Steffen Grünewälder

We demonstrate an equivalence between reproducing kernel Hilbert space (RKHS) embeddings of conditional distributions and vector-valued regressors. Expand

We propose a nonparametric approach to learning and representing transition dynamics in Markov decision processes (MDPs), which can be combined easily with dynamic programming methods for policy optimisation and value estimation. Expand

We study a variant of the stochastic K-armed bandit problem, which we call “bandits with delayed, aggregated anonymous feedback”. Expand

We propose a new method, based on machine learning techniques, for the analysis of a combination of continuous data from dataloggers and a sampling of contemporaneous behaviour observations to calibrate continuously recorded activity data. Expand

We show that the regret experienced by Bandit algorithms relative to the a posteriori optimal strategy of playing the best arm throughout based on benign assumptions about the covariance function dening the Gaussian process. Expand

We develop a generic approach to form smooth versions of basic mathematical operations like multiplication, composition, change of measure, and conditional expectation, among others. Expand

We provide theoretical statements about the LSTD value approximation error and induced metric of approximation spaces constructed by SFA and the state-of-the-art methods Krylov bases and proto-value functions (PVF). Expand

Non-linear optimization of this unsupervised learning method generates an orthogonal basis on the unknown latent space for a given time series. Expand

This paper develops a kernelized slow feature analysis (SFA) algorithm to extract features which encode latent variables from time series. Expand