We propose a framework which we call stochastic offline programming (SOP). The idea is to embed the development of combinatorial algorithms in an off-line learning environment whi...
MDPs are an attractive formalization for planning, but realistic problems often have intractably large state spaces. When we only need a partial policy to get from a fixed start s...
H. Brendan McMahan, Maxim Likhachev, Geoffrey J. G...
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
This paper presents a decomposition method for efficiently constructing 1-norm Support Vector Machines (SVMs). The decomposition algorithm introduced in this paper possesses many d...
: This paper focused on designing of a ubiquitous interface agent based on the ontology technology and interaction diagram with the backend information agent system, i.e., OntoIAS,...