We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Background: The recent increase in the use of high-throughput two-hybrid analysis has generated large quantities of data on protein interactions. Specifically, the availability of...
As data centers become more and more central in Internet communications, both research and operations communities have begun to explore how to better design and manage them. In th...
In many applications, we monitor data obtained from multiple streaming sources for collective decision making. The task presents several challenges. First, data in sensor networks...
Hashing is fundamental to many algorithms and data structures widely used in practice. For theoretical analysis of hashing, there have been two main approaches. First, one can ass...