Utility computing delivers compute and storage resources to applications as an `on-demand utility', much like electricity, from a distributed collection of computing resource...
We consider learning in a Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we wa...
Previous algorithms for learning lexicographic preference models (LPMs) produce a "best guess" LPM that is consistent with the observations. Our approach is more democra...
Fusun Yaman, Thomas J. Walsh, Michael L. Littman, ...
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...
The CELEBRATEproject developed and successfully demonstrated a federated learning object brokerage system architecture and made available to schools over 1350 learning objects prod...