The Complexity of Decentralized Control of Markov Decision Processes
Mathematics of Operations Research
Characterizing Markov Decision Processes
ECML '02 Proceedings of the 13th European Conference on Machine Learning
The complexity of multiagent systems: the price of silence
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Agent interaction in distributed POMDPs and its implications on complexity
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Dynamic programming for partially observable stochastic games
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Solving transition independent decentralized Markov decision processes
Journal of Artificial Intelligence Research
Taming decentralized POMDPs: towards efficient policy computation for multiagent settings
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Efficient nash computation in large population games with bounded influence
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Agent Influence and Intelligent Approximation in Multiagent Problems
WI-IAT '09 Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology - Volume 02
Dynamic coalition formation under uncertainty
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Prototype selection algorithms for distributed learning
Pattern Recognition
Towards a unifying characterization for quantifying weak coupling in dec-POMDPs
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Scaling up optimal heuristic search in Dec-POMDPs via incremental expansion
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
QueryPOMDP: POMDP-based communication in multiagent systems
EUMAS'11 Proceedings of the 9th European conference on Multi-Agent Systems
Incremental clustering and expansion for faster optimal planning in decentralized POMDPs
Journal of Artificial Intelligence Research
| Hi-index | 0.00 |
We study the effect of problem structure on the practical performance of optimal dynamic programming for decentralized decision problems. It is shown that restricting agent influence over problem dynamics can make the problem easier to solve. Experimental results establish that agent influence correlates with problem difficulty: as the gap between the influence of different agents grows, problems tend to become much easier to solve. The measure thus provides a general-purpose, automatic characterization of decentralized problems, identifying those for which optimal methods are more or less likely to work. Such a measure is also of possible use as a heuristic in the design of algorithms that create task decompositions and control hierarchies in order to simplify multiagent problems.