For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
In this work an R-tree variant, which uses minimum volume covering ellipsoids instead of usual minimum bounding rectangles, is presented. The most significant aspects, which dete...
Abstract— Research on numerical solution methods for partially observable Markov decision processes (POMDPs) has primarily focused on discrete-state models, and these algorithms ...
As it has been noted several times in literature, the difficult part of autocalibration efforts resides in the structural non-linearity of the search for the plane at infinity. I...
We show that for every α > 0, there exist n-point metric spaces (X, d) where every “scale” admits a Euclidean embedding with distortion at most α, but the whole space req...