Preference-aware Web Service Composition Using Hierarchical Reinforcement Learning

被引：0

作者：

Wang, Hongbing ^{[1
]}

Guo, Xiaohui ^{[1
]}

机构：

[1] Southeast Univ, Sch Comp Sci & Engn, Nanjing, Peoples R China

来源：

2009 IEEE/WIC/ACM INTERNATIONAL JOINT CONFERENCES ON WEB INTELLIGENCE (WI) AND INTELLIGENT AGENT TECHNOLOGIES (IAT), VOL 3 | 2009年

关键词：

Web Service Composition; Hierarchical Reinforcement Learning; MAXQ and Logic of Preference;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Dynamic web service composition is currently a hot issue in research. It mainly focuses on function-oriented or QoS-oriented, but the research combines with them are scanty. In this paper, we propose an HRLPLA algorithm to implement dynamic composition using hierarchical reinforcement learning and preference reasoning, which can consider both function-oriented and Qos-oriented. Experimental results will show its high effectiveness.

引用

页码：315 / 318

页数：4

共 7 条

[1]

ABOU R, 2007, IEEE INT C FUZZ SYST, P1

[2]

Alonso G., 2003, Web Services, V2004

[3] Recent Advances in Hierarchical Reinforcement Learning [J].

Andrew G. Barto ;

Sridhar Mahadevan .

Discrete Event Dynamic Systems, 2003, 13 (4) :341-379

[4]

Dietterich T. G., 2000, J ARTIFICIAL INTELLI

[5]

GAO AQ, 2005, ADV WEB AGE INFORM M

[6]

Hongbing Wang, 2008, 2008 IEEE Congress on Services Part II (SERVICES-2), P163, DOI 10.1109/SERVICES-2.2008.15

[7]

XIONG PC, 2007, IEEE 4 INT C FUZZ SY, V3, P632

← 1 →