Despite the success of modern Web search engines, challenges remain when it comes to providing people with access to the right information at the right time. In this paper, we desc...
A wide variety of function approximation schemes have been applied to reinforcement learning. However, Bayesian filtering approaches, which have been shown efficient in other field...
In this paper we consider the orienteering problem in undirected and directed graphs and obtain improved approximation algorithms. The point to point-orienteering-problem is the f...
TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (...
Abstract--The paper introduces DILOC, a distributed, iterative algorithm to locate sensors (with unknown locations) in 1, with respect to a minimal number of + 1 anchors with known...