Symposium on
Adaptive Agents and Multi-Agent Systems
22 - 23 March 2001
Sponsored by AISB
and AgentLink2
Program
The program of the Symposium can be viewed here. Abstracts of the accepted papers are also available online.
Motivation
In recent years, Intelligent agents and multi-agent systems have become
a highly active area of AI research. Intelligent Agents have been developed
and applied successfully in many domains, such as e-commerce, human-computer
interaction, entertainment, process management and traffic control.
When designing agent systems, it is impossible to foresee all the potential
situations an agent may encounter and specify an agent behavior optimally
in advance. Agents therefore have to learn from and adapt to their environment.
This task is even more complex when nature is not the only source of uncertainty,
and the agent is situated in an environment that contains other agents
with potentially different capabilities, goals, and beliefs. Multi-Agent
Learning, i.e., the ability of the agents to learn how to cooperate and
compete, becomes crucial in such domains.
The goal of this symposium is to increase awareness and interest in
adaptive agent research, encourage collaboration between ML experts and
agent system experts, and give a representative overview of current research
in the area of adaptive agents. The symposium will serve as an inclusive
forum for the discussion on ongoing or completed work in both theoretical
and practical issues.
Programme Committee
Chair: Daniel Kudenko
Department of Computer Science
University of York
Heslington, York, YO10 5DD
United Kingdom
kudenko@cs.york.ac.uk
Co- Chair: Eduardo Alonso,
Department of Computer Science, University of York
Programme Committee:
-
Michael
Fisher, Department of Computer Science, Manchester Metropolitan University.
-
Christophe Giraud-Carrier,
Department of Computer Science, University of Bristol.
-
Lyndon Lee, Intelligent
Agents Research Group, British Telecom Laboratories.
-
Michael Luck, Department
of Electronics and Computer Science, University of Southampton.
Keynote Speaker
Enric
Plaza will give a keynote talk at the symposium.
Topics of Interest
The proposed symposium will focus on (but is not
limited to) the following areas:
-
Learning and adaptation in Multi-Agent Systems:
The ability to learn is especially important for an agent when there are
other agents acting in the environment. An important open question is whether
and how single-agent learning techniques can be adapted to and applied
in a multi-agent setting.
-
Evolutionary agents and emergent Multi-Agent structures:
A particular machine learning approach that has been successfully applied
to social simulation and other multi-agent domains are genetic algorithms.
Specific techniques are still under development. One focus of this research
area is on observing emergent behaviors.
-
Learning from interaction with humans: The
problem how computers can adapt to individual users (i.e., the automatic
personalization of computers and software) is an important challenge in
the area of human-computer interaction.
-
Learning by observation, imitation, and cooperation:
These are three of the most important ways for agents to learn in multi-agent
systems and currently an active area of research.
-
Practical applications of learning agents:
Agent technology is already having a strong impact on various applications,
including e-commerce, entertainment, human-computer interfaces, and plant
control. Many of these applications are being equipped with machine learning
technology.
-
Agent learning and cognition: How can single-agent
and multi-agent (i.e., collaborative) learning be viewed as a cognitive
process, and what general principles can be derived from this?
-
Distributed Learning: The major question in
this area is how agents can learn in a collaborative way as a group. This
is in contrast to the alternative view on multi-agent learning where agents
in a group learn individually and the learning processes are mostly isolated
from each other.
Submissions
Initially, we require an extended abstract, up to four pages in
length (at least 10pt font). The following formats are acceptable:
-
Paper: A4, 3 copies
-
Email: PDF, Postscript, or MS Word
Please submit your abstracts on or before 21st December 2000. Please
post or email submissions to the programme chair (address given above).
Full papers (submitted after the extended abstract has been accepted)
should be no longer than 12 pages.
Accepted symposium papers will be published by AISB and the proceedings
will have an ISBN number.
Timetable
| Abstract submission deadline |
21st December 2000 |
| Notification re: extended abstracts |
20th January 2001 |
| Submission of full papers |
1st March 2001 |
| Convention |
21st - 24th March 2001 |
Please note, the submission of full papers deadline must not be broken
because the convention starts very soon after this.
Contacts and Links
If you have any questions about this symposium, please contact the programme
chair, either at the address given above, or by email: kudenko@cs.york.ac.uk
If you have any questions about the AISB'01 convention, please contact
the convention chair, Simon Colton: simonco@cs.york.ac.uk
If you have any questions about the local arrangements, please contact
the local arrangements chair, Eduardo Alonso: ea@cs.york.ac.uk
AISB'01
Convention Home Page (See this for accommodation, etc.)
The Society for the Study
of Artificial Intelligence and the Simulation of Behaviour (AISB)
How to reach York University
Gateway to York
York Tourism