Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms,includ...
Tommi Jaakkola, Michael I. Jordan, Satinder P. Sin...
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
As Computer Science educators, we know that students learn more from projects that are fun and challenging, that seem “real” to them, and that allow them to be creative in des...
A collective of agents often needs to maximize a “world utility” function which rates the performance of an entire system, while subject to communication restrictions among th...
The quality of student consultants and their development through training and education are major factors in determining long-term effectiveness of university Help Desk. To hire a...