PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
It is shown that bandwidth estimation in packet networks can be viewed in terms of min-plus linear system theory. The available bandwidth of a link or complete path is expressed i...
Programming technologies have improved continuously during the last decades, but from an Information Systems perspective, some well-known problems associated to the design and impl...
There have been innumerable glowing reports of the way hypermedia systems allow users to explore and use vast amounts of information in ways not possible using traditional informa...