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...
We present new results on the problem of finding an enclosing rectangle of minimum area that will contain a given a set of rectangles. Many simple scheduling tasks can be modelled...
Data centers are a major consumer of electricity and a significant fraction of their energy use is devoted to cooling the data center. Recent prototype deployments have investigat...
A wide variety of stability and performance questions about linear dynamical systems can be reformulated as convex optimization problems involving linear matrix inequalities (LMIs...
Erin M. Aylward, Pablo A. Parrilo, Jean-Jacques E....
Propositional canonical Gentzen-type systems, introduced in [2], are systems which in addition to the standard axioms and structural rules have only logical rules in which exactly ...