| Batch reinforcement learning S Lange, T Gabel, M Riedmiller Reinforcement learning: State-of-the-art, 45-73, 2012 | 755 | 2012 |
| Deep auto-encoder neural networks in reinforcement learning S Lange, M Riedmiller The 2010 international joint conference on neural networks (IJCNN), 1-8, 2010 | 520 | 2010 |
| Reinforcement learning for robot soccer M Riedmiller, T Gabel, R Hafner, S Lange Autonomous Robots 27, 55-73, 2009 | 403 | 2009 |
| Autonomous reinforcement learning on raw visual input data in a real world application S Lange, M Riedmiller, A Voigtländer The 2012 international joint conference on neural networks (IJCNN), 1-8, 2012 | 306 | 2012 |
| Calculating the perfect match: an efficient and accurate approach for robot self-localization M Lauer, S Lange, M Riedmiller RoboCup 2005: Robot Soccer World Cup IX 9, 142-153, 2006 | 172 | 2006 |
| Learn to swing up and balance a real pole based on raw visual input data J Mattner, S Lange, M Riedmiller Neural Information Processing: 19th International Conference, ICONIP 2012 …, 2012 | 59 | 2012 |
| Incremental GRLVQ: Learning relevant features for 3D object recognition TC Kietzmann, S Lange, M Riedmiller Neurocomputing 71 (13-15), 2868-2879, 2008 | 50 | 2008 |
| Real-time 3D Ball Recognition using Perspective and Catadioptric Cameras. A Voigtländer, S Lange, M Lauer, MA Riedmiller EMCR, 2007 | 40 | 2007 |
| 3D-objecttracking with a mixed omnidirectional stereo camera system M Lauer, M Schönbein, S Lange, S Welker Mechatronics 21 (2), 390-398, 2011 | 37 | 2011 |
| Deep learning of visual control policies. S Lange, MA Riedmiller ESANN, 2010 | 35 | 2010 |
| Making a robot learn to play soccer using reward and punishment H Müller, M Lauer, R Hafner, S Lange, A Merke, M Riedmiller KI 2007: Advances in Artificial Intelligence, 220-234, 2007 | 35 | 2007 |
| Modeling moving objects in a dynamically changing robot application M Lauer, S Lange, M Riedmiller KI 2005: Advances in Artificial Intelligence: 28th Annual German Conference …, 2005 | 31 | 2005 |
| Predicting Time Series with Space-Time Convolutional and Recurrent Neural Networks. W Groß, S Lange, J Bödecker, M Blum ESANN, 2017 | 29 | 2017 |
| Brainstormers tribots team description R Hafner, S Lange, M Lauer, M Riedmiller RoboCup International Symposium, 2008 | 29 | 2008 |
| Bridging the gap: Learning in the RoboCup simulation and midsize league T Gabel, R Hafner, S Lange, M Lauer, M Riedmiller Proceedings of the 7th Portuguese Conference on Automatic Control, 2006 | 26 | 2006 |
| Learning to dribble on a real robot by success and failure M Riedmiller, R Hafner, S Lange, M Lauer 2008 IEEE International Conference on Robotics and Automation, 2207-2208, 2008 | 18 | 2008 |
| Die brainstormers: Entwurfsprinzipien lernfähiger autonomer roboter M Riedmiller, T Gabel, R Hafner, S Lange, M Lauer Informatik-Spektrum 29, 175-190, 2006 | 18 | 2006 |
| Computational object recognition: a biologically motivated approach TC Kietzmann, S Lange, M Riedmiller Biological cybernetics 100, 59-79, 2009 | 17 | 2009 |
| Cognitive concepts in autonomous soccer playing robots M Lauer, R Hafner, S Lange, M Riedmiller Cognitive Systems Research 11 (3), 287-309, 2010 | 16 | 2010 |
| Motion estimation of moving objects for autonomous mobile robots M Lauer, S Lange, M Riedmiller Künstliche Intelligenz 20 (1), 11-17, 2006 | 14 | 2006 |
Martin RiedmillerDeepMindVerified email at google.com
