Deakin University
Browse

File(s) under permanent embargo

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

conference contribution
posted on 1997-01-01, 00:00 authored by H Bui, Svetha VenkateshSvetha Venkatesh, D Kieronska
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.

History

Event

Australian Joint Artificial Intelligence Conference (10th : 1997 : Perth, W. A.)

Pagination

164 - 178

Publisher

Springer

Location

Perth, W. A.

Place of publication

Heidelberg, Germany

Start date

1997-11-30

End date

1997-12-01

ISBN-10

3540647694

Language

eng

Publication classification

E1.1 Full written paper - refereed

Editor/Contributor(s)

W Wobcke, M Pagnucco, C Zhang

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

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC