Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
We present a method for transferring knowledge learned in one task to a related task. Our problem solvers employ reinforcement learning to acquire a model for one task. We then tra...
Lisa Torrey, Trevor Walker, Jude W. Shavlik, Richa...
In our research we study rational agents which learn how to choose the best conditional, partial plan in any situation. The agent uses an incomplete symbolic inference engine, emp...
The problem of choosing fast implementations for a class of recursive algorithms such as the fast Fourier transforms can be formulated as an optimization problem over the language...
This paper studies textual inference by investigating comma structures, which are highly frequent elements whose major role in the extraction of semantic relations has not been hi...
Vivek Srikumar, Roi Reichart, Mark Sammons, Ari Ra...