Loading ...
Sorry, an error occurred while loading the content.

9682nd CFP: MSDM Workshop @ AAMAS 2014

Expand Messages
  • ngmbrenda
    Jan 11, 2014
      We apologize for duplicate postings. Please publicize among your colleagues and students as the abstract and paper deadlines are fast approaching. Thanks.

      The 9th Workshop on
      Multiagent Sequential Decision Making Under Uncertainty (MSDM)
      (to be held at AAMAS 2014)

      May 5-6, 2014
      Paris, France

      Important Dates
      January 17, 2014 - Abstract submission due
      January 22, 2014 - Paper submission due
      February 26, 2014 - Author notification
      March 12, 2014 - Camera-ready submission due
      March 25, 2014 - Early registration
      May 6-7, 2014 - Workshop dates

      The MSDM workshop focuses on principled sequential decision-making methods, and applications, to systems of multiple agents. Several multiagent models have emerged for cooperative agents (e.g., MMDP, Dec-POMDP) as well as for self-interested agents (e.g., I-POMDP, POSG), under various assumptions about agents' capabilities to communicate, observe, and influence other agents. The high complexity associated with such models has prompted development of planning and learning techniques that (1) exploit structure in agents' interactions and the problem, (2) find exact and more efficient approximate solutions, and (3) decentralize and distribute computation. Through a tutorial, presentations by authors and distinguished invitees, and discussions, we aim to facilitate collaboration among researchers and practitioners toward advancing MSDM theory and application.

      Multiagent sequential decision making comprises (1) problem representation, (2) planning, (3) coordination, and (4) learning, in self-interested as well as cooperative agent systems. The MSDM workshop addresses this full range of aspects. Topics of particular interest include:
      * Fundamental modeling challenges (e.g., model specification and model granularity)
      * Novel representations, algorithms and complexity results
      * Comparisons of algorithms
      * Relationships between models and their assumptions
      * Decentralized vs. centralized planning approaches
      * Online vs. offline planning
      * Communication and coordination during execution
      * Computational issues involving long decision horizons and large number of agents, states, observations and actions
      * (Reinforcement) learning in partially observable multiagent systems
      * Cooperative, competitive, and self-interested agents
      * Application domains
      * Benchmarks and evaluation methodologies
      * Standardization of software
      * High-level principles in MSDM: past trends and future directions

      Please refer to the workshop website (http://masplan.org/msdm2014) for more details.

      Submission Instructions
      Authors are encouraged to submit papers up to 8 pages in length, as per the instructions posted on:

      The proceedings of the MSDM workshop are not archival. In addition to original papers, we also encourage papers that are currently under submission or recently published elsewhere.

      Organizing Committee
      Prashant Doshi, University of Georgia
      Stefan J. Witwicki, Ecole Polytechnique Federale de Lausanne
      Brenda M. Ng, Lawrence Livermore National Laboratory
      Jilles S. Dibangoye, INRIA
      Eric Shieh, University of Southern California
      Joao V. Messias, Instituto Superior Tecnico