The PolicyUpdater1 system is a fully-implemented access control system that provides policy evaluations as well as dynamic policy updates. These functions are achieved by the use o...
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
We consider the classical finite-state discounted Markovian decision problem, and we introduce a new policy iteration-like algorithm for finding the optimal state costs or Q-facto...
In this paper, we consider the problem of planning and learning in the infinite-horizon discounted-reward Markov decision problems. We propose a novel iterative direct policysearc...
Concurrent programming errors arise when threads share data incorrectly. Programmers often avoid these errors by using synchronization to enforce a simple ownership policy: data i...
Jean-Phillipe Martin, Michael Hicks, Manuel Costa,...