332 search results - page 1 / 67 » Ranking policies in discrete Markov decision processes |
AMAI
2010
Springer
13 years 8 months ago
2010
Springer
ICML
2006
IEEE
14 years 11 months ago
2006
IEEE
Inference in Markov Decision Processes has recently received interest as a means to infer goals of an observed action, policy recognition, and also as a tool to compute policies. ...
ML
2002
ACM
13 years 10 months ago
2002
ACM
Abstract. The problemof state abstractionis of centralimportancein optimalcontrol,reinforcement learning and Markov decision processes. This paper studies the case of variable reso...
UAI
2000
14 years 7 days ago
2000
We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a mo...
NIPS
2004
14 years 8 days 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:...