Fast Reinforcement Learning By Mirror Images

被引：0

作者：

Kitao, Takehiro ^{[1
]}

Miura, Takao ^{[1
]}

机构：

[1] Hosei Univ, Dept Adv Sci, Kajinocho 3-7-2, Koganei, Tokyo, Japan

来源：

2016 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE (WI 2016) | 2016年

关键词：

Reinforcement Learning; Q-Learning; Mirror Images;

D O I：

10.1109/WI.2016.112

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we propose how to accelerate Q-learning which is one of the most successful reinforcement learning methods using mirror images for hunting problems. Mirror images have symmetric differences of views, and they allow us to accelerate Q-learning dramatically. In the results we show Q-learning goes 2 times faster (one mirror) or 3 times faster (2 mirrors) but a few percents of capturing ability decreases. Moreover, we prove that the proposed approach converges if the one with no mirror does.

引用

页码：660 / 663

页数：4