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 paper, we extend the recently proposed Core Vector Machine algorithm to the regression setting by generalizing the underlying minimum enclosing ball problem. The resultant...
In this contribution we introduce adaptive finite element methods for forward modeling in fluorescence optical tomography. Adaptive local mesh refinement increases the accuracy of...
Amit Joshi, Eva M. Sevick-Muraca, Alan B. Thompson...
We present a fully four-dimensional, globally convergent, incremental gradient algorithm to estimate the continuous-time tracer density from list mode positron emission tomography...
We consider the problem of minimizing the delay in signal transmission over point-to-point connections across multiple metal layers in a VLSI circuit. We present an exact solution...