Empirical risk minimization offers well-known learning guarantees when training and test data come from the same domain. In the real world, though, we often wish to adapt a classi...
John Blitzer, Koby Crammer, Alex Kulesza, Fernando...
In recent years there has been a great deal of interest in "modular reinforcement learning" (MRL). Typically, problems are decomposed into concurrent subgoals, allowing ...
Sooraj Bhat, Charles Lee Isbell Jr., Michael Matea...
Epistemic logic allows to reason not only about situations, but also about the knowledge that a set of agents have about situations. In later years, epistemic logic has been appli...
A key assumption of all problem-solving approaches based on utility theory, including heuristic search, is that we can assign a utility or cost to each state. This in turn require...
Pronolninalization has been related to tile idea of a local focus - a set of discourse entities in the speaker's centre of attention, for exmnple ill Gundel et al. (1993)...