Strategy Entropy as a Measure of Strategy Convergence in Reinforcement Learning

摘要：

The concept of entropy is introduced into reinforcement learning.The definitions of the local and global strategy entropy are presented.The global strategy entropy is experimentally proved to be the quantitative problem-independent measure of the strategy’s convergence degree.The experimental results show that the learning based on the local strategy entropy improves the learning performance.

作者: Xiaodong Zhuang Zhuo Chen

作者单位: Electronics & Engineering Dept.,Automation Engineering College,Qingdao University,Qingdao,China College of Information Science & Technology,Qingdao University of Science and Technology,Qingdao,Chi

会议类型: 国际会议

会议名称: 第一届智能网络与智能系统国际会议(ICINIS 2008)(The First International Conference on Intelligent Networks and Intelligent Systems)

会议地点: 武汉

会议语种:英文

在线出版日期: 2008-11-01（万方平台首次上网日期，不代表论文的发表时间）