Practical sparse approximation algorithms (particularly greedy algorithms) suffer two significant drawbacks: they are difficult to implement in hardware, and they are inefficie...
Christopher J. Rozell, Don H. Johnson, Richard G. ...
Inference is a key component in learning probabilistic models from partially observable data. When learning temporal models, each of the many inference phases requires a complete ...
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...
The r-domination search game on graphs is a game-theoretical approach to several graph and hypergraph parameters including treewidth and hypertree width. The task is to identify t...
Fedor V. Fomin, Petr A. Golovach, Dimitrios M. Thi...
Optimistic concurrency algorithms provide good performance for parallel programs but they are extremely hard to reason about. Program logics such as concurrent separation logic and...
Ming Fu, Yong Li, Xinyu Feng, Zhong Shao, Yu Zhang