We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for any g...
Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multiarmed bandit problem, where the payoff function is ...
Niranjan Srinivas, Andreas Krause, Sham Kakade, Ma...
Energy feedback systems, particularly residential energy feedback systems (REFS), have emerged as a key area for HCI and interaction design. However, we argue that HCI researchers...
James Pierce, Chloe Fan, Derek Lomas, Gabriela Mar...
Artifacts can be used to inspire, guide, and create new designs. As approaches to design can range from focusing on inspiration to formalized reasoning, we seek to create and stud...
Shahtab Wahid, Stacy M. Branham, D. Scott McCricka...
We present and evaluate a machine learning approach to constructing patient-specific classifiers that detect the onset of an epileptic seizure through analysis of the scalp EEG, a...