We consider the problem of estimating the policy gradient in Partially Observable Markov Decision Processes (POMDPs) with a special class of policies that are based on Predictive ...
Abstract. Graphs are an intuitive model for states of a (software) system that include pointer structures — for instance, object-oriented programs. However, a naive encoding resu...
We introduce a set of transformations on the set of all probability distributions over a finite state space, and show that these transformations are the only ones that preserve c...
High-level semi-Markov modelling paradigms such as semi-Markov stochastic Petri nets and process algebras are used to capture realistic performance models of computer and communic...
Marcel C. Guenther, Nicholas J. Dingle, Jeremy T. ...
Intelligent user interfaces often rely on modified applications and detailed application models. Such modifications and models are expensive to build and maintain. We propose to a...