Symmetry in constraint satisfaction problems (CSPs) has been considered in two fundamentally different ways: as an operation preserving the solutions of a CSP instance, or as an o...
David A. Cohen, Peter Jeavons, Christopher Jeffers...
In the context of web search engines, the escalation between ranking techniques and spamdexing techniques has led to the appearance of faked contents in web pages. If random sequen...
We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...
End-to-end evaluations of conversational dialogue systems with naive users are currently uncovering severe usability problems that result in low task completion rates. Preliminary...
Learning on real robots in an real, unaltered environment provides an extremely challenging problem. Many of the simplifying assumptions made in other areas of learning cannot be ...