[agents] CFP - MSDM 2014: AAMAS Workshop on Multiagent Sequential Decision Making Under Uncertainty

[Brenda Ng]

*========================================================
                      CALL FOR PAPERS                       The 9th
Workshop on Multiagent Sequential Decision Making Under Uncertainty (MSDM)
             (to be held at AAMAS
2014)========================================================May 5-6, 2014
Paris, Francehttp://masplan.org/msdm2014 <http://masplan.org/msdm2014>In
sequential decision making, an agent's objective is to choose actions based
on observations of its environment that will maximize the expected
performance over multiple steps. In worlds where actions are not
deterministic or observations incomplete, Markov Decision Processes (MDPs)
and Partially-Observable MDPs (POMDPs) serve as the basis for principled
approaches to single-agent sequential decision making. Extending these
models to systems of multiple agents has become the subject of an
increasingly active area of research. Over the past decade, a variety of
different multiagent models have emerged for cooperative agents (e.g.,
MMDP, MTDP and Dec-POMDP) and self-interested agents (e.g., I-POMDP and
POSG), and under an assortment of different assumptions about agents'
capabilities to communicate (e.g., Dec-MDP-Com, COM-MTDP), observe (e.g.,
Dec-MDP) and influence other agents (e.g., TI-Dec-MDP, ND-POMDP). The high
computational complexity has driven researchers to develop multiagent
planning and learning methods that exploit structure in agents'
interactions, methods geared toward efficient approximate solutions,
decentralized methods that distribute computation among the agents, and new
ways for agents to model and reason about their interactions with other
agents.The purpose of this workshop is to bring together current and future
researchers in the field of multiagent sequential decision making (MSDM) to
present and discuss promising new work, to identify recent trends in model
and algorithmic development, and to establish important directions and
goals for further research and collaboration. This workshop also strives to
develop consensus within the community on benchmarks and evaluation
methodology in order to compare and validate alternative approaches and
models. Further, we hope that these active discussions and collaborations
will help us to overcome the challenges of successfully applying MSDM
methods to real-world problems in security, sustainability, public safety
and health, and other challenging domains.This year, the MSDM workshop will
also include an extensive tutorial geared towards introducing the
fundamental concepts of multiagent sequential decision making, acclimating
researchers to the broad landscape of MSDM models and methods, and
informing potential practitioners of the state of the
art.Topics----------------------------------------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: how should models be derived? ... model
granularity: how should one decide on an appropriate level of abstraction
to express decision-making models?- 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... ... large numbers of agents
... large numbers of discrete / continuous states, observations and actions
... long decision horizons- (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 directionsImportant
Dates----------------------------------------January 17, 2014    - Abstract
submission dueJanuary 22, 2014    - Paper submission dueFebruary 19, 2014
 - Author notificationMarch 12, 2014      - Camera-ready submission dueMay
6-7, 2014         - Workshop datesSubmission
Instructions----------------------------------------Authors are encouraged
to submit papers up to 8 pages in length, as per the instructions posted on
the workshop website:
<http://gaips.inesc-id.pt/%7Eswitwicki/msdm2013/>https://masplan.org/msdm2014:instructions
<https://masplan.org/msdm2014:instructions>Each submission will be reviewed
by at least three Program Committee members. The review process will be
"single-blind"; thus authors do not have to remove their names when
submitting papers.The proceedings of the MSDM workshop are not archival. In
addition to novel works, we will also consider works that are either under
submission or recently published elsewhere. However, authors should note
this in their paper submissions (by titlenote and reference if
applicable).Organizing
Committee----------------------------------------Prashant Doshi, University
of GeorgiaStefan J. Witwicki, Ecole Polytechnique Federale de
LausanneBrenda M. Ng, Lawrence Livermore National LaboratoryJilles S.
Dibangoye, INRIAEric Shieh, University of Southern CaliforniaJoao V.
Messias, Instituto Superior
TecnicoTutors----------------------------------------Chris Amato,
MITPrashant Doshi, University of GeorgiaFrans Oliehoek, Maastricht
UniversityZinovi Rabinovich, MobileyeMatthijs Spaan, Delft University of
TechnologyStefan J. Witwicki, Ecole Polytechnique Federale de
LausanneAdvisory Committee----------------------------------------Chris
Amato, MITPrashant Doshi, University of GeorgiaEd Durfee, University of
MichiganAbdel-Illah Mouaddib, University of CaenFrans Oliehoek, Maastricht
UniversityZinovi Rabinovich, MobileyeMatthijs Spaan, Delft University of
TechnologyMilind Tambe, University of Southern CaliforniaPradeep
Varakantham, Singapore Management UniversityMakoto Yokoo, Kyushu
UniversityShlomo Zilberstein, University of Massachusetts AmherstProgram
Committee----------------------------------------Martin Allen, University
of Wisconsin-La Crosse Computer ScienceChris Amato, MITBikramjit Banerjee,
University of Southern MississippiDaniel Bernstein, Fiksu, Inc.Aurelie
Beynier, University of Pierre and Marie CurieMatthew Brown, University of
Southern CaliforniaOlivier Buffet, INRIA/LORIABrahim Chaib-Draa, Laval
UniversityFrancois Charpillet, INRIA/LORIAEd Durfee, University of
MichiganAlberto Finzi, University of Napoli “Federico II”Akshat Kumar, IBM
ResearchJun-Young Kwak, SpokeoFrancisco Melo, Instituto Superior
Tecnico/INESC-IDHala Mostafa, BNN TechnologiesAbdel-Illah Mouaddib,
University of CaenEnrique Munoz de Cote, INAOEFrans Oliehoek, Maastricht
UniversityPraveen Paruchuri, CMUDavid Pynadath, University of Southern
CaliforniaZinovi Rabinovich, MobileyeAnita Raja, University of North
Carolina at CharlotteEkhlas Sonu, University of GeorgiaMatthijs Spaan,
Delft University of TechnologyKatia Sycara, CMUKarl Tuyls, Maastricht
UniversityPradeep Varakantham, Singapore Management UniversityMakoto Yokoo,
Kyushu UniversityChongjie Zhang, University of Massachusetts AmherstShlomo
Zilberstein, University of Massachusetts Amherst*