Recent research has shown the benefit of framing problems of imitation learning as solutions to Markov Decision Problems. This approach reduces learning to the problem of recoveri...
Brian Ziebart, Andrew L. Maas, J. Andrew Bagnell, ...
It is well known that there cannot be a single "best" heuristic for optimal planning in general. One way of overcoming this is by combining admissible heuristics (e.g. b...
This paper describes our work constructing a generalized framework for modeling multi agent interactions in education-related applications. Historically, interactive learning syst...
We present a method for dependency grammar induction that utilizes sparse annotations of semantic relations. This induction set-up is attractive because such annotations provide u...
We present a novel application of structured classification: identifying function entry points (FEPs, the starting byte of each function) in program binaries. Such identification ...
Nathan E. Rosenblum, Xiaojin Zhu, Barton P. Miller...