Cooperative Learning Based on Multi-Agent Systems

被引：0

作者：

Cheng Xian-yi ^{[1
,2
]}

Qiu Jian-lin ^{[1
]}

Liu Ying ^{[2
]}

机构：

[1] Nantong Univ, Coll Comp Sci, Nantong 226019, Peoples R China

[2] Jiangsu Univ, Coll Comp Sci & Commun Engn, Zhjiang 212013, Peoples R China

来源：

THIRD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING: WKDD 2010, PROCEEDINGS | 2010年

关键词：

machine learning; agent cooperation; genetic algorithm;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The paper propped a cooperation learning based on multi-agent system, The system comprised several agents, and agents with different study methods composed the learning part. To realize the cooperative study, a learning mode based on genetic algorithm is discussed deliberately.

引用

页码：455 / 457

页数：3

共 9 条

[1] Multiagent reinforcement learning using function approximation [J].

Abul, O ;

Polat, F ;

Alhajj, R .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2000, 30 (04) :485-497

[2]

BERENJI HR, 1999, 1999 IEEE INT FUZZ S, P621

[3] A ROBUST LAYERED CONTROL-SYSTEM FOR A MOBILE ROBOT [J].

BROOKS, RA .

IEEE JOURNAL OF ROBOTICS AND AUTOMATION, 1986, 2 (01) :14-23

[4]

Ho F, 1998, 1998 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS - PROCEEDINGS, VOLS 1-3, P279, DOI 10.1109/IROS.1998.724632

[5]

LIU Y, 2001, WUHAN U J NATURAL SC, V6, P547

[6] Combining reinforcement learning with GA to find co-ordinated control rules for multi-agent system [J].

Mikami, S ;

Mitsuo, W ;

Kakazu, Y .

1996 IEEE INTERNATIONAL CONFERENCE ON EVOLUTIONARY COMPUTATION (ICEC '96), PROCEEDINGS OF, 1996, :356-361

[7]

NILSSON N, 1991, ARTIF INTELL, V47, P71

[8]

Quinn M, 2000, 2000 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2000), VOLS 1-3, PROCEEDINGS, P1798, DOI 10.1109/IROS.2000.895232

[9] Cooperative learning and planning for multiple robots [J].

van der Zwaan, S ;

Moreira, JAA ;

Lima, PU .

PROCEEDINGS OF THE 2000 IEEE INTERNATIONAL SYMPOSIUM ON INTELLIGENT CONTROL, 2000, :351-356

← 1 →