首页> 外文会议>Agents in principle, agents in practice >Adaption of Stepsize Parameter Using Newton's Method
【24h】

Adaption of Stepsize Parameter Using Newton's Method

机译:牛顿法自适应调整步长参数

获取原文
获取原文并翻译 | 示例

摘要

A method to optimize stepsize parameters in exponential moving average (EMA) based on Newton's method to minimize square errors is proposed. The stepsize parameters used in reinforcement learning methods should be selected and adjusted carefully for dynamic and non-stationary environments. To find the suitable values for the stepsize parameters through learning, a framework to acquire higher-order derivatives of learning values by the stepsize parameters has been proposed. Based on this framework, the authors extend a method to determine the best stepsize using Newton's method to minimize EMA of square error of learning. The method is confirmed by mathematical theories and by results of experiments.
机译:提出了一种基于牛顿法最小化平方误差的指数移动平均(EMA)参数优化方法。对于动态和非平稳环境,应仔细选择和调整用于强化学习方法的逐步参数。为了通过学习找到适合逐步参数的值,提出了一种通过逐步参数获取学习值的高阶导数的框架。在此框架的基础上,作者扩展了一种方法,该方法使用牛顿方法来确定最佳步长,以最小化学习的平方误差。通过数学理论和实验结果证实了该方法。

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