We consider the problem of designing auctions with worst case revenue guarantees for sponsored search. This problem differs from previous work because of ad dependent clickthroug...
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...
Abstract. Kernel based methods (such as k-nearest neighbors classifiers) for AI tasks translate the classification problem into a proximity search problem, in a space that is usu...
We have considered a problem of continuous piecewise linear approximation of the digital curves with a minimum number of the line segments. Fast suboptimal algorithm for constrain...
Relaxations based on (either complete or partial) ignoring delete effects of the actions provide the basis for some seminal classical planning heuristics. However, the palette of ...