Abstract. Greedy machine learning algorithms suffer from shortsightedness, potentially returning suboptimal models due to limited exploration of the search space. Greedy search mis...
Peer-to-peer network overlays have mostly been designed to support search over document names, identifiers, or keywords from a small or controlled vocabulary. In this paper we pro...
Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maxi...
Cognitive architectures aspire for generality both in terms of problem solving and learning across a range of problems, yet to date few examples of domain independent learning has...
Geography is becoming increasingly important in web search. Search engines can often return better results to users by analyzing features such as user location or geographic terms...
Qingqing Gan, Josh Attenberg, Alexander Markowetz,...