We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...
A scalable podcast solution developed at the University of Washington makes the podcasting of class lectures easy for faculty by automating the capture, uploading, and delivery of...
Machine learning techniques are applicable to computer system optimization. We show that shared memory multiprocessors can successfully utilize machine learning algorithms for mem...
M. F. Sakr, Steven P. Levitan, Donald M. Chiarulli...
Discourse, a form of collaborative learning [44], is one of the most widely used methods of teaching and learning in the online environment. Particularly in large courses, discour...
I. Wong-Bushby, Starr Roxanne Hiltz, Michael Biebe...