Held in association with AAMAS 2007, in Honolulu, Hawai'i, May 14-18, 2007.


Click HERE to Register


Click HERE for the Call for Proposals


Accepted Papers

(Click HERE for Proceedings)

  • "Approximate State Estimation in Multiagent Settings with Continuous or Large Discrete State Spaces"
    Prashant Doshi

  • "Bounded Dynamic Programming for Decetralized POMDPs"
    Christopher Amato, Alan Carlin and Shlomo Zilberstein

  • "Dec-POMDPs with Delayed Communication"
    Frans A. Oliehoek, Matthijs T.J. Spaan and Nikos Vlassis

  • "Applying MDP Approaches for Estimating Outcome of Interaction in Collaborative Human-Computer Settings"
    Ece Kamar and Barbara J. Grosz

  • "Agent Influence as a Predictor of Difficulty for Decentralized Problem-Solving"
    Martin Allen and Shlomo Zilberstein

  • "Anytime Coordination Using Separable Bilinear Programs"
    Marek Petrik and Shlomo Zilberstein

  • "Detecting Deviations from Joint Plans in Cooperative Multi-Agent Systems"
    Doran Chakraborty and Sandip Sen

  • "On Opportunistic Techniques for Solving Decentralized Markov Decision Processes with Temporal Constraints"
    Janusz Marecki and Milind Tambe
The presentation order and times are still to be determined.

Overview

Sequential decision making under uncertainty is the problem an agent faces when it tries to maximize its performance through interacting with its environment (and possibly other agents) based upon its observations of the world. Single-agent decision-theoretic approaches to this problem have centered around two primary models, the Markov Decision Problem (MDP) and the Partially Observable Markov Decision Problem (POMDP), depending on whether the agent's knowledge about the world is complete or partial.

These mathematically rigorous models have been used very successfully in single-agent systems so it is only natural to apply them to systems with many agents. Just as in single-agent decision-theoretic work, the decision-theoretic multi-agent community has focused on two kinds of models: i) where each agent has complete knowledge about the state of the world, and ii) where each agent has partial (and potentially different) knowledge about the state of the world.

The high computational complexity of finding optimal solutions in these multi-agent models has been a significant barrier to applying them to complex real world problems. Much of the work in this area relates to addressing this complexity through exploiting problem structure like locality of interaction, decomposition of reward and independence between the agents, and through approximate algorithms that converge to a local optimum instead of a global optimum.

The purpose of this workshop is to bring together researchers in the field of sequential decision-making in stochastic multi-agent systems to present and discuss promising new work, to discuss the relationships between the various models in use, and to establish important directions and goals for further research and collaboration. This workshop will strive to develop consensus within the community on benchmarks and evaluation methodology in order to contrast the alternative approaches and models, and to study the tradeoffs associated with the use of each. Furthermore, we will discuss the creation of online problem sets for testing the various algorithms to facilitate comparison.

Topics

The workshop will address a range of topics relating to new and existing models of multi-agent systems (i.e. MMDP, Dec-MDP, Dec-POMDP, Dec-MDP-Com, MTDP, COM-MTDP, R-MTDP, E-MTDP, EMT, I-POMDP, POSG, POIPSG, ND-POMDP, TI-Dec-MDP) including:
  • Relationships between the models and their assumptions
  • Algorithms for policy generation and coordination
  • Comparisons of algorithms
  • Distributed vs. centralized planning
  • Online vs. offline planning
  • Communication during policy generation
  • Communication decisions during execution
  • Techniques for scaling problems
  • Identifying subclasses of problems and their complexity
  • Cooperative and competitive agent systems
  • Theoretical and empirical results
  • Benchmarks and evaluation methodologies for comparing different approaches

Important Dates

FEBRUARY 5, 2007: Workshop paper submission deadline

MARCH 5, 2007: Notification of accepted papers

MARCH 19, 2007: Camera-ready submission

MAY 14 or 15, 2007: Day of workshop

Submission Procedure

Authors are encouraged to submit papers up to 15 pages in length in the standard LaTeX Article format (12 pt font). Submissions should be sent to msdm2007@gmail.com, in PostScript or PDF form. Each submission will be reviewed by at least two Program Committee members.

Organizing Committee

Rajiv Maheswaran
Computer Science Department and Information Sciences Institute,
University of Southern California
USC-ISI, 4676 Admiralty Way, #1001, Marina Del Rey, CA 90292
Phone: +1(310) 448-8269
http://cs.usc.edu/~maheswar

Jiaying Shen
Department of Computer Science,
University of Massachusetts Amherst
140 Governor's Drive, Amherst, MA 01003, USA
Phone: +1(413)545-3444
http://www.cs.umass.edu/~jyshen

Pradeep Varakantham
Computer Science Department,
University of Southern California
PHE 204 3737 Watt Way, Los Angeles, CA 90089
Phone: +1 (213) 740-6569

Program Committee

Raphen Becker University of Massachusetts
Daniel Bernstein University of Massachusetts
Aurelie Beynier University of Caen
Dmitri Dolgov University of Michigan
Prashant Doshi University of Georgia
Rosemary Emery-Montemerlo Google
Piotr Gmytrasiewicz University of Illinois--Chicago
Eric Hansen Mississippi State University
Sven Koenig University of Southern California
Victor Lesser University of Massachusetts
Abdel-Illah Mouaddib Universite de Caen
David Musliner Honeywell Laboratories
Ranjit Nair Germinit Solutions
Praveen Paruchuri University of Southern California
John Phelps Honeywell Laboratories
David Pynadath Information Sciences Institute
Zinovi Rabinovich Hebrew University
Anita Raja University of North Carolina at Charlotte
Jeffrey Rosenschein Hebrew University
Maayan Roth Carnegie Mellon University
Matthijs Spaan Institute for Systems and Robotics - Lisbon
Milind Tambe University of Southern California
Ping Xuan Clark University
Makoto Yokoo Kyushu University
Shlomo Zilberstein University of Massachusetts