Publications

For a comprehensive list of publications and stats, please visit:

2020


2019


2018


2017


2016


2015


2014

  • David Silver, G. Lever, Nicolas Heess, Thomas Degris, Daan Wierstra, Martin Riedmiller (2014) Deterministic Policy Gradient Algorithms. In The 31st International Conference on Machine Learning (ICML 2014). Beijing, China.

  • Alexey Dosovitskiy, Jost Tobias Springenberg, Martin Riedmiller, Thomas Brox (2014) Discriminative Unsupervised Feature Learning with Convolutional Neural Networks. In 28th Annual Conference on Neural Information Processing Systems (NIPS).

  • M Duempelmann, S Ewing, M Blum, R Rostek, P Woias, M Riedmiller, A Schulze-Bonhage (2014) Investigation of low complexity seizure detection algorithm for closed loop devices in epilepsy treatment. Clinical Neurophysiology pp. S80.


2013

  • Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller (2013) Playing Atari with Deep Reinforcement Learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning.


2012

  • Jost Tobias Springenberg, Martin Riedmiller (2012) Learning temporal coherent features through life-time sparsity. In International Conference on Neural Information Processing (ICONIP). pp. 347–356.


2011

  • Thomas Gabel, Martin Riedmiller (2011) Distributed Policy Search Reinforcement Learning for Job-Shop Scheduling Tasks. TPRS International Journal of Production Research 50 (1) pp. available online from May 2011. Taylor & Francis.

  • Manuel Blum, Martin Riedmiller (2011) Q-function Approximation in Batch Mode Reinforcement Learning. In International Workshop on Bio-Inspired Robots.


2010

  • Sascha Lange, Martin Riedmiller (2010) Deep Learning of Visual Control Policies. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2010). Brugge, Belgium.


2009

  • S. Timmer, M. Riedmiller (2009) Efficient Identification of State in Reinforcement Learning. Künstliche Intelligenz BöttcherIT Verlag.

  • Martin Lauer, Martin Riedmiller (2009) Participating in Autonomous Robot Competitions: Experiences from a Robot Soccer Team.


2008

  • T. Gabel, M. Riedmiller (September 2008) Gradient-Descent Policy Search for Job-Shop Scheduling Problems. In Online Proceedings of the 18th International Conference on Automated Planning and Scheduling (ICAPS 2008). AAAI Press. Sydney, Australia.

  • Thomas. Gabel., Martin Riedmiller (June 2008) Evaluation of Batch-Mode Reinforcement Learning for Solving DEC-MDPs with Changing Action Sets. In Proceedings of the 8th Biennial European Workshop on Reinforcement Learning (EWRL 2008). Springer. Lille, France.

  • S. Riedmiller, M. Riedmiller (2008) Konzepte und Anwendungen lernf{ä}higer Systeme. Medizinisch Orthop”adische Technik 5 (December) Verlagsgesellschaft Tischler GmbH.

  • Martin Riedmiller, Roland Hafner, Sascha Lange, Martin Lauer (2008) Learning to Dribble on a Real Robot by Success and Failure. In Proceedings of the 2008 International Conference on Robotics and Automation (ICRA 2008). Springer. Pasadena CA.


2007

  • Heiko Müller, Martin Lauer, Roland Hafner, Sascha Lange, Martin Riedmiller (2007) Making a Robot Learn to Play Soccer Using Reward and Punishment. In Proceedings of the German Conference on Artificial Intelligence, KI 2007. Osnabrück Germany.

  • Stephan Timmer, Martin Riedmiller (2007) Safe Q-Learning on Complete History Spaces. In Proceedings of the 18th European Conference on Machine Learning, ECML 07. Springer. Warsaw, Poland.

  • Martin Riedmiller, Mike Montemerlo, Hendrik Dahlkamp (2007) Learning to Drive in 20 Minutes. In Proceedings of the FBIT 2007 conference.. Springer. Jeju, Korea.

  • Arne Voigtländer, Sascha Lange, Martin Lauer, Martin Riedmiller (2007) Real-time 3D Ball Recognition using Perspective and Catadioptric Cameras. In Proceedings of the European Conference on Mobile Robots ECMR 2007. Freiburg Germany.

  • Roland Hafner, Martin Riedmiller (2007) Neural Reinforcement Learning Controllers for a Real Robot Application. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 07). Rome, Italy.

  • S. Timmer, M. Riedmiller (2007) Fitted Q Iteration with CMACs. In Proceedings of the IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 07). Honolulu, USA.

  • Martin Riedmiller, Jan Peters, Stefan Schaal (2007) Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark. In Proceedings of the IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 07). Honolulu, USA.


2006

  • M. Riedmiller, T. Gabel, R. Hafner, S. Lange, M. Lauer (2006) Die Brainstormers: Entwurfsprinzipien lernfaehiger autonomer Roboter. Informatik-Spektrum 20(3) pp. 175-190. Springer.

  • M. Lauer, S. Lange, M. Riedmiller (2006) Motion Estimation of Moving Objects for Autonomous mobile Robots. Künstliche Intelligenz 1 pp. 11-17. Springer.

  • S. Lange, M. Riedmiller (2006) Appearance Based Robot Discrimination using Eigenimages. In In Proceedings of the RoboCup Symposium 2006. Bremen, Germany.

  • S. Timmer, M. Riedmiller (2006) Abstract State Spaces with History. In Proceedings of the NAFIPS Conference, the North American Fuzzy Information Processing Society, Montreal, Canada.


2005

  • D. Withopf, M. Riedmiller (October 2005) Comparing Different Methods to Speed-Up Reinforcement Learning in a Complex Domain. In Proc. of the Int. Conference on Systems, Man and Cybernetics, 2005. Big Island, USA.

  • S. Timmer, M. Riedmiller (October 2005) Learning Policies for Abstract States. In Proc. of the Int. Conference on Systems, Man and Cybernetics, 2005. Big Island, USA.

  • D. Withopf, M. Riedmiller (2005) Effective Methods for Reinforcement Learning in Large Multi-Agent Domains. it - Information Technology Journal 5 (47) pp. 241-249. Oldenbourg.

  • R. Hafner, M.Riedmiller (2005) Case study: control of a real world system in CLSquare. In Proceedings of the NIPS Workshop on Reinforcement Learning Comparisons, Whistler, British Columbia, Canada.

  • M. Lauer, S. Lange, M. Riedmiller (2005) Calculating the Perfect Match: An Efficient and Accurate Approach for Robot Self-Localisation. In RoboCup-2005: Robot Soccer World Cup IX, LNCS. Springer.

  • A. Sung, A. Merke, M. Riedmiller (2005) Reinforcement Learning using a Grid-Based Function Approximator. In Biomimetic Neural Learning for Intelligent Robots.


2004

  • M. Riedmiller (September 2004) Machine Learning for Autonomous Robots. Keynote Speech.. In Proceedings of the KI '04, Ulm, Germany.

  • R. Schoknecht, M. Spott, M. Riedmiller (May 2004) textsc{Fynesse}: An Architecture for Integrating Prior Knowledge in Autonomously Learning Agents. Soft Computing 8 (6) pp. 397-408. Springer.

  • Enrico Pagello, Emanuele Menegatti, Daniel Polani, Ansgar Bredenfel, Paulo Costa, Thomas Christaller, Adam Jacoff, Martin Riedmiller, Alessandro Saffiotti, Elizabeth Sklar, Takashi Tomoichi (2004) RoboCup-2003: New Scientific and Technical Advances. AI Magazine American Association for Artificial Intelligence (AAAI).

  • M. Lauer, M. Riedmiller (2004) Reinforcement Learning for Stochastic Cooperative Multi-Agent Systems. In Proceedings of the AAMAS '04, New York.

  • A. Merke, S. Welker, M. Riedmiller (2004) Line Base Robot Localisation under Natural Light Conditions. In ECAI Workshop on Agents in Dynamic and Real-Time Environments.

  • S. Lange, M. Riedmiller (2004) Evolution of Computer Vision Subsystems in Robot Navigation and Image Classification Tasks. In RoboCup-2004: Robot Soccer World Cup VIII, LNCS. Springer.


2003

  • R. Schoknecht, M. Riedmiller (November 2003) Reinforcement Learning on Explicitly Specified Time-scales. Neural Computing & Applications 12 (2) pp. 61-80. Springer.

  • M. Arbatzat, S. Freitag, M. Fricke, R. Hafner, C. Heermann, K. Hegelich, A. Krause, J. Krüger, M. Lauer, M. Lewandowski, A. Merke, H. Müller, M. Riedmiller, J. Schanko, M. Schulte-Hobein, M. Theile, S. Welker, D. Withopf (2003) Creating a Robot Soccer Team from Scratch: the Brainstormers Tribots. In CD attached to Robocup 2003 Proceedings, Padua, Italy.

  • M. Riedmiller, A. Merke, W. Nowak, M. Nickschas, D. Withopf (2003) Brainstormers 2003 - Team Description. In CD attached to Robocup 2003 Proceedings, Padua, Italy.

  • Roland Hafner, Martin Riedmiller (2003) Reinforcement Learning on an omnidirectional mobile robot. In Proceedings of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003), Las Vegas.

  • R. Schoknecht, M. Riedmiller (2003) Learning to Control at Multiple Time Scales. In Proceedings of the Thirteenth International Conference on Artificial Neural Networks (ICANN). pp. 479–487. Springer.

  • Martin Lauer, Martin Riedmiller, Thomas Ragg, Walter Baum, Michael Wigbers (2003) The Smaller the Better: Comparison of Two Approaches for Sales Rate Prediction. In Advances in Intelligent Data Analysis V. pp. 451-461. Springer.

  • M. Riedmiller, A. Merke (2003) Using machine learning techniques in complex multi-agent domains. In Adaptivity and Learning. Springer.


2002

  • R. Schoknecht, M. Riedmiller (2002) Speeding up Reinforcement Learning with Multi-Step Actions. In Proceedings of International Conference on Artificial Neural Networks, ICANN'02. Madrid, Spain.

  • M. Lauer, M. Riedmiller (2002) Generalisation in Reinforcement Learning and the Use of Observation-Based Learning. In Proceedings of the FGML Workshop 2002. pp. 100-107.


2001

  • R. Schoknecht, M. Riedmiller (2001) Using Multi-step Actions for Faster Reinforcement Learning. In Fifth European Workshop on Reinforcement Learning.

  • W. Hunger, M. Riedmiller (2001) Scheduling with adaptive agents - an empirical evaluation. In Fifth European Workshop on Reinforcement Learning.

  • A. Merke, M. Riedmiller (2001) Karlsruhe Brainstormers - A Reinforcement Learning Way to Robotic Soccer II. In RoboCup-2001: Robot Soccer World Cup V, LNCS. pp. 322-327. Springer.

  • Martin Riedmiller (2001) Wie Roboter von Gehirnen lernen. In Kosmos Gehirn. BMBF.

  • Martin Riedmiller, Andrew Moore, Jeff Schneider (2001) Reinforcement Learning for Cooperating and Communicating Reactive Agents in Electrical Power Grids. In Balancing Reactivity and Social Deliberation in Multi-agent Systems. pp. 137-149. Springer, LNAI 2103.


2000

  • M. Riedmiller (2000) Concepts and facilities of a neural reinforcement learning control architecture for technical process control. Neural Computing & Applications 8 pp. 323-338. Springer.

  • M. Riedmiller, A. Merke, D. Meier, A. Hoffmann, A. Sinner, O. Thate, C. Kill, R. Ehrmann (2000) Karlsruhe Brainstormers - A Reinforcement Learning Way to Robotic Soccer. In RoboCup-2000: Robot Soccer World Cup IV, LNCS. Springer.

  • S. Buck, M. Riedmiller (2000) Learning Situation Dependent Success Rates Of Actions In A RoboCup Scenario. In Proceedings of PRICAI '00. pp. 809. Melbourne, Australia.

  • M. Lauer, M. Riedmiller (2000) An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems. In Proceedings of International Conference on Machine Learning, ICML '00. pp. 535-542. Stanford, CA.

  • R. Schoknecht, M. Spott, M. Riedmiller (2000) Design of self-learning controllers using { sc Fynesse}. In Deep Fusion of Computational and Symbolic Processing. Physica.


1999

  • M. Spott, R. Schoknecht, M. Riedmiller (1999) Approaches for the integration of a priori knowledge into an autonomously learning control architecture.. In Proc. of EUFIT99. Aachen, Germany.

  • J. Schneider, W. Wong, A. Moore, M. Riedmiller (1999) Distributed Value Functions. In Proceedings of International Conference on Machine Learning, ICML'99. pp. 371-378. Bled, Slovenia.

  • R. Schoknecht, M. Spott, F. Liekweg, M. Riedmiller (1999) Search Space Reduction for Strategy Learning in Sequential Decision Processes. In Proceedings of the International Conference on Neural Information Processing (ICONIP '99). Perth, Australia.

  • M. Riedmiller, S. Buck, A. Merke, R. Ehrmann, O. Thate, S. Dilger, A. Sinner, A. Hofmann, L. Frommberger (1999) Karlsruhe Brainstormers - Design Principles. In RoboCup-1999: Robot Soccer World Cup III, LNCS. Springer.

  • R. Schoknecht, M. Riedmiller (1999) Using reinforcement learning for engine control. In Proceedings of International Conference on Artificial Neuraln Networks, ICANN'99. Edinburgh.

  • T. Gaul, M. Spott, M. Riedmiller, R. Schoknecht (1999) Fuzzy-Neuro-Controlled Verified Instruction Scheduler. In Conference-Proceedings. New York.

  • S. Riedmiller, M. Riedmiller (1999) A neural reinforcement learning approach to learn local dispatching policies in production scheduling. In Proceedings of International Joint Conference on Artificial Intelligence, ICJAI'99. Stockholm.

  • M. Riedmiller, M. Spott, J. Weisbrod (1999) Fynesse: A hybrid architecture for self-learning control. In Knowledge Based Neuro Computing. MIT Press.


1998

  • R. Schoknecht, M. Spott, M Riedmiller (1998) Design of self-learning controllers using { sc Fynesse} (in German). In Fuzzy Karlsruhe '98. Karlsruhe.

  • K. Santa, M. Mews, M. Riedmiller (1998) A Neural Approach for the Control of Piezoelectric Micromanipulation Robots. Journal of Intelligent and Robotic Systems 22 pp. 351-374.

  • M. Riedmiller (1998) High quality thermostat control by reinforcement learning - a case study. In Proceedings of the Conald Workshop 1998. Carnegie-Mellon-University.

  • M. Riedmiller, R. Schoknecht (1998) Self-learning controllers in automotive applications (in German). In Proceedings of VDI/GMA -Aussprachetag. Berlin.

  • M. Spott, M. Riedmiller (1998) Improving a priori control knowledge by reinforcement learning. In Proceedings in Artificial Intelligence: Fuzzy-Neuro-Systems '98. pp. 146–153. infix Verlag. Muenchen, Deutschland.

  • M. Riedmiller (1998) Reinforcement learning without an explicit terminal state. In Proc. of the International Joint Conference on Neural Networks, IJCNN '98. Anchorage, Alaska.


1997

  • M. Riedmiller, M. Wigbers (1997) A New Method for the Analysis of Neural Reference Model Control. In IEEE International Conference on Neural Networks ICNN;97. Huston, Texas.

  • G. Goos, M. Spott, J. Weisbrod, M. Riedmiller (1997) Interpretation und Adaption unscharfer Relationen innerhalb einer hybriden selbstlernenden Steuerungsarchitektur. In Proceedings in Artificial Intelligence: Fuzzy-Neuro-Systeme '97. pp. 332–339. infix Verlag. Soest, Deutschland.

  • M. Riedmiller (1997) Generating continuous control signals for reinforcement controllers using dynamic output elements. In European Symposium on Artificial Neural Networks, ESANN'97. Bruges.

  • M. Riedmiller, M. Spott, J. Weisbrod (1997) First Results on the Application of the Fynesse Control Architecture. In IEEE 1997 International Aerospace Conference. pp. 421–434. Aspen, USA.

  • M. Riedmiller, S. Gutjahr, J. Klingemann (1997) Predicting exchange rates using neural networks. In Joint International Conference on Expert Systems (PACES/SPICES '97). Singapore.

  • A. Stahlberger, M. Riedmiller (1997) Fast Network Pruning and Feature Extraction using the Unit-OBS Algorithm. In Advances in Neural Information Processing Systems 9. MIT Press.


1996

  • M. Riedmiller (1996) Application of sequential reinforcement learning to control dynamic systems. In IEEE Intenational Conference on Neural Networks (ICNN '96). Washington.

  • M. Riedmiller (1996) Learning to Control Dynamic Systems. In Proceedings of the 13th. European Meeting on Cybernetics and Systems Research - 1996 (EMCSR '96). Vienna.

  • M. Riedmiller (1996) Selbständig lernende neuronale Steuerungen. VDI-Verlag.


1995

  • M. Riedmiller, B. Janusz (1995) Using Neural Reinforcement Controllers in Robotics. In Proceedings of the 8th. Australian Conference on Artificial Intelligence (AI '95). World Scientific Publishing. Singapore.

  • M. Riedmiller, B. Janusz (1995) Self learning control of a mobile robot. In Proceedings of the IEEE ICNN '95. Perth, Australia.

  • D. Koll, M. Riedmiller, H. Braun (1995) Massively Parallel Training of Multi Layer Perceptrons with Irregular Topologies. In Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms ICANNGA95. Springer (Vienna). Ales, France.


1994

  • M. Riedmiller (oct 1994) Aspects of Learning Neural Control. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. San Antonio, Texas.

  • M. Riedmiller (1994) Advanced Supervised Learning in Multi-layer Perceptrons - From Backpropagation to Adaptive Learning Algorithms. Int. Journal of Computer Standards and Interfaces 16 pp. 265-278.


1993

  • M. Riedmiller (oct 1993) Controlling an Inverted Pendulum by Neural Plant Identification. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Le Touquet.

  • M. Riedmiller (sep 1993) Untersuchungen zu Konvergenz und Generalisierungsverhalten überwachter Lernverfahren mit dem SNNS. In SNNS 1993 Workshop-Proceedings. pp. 107 - 116. Stuttgart.

  • M. Riedmiller, H. Braun (1993) A Direct Adaptive Method for Faster Backpropagation Learning: The {RPROP} Algorithm. In Proceedings of the IEEE International Conference on Neural Networks (ICNN). pp. 586 - 591. San Francisco.

  • M. Riedmiller, H. Braun (1993) {RPROP}: A Fast and Robust Backpropagation Learning Strategy. In Fourth Australian Conference on Neural Networks. pp. 169 - 172. Melbourne.


1992

  • M. Riedmiller, H. Braun (1992) {RPROP}: A Fast Adaptive Learning Algorithm. In International Symposium on Computer and Information Science VII. pp. 279 - 286. Antalya, Turkey.


1986


1985