Safe exploration for reinforcement learning. A Hans, D Schneegaß, AM Schäfer, S Udluft ESANN, 143-148, 2008 | 174 | 2008 |
Ensembles of neural networks for robust reinforcement learning A Hans, S Udluft 2010 Ninth International Conference on Machine Learning and Applications …, 2010 | 47 | 2010 |
Efficient uncertainty propagation for reinforcement learning with limited data A Hans, S Udluft Artificial Neural Networks–ICANN 2009: 19th International Conference …, 2009 | 24 | 2009 |
Method for the computer-assisted modeling of a technical system S Düll, A Hans, S Udluft US Patent 9,489,619, 2016 | 19 | 2016 |
Method for the computer-assisted exploration of states of a technical system A Hans, D Schneegaβ, AM Schäfer, V Sterzing, S Udluft US Patent 8,494,980, 2013 | 15 | 2013 |
Method for the computer-assisted learning of a control and/or a feedback control of a technical system using a modified quality function and a covariance matrix A Hans, S Udluft US Patent 8,380,646, 2013 | 14 | 2013 |
Agent self-assessment: Determining policy quality without execution A Hans, S Duell, S Udluft 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement …, 2011 | 12 | 2011 |
Uncertainty in reinforcement learning-awareness, quantisation, and control D Schneegass, A Hans, S Udluft Robot Learning, Sciyo, 65-90, 2010 | 10 | 2010 |
Ensemble Usage for More Reliable Policy Identification in Reinforcement Learning. A Hans, S Udluft ESANN, 2011 | 7 | 2011 |
The Markov Decision Process Extraction Network. S Duell, A Hans, S Udluft ESANN, 2010 | 7 | 2010 |
Uncertainty Propagation for Efficient Exploration in Reinforcement Learning. A Hans, S Udluft ECAI, 361-366, 2010 | 2 | 2010 |
Sichere Exploration für Reinforcement-Learning-basierte Regelung A Hans, D Schneegaß, AM Schäfer, S Udluft Tagungsband des Workshops für Computational Intelligence der GMA-FA 5, 117-131, 2007 | 2 | 2007 |
Recurrent Neural State Estimation in Domains with Long-Term Dependencies. S Duell, L Weichbrodt, A Hans, S Udluft ESANN, 2012 | 1 | 2012 |
Untersuchungen zur sicheren Exploration in Reinforcement Learning A Hans Diploma Thesis. Ilmenau, Germany: TU Ilmenau, 2007 | 1 | 2007 |
Advancing the Applicability of Reinforcement Learning to Autonomous Control A Hans | | 2014 |
Development of a Network Adapter for the Stream Router A Hans | | 2007 |
Sensoren-Weiterentwicklung eines MID zu einem Inline-Messgerat fur rheologische Parameter-Fur eine praxistaugliche Regelung von rheologischen Parametern ist eine Inline-Messung … A Hans Automatisierungstechnische Praxis 43 (7), 49-54, 2001 | | 2001 |