Modular model is a particular type of committee machine and is comprised of a set of specialized (local) models each of which is responsible for a particular region of the input s...
We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
Christian Vollmer, Erik Schaffernicht, Horst-Micha...
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
Abstract. In the past thirty years, cryptology has evolved from a secret art to a modern science. Weaker algorithms and algorithms with short keys are disappearing, political contr...
Abstract. In this paper, we consider two new online optimization problems (each with several variants), present similar online algorithms for both, and show that one reduces to the...