Thomas Rückstieß

State-Dependent Exploration for Policy Gradient Methods

Jürgen Schmidhuber, Martin Felder, Thomas Rückstieß, 2008, ECML/PKDD.

Sequential Feature Selection for Classification

Christian Osendorfer, Patrick van der Smagt, Thomas Rückstieß, 2011, Australasian Conference on Artificial Intelligence.

Fast and Accurate Environment Modelling using Omnidirectional Vision

Andreas Zell, Thomas Rückstieß, Patrick Heinemann, 2004 .

Parameter-exploring policy gradients

Frank Sehnke, Christian Osendorfer, Jürgen Schmidhuber, 2010, Neural Networks.

Minimizing data consumption with sequential online feature selection

Christian Osendorfer, Patrick van der Smagt, Thomas Rückstieß, 2013, Int. J. Mach. Learn. Cybern..

Exploring parameter space in reinforcement learning

Tom Schaul, Yi Sun, Frank Sehnke, 2010, Paladyn J. Behav. Robotics.

Policy Gradients with Parameter-Based Exploration for Control

Frank Sehnke, Christian Osendorfer, Jürgen Schmidhuber, 2008, ICANN.