In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...
Takamitsu Matsubara, Tetsuro Morimura, Jun Morimot...
One of the most challenging aspects of managing a very large data warehouse is identifying how queries will behave before they start executing. Yet knowing their performance charac...
Archana Ganapathi, Harumi A. Kuno, Umeshwar Dayal,...
Abstract. Planning information security investment is somewhere between art and science. This paper reviews and compares existing scientific approaches and discusses the relation ...
We propose a novel Riemannian framework for comparing signals and images in a manner that is invariant to their levels of blur. This framework uses a log-Fourier representation of...
Zhengwu Zhang, Eric Klassen, Anuj Srivastava, Pava...
Program dependence information is useful for a variety of software testing and maintenance tasks. Properly defined, control and data dependencies can be used to identify semantic...