10493 search results - page 2078 / 2099 » Dynamic Word Problems |
CORR
2006
Springer
13 years 7 months ago
2006
Springer
This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(), LSTD()...
JAIR
2008
13 years 7 months ago
2008
In this paper, we elucidate the equivalence between inference in game theory and machine learning. Our aim in so doing is to establish an equivalent vocabulary between the two dom...
JCIT
2008
13 years 7 months ago
2008
Many prominent applications in wireless sensor networks require collected information has to be routed to end nodes in an efficient manner. In general, Connected Dominating Set (C...
CORR
2007
Springer
13 years 7 months ago
2007
Springer
The subject of this article is the long standing open problem of developing a general capacity theory for wireless networks, particularly a theory capable of describing the fundam...
JAIR
2006
13 years 7 months ago
2006
A decision process in which rewards depend on history rather than merely on the current state is called a decision process with non-Markovian rewards (NMRDP). In decisiontheoretic...