning algorithm in the area of economy (optimization of investing strategy at Warsaw Stock Exchange) are also presented.
机译:本文致力于将仿真应用于没有给定动力学模型的系统的最优控制生成过程。我们展示了一种称为Q学习的算法,该算法在最近的十年中推出,并且仍在不断开发中。使用该算法,可以在仿真的基础上计算最佳控制策略。还介绍了在经济领域成功应用Q学习算法(在华沙证券交易所优化投资策略)的一些结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号