In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
Suppose an unpredictable evader is free to move around in a polygonal environment of arbitrary complexity that is under full camera surveillance. How many pursuers, each with the ...
Information about the spread of crop disease is vital in developing countries, and as a result the governments of such countries devote scarce resources to gathering such data. Un...
John Alexander Quinn, Kevin Leyton-Brown, Ernest M...
Many algorithms for performing inference in graphical models have complexity that is exponential in the treewidth - a parameter of the underlying graph structure. Computing the (m...
Automated feature discovery is a fundamental problem in machine learning. Although classical feature discovery methods do not guarantee optimal solutions in general, it has been r...