This paper presents a novel framework for simultaneously learning representation and control in continuous Markov decision processes. Our approach builds on the framework of proto...
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...
We propose a purely logical framework for planning in partially observable environments. Knowledge states are expressed in a suitable fragment of the epistemic logic S5. We show h...
Abstract. Various methods exists in the literature for denoting the configuration of a Turing Machine. A key difference is whether the head position is indicated by some integer ...
We introduce novel discriminative learning algorithms for dynamical systems. Models such as Conditional Random Fields or Maximum Entropy Markov Models outperform the generative Hi...