=========================================
Apologies if you receive multiple copies.
=========================================
AGENTS-00/ECML-00 Joint Workshop
on
Learning Agents
June 3,2000
Barcelona, Spain
**********************
Call for Participation
**********************
Description
-----------
Machine learning research has matured into an effective tool at the
disposition of the designer/developer of intelligent agent based systems.
Such agents often work in environments which are at best partially
understood and where the domain characteristics or participants change over
time. In addition, agents can serve their associated users much more
effectively if they are able to capture the unspecified and/or changing
preferences of these users.
Another aspect of agent based systems is that they often are situated in a
multiagent environment. Agents in such systems have to interact both with
associated users and other agents in their environments. Coordination of
the activities of multiple agents, whether selfish or cooperative, is
essential for the viability of any system in which multiple agents must
coexist. Learning and adaptation are invaluable mechanisms by which agents
can evolve coordination strategies that meet the demands of the
environments and the requirements of individual agents.
Recognizing the applicability and limitations of current machine learning
research when applied to situated agents will be of particular relevance to
this workshop.
We emphasize three different ways in which machine learning can be used
to enhance the performance of an Agent Based System:
1) An agent can learn the preferences and changing priorities of associated
users.
2) An agent can learn about other agents in the environment in
order to compete and/or cooperate with them. An agent can learn from
other agents, taking advantage of their experiences and incorporating
these into its own knowledge base.
3) An agent can learn about other regularities in its environment.
Topics of interest
------------------
The goal of this workshop is to focus on research that addresses
unique requirements for agents learning and adapting to their
environment. The workshop authors were asked to address the
following and related issues:
1) Benefits of adaptive/learning agents over agents with fixed behavior.
2) Evaluation of the effectiveness of individual learning strategies
(e.g., case-based, explanation-based, inductive), or multistrategy
combinations.
3) Characterization of learning and adaptation methods in terms of
modeling power, communication abilities, knowledge requirement,
processing abilities of individual agents.
4) Developing learning and adaptation strategies, or reward
structures, for environments with cooperative agents, selfish
agents, partially cooperative (will cooperate only if individual
goals are not sacrificed) and for environments that can contain
mixture of these types of agents.
5) Analyzing and constructing algorithms that guarantee convergence
and stability of group behavior.
6) Analyzing effects of knowledge acquisition mechanism on
responsiveness of agents or groups to addition/deletion of other
agents from the environment.
7) Agents learning via passive or non-intrusive observation of user
behaviors.
8) Agents learning to serve its user better by observing other agents
do their job.
9) Evolving agent behaviors or co-evolving multiple agents with
similar/opposing interests.
10) Investigation of teacher-student relationships between the agent and
associated user.
Registration Information:
------------------------
This workshop is associated with both ECML-2000 and Agents-2000. You
must register for at least one of these conferences to participate.
The relevant URLs can be accessed from
http://www.iiia.csic.es/ecml2000 and
http://www.iiia.csic.es/agents2000 (mirrored at http://agents2000.cs.umn.edu)
Organizing Committee
--------------------
Peter Stone (Co-Chair), AT&T Labs -- Research, [log in to unmask]
Sandip Sen (Co-Chair), University of Tulsa, [log in to unmask]
Hans-Dieter Burkhard, Humboldt University, [log in to unmask]
Jeff Rosenschein, Hebrew University, [log in to unmask]
Moshe Tennenholtz, Technion/Stanford University, [log in to unmask]
Eiji Uchibe, Osaka University, [log in to unmask]
Jose Vidal, University of South Carolina, [log in to unmask]
Program (tentative)
--------
June 3, 2000
09:00 - 09:15 Opening Remarks
09:15 - 09:40 "Learning Models of Other Agents"
Ricardo Aler, Daniel Borrajo, Ines Galvan, and Agapito Ledezma
09:40 - 10:05 "Quantifying the utility of building agent models: An
experimental study"
Leonardo Garrido, Katia Sycara, and Ramon Brena
10:05 - 10:30 "Inducing Decision Trees for Agent Capability Assessment"
Enrico Blanzieri and Gerhard Wickler
10:30 - 11:00 Coffee Break
11:00 - 11:25 "An Illustration of The COIN Approach to Design of Multi-Agent Systems"
David H. Wolpert and Kagan Tumer
11:25 - 11:50 "Combining Multiple Perspectives"
Bikramjit Banerjee, Sandip Debnath, and Sandip Sen
11:50 - 12:15 "The Risk of Exploration in Multi-Agent Learning systems: A Case Study"
Andres Perez-Uribe and Beat Hirsbrunner
12:15 - 12:40 "A Personalized Web-Search Agent based on Monitoring
User Actions: First Results"
Yubelsi Bello, Victor Dias, Sandra Zabala, and Gabor
Loerincs
12:40 - 13:00 Research Summaries:
"Machine Learning and Musical Improvisation"
Belinda Thom
"Data Partitioning for Collaborative Learning Agents"
Steven J. Lynden and Omer F. Rana
"Intelligent Assistants and Smart Environments"
Michael Mahan and Mark R. Adler
13:00 - 14:30 Lunch Break
14:30 - 14:55 "Evaluating Competitive Learners"
Bikramjit Banerjee, Sandip Sen, and Jing Peng
14:55 - 15:20 "On Behavior Classification in Adversarial Environments"
Patrick Riley and Manuela Veloso
15:20 - 16:00 Invite Talk: Pat Langley
Title TBA
16:00 - 16:30 Coffee Break
16:30 - 16:55 "Agents that Learn from Distributed Dynamic Data Sources"
Doina Caragea, Adrian Silvescu, and Vasant Honavar
16:55 - 17:30 Panel (TBA)
OR
16:55 - 17:10 Closing comments
For further information visit the following URL:
http://www.mcs.utulsa.edu/~sandip/wshop/agents00
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
