Study on Online εNN Q-Learning for Multi-Robot System Based on Community Perception Network

被引：0

作者：

Jin, Lu ^{[1
]}

Yang, Yuequan ^{[1
]}

Ni, Chunbo ^{[1
]}

Kong, Yifei ^{[1
]}

Cao, Zhiqiang ^{[2
]}

机构：

[1] Yangzhou Univ, Coll Informat Engn, Yangzhou 225009, Jiangsu, Peoples R China

[2] Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China

来源：

PROCEEDINGS OF 2013 CHINESE INTELLIGENT AUTOMATION CONFERENCE: INTELLIGENT AUTOMATION | 2013年 / 254卷

基金：

中国国家自然科学基金;

关键词：

Multi-robot system; Q-learning; epsilon NN; Community perception network;

D O I：

10.1007/978-3-642-38524-7_96

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Considering the curse of dimensionality and inadequate learning of the historical information provided by the other robots, an online epsilon-radius Nearest Neighbors (epsilon NN) classification method is employed in the community perception network environment. In order to increase learning efficiency, a new multi-robot reinforcement learning strategy is proposed by employing classification of historical states and information sharing mechanism. Finally, the analysis of convergence of Q values matrix is done, and simulations are shown the effectiveness and efficiency of the proposed scheme.

引用

页码：861 / 868

页数：8

共 18 条

[1] Robust high performance reinforcement learning through weighted k-nearest neighbors
Antonio Martin H, Jose
de Lope, Javier
Maravall, Dario
[J]. NEUROCOMPUTING, 2011, 74 (08) : 1251 - 1259
[2] Martín JA, 2009, LECT NOTES COMPUT SC, V5601, P305, DOI 10.1007/978-3-642-02264-7_32
[3] Martín JAH, 2007, LECT NOTES COMPUT SC, V4739, P138
[4] Chao S, 2010, IEEE RSJ INT C INT R, P5302
[5] Gao Yang, 2004, Acta Automatica Sinica, V30, P86
[6] Geng XL, 2011, SCI TECHNOL ENG, V11, P756
[7] Han F, 2012, PROCEEDINGS OF THE 10TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA 2012), P3648, DOI 10.1109/WCICA.2012.6359080
[8] Jin L., 2012, INT C MECH AUT CONTR, P511
[9] A Communication Robot in a Shopping Mall
Kanda, Takayuki
Shiomi, Masahiro
Miyashita, Zenta
Ishiguro, Hiroshi
Hagita, Norihiro
[J]. IEEE TRANSACTIONS ON ROBOTICS, 2010, 26 (05) : 897 - 913
[10] Ke WD, 2012, COMPUT APPL, V48, P207

← 1 2 →