Adaptive and Learning Agents Workshop (ALAg 07) - A Workshop at AAMAS-2007
  


AAMAS 2007 Workshop on

Adaptive and Learning Agents (ALAg-07)


Workshop Schedule:

8:45-9:00 Opening Remarks  
9:00-9:25 Consistent Exploration Improves Convergence of Reinforcement Learning on POMDPs Paul A. Crook and Gillian Hayes
9:25-9:45 Using Adaptive Consultation of Experts to Improve Convergence Rates in Multiagent Learning Greg Hines and Kate Larson
9:45-10:10 Limiting Games of Multi-agent Multi-state Problems Peter Vrancx, Katja Verbeeck, and Ann Nowe
10:10-10:30 Labeled Initialized Adaptive Play Q-learning for Stochastic Games Andriy Burkov and Brahim Chaib-draa
10:30-11:00 Break  
11:00-12:15 Panel Discussion: New Directions for Learning Agents  
12:15-2:00 Lunch  
2:00-2:25 A Bee Algorithm for Multi-agent Systems: Recruitment and Navigation Combined Nyree Lemmens, Steven de Jong, Karl Tuyls, and Ann Nowe
2:25-2:50 Prediction in Dynamic Environment: Robocup Rescue Exploration Andy Song, Lin Padgham, and Lawrence Cavendon
2:50-3:15 Learning to Identify Beneficial Partners Sandip Sen, Anil Gursel, and Stephane Airiau
3:15-3:40 Learning Policy Selection for Autonomous Intersection Management Kurt Dresner and Peter Stone
3:40-4:00 Meta-level Control of Multiagent Learning in Dynamic Resource Sharing Problems based on the WoLF Principle Itsuki Noda and Masayuki Ohta
4:00-4:30 Break  
4:30-4:50 Effective Policies for Resource Limited Agents Matt Knudson and Kagan Tumer
4:50-5:10 Norm Emergence in Spatially Constrained Interactions Partha Mukherjee, Sandip Sen, and Stephane Airiau
5:10-5:30 A Learning Approach to Dynamic Coalition Formation Enrique Munoz de Cote, Alessandro Lazaric, and Marcello Restelli
5:30-5:45 Discussion and Closing Remarks  


Call for Papers:
As agent-based systems get larger and more complex, there is a compelling need for agents to learn and adapt to their dynamic environments. Indeed, how to adaptively control, coordinate and optimize adaptive multiagent systems is one of the emerging multi-disciplinary research areas today. Such systems are often deployed in real-world situations with stochastic environments where agents have limited perception and communication capabilities. Furthermore, in a number of distributed domains without centralized control, different agents will have different behaviors, capabilities, learning strategies, etc. There is a pressing need, then, to both study and develop the convergence of multiple learners using the same learning scheme as well as understand the emergent dynamics of multiple learners with varying learning schemes.
This workshop will explore all agent learning approaches, with particular emphasis on multiagent settings where the scale and complexity of the environment require novel learning techniques. We anticipate this workshop to grow into a yearly event as it addresses an emerging multi-disciplinary research topic at the intersection of Computer Science, Control Theory, and Economics. We welcome and encourage all researchers actively involved in this area to contribute to this workshop.

The topics of interest include but are not limited to:
  • Reinforcement learning in multiagent systems
  • Adaptation and learning in dynamic environments
  • Evolution of agents in complex environments
  • Co-evolution of agents in a multiagent setting
  • Cooperative exploration
  • Learning to cooperate and collaborate
  • Learning trust and reputation
  • Learning to negotiate
  • Learning information agents
  • Coordination in large multiagent systems
  • Communication restrictions and their impact on multiagent coordination
  • Team formation in multiagent systems
  • Reward structure design for cooperation in multiagent systems
  • Evolutionary fitness design for coordination
  • Scaling learning techniques to large multiagent systems
  • Coordination of heterogeneous agents
  • Game theoretical analysis of multiagent systems
  • Emergent behavior in multiagent systems
  • Neuro control in multiagent systems
  • Bio-inspired control in large multiagent systems
Applications of these methods span:
  • Controlling multiple autonomous vehicles
  • Managing traffic congestion
  • Routing data over a network
  • Controlling constellations of satellites
  • Coordinating thousands of simple devices
  • Managing power distribution
  • Stabilizing aircraft wings
  • Flying in formation
  • Morphing matter: Smart structures/adaptive wings
  • Coordinating (micro) air vehicles
  • Managing system health
  • Controlling nano/micro devices
  • Managing air traffic flow
  • Information assurance and security infrastructure management
  • Agent based web and data mining
The goal of this workshop is to bring together not only scientists from different areas of computer science, e.g., agent architectures, reinforcement learning, evolutionary algorithms but also from different fields studying similar concepts, e.g., game theory, bio-inspired control, mechanism design. This workshop will serve as an inclusive forum for the discussion on ongoing or completed work and include both theoretical and practical issues.


Organizing Committee:
Kagan Tumer
        Oregon State University
        204 Rogers Hall, Corvallis, OR 97331, USA
       
        http://engr.oregonstate.edu/~ktumer
Sandip Sen
        The University of Tulsa
        600 S. College, Tulsa, OK 74104, USA
       
        http://www.mcs.utulsa.edu/~sandip/
Liviu Panait
        Google Inc.
        604 Arizona Ave, Santa Monica, CA 90405, USA
       
        http://cs.gmu.edu/~lpanait/

Venue:
ALAg-07 will be held at the Hawaii Convention Center in Honolulu, Hawaii, as part of the workshop program at the Sixth International Conference on Autonomous Agents and Multi Agent Systems (AAMAS 07). For local information, including registration and accomodotation details, please visit the main AAMAS 2007 website.

Program committee:
Adrian Agogino, U. California, Santa Cruz, USA
Jake Crandall, MIT, USA
Edwin De Jong, Universiteit Utrecht, Netherlands
Alan Fern, Oregon State University, USA
Pieter Jan 't Hoen, Centrum voor Wiskunde en Informatica, Netherlands
Daniel Kudenko, University of York, UK
Akira Namatame, National Defense Academy, Japan
Eugenio Oliveira, Universidade de Porto, Portugal
Lynne Parker, University of Tennessee, USA
David Parkes, Harvard University, USA
Simon Parsons, Brooklyn College, USA
Enric Plaza, Institut d'Investigacio en Intelligencia Artificial, Spain
Jeffrey Rosenschein, The Hebrew University of Jerusalem, Israel
Michael Rovatsos, Centre for Intelligent Systems and their Applications, UK
Gerry Tessauro, IBM T. J. Watson Research Center, USA
Karl Tuyls, University of Maastricht, Netherlands
Eiji Uchibe, Okinawa Institute of Science and Technology, Japan
Katja Verbeeck, Vrije Universiteit Brussel, Belgium


Important Dates:
    Deadline for Submitting Contributions:
    Acceptance Notification to authors:
    Deadline for camera-ready Contributions:
    ALAg 07 Workshop:
    February 15, 2007
    March 5, 2007
    March 19, 2007
    May 14, 2007


Submission Requirements:
The papers (up to 5 pages in length) must follow the AAMAS-2007 guidelines for paper submission (more information about the formatting can be found here, check the sections for Word or Word Perfect Users and LaTeX Users). Papers (in PDF format) should be emailed to Liviu Panait at lpanait@cs.gmu.edu (as well as any comments related to the submission process). Please include "ALAg-07 WORKSHOP SUBMISSION" in the subject of the email, and include the paper as an attachment. Expect an acknowledgement of receipt within a week (if you do not receive an email confirmation, please contact us via email to make sure we have received your paper).