We propose a theoretical framework for specification and analysis of a class of learning problems that arise in open-ended environments that contain multiple, distributed, dynamic...
"How can we make sure our students learn what we want them to?" is the number one question in teaching. This paper is intended to provide the reader with: i) a general a...
We consider a general class of regularization methods which learn a vector of parameters on the basis of linear measurements. It is well known that if the regularizer is a nondecr...
Andreas Argyriou, Charles A. Micchelli, Massimilia...
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Abstract--Reinforcement learning (RL) research typically develops algorithms for helping an RL agent best achieve its goals-however they came to be defined--while ignoring the rela...