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 ...
We introduce a natural generalization of submodular set cover and exact active learning with a finite hypothesis class (query learning). We call this new problem interactive submo...
We consider the problem of evaluating multiple overlapping queries defined on data streams, where each query is a conjunction of multiple filters and each filter may be shared acr...
We consider layouting news articles on a page as a cutting and packing problem with output maximization. We propose to tailor news articles by employing automatic summarization to...