lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
Students with visual disabilities face unique challenges in learning to be computer scientists. These challenges can be overcome, however, with the use of specialized software too...
For several decades there has been a debate in the computing sciences about the relative roles of design and empirical research, and about the contribution of design and research ...
Interactively learning from a small sample of unlabeled examples is an enormously challenging task, one that often arises in vision applications. Relevance feedback and more recen...
ShyamSundar Rajaram, Charlie K. Dagli, Nemanja Pet...
There are numerous ways to evaluate student programming ability, all of which have benefits and drawbacks. In this paper we discuss how we have combined a number of those evaluati...