Abstract. Bayesian reinforcement learning (RL) is aimed at making more efficient use of data samples, but typically uses significantly more computation. For discrete Markov Decis...
Abstract-- We propose a formal method for feedback controller synthesis using interactive computer programs with graphical interface (in short, computer games). The main theoretica...
In the past decade, moving horizon estimation (MHE) has emerged as a powerful technique for estimating the state of a dynamical system in the presence of nonlinearities and disturb...
Angelo Alessandri, Marco Baglietto, Giorgio Battis...
Coordinated data structures are sets of (perhaps unbounded) data structures where the nodes of each structure may share types with the corresponding nodes of the other structures....
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...