We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...
One claim of Technology-Enhanced Learning (TEL) is to support and exploit benefits from distance learning and remote collaboration. On the other hand, several approaches to learnin...
In this paper, we study the problem of learning phylogenies and hidden Markov models. We call the Markov model nonsingular if all transtion matrices have determinants bounded away...
We give the first representation-independent hardness results for PAC learning intersections of halfspaces, a central concept class in computational learning theory. Our hardness...
This study presents a shared document-based annotation tool, EDUCOSM. Usefulness of the system is empirically evaluated in a real-life collaborative learning context. Relationship...
Petri Nokelainen, Jaakko Kurhila, Miikka Miettinen...