| 强化学习中资格迹的作用 |
| |
| 引用本文： | 孙羽,张汝波,徐东.强化学习中资格迹的作用[J].计算机工程,2002,28(5):128-129,198. |
| |
| 作者姓名： | 孙羽 张汝波 徐东 |
| |
| 作者单位： | 1. 湛江海洋大学工程学院计算机系,湛江,524088
2. 哈尔滨工程大学计算机系,哈尔滨,150001 |
| |
| 基金项目： | 黑龙江省自然科学基金资助项目()F9911 |
| |
| 摘 要： | 强化学习一词来自行为心理学，该学科把学习看作反复试验的过程，强化学习系统中的资格迹用来解决时间信度分配问题，文章介绍了资格迹的基本原理和实现方法。
|
| 关 键 词： | 资格迹 强化学习 机器学习 智能系统 |
| 文章编号： | 1000-3428(2002)05-0128-02 |
The Function of Eligibility Traces in Reinforcement Learning |
| |
| SUN Yu,ZHANG Rubo,XU Dong.The Function of Eligibility Traces in Reinforcement Learning[J].Computer Engineering,2002,28(5):128-129,198. |
| |
| Authors: | SUN Yu ZHANG Rubo XU Dong |
| |
| Affiliation: | SUN Yu1,ZHANG Rubo2,XU Dong2 |
| |
| Abstract: | The word, reinforcement learning, comes from behavior psychology. This subject takes learning as trial and error process so as to map world state to the actions. The eligibility traces of reinforcement learning system are used to solve temporal credit assignment problems. In this paper, the basic principle and implementation methods of eligibility traces are presented. ;; |
| |
| Keywords: | Eligibility traces Reinforcement learning Machine learning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
