Search Results - "Udluft, S."

Uncertainty propagation for quality assurance in Reinforcement Learning by Schneegass, D., Udluft, S., Martinetz, T.

“…In this paper we address the reliability of policies derived by Reinforcement Learning on a limited amount of observations. This can be done in a principled…”
Get full text

Hardware preprocessing for the H1-Level 2 neural network trigger upgrade by Prevotet, J.-C., Denby, B., Fent, J., Frochtenicht, W., Garda, P., Granado, B., Haberer, W., Grindhammer, G., Janauschek, L., Kiesling, C., Kobler, I., Koblitz, B., Nellen, G., Schmidt, S., Tzamariudaki, E., Udluft, S.

“…The H1-Level 2 neural network trigger has been running successfully at Deutsches Elektronen Synchrotron (DESY) for four years. In order to provide increased…”
Get full text

Ensembles of Neural Networks for Robust Reinforcement Learning by Hans, A, Udluft, S

“…Reinforcement learning algorithms that employ neural networks as function approximators have proven to be powerful tools for solving optimal control problems…”
Get full text

Agent self-assessment: Determining policy quality without execution by Hans, A., Duell, S., Udluft, S.

“…With the development of data-efficient reinforcement learning (RL) methods, a promising data-driven solution for optimal control of complex technical systems…”
Get full text

A Neural Reinforcement Learning Approach to Gas Turbine Control by Schaefer, A.M., Schneegass, D., Sterzing, V., Udluft, S.

“…In this paper a new neural network based approach to control a gas turbine for stable operation on high load is presented. A combination of recurrent neural…”
Get full text

A Recurrent Control Neural Network for Data Efficient Reinforcement Learning by Schaefer, A.M., Udluft, S., Zimmermann, H.-G.

“…In this paper we introduce a new model-based approach for a data-efficient modelling and control of reinforcement learning problems in discrete time. Our…”
Get full text