87 search results - page 1 / 18 » A policy iteration algorithm for Markov decision processes s... |
DAGSTUHL
2007
13 years 6 months ago
2007
AAAI
2006
13 years 6 months ago
2006
Despite the significant progress to extend Markov Decision Processes (MDP) to cooperative multi-agent systems, developing approaches that can deal with realistic problems remains ...
ICML
2006
IEEE
14 years 5 months ago
2006
IEEE
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
ICML
2001
IEEE
14 years 5 months ago
2001
IEEE
This paper examines the notion of symmetry in Markov decision processes (MDPs). We define symmetry for an MDP and show how it can be exploited for more effective learning in singl...
NIPS
2004
13 years 6 months ago
2004
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:...