In this paper we study, for the first time explicitly, the implications of endowing an interested party (i.e. a teacher) with the ability to modify the underlying dynamics of the ...
Zinovi Rabinovich, Lachlan Dufton, Kate Larson, Ni...
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...
Autonomous agents that learn about their environment can be divided into two broad classes. One class of existing learners, reinforcement learners, typically employ weak learning ...
Social networking sites have come under criticism for their poor privacy protection track record. Yet, there is an inherent difficulty in deciding which principals should have acc...
We present MI-Winnow, a new multiple-instance learning (MIL) algorithm that provides a new technique to convert MIL data into standard supervised data. In MIL each example is a co...
Sharath R. Cholleti, Sally A. Goldman, Rouhollah R...