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...
Consider the space of two dimensional vector functions whose components and curl are square integrable with respect to the degenerate weight given by the radial variable. This spac...
Dylan M. Copeland, Jayadeep Gopalakrishnan, Minah ...
For the approximation of time-dependent data tensors and of solutions to tensor differential equations by tensors of low Tucker rank, we study a computational approach that can be ...
Abstract. We introduce hybridization and postprocessing techniques for the RaviartThomas approximation of second-order elliptic eigenvalue problems. Hybridization reduces the Ravia...
Bernardo Cockburn, Jayadeep Gopalakrishnan, F. Li,...
The discovery and extraction of general lists on the Web continues to be an important problem facing the Web mining community. There have been numerous studies that claim to autom...
Tim Weninger, Fabio Fumarola, Rick Barber, Jiawei ...