Sciweavers

802 search results - page 6 / 161
» Experts in a Markov Decision Process
Sort
View
CDC
2010
IEEE
141views Control Systems» more  CDC 2010»
14 years 6 months ago
A dynamic programming algorithm for decentralized Markov decision processes with a broadcast structure
We give an optimal dynamic programming algorithm to solve a class of finite-horizon decentralized Markov decision processes (MDPs). We consider problems with a broadcast informati...
Jeff Wu, Sanjay Lall
COLT
2007
Springer
15 years 5 months ago
Bounded Parameter Markov Decision Processes with Average Reward Criterion
Bounded parameter Markov Decision Processes (BMDPs) address the issue of dealing with uncertainty in the parameters of a Markov Decision Process (MDP). Unlike the case of an MDP, t...
Ambuj Tewari, Peter L. Bartlett
ORL
2007
70views more  ORL 2007»
14 years 11 months ago
Linear dependence of stationary distributions in ergodic Markov decision processes
In ergodic MDPs we consider stationary distributions of policies that coincide in all but n states, in which one of two possible actions is chosen. We give conditions and formulas...
Ronald Ortner
FMSD
2010
77views more  FMSD 2010»
14 years 10 months ago
A game-based abstraction-refinement framework for Markov decision processes
ASED ABSTRACTION-REFINEMENT FRAMEWORK FOR MARKOV DECISION PROCESSES Mark Kattenbelt Marta Kwiatkowska Gethin Norman David Parker CL-RR-08-06  Oxford University Computing Laborator...
Mark Kattenbelt, Marta Z. Kwiatkowska, Gethin Norm...
ARTMED
2000
105views more  ARTMED 2000»
14 years 11 months ago
Planning treatment of ischemic heart disease with partially observable Markov decision processes
Diagnosis of a disease and its treatment are not separate, one-shot activities. Instead, they are very often dependent and interleaved over time. This is mostly due to uncertainty...
Milos Hauskrecht, Hamish S. F. Fraser