Sciweavers

268 search results - page 23 / 54
» Solving multiagent assignment Markov decision processes
Sort
View
ATAL
2007
Springer
14 years 3 months ago
Regret based dynamics: convergence in weakly acyclic games
Regret based algorithms have been proposed to control a wide variety of multi-agent systems. The appeal of regretbased algorithms is that (1) these algorithms are easily implement...
Jason R. Marden, Gürdal Arslan, Jeff S. Shamm...
ICML
2005
IEEE
14 years 10 months ago
A causal approach to hierarchical decomposition of factored MDPs
We present Variable Influence Structure Analysis, an algorithm that dynamically performs hierarchical decomposition of factored Markov decision processes. Our algorithm determines...
Anders Jonsson, Andrew G. Barto
NIPS
2004
13 years 11 months ago
VDCBPI: an Approximate Scalable Algorithm for Large POMDPs
Existing algorithms for discrete partially observable Markov decision processes can at best solve problems of a few thousand states due to two important sources of intractability:...
Pascal Poupart, Craig Boutilier
SIGMETRICS
2000
ACM
105views Hardware» more  SIGMETRICS 2000»
14 years 2 months ago
Using the exact state space of a Markov model to compute approximate stationary measures
We present a new approximation algorithm based on an exact representation of the state space S, using decision diagrams, and of the transition rate matrix R, using Kronecker algeb...
Andrew S. Miner, Gianfranco Ciardo, Susanna Donate...
ATAL
2007
Springer
14 years 3 months ago
Graphical models for online solutions to interactive POMDPs
We develop a new graphical representation for interactive partially observable Markov decision processes (I-POMDPs) that is significantly more transparent and semantically clear t...
Prashant Doshi, Yifeng Zeng, Qiongyu Chen