A comparative study of parallel reinforcement learning methods with a PC cluster system

被引：6

作者：

Kushida, Masayuki ^{[1
]}

Takahashi, Kenichi ^{[1
]}

Ueda, Hiroaki ^{[1
]}

Miyahara, Tetsuhiro ^{[1
]}

机构：

[1] Hiroshima City Univ, Fac Informat Sci, Hiroshima 7313194, Japan

来源：

2006 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON INTELLIGENT AGENT TECHNOLOGY, PROCEEDINGS | 2006年

关键词：

D O I：

10.1109/IAT.2006.3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a comparative study of three parallel implementation models for reinforcement learning. Two of them utilize Q-learning, and the other one utilizes fuzzy Q-learning for agent learning. In order to evaluate performance and validity of the three method, a PC(personal computer) cluster system consisting of 16 PCs connected via Gigabit ethernet has been built. For communications to deliver data among PCs, MPI (Message Passing Interface) is employed Experimental results are compared with one another to show the performance and characteristics of the three methods.

引用

页码：416 / +

页数：2