Martin A. Riedmiller, a German computer scientist, since 2015 research scientist at Google DeepMind, and before, professor at the University of Freiburg, the University of Osnabrück and the University of Dortmund. His research interests center around artificial intelligence, machine learning, robotics, pattern recognition, neural networks and deep learning. In the 90s, while affiliated with the University of Karlsruhe where he defended his Ph.D. in 1996, he devised the Rprop algorithms (resilient backpropagation) for supervised learning in feedforward neural networks along with Heinrich Braun. To demonstrate the performance of the learning procedures on realistic problems, characterized by large networks and pattern sets, a network was trained to play the endgame of Nine Men’s Morris [1].
Martin Riedmiller [2]

Selected Publications

1992 ...

• Martin Riedmiller, Heinrich Braun (1992). Rprop - A Fast Adaptive Learning Algorithm. Proceedings of the International Symposium on Computer and Information Science
• Martin Riedmiller, Heinrich Braun (1993). A direct adaptive method for faster backpropagation learning: The RPROP algorithm. IEEE International Conference On Neural Networks, pdf
• Martin Riedmiller (1994). Rprop - Description and Implementation Details. Technical Report, University of Karlsruhe, pdf

2000 ...

• Martin Riedmiller (2004). Machine Learning for Autonomous Robots. KI 2004, Springer
• Martin Riedmiller (2005). Neural fitted Q iteration–first experiences with a data efficient neural reinforcement learning method. ECML 2005, Springer, pdf
• Martin Riedmiller, Thomas Gabel (2007). On experiences in a complex and competitive gaming domain: Reinforcement learning meets robocup. CIG 2007, pdf ^[4]

2010 ...

• Martin Riedmiller (2012). 10 Steps and Some Tricks to Set up Neural Reinforcement Controllers. Neural Networks: Tricks of the Trade, Springer (2nd ed.), pdf
• Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller (2013). Playing Atari with Deep Reinforcement Learning. arXiv:1312.5602 ^[5]
• Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis (2015). Human-level control through deep reinforcement learning. Nature, Vol. 518

External Links

• Martin Riedmiller | LinkedIn
• Martin Riedmiller - Google Scholar Citations
• Machine Learning Lab, University of Freiburg - Martin Riedmiller

References

1. ^ Martin Riedmiller, Heinrich Braun (1993). A direct adaptive method for faster backpropagation learning: The RPROP algorithm. IEEE International Conference On Neural Networks, pdf
2. ^ Machine Learning Lab, University of Freiburg - Martin Riedmiller
3. ^ dblp: Martin A. Riedmiller
4. ^ RoboCup from Wikipedia
5. ^ Demystifying Deep Reinforcement Learning by Tambet Matiisen, Nervana, December 21, 2015

What links here?