Deakin home > Deakin University Library > Deakin Research Online > A framework for co-ordination and learning among teams of agents

A framework for co-ordination and learning among teams of agents

Bui, Hung H., Venkatesh, Svetha and Kieronska, Dorota 1997, A framework for co-ordination and learning among teams of agents, in Agents and multi-agent systems : formalisms, methodologies, and applications : based on the AI'97 Workshops on Commonsense Reasoning, Intelligent Agents, and Distributed Artificial Intelligence, Springer, Heidelberg, Germany, pp. 164-178.

Attached Files (Some files may be inaccessible until you login with your Deakin Research Online credentials)
Name Description MIMEType Size Downloads

Title A framework for co-ordination and learning among teams of agents
Author(s) Bui, Hung H.
Venkatesh, Svetha
Kieronska, Dorota
Conference name Australian Joint Artificial Intelligence Conference (10th : 1997 : Perth, W. A.)
Conference location Perth, W. A.
Conference dates 30 Nov.-1 Dec. 1997
Title of proceedings Agents and multi-agent systems : formalisms, methodologies, and applications : based on the AI'97 Workshops on Commonsense Reasoning, Intelligent Agents, and Distributed Artificial Intelligence
Editor(s) Wobcke, Wayne
Pagnucco, Maurice
Zhang, Chengqi
Publication date 1997
Conference series Australian Joint Artificial Intelligence Conference
Start page 164
End page 178
Total pages 15
Publisher Springer
Place of publication Heidelberg, Germany
Keyword(s) team coordination
incomplete information
learning in multi-agent systems
Summary We present a framework for team coordination under incomplete information based on the theory of incomplete information games. When the true distribution of the uncertainty involved is not known in advance, we consider a repeated interaction scenario and show that the agents can learn to estimate this distribution and share their estimations with one another. Over time, as the set of agents' estimations become more accurate, the utility they can achieve approaches the optimal utility when the true distribution is known, while the communication requirement for exchanging the estimations among the agents can be kept to a minimal level.
ISBN 3540647694
Language eng
Field of Research 089999 Information and Computing Sciences not elsewhere classified
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1.1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30044851

Document type: Conference Paper
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in Deakin Research Online is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 17 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Tue, 01 May 2012, 11:02:25 EST