Abstract. We consider batch reinforcement learning problems in continuous space, expected total discounted-reward Markovian Decision Problems. As opposed to previous theoretical wo...
Abstract. In this paper, nogood recording is investigated for CSP within the randomization and restart framework. Our goal is to avoid the same situations to occur from one run to ...
We develop new structural results for apex-minor-free graphs and show their power by developing two new approximation algorithms. The first is an additive approximation for colorin...
Erik D. Demaine, MohammadTaghi Hajiaghayi, Ken-ich...
An asymmetric binary covering code of length n and radius R is a subset C of the n-cube Qn such that every vector x Qn can be obtained from some vector c C by changing at most R...
Joshua N. Cooper, Robert B. Ellis, Andrew B. Kahng
— The lower and upper bounds for the information capacity of two-layer feedforward neural networks with binary interconnections, integer thresholds for the hidden units, and zero...