| 基于强化学习的特征选择算法 |
| |
| 引用本文： | 朱振国,赵凯旋,刘民康. 基于强化学习的特征选择算法[J]. 计算机系统应用, 2018, 27(10): 214-218 |
| |
| 作者姓名： | 朱振国 赵凯旋 刘民康 |
| |
| 作者单位： | 重庆交通大学 信息科学与工程学院, 重庆 400074,重庆交通大学 信息科学与工程学院, 重庆 400074,重庆交通大学 信息科学与工程学院, 重庆 400074 |
| |
| 摘 要： | 针对在数据挖掘过程中存在的维度灾难和特征冗余问题，本文在传统特征选择方法的基础上结合强化学习中Q学习方法，提出基于强化学习的特征选择算法，智能体Agent通过训练学习后自主决策得到特征子集.实验结果表明，本文提出的算法能有效的减少特征数量并有较高的分类性能.
|
| 关 键 词： | 强化学习 特征选择 Q学习 特征子集 数据挖掘 |
| 收稿时间： | 2018-03-13 |
| 修稿时间： | 2018-03-20 |
Feature Selection Algorithm Based on Reinforcement Learning |
| |
| ZHU Zhen-Guo,ZHAO Kai-Xuan and LIU Min-Kang. Feature Selection Algorithm Based on Reinforcement Learning[J]. Computer Systems& Applications, 2018, 27(10): 214-218 |
| |
| Authors: | ZHU Zhen-Guo ZHAO Kai-Xuan LIU Min-Kang |
| |
| Affiliation: | School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, China,School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, China and School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, China |
| |
| Abstract: | For the dimensional disaster and feature redundancy problems in the process of data mining, a reinforcement learning based feature selection algorithm, which is combined Q learning methods with traditional feature selection methods, is proposed in this study. In the proposed method, the agent acquires a subset of characteristics autonomously through training and learning. Experimental results show that the proposed algorithm can effectively reduce the number of features and has higher classification performance. |
| |
| Keywords: | reinforcement learning feature selection Q-learning feature subset data mining |
|
| 点击此处可从《计算机系统应用》浏览原始摘要信息 |
|
点击此处可从《计算机系统应用》下载全文 |
|
