Call for Papers
Second Symposium on Adaptive Agents and Multi-Agent Systems (AAMAS-2),
AISB'02 Convention, April 2002, Imperial College, London.
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
The proposed symposium is a continuation of the Symposium on Adaptive Agents
and Multi-Agent Systems, held as part of AISB-01 in York, March 2001. The
event was a pioneering experience, as no symposium on learning agents had
been organised previously in the UK. The success of the symposium has
encouraged us to propose AAMAS-2.
Chair: Eduardo Alonso
Department of Computing
Northampton Square, London EC1V 0HB
Co- Chair: Daniel Kudenko, Department of Computer Science, University of
Co- Chair: Dimitar Kazakov, Department of Computer Science, University of
- Eugenio Oliveira, Department of Computing and Electrical Engineering,
University of Porto.
- Pete Edwards, Department of Computer Science, University of Aberdeen.
- Niek Wijngaards, Department of Artificial Intelligence, Vrije
- Michael Schroeder, Department of Computing, City University.
- Kostas Stathis, Department of Computing, City University.
- Kurt Driessens, Computer Science Department, Catholic University of
Luc Steels, from Free University of Brussels, will give a keynote talk at
Topics of Interest
The proposed symposium will focus on (but is not limited to) the following
1. 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.
2. Logic-based learning: The ability to incorporate background knowledge to
the agents' decision-making and learning processes is arguably essential for
effective performance in complex, dynamic domains. Logic-based learning
mechanisms such as explanation-based learning and inductive logic
programming are being used to test this hypothesis.
3. Learning and communication When several learning agents work in a team it
may be beneficial for them to cooperate not just on the task achievement but
also on the learning process itself. Clearly, communication is an important
tool for such cooperation.
4. Natural selection, language and learning: These three issues are
inter-linked through the evolutionary search for the best language bias used
5. Evolutionary agents and emergent Multi-Agent structures: Genetic
algorithms are a particular machine learning approach that has been
successfully applied to social simulation and other multi-agent domains.
Specific techniques are still under development. One focus of this research
area is on observing emergent behaviors.
6. Industrial 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.
7. 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 separate theories are obtained.
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 2001. 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.
Abstract submission deadline 21st December 2001
Notification re: extended abstracts 31st January 2002
Submission of full papers 11th March 2002
Convention 2nd - 5th April 2002
Please note, the submission of full papers deadline must not be broken
because the convention starts very soon after this.
This archive was generated by hypermail 2b30 : Fri Oct 19 2001 - 13:28:08 MET DST