In order to enhance the study speed and the convergence rate of Q-learning algorithm, an algorithm that based on the experience knowledge about environment is proposed.
为了提高智能体系统中的典型的强化学习——Q -学习的学习速度和收敛速度，使学习过程充分利用环境信息，本文提出了一种基于经验知识的Q -学习算法。
Author believes that the problems of the disciplinary convergence in the final analysis are the problem of how to manage the knowledge of the organization efficiently.
作者认为，学科会聚平台出现的弊端，归根结底就是如何高效管理组织知识的问题。
The main features of DE are simple to use, fast convergence speed and few field knowledge needed.
它的主要特点是算法简单、收敛速度快，所需领域知识少。
This paper introduces the method with examples to explain it, including its connective knowledge, theory bases, error estimation, convergence order, and the choosing rule for starting value of it.
牛顿迭代法也称为牛顿切线法，是解非线性方程的一种方法，通过实例对该方法进行了介绍，包括其理论依据、误差估计、收敛阶数、迭代法初始值的选取规则等。
This paper introduces the method with examples to explain it, including its connective knowledge, theory bases, error estimation, convergence order, and the choosing rule for starting value of it.
牛顿迭代法也称为牛顿切线法，是解非线性方程的一种方法，通过实例对该方法进行了介绍，包括其理论依据、误差估计、收敛阶数、迭代法初始值的选取规则等。
应用推荐