A survey on multiagent reinforcement learning towards multi-robot systems

Erfu Yang, Dongbing Gu

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

8 Citations (Scopus)

Abstract

Multiagent reinforcement learning for multirobot systems is a challenging issue in both robotics and artificial intelligence. With the ever increasing interests in theoretical research and practical applications, currently there have been a lot of efforts towards providing some solutions to this challenge. However, there are still many difficulties in scaling up multiagent reinforcement learning to multi-robot systems. The main objective of this paper is to provide a survey on multiagent reinforcement learning in multi-robot systems, based on the literature the authors collected. After reviewing some important advances in this field, some challenging problems are analyzed. A concluding remark is made from the perspectives of the authors.

Original languageEnglish
Title of host publicationIEEE 2005 Symposium on Computational Intelligence and Games, CIG'05
PublisherIEEE
Pages292-299
Number of pages8
Publication statusPublished - 1 Dec 2005
Event2005 IEEE Symposium on Computational Intelligence and Games, CIG'05 - Colchester, Essex, United Kingdom
Duration: 4 Apr 20056 Apr 2005

Conference

Conference2005 IEEE Symposium on Computational Intelligence and Games, CIG'05
CountryUnited Kingdom
CityColchester, Essex
Period4/04/056/04/05

Fingerprint

Reinforcement learning
Robots
Artificial intelligence
Robotics

Keywords

  • multi-robot systems
  • artificial Intelligence
  • multiagent reinforcement learning

Cite this

Yang, E., & Gu, D. (2005). A survey on multiagent reinforcement learning towards multi-robot systems. In IEEE 2005 Symposium on Computational Intelligence and Games, CIG'05 (pp. 292-299). IEEE.
Yang, Erfu ; Gu, Dongbing. / A survey on multiagent reinforcement learning towards multi-robot systems. IEEE 2005 Symposium on Computational Intelligence and Games, CIG'05. IEEE, 2005. pp. 292-299
@inproceedings{198a8436d76b4002b225e5ae1e462576,
title = "A survey on multiagent reinforcement learning towards multi-robot systems",
abstract = "Multiagent reinforcement learning for multirobot systems is a challenging issue in both robotics and artificial intelligence. With the ever increasing interests in theoretical research and practical applications, currently there have been a lot of efforts towards providing some solutions to this challenge. However, there are still many difficulties in scaling up multiagent reinforcement learning to multi-robot systems. The main objective of this paper is to provide a survey on multiagent reinforcement learning in multi-robot systems, based on the literature the authors collected. After reviewing some important advances in this field, some challenging problems are analyzed. A concluding remark is made from the perspectives of the authors.",
keywords = "multi-robot systems, artificial Intelligence, multiagent reinforcement learning",
author = "Erfu Yang and Dongbing Gu",
year = "2005",
month = "12",
day = "1",
language = "English",
pages = "292--299",
booktitle = "IEEE 2005 Symposium on Computational Intelligence and Games, CIG'05",
publisher = "IEEE",

}

Yang, E & Gu, D 2005, A survey on multiagent reinforcement learning towards multi-robot systems. in IEEE 2005 Symposium on Computational Intelligence and Games, CIG'05. IEEE, pp. 292-299, 2005 IEEE Symposium on Computational Intelligence and Games, CIG'05, Colchester, Essex, United Kingdom, 4/04/05.

A survey on multiagent reinforcement learning towards multi-robot systems. / Yang, Erfu; Gu, Dongbing.

IEEE 2005 Symposium on Computational Intelligence and Games, CIG'05. IEEE, 2005. p. 292-299.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - A survey on multiagent reinforcement learning towards multi-robot systems

AU - Yang, Erfu

AU - Gu, Dongbing

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Multiagent reinforcement learning for multirobot systems is a challenging issue in both robotics and artificial intelligence. With the ever increasing interests in theoretical research and practical applications, currently there have been a lot of efforts towards providing some solutions to this challenge. However, there are still many difficulties in scaling up multiagent reinforcement learning to multi-robot systems. The main objective of this paper is to provide a survey on multiagent reinforcement learning in multi-robot systems, based on the literature the authors collected. After reviewing some important advances in this field, some challenging problems are analyzed. A concluding remark is made from the perspectives of the authors.

AB - Multiagent reinforcement learning for multirobot systems is a challenging issue in both robotics and artificial intelligence. With the ever increasing interests in theoretical research and practical applications, currently there have been a lot of efforts towards providing some solutions to this challenge. However, there are still many difficulties in scaling up multiagent reinforcement learning to multi-robot systems. The main objective of this paper is to provide a survey on multiagent reinforcement learning in multi-robot systems, based on the literature the authors collected. After reviewing some important advances in this field, some challenging problems are analyzed. A concluding remark is made from the perspectives of the authors.

KW - multi-robot systems

KW - artificial Intelligence

KW - multiagent reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=65149099581&partnerID=8YFLogxK

UR - http://cswww.essex.ac.uk/cig/2005/papers/p1012.pdf

UR - http://cswww.essex.ac.uk/cig/2005/papers/proceedings.pdf

M3 - Conference contribution book

SP - 292

EP - 299

BT - IEEE 2005 Symposium on Computational Intelligence and Games, CIG'05

PB - IEEE

ER -

Yang E, Gu D. A survey on multiagent reinforcement learning towards multi-robot systems. In IEEE 2005 Symposium on Computational Intelligence and Games, CIG'05. IEEE. 2005. p. 292-299