MSDM-2012 Workshop Schedule

June 5, 2012



Welcome, Introductions, and Icebreaker

8:55 - 9:15

Paper Session A


Solving Finite Horizon Decentralized POMDPs by Distributed Reinforcement Learning

Bikramjit Banerjee, Jeremy Lyle, Landon Kraemer, and Rajesh Yellamraju

9:15 - 9:40


Coordinated Multi-Agent Learning for Decentralized POMDPs

Chongjie Zhang and Victor Lesser

9:40 - 10:05


Discussion

10:05 - 10:20

Morning Coffee Break

10:20 - 10:50

Paper Session B


POMDPs in OpenMarkov and ProbModelXML

Manuel Arias, Francisco Díez, Miguel Palacios-Alonso, Mar Yebra, and Jorge Fernández

10:50 - 11:05


Planning Delayed-Response Queries and Transient Policies under Reward Uncertainty

Robert Cohn, Edmund Durfee, and Satinder Singh

11:05 - 11:30


Exploiting Sparse Interactions for Optimizing Communication in Dec-MDPs

Francisco S. Melo, Matthijs Spaan, and Stefan Witwicki

11:30 - 11:55


Discussion

11:55 - 12:15

Invited Talk

Professor Makoto Yokoo

Repeated Games with Private Monitoring: A New Frontier for POMDP Researchers

12:15 - 13:00

Lunch Break

13:00 - 14:20

Paper Session C


Strategic Behaviour Under Constrained Autonomy

Zinovi Rabinovich

14:20 - 14:45


Tree-based Pruning for Multiagent POMDPs with Delayed Communication

Frans Oliehoek and Matthijs Spaan

14:45 - 15:10


Automated Equilibrium Analysis of Repeated Games with Private Monitoring:

A POMDP Approach

Yongjoon Joe, Atsushi Iwasaki, Michihiro Kandori, Ichiro Obara, and Makoto Yokoo

15:10 - 15:35


Discussion

15:35 - 16:00

Afternoon Coffee Break

16:00 - 16:30

Paper Session D


Prioritized Shaping of Models for Solving DEC-POMDPs

Pradeep Varakantham, William Yeoh, Prasanna Velagapudi, Katia Sycara, and Paul Scerri

16:30 - 16:45


Improved Solution of Decentralized MDPs through Heuristic Search

Jilles Dibangoye, Christopher Amato, and Arnaud Doniec

16:45 - 17:10


Discussion

17:10 - 17:25

Final Discussion and Closing Remarks

17:25 - 18:00

 

 

Note: In this year's program, there are two types of oral presentations — longer talks of 25 minutes and shorter talks of 15 minutes. The choice of which slot to allocate each paper was made based on its scores given by reviewers.