中国邮电高校学报(英文)

• Others • 上一篇    下一篇

Artificial emotion model based on reinforcement learning mechanism of neural network

史雪飞1,Zhi-liang Wang1,An PING2   

  1. 1. 北京科技大学
    2.The Translation Group of the Certain Department of the Second Artillery of PLA, Beijing 100015, China
  • 收稿日期:2010-11-03 修回日期:2011-02-18 出版日期:2011-06-30 发布日期:2011-06-13
  • 通讯作者: Zhi-liang Wang E-mail:wangzhiliang@ies.ustb.edu.cn
  • 基金资助:

    论文得到863国家高技术发展计划(2007AA04Z218)的支持;北京市自然科学基金重点项目(KZ200810028016)的支持

Artificial emotion model based on reinforcement learning mechanism of neural network

  • Received:2010-11-03 Revised:2011-02-18 Online:2011-06-30 Published:2011-06-13

摘要:

A hierarchical-processed frame construction of artificial emotion model for intelligent system is proposed in the paper according to the basic conclusion of emotional psychology. The general method of emotion processing, which considers only one single layer, has been changed in the presented construction. An artificial emotional development model is put forward based on reinforcement learning mechanism of neural network. The new model takes the emotion itself as reinforcement signal and describes its different influences on action learning efficiency corresponding to different individualities. In the end, simulation result based on child playmate robot is discussed and the effectiveness of the model is verified.

关键词:

artificial emotion model, reinforcement learning, hierarchical structure, neural network

Abstract:

A hierarchical-processed frame construction of artificial emotion model for intelligent system is proposed in the paper according to the basic conclusion of emotional psychology. The general method of emotion processing, which considers only one single layer, has been changed in the presented construction. An artificial emotional development model is put forward based on reinforcement learning mechanism of neural network. The new model takes the emotion itself as reinforcement signal and describes its different influences on action learning efficiency corresponding to different individualities. In the end, simulation result based on child playmate robot is discussed and the effectiveness of the model is verified.

Key words:

artificial emotion model, reinforcement learning, hierarchical structure, neural network