Learning a new task from a handful of examples remains an open challenge...
Partial Differential Equations (PDEs) are used to model a variety of
dyn...
Time series observations can be seen as realizations of an underlying
dy...
Recent studies on few-shot classification using transfer learning pose
c...
The transduction of sequence has been mostly done by recurrent networks,...
Resolving the exploration-exploitation trade-off remains a fundamental
p...
Learning from demonstrations (LfD) improves the exploration efficiency o...
Reinforcement learning methods that consider the context, or current sta...