未找到相关数据
Neural Q-learning
被引：0
作者：
Stephan ten Hagen
Ben Kröse
机构：
[1] University of Amsterdam,Faculty of Science
来源：
Neural Computing & Applications
|
2003年
/
12卷
关键词：
Feed-forward network;
Learning from real systems;
Nonlinear systems;
Optimal control Reinforcement learning;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this paper we introduce a novel neural reinforcement learning method. Unlike existing methods, our approach does not need a model of the system and can be trained directly using the measurements of the system. We achieve this by only using one function approximator and approximate the improved policy from this. An experiment using a mobile robot shows that it can be trained using a real system within reasonable time.
引用
收藏
页码：81 / 88
页数：7
相关论文