Predictive state representations (PSRs) use predictions of a set of tests to represent the state of controlled dynamical systems. One reason why this representation is exciting as...
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
In 2004 Csima, Hirschfeldt, Knight, and Soare [1] showed that a set A T 0 is nonlow2 if and only if A is prime bounding, i.e. for every complete atomic decidable theory T , there i...
Different quantifier types in Quantified Boolean Formulae (QBF) introduce variable dependencies which have to be taken into consideration when deciding satisfiability of a QBF....
Shannon's sampling theory and its variants provide effective solutions to the problem of reconstructing a signal from its samples in some "shift-invariant " space, ...
Sathish Ramani, Dimitri Van De Ville, Michael Unse...