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...
This paper explores the issue of recognizing, generalizing and reproducing arbitrary gestures. We aim at extracting a representation that encapsulates only the key aspects of the ...
Software systems have to be changed continuously and evolutionarily throughout the whole time of their development and usage. Meanwhile, the software systems have to remain flexi...
In this paper, we introduce a novel vector quantization (VQ) scheme for distributing the quantization error equally among the quantized dimensions. Afterwards, the proposed VQ sch...
MINLP problems are hard constrained optimization problems, with nonlinear constraints and mixed discrete continuous variables. They can be solved using a Branch-and-Bound scheme c...