The family of temporal difference (TD) methods span a spectrum from computationally frugal
linear methods like TD (λ) to data efficient least squares methods. Least square methods …

This paper investigates different vector step-size adaptation approaches for non-stationary
online, continual prediction problems. Vanilla stochastic gradient descent can be …

This thesis investigates the use of bootstrapping in Temporal Difference (TD) learning, a
central mechanism in reinforcement learning (RL), when applied to deep neural networks. I …

This thesis deals with linearly approximated gradient temporal difference learning. The
applicability of the underlying cost functions are discussed and investigated with respect to …

The central idea of this thesis is to understand the notion of acceleration in stochastic
approximation algorithms. Specifically, we attempt to answer the question: How does …

A common scientific challenge for putting a reinforcement learning agent into practice is how
to improve sample efficiency as much as possible with limited computational or memory …

In this thesis, we investigate different vector step-size adaptation approaches for continual,
online prediction problems. Vanilla stochastic gradient descent can be considerably …