This is an archived version of the Machine Learning Lab website for documentation purposes. The host is in no way affiliated with the University of Freiburg, its Faculty of Engineering or any of its members.

Full Publication List for Prof. Dr. Martin Riedmiller

The following list contains publications up to the beginning of Summer Term 2015. For newer publications, please refer to this list at Google Scholar.

2016

SS Kumar, J Wülfing, S Okujeni, J Boedecker, M Riedmiller, U Egert (2016) Autonomous Optimization of Targeted Stimulation of Neuronal Networks. PLoS Comput Biol 12 (8) pp. e1005054. web Bibtex

@article{kumar2016plos,
  title={Autonomous Optimization of Targeted Stimulation of Neuronal Networks},
  author={Kumar, SS and Wülfing, J and Okujeni, S and Boedecker, J and Riedmiller, M and Egert, U},
  journal={PLoS Comput Biol},
  keywords = {EXC1086; BoedeckerSelect},
  volume={12},
  number={8},
  pages={e1005054},
  url={http://dx.doi.org/10.1371/journal.pcbi.1005054},
  year={2016}
}

2015

Wendelin Böhmer, Jost Tobias Springenberg, Joschka Boedecker, Martin Riedmiller, Klaus Obermayer (2015) Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations. KI - Künstliche Intelligenz pp. 1-10. Springer Berlin Heidelberg. doi web Bibtex

@article{BoeSprBoeRieObeKI2015,
  year={2015},
  issn={0933-1875},
  journal={KI - Künstliche Intelligenz},
  doi={10.1007/s13218-015-0356-1},
  title={Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations},
  url={http://dx.doi.org/10.1007/s13218-015-0356-1},
  publisher={Springer Berlin Heidelberg},
  keywords={End-to-end reinforcement learning; Representation learning; Deep auto-encoder networks; Slow feature analysis; Autonomous robotics; BoedeckerSelect},
  author={Böhmer, Wendelin and Springenberg, Jost Tobias and Boedecker, Joschka and Riedmiller, Martin and Obermayer, Klaus},
  pages={1-10}
}

J. T. Springenberg, A. Dosovitskiy, T. Brox, M. Riedmiller (2015) Striving for Simplicity: The All Convolutional Net. In arXiv:1412.6806, also appeared at ICLR 2015 Workshop Track. web Bibtex

@INPROCEEDINGS{SprDosBroRied15,
  AUTHOR =       {J. T. Springenberg and A. Dosovitskiy and T. Brox and M. Riedmiller},
  TITLE =        {Striving for Simplicity: The All Convolutional Net},
  BOOKTITLE =    {arXiv:1412.6806, also appeared at ICLR 2015 Workshop Track},
  CONFERENCE = {ICLR 2015 Workshop Track},
  YEAR =         {2015},
  url = {http://arxiv.org/abs/1412.6806},
  keywords = {EXC1086;BLBT;Deep Learning}
}

A. Eitel, J. T. Springenberg, L. Spinello, M. Riedmiller, W. Burgard (2015) Multimodal Deep Learning for Robust RGB-D Object Recognition. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). web Bibtex

@INPROCEEDINGS{EitSprSpiRieBur15,
   author = {Eitel, A. and Springenberg, J. T. and Spinello, L. and Riedmiller, M. and Burgard, W.},
   title = {Multimodal Deep Learning for Robust RGB-D Object Recognition},
   booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
   keywords = {EXC1086;BLBT;Deep Learning;RGB-D;Robotics},
   url = {http://arxiv.org/abs/1507.06821},
   year = 2015
}

Manuel Watter, Jost Springenberg, Joschka Boedecker, Martin Riedmiller (2015) Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images. In Advances in Neural Information Processing Systems 28. pp. 2728–2736. PDF Bibtex

@incollection{watter2015e2c,
  title = {Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images},
  author = {Watter, Manuel and Springenberg, Jost and Boedecker, Joschka and Riedmiller, Martin},
  booktitle = {Advances in Neural Information Processing Systems 28},
  editor = {C. Cortes and N.D. Lawrence and D.D. Lee and M. Sugiyama and R. Garnett and R. Garnett},
  pages = {2728--2736},
  keywords = {EXC1086; SPP; BoedeckerSelect},
  year = {2015},
  file = {http://papers.nips.cc/paper/5964-embed-to-control-a-locally-linear-latent-dynamics-model-for-control-from-raw-images.pdf}
}

2014

Thomas Lampe, Lukas D. J. Fiederer, Martin Voelker, Alexander Knorr, Martin Riedmiller, Tonio Ball (2014) A Brain-Computer Interface for High-Level Remote Control of an Autonomous, Reinforcement-Learning-Based Robotic System for Reaching and Grasping. In International Conference on Intelligent User Interfaces (IUI 2014). Haifa, Israel. web Bibtex

@inproceedings{LampeFiedererIUI2014,
  author = {Thomas Lampe and Lukas D. J. Fiederer and Martin Voelker and Alexander Knorr and Martin Riedmiller and Tonio Ball},
  title = {A Brain-Computer Interface for High-Level Remote Control of an Autonomous, Reinforcement-Learning-Based Robotic System for Reaching and Grasping},
  booktitle = {International Conference on Intelligent User Interfaces (IUI 2014)},
  address = {Haifa, Israel},
  year = {2014},
  url = {http://dl.acm.org/citation.cfm?id=2557500.2557533&coll=DL&dl=ACM&CFID=298536792&CFTOKEN=73699462},
  keywords = {EXC1086;BLBT;Neurobots;BCI;Grasping}
}

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). Bejing, China. web Bibtex

@inproceedings{SilveretalICML2014,
  author = {David Silver and G. Lever and Nicolas Heess and Thomas Degris and Daan Wierstra and Martin Riedmiller},
  title = {Deterministic Policy Gradient Algorithms},
  booktitle = {The 31st International Conference on Machine Learning (ICML 2014)},
  address = {Bejing, China},
  year = {2014},
  url = {http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Publications_files/deterministic-policy-gradients.pdf}
}

Thomas Lampe, Martin Riedmiller (2014) Approximate Model-Assisted Neural Fitted Q-Iteration. In IEEE International Joint Conference on Neural Networks (IJCNN 2014). Beijing, China. PDF Bibtex

@inproceedings{LampeRiedmillerIJCNN2014,
  author = {Thomas Lampe and Martin Riedmiller},
  title = {Approximate Model-Assisted Neural Fitted Q-Iteration},
  booktitle = {IEEE International Joint Conference on Neural Networks (IJCNN 2014)},
  address = {Beijing, China},
  year = {2014},
  keywords = {NFQ;Model-based Learning;EXC1086;BLBT;Neurobots;PR2},
  file = {lampe_riedmiller_ijcnn14.pdf}
}

Joschka Boedecker, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2014) Approximate Real-Time Optimal Control Based on Sparse Gaussian Process Models. In Adaptive Dynamic Programming and Reinforcement Learning (ADPRL). PDF Bibtex

@INPROCEEDINGS{BoeSprWuel2014,
  author = {Joschka Boedecker and Jost Tobias Springenberg and Jan Wülfing and Martin Riedmiller},
  title = {Approximate Real-Time Optimal Control Based on Sparse Gaussian Process Models},
  booktitle = {Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)},
  year = {2014},
  file = {adprl-2014.pdf},
  keywords= {EXC1086;BLBT;Neurobots;PR2;BoedeckerSelect}
}

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). Bibtex

@INPROCEEDINGS{DosSpr2014,
  author = {Alexey Dosovitskiy and Jost Tobias Springenberg and Martin Riedmiller and Thomas Brox},
  title = {Discriminative Unsupervised Feature Learning with Convolutional Neural Networks},
  booktitle = {28th Annual Conference on Neural Information Processing Systems (NIPS)},
  year = {2014}
}

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. Bibtex

@article{duempelmann2014p121,
  title={Investigation of low complexity seizure detection algorithm for closed loop devices in epilepsy treatment},
  author={Duempelmann, M and Ewing, S and Blum, M and Rostek, R and Woias, P and Riedmiller, M and Schulze-Bonhage, A},
  journal={Clinical Neurophysiology},
  number={125},
  pages={S80},
  year={2014}
}

2013

Manuel Blum, Martin Riedmiller (2013) Electricity Demand Forecasting using Gaussian Processes. In The AAAI-13 Workshop on Trading Agent Design and Analysis (TADA-13). PDF Bibtex

@inproceedings{blum2013a,
  author = {Manuel Blum and Martin Riedmiller},
  booktitle = {The AAAI-13 Workshop on Trading Agent Design and Analysis (TADA-13)},
  title = {Electricity Demand Forecasting using Gaussian Processes},
  year = {2013},
  file = {http://ml.informatik.uni-freiburg.de/_media/publications/blum2013a.pdf}
}

Thomas Gabel, Martin Riedmiller (2013) The Cooperative Driver: Multi-Agent Learning for Preventing Traffic Jams. International Journal of Traffic and Transportation Engineering 1 (4) pp. 67–76. Scientific & Academic Publishing. PDF Bibtex

@article{gabel2013,
  author = {Thomas Gabel and Martin Riedmiller},
  title = {The Cooperative Driver: Multi-Agent Learning for Preventing Traffic Jams},
  journal = {International Journal of Traffic and Transportation Engineering},
  volume = {1},
  number = {4},
  pages = {67--76},
  year = {2013},
  publisher = {Scientific & Academic Publishing},
  file = {gabel2013.pdf}
}

Manuel Blum, Martin Riedmiller (2013) Optimization of Gaussian Process Hyperparameters using Rprop. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. PDF Bibtex

@inproceedings{blumesann2013,
  author = {Manuel Blum and Martin Riedmiller},
  booktitle = {European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning},
  title = {{Optimization of Gaussian Process Hyperparameters using Rprop}},
  year = {2013},
  file = {http://ml.informatik.uni-freiburg.de/_media/publications/blumesann2013.pdf}
}

Thomas Lampe, Martin Riedmiller (2013) Acquiring Visual Servoing Reaching and Grasping Skills using Neural Reinforcement Learning. In IEEE International Joint Conference on Neural Networks (IJCNN 2013). Dallas, TX. PDF Bibtex

@inproceedings{LampeRiedmiller2013,
  author = {Thomas Lampe and Martin Riedmiller},
  title = {Acquiring Visual Servoing Reaching and Grasping Skills using Neural Reinforcement Learning},
  booktitle = {IEEE International Joint Conference on Neural Networks (IJCNN 2013)},
  address = {Dallas, TX},
  year = {2013},
  file = {lampe2013.pdf},
  keywords = {NFQ;Grasping;Visual Servoing;EXC1086;BLBT;Neurobots;PR2}
}

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. web Bibtex

@article {MnihetalAtari13,
  author = {Volodymyr Mnih and Koray Kavukcuoglu and David Silver and Alex Graves and Ioannis Antonoglou and Daan Wierstra and Martin Riedmiller},
  title = {Playing Atari with Deep Reinforcement Learning},
  year = {2013},
  eprint = {"arXiv/1312.5602"},
  booktitle = {NIPS Workshop on Deep Learning and Unsupervised Feature Learning},
  url = {http://arxiv.org/pdf/1312.5602.pdf}
}

Joschka Boedecker, Thomas Lampe, Martin Riedmiller (2013) Modeling effects of intrinsic and extrinsic rewards on the competition between striatal learning systems. Frontiers in Psychology 4 (739) doi web Bibtex

@ARTICLE{BoedeckerLampeRiedmiller2013,
  AUTHOR = {Boedecker, Joschka  and  Lampe, Thomas  and  Riedmiller, Martin},
  TITLE = {Modeling effects of intrinsic and extrinsic rewards on the competition between striatal learning systems},
  JOURNAL = {Frontiers in Psychology},
  VOLUME = {4},
  YEAR = {2013},
  NUMBER = {739},
  URL = {http://www.frontiersin.org/cognitive_science/10.3389/fpsyg.2013.00739/abstract},
  DOI = {10.3389/fpsyg.2013.00739},
  ISSN = {1664-1078},
  keywords = {Cognitive Modeling;Striatum;BoedeckerSelect}
}

Jost Tobias Springenberg, Martin Riedmiller (2013) Improving Deep Neural Networks with Probabilistic Maxout Units. In arXiv:1312.6116, also appeared at ICLR 2014 Workshop Track. web Bibtex

@INPROCEEDINGS{SprRied2014a,
  AUTHOR =       {Jost Tobias Springenberg and Martin Riedmiller},
  TITLE =        {Improving Deep Neural Networks with Probabilistic Maxout Units},
  BOOKTITLE =    {arXiv:1312.6116, also appeared at ICLR 2014 Workshop Track},
  CONFERENCE = {ICLR 2014 Workshop Track},
  YEAR =         {2013},
  url = {http://arxiv.org/abs/1312.6116}
}

2012

Martin Riedmiller, Sascha Lange, Arne Voigtlaender (2012) Autonomous reinforcement learning on raw visual input data in a real world application. In International Joint Conference on Neural Networks. Brisbane, Australia. PDF Bibtex

@INPROCEEDINGS{rieijcnn12,
  AUTHOR = {Martin Riedmiller and Sascha Lange and Arne Voigtlaender},
  ADDRESS = {Brisbane, Australia},
  BOOKTITLE = {International Joint Conference on Neural Networks},
  TITLE = {Autonomous reinforcement learning on raw visual input data in a real world application},
  YEAR = {2012},
  FILE = {rieijcnn12.pdf}
}

Manuel Blum, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2012) A Learned Feature Descriptor for Object Recognition in RGB-D Data. In IEEE International Conference on Robotics and Automation (ICRA). St. Paul, Minnesota, USA. PDF Bibtex

@INPROCEEDINGS{blumicra2012,
  AUTHOR = {Manuel Blum and Jost Tobias Springenberg and Jan Wülfing and Martin Riedmiller},
  ADDRESS = {St. Paul, Minnesota, USA},
  BOOKTITLE = {IEEE International Conference on Robotics and Automation (ICRA)},
  TITLE = {A Learned Feature Descriptor for Object Recognition in RGB-D Data},
  YEAR = {2012},
  FILE = {http://ml.informatik.uni-freiburg.de/_media/publications/blumicra2012.pdf}
}

Oliver Obst, Martin Riedmiller (2012) Taming the Reservoir: Feedforward Training for Recurrent Neural Networks. In International Joint Conference on Neural Networks. Brisbane, Australia. PDF Bibtex

@INPROCEEDINGS{obstrieijcnn12,
  AUTHOR = {Oliver Obst and Martin Riedmiller},
  ADDRESS = {Brisbane, Australia},
  BOOKTITLE = {International Joint Conference on Neural Networks},
  TITLE = {Taming the Reservoir: Feedforward Training for Recurrent Neural Networks},
  YEAR = {2012},
  FILE = {obstrieijcnn12.pdf}
}

Jan Wülfing, Martin Riedmiller (2012) Unsupervised Learning of Local Features for Music Classification. In Proceedings of the 13th International Society for Music Information Retrieval Conference (ISMIR). Porto, Portugal. PDF Bibtex

@INPROCEEDINGS{wuelf2012,
  AUTHOR = {Jan Wülfing and Martin Riedmiller},
  ADDRESS = {Porto, Portugal},
  BOOKTITLE = {Proceedings of the 13th International Society for Music Information Retrieval Conference (ISMIR)},
  TITLE = {Unsupervised Learning of Local Features for Music Classification},
  YEAR = {2012},
  FILE = {wuelf2012.pdf}
}

Jan Mattner, Sascha Lange, Martin Riedmiller (2012) Learn to Swing Up and Balance a Real Pole Based on Raw Visual Input Data. In Proceedings of the 19th International Conference on Neural Information Processing (5) (ICONIP 2012). pp. 126–133. Dohar, Qatar. PDF Bibtex

@inproceedings{MattnerLangeRiedmiller2012,
  author = {Jan Mattner and Sascha Lange and Martin Riedmiller},
  title = {Learn to Swing Up and Balance a Real Pole Based on Raw Visual Input Data},
  booktitle = {Proceedings of the 19th International Conference on Neural Information Processing (5) (ICONIP 2012)},
  address = {Dohar, Qatar},
  year = {2012},
  pages = {126--133},
  file = {mattner.pdf}
}

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. Bibtex

@INPROCEEDINGS{springj2012a,
  title = {Learning temporal coherent features through life-time sparsity},
  author = {Jost Tobias Springenberg and Martin Riedmiller},
  booktitle = {International Conference on Neural Information Processing (ICONIP)},
  pages = {347--356},
  year = {2012},
  organization = {Springer}
}

Martin Riedmiller (2012) 10 Steps and Some Tricks to Set up Neural Reinforcement Controllers.. In Neural Networks: Tricks of the Trade (2nd ed.). pp. 735-757. PDF Bibtex

@inproceedings{RiedmillerTricks12,
  author = {Martin Riedmiller},
  title = {10 Steps and Some Tricks to Set up Neural Reinforcement Controllers.},
  booktitle = {Neural Networks: Tricks of the Trade (2nd ed.)},
  year = {2012},
  pages = {735-757},
  crossref = {2012},
  file = {12riedmillertricks.pdf}
}

2011

T. Gabel, C. Lutz, M. Riedmiller (April 2011) Improved Neural Fitted Q Iteration Applied to a Novel Computer Gaming and Learning Benchmark. In In Proceedings of the IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2011). IEEE Press. Paris France. PDF Bibtex

@inproceedings{GLR11,
  author = {T. Gabel and C. Lutz and M. Riedmiller},
  ADDRESS = {Paris France},
  title = {Improved Neural Fitted Q Iteration Applied to a Novel Computer Gaming and Learning Benchmark},
  booktitle = {In Proceedings of the IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2011)},
  publisher = {IEEE Press},
  month = {April},
  year = {2011},
  file = {GLR11.pdf} 
}

Andreas Witsch, Roland Reichle, Sascha Lange, Martin Riedmiller, Kurt Geihs (April 2011) Enhancing the Episodic Natural Actor-Critic Algorithm by a Regularisation Term to Stabilize Learning of Control Structures. In In Proceedings of the IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2011). IEEE Press. Paris France. PDF Bibtex

@inproceedings{WRLRG11,
  author = {Andreas Witsch and Roland Reichle and Sascha Lange and Martin Riedmiller and Kurt Geihs},
  ADDRESS = {Paris France},
  title = {Enhancing the Episodic Natural Actor-Critic Algorithm by a Regularisation Term to Stabilize Learning of Control Structures},
  booktitle = {In Proceedings of the IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2011)},
  publisher = {IEEE Press},
  month = {April},
  year = {2011},
  file = {WRLRG11.pdf} 
}

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. Bibtex

@article{GR11,
  author = {Thomas Gabel and Martin Riedmiller},
  title = {Distributed Policy Search Reinforcement Learning for Job-Shop Scheduling Tasks},
  journal = {TPRS International Journal of Production Research},
  publisher = {Taylor & Francis},
  volume = {50},
  number = {1},
  pages = {available online from May 2011},
  note = {},
  year = {2011}
}

Roland Hafner, Martin Riedmiller (2011) Reinforcement learning in feedback control. Machine Learning 27 (1) pp. 55–74. available online at http://dx.doi.org/10.1007/s10994-011-5235-x or upon request at riedmiller@informatik.uni-freiburg.de. Springer Netherlands. web Bibtex

@article{HRMLJ11,
  author = {Hafner, Roland and Riedmiller, Martin},
  affiliation = {Machine Learning Lab, Albert-Ludwigs University Freiburg, Freiburg im Breisgau, Germany},
  title = {Reinforcement learning in feedback control},
  journal = {Machine Learning},
  publisher = {Springer Netherlands},
  issn = {0885-6125},
  volume = {27},
  number = {1},
  pages = {55--74. available online at http://dx.doi.org/10.1007/s10994-011-5235-x or upon request at riedmiller@informatik.uni-freiburg.de},
  keyword = {Computer Science},
  url = {http://dx.doi.org/10.1007/s10994-011-5235-x},
  note = {10.1007/s10994-011-5235-x},
  year = {2011}
}

Manuel Blum, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2011) On the Applicability of Unsupervised Feature Learning for Object Recognition in RGB-D Data. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning. Granada, Spain. PDF Bibtex

@INPROCEEDINGS{blumnips2011,
  AUTHOR = {Manuel Blum and Jost Tobias Springenberg and Jan Wülfing and Martin Riedmiller},
  ADDRESS = {Granada, Spain},
  BOOKTITLE = {NIPS Workshop on Deep Learning and Unsupervised Feature Learning},
  TITLE = {On the Applicability of Unsupervised Feature Learning for Object Recognition in RGB-D Data},
  YEAR = {2011},
  FILE = {http://ml.informatik.uni-freiburg.de/_media/publications/blumnips2011.pdf}
}

Roland Hafner, Martin Riedmiller (2011) Learning (Near) Time Optimal Control for Flexible Robot Joints. In Workshop on Comparison of Reinforcement Learning and Optimal Control Methods for Real-World Robotic Tasks, RSS 2011. Los Angeles, CA. PDF Bibtex

@inproceedings{HafnerRiedmiller2011,
  author = {Roland Hafner and Martin Riedmiller},
  title = {Learning (Near) Time Optimal Control for Flexible Robot Joints},
  booktitle = {Workshop on Comparison of Reinforcement Learning and Optimal Control Methods for Real-World Robotic Tasks, RSS 2011},
  address = {Los Angeles, CA},
  year = {2011},
  file = {11_rss11_hafnerriedmiller.pdf}
}

S. Lange, T. Gabel, M. Riedmiller (2011) Batch Reinforcement Learning. In Reinforcement Learning: State of the Art. Springer, in press. PDF Bibtex

@incollection{LangeGabelRiedmiller2011chapter,
  title = {{Batch Reinforcement Learning}},
  author = {Lange, S. and Gabel, T. and Riedmiller, M.},
  booktitle = {Reinforcement Learning: State of the Art},
  editor = {Wiering, M. and van Otterlo, M.},
  publisher = {Springer, in press},
  year = {2011},
  file = {LangeGabelRiedmiller2011chapter.pdf}
}

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

@inproceedings{blum2011q,
  title={Q-function Approximation in Batch Mode Reinforcement Learning},
  author={Blum, Manuel and Riedmiller, Martin},
  booktitle={International Workshop on Bio-Inspired Robots},
  year={2011}
}

2010

Martin Lauer, Roland Hafner, Sascha Lange, Martin Riedmiller (2010) Cognitive concepts in autonomous soccer playing robots. Cognitive Systems Research 11 (3) pp. 287-309. doi web PDF Bibtex

@article{LauerCSR10,
  title = {Cognitive concepts in autonomous soccer playing robots},
  journal = {Cognitive Systems Research},
  volume = {11},
  number = {3},
  pages = {287-309},
  year = {2010},
  issn = {1389-0417},
  doi = {DOI:10.1016/j.cogsys.2009.12.003},
  url = {http://www.sciencedirect.com/science/article/B6W6C-4Y3JYGW-1/2/d4f3b83d84a1558bf5627211e55f91ea},
  author = {Martin Lauer and Roland Hafner and Sascha Lange and Martin Riedmiller},
  file = {LauerCSR10.pdf},
  keywords = {Soccer}
}

Thomas Gabel, Martin Riedmiller (2010) On Progress in RoboCup: The Simulation League Showcase. In RoboCup 2010: Robot Soccer World Cup XIV, LNCS. Springer. Singapore. web PDF Bibtex

@inproceedings{GRRCSym2010,
  author = {Thomas Gabel and Martin Riedmiller},
  ADDRESS = {Singapore},
  title = {On Progress in RoboCup: The Simulation League Showcase},
  booktitle = {RoboCup 2010: Robot Soccer World Cup XIV, LNCS},
  publisher = {Springer},
  note = {},
  year = {2010},
  url = {http://www.youtube.com/watch?v = Fk8MEkAgMNU},
  file = {GRRCSym2010.pdf},
  keywords = {Soccer}
}

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. PDF Bibtex

@INPROCEEDINGS{LangeESANN2010,
  AUTHOR = {Sascha Lange and Riedmiller, Martin},
  ADDRESS = {Brugge, Belgium},
  BOOKTITLE = {European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2010)},
  TITLE = {Deep Learning of Visual Control Policies},
  YEAR = {2010},
  FILE = {LangeESANN2010.pdf}
}

Sascha Lange, Martin Riedmiller (2010) Deep Auto-Encoder Neural Networks in Reinforcement Learning. In International Joint Conference on Neural Networks (IJCNN 2010). Barcelona, Spain. PDF Bibtex

@INPROCEEDINGS{LangeIJCNN2010,
  AUTHOR = {Sascha Lange and Riedmiller, Martin},
  ADDRESS = {Barcelona, Spain},
  BOOKTITLE = {International Joint Conference on Neural Networks (IJCNN 2010)},
  TITLE = {Deep Auto-Encoder Neural Networks in Reinforcement Learning},
  YEAR = {2010},
  FILE = {LangeIJCNN2010.pdf}
}

Sascha Lange, Martin Riedmiller (2010) A Vision for Reinforcement Learning and its Implications for Neural Computation. In NC2 Workshop, German Conference on Artificial Intelligence (KI2010), accepted. Karlsruhe, Germany. PDF Bibtex

@INPROCEEDINGS{LangeNC2KI10,
  AUTHOR = {Sascha Lange and Riedmiller, Martin},
  ADDRESS = {Karlsruhe, Germany},
  BOOKTITLE = {NC2 Workshop, German Conference on Artificial Intelligence (KI2010), accepted},
  TITLE = {A Vision for Reinforcement Learning and its Implications for Neural Computation},
  YEAR = {2010},
  FILE = {LangeNC2KI10.pdf}
}

2009

T. Kietzmann, M. Riedmiller (Dec 2009) The Neuro Slot Car Racer: Reinforcement Learning in a Real World Setting. In Proceedings of the Int. Conference on Machine Learning Applications (ICMLA09). Springer. Miami, Florida. PDF Bibtex

@inproceedings{KR09,
  author = {T. Kietzmann and M. Riedmiller},
  ADDRESS = {Miami, Florida},
  title = {The Neuro Slot Car Racer: Reinforcement Learning in a Real World Setting},
  booktitle = {Proceedings of the Int. Conference on Machine Learning Applications (ICMLA09)},
  publisher = {Springer},
  month = {Dec},
  year = {2009},
  file = {KR09.pdf}
}

M. Riedmiller, T. Gabel, R. Hafner, S. Lange (2009) Reinforcement Learning for Robot Soccer. Autonomous Robots 27 (1) pp. 55–74. Springer. PDF Bibtex

@article{GR+09,
  author = {M. Riedmiller and T. Gabel and R. Hafner and S. Lange},
  title = {Reinforcement Learning for Robot Soccer},
  journal = {Autonomous Robots},
  publisher = {Springer},
  volume = {27},
  number = {1},
  pages = {55--74},
  year = {2009},
  file = {GR+09.pdf},
  keywords = {Soccer}
}

T. Kietzmann, S. Lange, M. Riedmiller (2009) Computational Object Recognition: A Biologically Motivated Approach. Biological Cybernetics 100 (1) pp. 55–73. IEEE Press. PDF Bibtex

@article{KLR09,
  author = {T. Kietzmann and S. Lange and M. Riedmiller},
  title = {Computational Object Recognition: A Biologically Motivated Approach},
  journal = {Biological Cybernetics},
  publisher = {IEEE Press},
  volume = {100},
  number = {1},
  year = {2009},
  pages = {55--73},
  file = {KLR09.pdf}
}

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

@article{TR09,
  author = {S. Timmer and M. Riedmiller},
  title = {Efficient Identification of State in Reinforcement Learning},
  journal = {Künstliche Intelligenz},
  publisher = {BöttcherIT Verlag},
  year = {2009}
}

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

@misc{lauer09ijcai,
  author = {Martin Lauer and Martin Riedmiller},
  title = {Participating in Autonomous Robot Competitions: Experiences from a Robot Soccer Team},
  howpublished = {Proceedings of the Workshop on Competitions in Artificial Intelligence and Robotics at the International Joint Conference on Artificial Intelligence},
  year = 2009,
  %url = 
  {http://www.informatik.uni-freiburg.de/ helmert/events/ijcai09-ws/program.html
  },
  keywords = {Soccer}
}

2008

T. Gabel, M. Riedmiller (September 2008) Joint Equilibrium Policy Search for Multi-Agent Scheduling Problems. In Proceedings of the 6th Conference on Multiagent System Technologies (MATES 2008). Springer. Kaiserslautern. PDF Bibtex

@inproceedings{GR08.1,
  author = {T. Gabel and M. Riedmiller},
  ADDRESS = {Kaiserslautern},
  title = {Joint Equilibrium Policy Search for Multi-Agent Scheduling Problems},
  booktitle = {Proceedings of the 6th Conference on Multiagent System Technologies (MATES 2008)},
  publisher = {Springer},
  month = {September},
  year = {2008},
  file = {GR08.1.pdf} 
}

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. Bibtex

@inproceedings{GR08.2,
  author = {T. Gabel and M. Riedmiller},
  ADDRESS = {Sydney, Australia},
  title = {Gradient-Descent Policy Search for Job-Shop Scheduling Problems},
  booktitle = {Online Proceedings of the 18th International Conference on Automated Planning and Scheduling (ICAPS 2008)},
  publisher = {AAAI Press},
  month = {September},
  year = {2008} 
}

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. Bibtex

@inproceedings{GR08.4,
  author = {Thomas. Gabel. and Riedmiller, Martin},
  ADDRESS = {Lille, France},
  title = {Evaluation of Batch-Mode Reinforcement Learning for Solving DEC-MDPs with Changing Action Sets},
  booktitle = {Proceedings of the 8th Biennial European Workshop on Reinforcement Learning (EWRL 2008)},
  publisher = {Springer},
  month = {June},
  year = {2008},
  files = {GR08.4.pdf} 
}

T. Kietzmann, S. Lange, M. Riedmiller (2008) Incremental GRLVQ: Learning Relevant Features for 3D Object Recognition. Neurocomputing 71 (13-15) pp. 2868–2879. Elsevier. PDF Bibtex

@article{KLR07,
  author = {T. Kietzmann and S. Lange and M. Riedmiller},
  title = {Incremental GRLVQ: Learning Relevant Features for 3D Object Recognition},
  journal = {Neurocomputing},
  publisher = {Elsevier},
  volume = {71 (13-15)},
  year = {2008},
  pages = {2868--2879},
  file = {KLR07.pdf}
}

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

@article{RR09,
  author = {S. Riedmiller and M. Riedmiller},
  title = {Konzepte und Anwendungen lernf{ä}higer Systeme},
  journal = {Medizinisch Orthop"adische Technik},
  publisher = {Verlagsgesellschaft Tischler GmbH},
  volume = {5 (December)},
  year = {2008}
}

T. Gabel, M. Riedmiller (2008) Increasing Precision of Credible Case-Based Inference. In Proceedings of the 9th European Conference on Case-Based Reasoning (ECCBR 2008). Springer. Trier, Germany. PDF Bibtex

@inproceedings{GR08.3,
  author = {T. Gabel and M. Riedmiller},
  ADDRESS = {Trier, Germany},
  title = {Increasing Precision of Credible Case-Based Inference},
  booktitle = {Proceedings of the 9th European Conference on Case-Based Reasoning (ECCBR 2008)},
  publisher = {Springer},
  year = {2008},
  file = {GR08.3.pdf}
}

Thomas Gabel, Martin Riedmiller (2008) Reinforcement Learning for DEC-MDPs with Changing Action Sets and Partially Ordered Dependencies. In {Proceedings of the 7th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2008)}. Springer. Estoril, Portugal. PDF Bibtex

@inproceedings{GR08,
  author = {Thomas Gabel and Martin Riedmiller},
  ADDRESS = {Estoril, Portugal},
  title = {Reinforcement Learning for DEC-MDPs with Changing Action Sets and Partially Ordered Dependencies},
  booktitle = { {Proceedings of the 7th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2008)}},
  publisher = {Springer},
  year = {2008},
  file = {GR08.pdf} 
}

Thomas Gabel, Martin Riedmiller, Florian Trost (2008) A Case Study on Improving Defense Behavior in Soccer Simulation 2D: The NeuroHassle Approach. In RoboCup 2008: Robot Soccer World Cup XII, LNCS. Springer. Shouzou, China. PDF Bibtex

@inproceedings{GRTRobocup08,
  author = {Thomas Gabel and Martin Riedmiller and Florian Trost},
  ADDRESS = {Shouzou, China},
  title = {A Case Study on Improving Defense Behavior in Soccer Simulation 2D: The NeuroHassle Approach},
  booktitle = {RoboCup 2008: Robot Soccer World Cup XII, LNCS},
  publisher = {Springer},
  note = {},
  year = {2008},
  file = {GRTRobocup08.pdf},
  keywords = {Soccer}
}

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. Bibtex

@inproceedings{RHLL08,
  author = {Martin Riedmiller and Roland Hafner and Sascha Lange and Martin Lauer},
  ADDRESS = {Pasadena CA},
  title = {Learning to Dribble on a Real Robot by Success and Failure},
  booktitle = {Proceedings of the 2008 International Conference on Robotics and Automation (ICRA 2008)},
  publisher = {Springer},
  note = {video presentation},   
  year = {2008} 
}

2007

Thomas Gabel, Martin Riedmiller (2007) An Analysis of Case-Based Value Function Approximation by Approximating State Transition Graphs. In Proceedings of the 7th International Conference on Case-Based Reasoning (ICCBR 2007). Springer. Belfast, UK. PDF Bibtex

@inproceedings{GR07ICCBR,
  author = {Thomas Gabel and Martin Riedmiller},
  ADDRESS = {Belfast, UK},
  title = {An Analysis of Case-Based Value Function Approximation by Approximating State Transition Graphs},
  booktitle = {Proceedings of the 7th International Conference on Case-Based Reasoning (ICCBR 2007)},
  publisher = {Springer},
  note = {Nominated for Best Paper Award.},
  year = {2007},
  file = {GR07ICCBR.pdf} 
}

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. Bibtex

@inproceedings{MLHLMR07,
  author = {Heiko Müller and Martin Lauer and Roland Hafner and  Sascha Lange and Martin Riedmiller},
  ADDRESS = {Osnabrück Germany},
  title = {Making a Robot Learn to Play Soccer Using Reward and Punishment},
  booktitle = {Proceedings of the German Conference on Artificial Intelligence, KI 2007},
  year = {2007},
  keywords = {Soccer}
}

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. Bibtex

@inproceedings{TR07,
  author = {Stephan Timmer and Martin Riedmiller},
  ADDRESS = {Warsaw, Poland},
  title = {Safe Q-Learning on Complete History Spaces},
  booktitle = {Proceedings of the 18th European Conference on Machine Learning, ECML 07},
  publisher = {Springer},
  year = {2007} 
}

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

@inproceedings{RieFBIT07,
  author = {Martin Riedmiller and Mike Montemerlo and Hendrik Dahlkamp},
  ADDRESS = {Jeju, Korea},
  title = {Learning to Drive in 20 Minutes},
  booktitle = {Proceedings of the FBIT 2007 conference.},
  publisher = {Springer},
  note = {Best Paper Award.},
  year = {2007},
  file = {RieFBIT07.pdf} 
}

T. Gabel, M. Riedmiller (2007) Adaptive Reactive Job-Shop Scheduling with Reinforcement Learning Agents. International Journal of Information Technology and Intelligent Computing 24 (4) IEEE Press. PDF Bibtex

@article{GR07,
  author = {T. Gabel and M. Riedmiller},
  title = {Adaptive Reactive Job-Shop Scheduling with Reinforcement Learning Agents},
  journal = {International Journal of Information Technology and Intelligent Computing},
  volume = {24},
  number = {4},
  publisher = {IEEE Press},
  year = {2007},
  file = {GR07.pdf}
}

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. Bibtex

@inproceedings{VLLR07,
  author = {Arne Voigtländer and Sascha Lange and Martin Lauer and Martin Riedmiller},
  ADDRESS = {Freiburg Germany},
  title = {Real-time 3D Ball Recognition using Perspective and Catadioptric Cameras},
  booktitle = {Proceedings of the European Conference on Mobile Robots ECMR 2007},
  year = {2007} 
}

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. Bibtex

@inproceedings{RiedmillerHafnerICRA07,
  author = {Roland Hafner and Martin Riedmiller},
  ADDRESS = {Rome, Italy},
  title = {Neural Reinforcement Learning Controllers for a Real Robot Application},
  booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 07)},
  year = {2007} 
}

T. Gabel, M. Riedmiller (2007) Scaling Adaptive Agent-Based Reactive Job-Shop Scheduling to Large-Scale Problems. In Proceedings of the IEEE Symposium on Computational Intelligence in Scheduling (CI-Sched 2007). Honolulu, USA. PDF Bibtex

@inproceedings{GabelRiedmiller07b,
  author = {T. Gabel and M. Riedmiller},
  ADDRESS = {Honolulu, USA},
  title = {Scaling Adaptive Agent-Based Reactive Job-Shop Scheduling to Large-Scale Problems},
  booktitle = {Proceedings of the IEEE Symposium on Computational Intelligence in Scheduling (CI-Sched 2007)},
  year = {2007},
  file = {GabelRiedmiller07b.pdf} 
}

T. Gabel, M. Riedmiller (2007) On Experiences in a Complex and Competitive Gaming Domain: Reinforcement Learning Meets RoboCup. In Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG 2007). Honolulu, USA. PDF Bibtex

@inproceedings{RiedmillerGabel07c,
  author = {T. Gabel and M. Riedmiller},
  ADDRESS = {Honolulu, USA},
  title = {On Experiences in a Complex and Competitive Gaming Domain: Reinforcement Learning Meets RoboCup},
  booktitle = {Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG 2007)},
  year = {2007},
  file = {RiedmillerGabel07c.pdf},
  keywords = {Soccer}
}

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. Bibtex

@inproceedings{RiedmillerTimmer07,
  author = {S. Timmer and M. Riedmiller},
  ADDRESS = {Honolulu, USA},
  title = {Fitted Q Iteration with CMACs},
  booktitle = {Proceedings of the IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 07)},
  year = {2007} 
}

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. Bibtex

@inproceedings{RiedmillerPeters07,
  author = {Martin Riedmiller and Jan Peters and Stefan Schaal},
  ADDRESS = {Honolulu, USA},
  title = {Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark},
  booktitle = {Proceedings of the IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 07)},
  year = {2007} 
}

T. Gabel, M. Riedmiller (2007) On a Successful Application of Multi-Agent Reinforcement Learning to Operations Research Benchmarks. In Proceedings of the IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 07). Honolulu, USA. PDF Bibtex

@inproceedings{GabelRiedmiller07a,
  author = {T. Gabel and M. Riedmiller},
  ADDRESS = {Honolulu, USA},
  title = {On a Successful Application of Multi-Agent Reinforcement Learning to Operations Research Benchmarks},
  booktitle = {Proceedings of the IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 07)},
  year = {2007},
  file = {GabelRiedmiller07a.pdf} 
}

2006

T. Gabel, M. Riedmiller (2006) Learning a Partial Behavior for a competitive Soccer Agent. K{ü}nstliche Intelligenz 2 pp. 18-23. Springer. PDF Bibtex

@article{GR05KI,
  author = {T. Gabel and M. Riedmiller},
  title = {Learning a Partial Behavior for a competitive Soccer Agent},
  journal = {K{ü}nstliche Intelligenz},
  volume = {2},
  pages = {18-23},
  publisher = {Springer},
  year = {2006},
  file = {GR05KI.pdf},
  keywords = {Soccer}
}

M. Riedmiller, T. Gabel, R. Hafner, S. Lange, M. Lauer (2006) Die Brainstormers: Entwurfsprinzipien lernf{ä}higer autonomer Roboter. Informatik-Spektrum 20(3) pp. 175-190. Springer. Bibtex

@article{brainstormer06riedmiller,
  author = {M. Riedmiller and T. Gabel and R. Hafner and S. Lange and M. Lauer},
  title = {Die Brainstormers: Entwurfsprinzipien lernf{ä}higer autonomer Roboter},
  journal = {Informatik-Spektrum},
  volume = {20(3)},
  pages = {175-190},
  publisher = {Springer},
  year = {2006}
}

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

@article{LLR06:KI,
  author = {M. Lauer and S. Lange and M. Riedmiller},
  title = {Motion Estimation of Moving Objects for Autonomous mobile Robots},
  journal = {Künstliche Intelligenz},
  volume = {1},
  pages = {11-17},
  publisher = {Springer},
  year = {2006}
}

T. Gabel, M. Riedmiller (2006) Multi-Agent Case-Based Reasoning for Cooperative Reinforcement Learners. In In Proceedings of the 8th European Conference on Case-Based Reasoning (ECCBR 2006). Fethiye, Turkey. PDF Bibtex

@inproceedings{GRECCBR06,
  author = {T. Gabel and M. Riedmiller},
  ADDRESS = {Fethiye, Turkey},
  title = {Multi-Agent Case-Based Reasoning for Cooperative Reinforcement Learners},
  booktitle = {In Proceedings of the 8th European Conference on Case-Based Reasoning (ECCBR 2006)},
  year = {2006},
  file = {GRECCBR06.pdf} 
}

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

@inproceedings{LR06,
  author = {S. Lange and M. Riedmiller},
  ADDRESS = {Bremen, Germany},
  title = {Appearance Based Robot Discrimination using Eigenimages},
  booktitle = {In Proceedings of the RoboCup Symposium 2006},
  year = {2006},
  keywords = {Soccer}
}

T. Gabel, M. Riedmiller (2006) Reducing Policy Degradation in Neuro-Dynamic Programming. In In Proceedings of the 11th European Symposium on Artificial Neural Networks (ESANN 2006). Bruges, Belgium. PDF Bibtex

@inproceedings{GRESANN06,
  author = {T. Gabel and M. Riedmiller},
  ADDRESS = {Bruges, Belgium},
  title = {Reducing Policy Degradation in Neuro-Dynamic Programming},
  booktitle = {In Proceedings of the 11th European Symposium on Artificial Neural Networks (ESANN 2006)},
  year = {2006},
  file = {GRESANN06.pdf} 
}

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. Bibtex

@inproceedings{history06timmer,
  author = {S. Timmer and M. Riedmiller},
  title = {Abstract State Spaces with History},
  booktitle = {Proceedings of the NAFIPS Conference, the North American Fuzzy Information Processing Society, Montreal, Canada},
  year = {2006} 
}

T. Gabel, R. Hafner, S. Lange, M. Lauer, M. Riedmiller (2006) Bridging the Gap: Learning in the RoboCup Simulation and Midsize League. In Proceedings of the 7th Portuguese Conference on Automatic Control (Controlo 2006). Portuguese Society of Automatic Control. Porto, Portugal. PDF Bibtex

@inproceedings{ghllr2006,
  author = {T. Gabel and R. Hafner and S. Lange and M. Lauer and M. Riedmiller},
  title = {Bridging the Gap: Learning in the RoboCup Simulation and Midsize League},
  publisher = {Portuguese Society of Automatic Control},
  address = {Porto, Portugal},
  booktitle = {Proceedings of the 7th Portuguese Conference on Automatic Control (Controlo 2006)},
  year = {2006},
  file = {ghllr2006.pdf},
  keywords = {Soccer}
}

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. Bibtex

@InProceedings{WR05,
  author = {D. Withopf and M. Riedmiller},
  ADDRESS = {Big Island, USA},
  title = {Comparing Different Methods to Speed-Up Reinforcement Learning in a Complex Domain},
  booktitle = {Proc. of the Int. Conference on Systems, Man and Cybernetics, 2005},
  editors = {},
  year = {2005},
  month = {October}
}

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. Bibtex

@InProceedings{TR05,
  author = {S. Timmer and M. Riedmiller},
  ADDRESS = {Big Island, USA},
  title = {Learning Policies for Abstract States},
  booktitle = {Proc. of the Int. Conference on Systems, Man and Cybernetics, 2005},
  editors = {},
  year = {2005},
  month = {October}
}

M. Riedmiller (October 2005) Neural Fitted Q Iteration - First experiences with a data efficient neural Reinforcement Learning Method. In Lecture Notes in Computer Science: Proc. of the European Conference on Machine Learning, ECML 2005. pp. 317-328. Porto, Portugal. PDF Bibtex

@InProceedings{RieECML05,
  author = {M. Riedmiller},
  ADDRESS = {Porto, Portugal},
  title = {Neural Fitted Q Iteration - First experiences with a data efficient neural Reinforcement Learning Method},
  booktitle = {Lecture Notes in Computer Science: Proc. of the European Conference on Machine Learning, ECML 2005},
  editors = { João Gama, Rui Camacho, Pavel Brazdil, Alípio Jorge, Luís Torgo},
  year = {2005},
  pages = {317-328},
  month = {October},
  file = {RieECML05.pdf}
}

M. Riedmiller (October 2005) Neural Reinforcement Learning to Swing-Up and Balance a Real Pole. In Proc. of the Int. Conference on Systems, Man and Cybernetics, 2005. Big Island, USA. PDF Bibtex

@InProceedings{RieSMC05,
  author = {M. Riedmiller},
  ADDRESS = {Big Island, USA},
  title = {Neural Reinforcement Learning to Swing-Up and Balance a Real Pole},
  booktitle = {Proc. of the Int. Conference on Systems, Man and Cybernetics, 2005},
  editors = {},
  year = {2005},
  month = {October},
  file = {RieSMC05.pdf}
}

T. Gabel, M. Riedmiller (August 2005) CBR for State Value Function Approximation in Reinforcement Learning. In Proceedings of the International Conference on Case Based Reasoning 2005 (ICCBR 2005). Springer. Chicago, USA. PDF Bibtex

@InProceedings{GR05,
  author = {T. Gabel and M. Riedmiller},
  title = {CBR for State Value Function Approximation in Reinforcement Learning},
  booktitle = {Proceedings of the International Conference on Case Based Reasoning 2005 (ICCBR 2005)},
  editors = {},
  address = {Chicago, USA},
  year = {2005},
  publisher = {Springer},
  month = {August},
  file = {GR05.pdf}
}

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. Bibtex

@Article{WR05:IT,
  author = {D. Withopf and M. Riedmiller},
  title = {Effective Methods for Reinforcement Learning in Large Multi-Agent Domains},
  journal = {it - Information Technology Journal},
  year = {2005},
  month = {},
  publisher = {Oldenbourg},
  PAGES = {241-249},
  VOLUME = {5},
  NUMBER = {47},
  self = {j}
}

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. Bibtex

@inproceedings{clsquare05hafner,
  author = {R. Hafner and M.Riedmiller},
  title = {Case study: control of a real world system in CLSquare},
  booktitle = {Proceedings of the NIPS Workshop on Reinforcement Learning Comparisons, Whistler, British Columbia, Canada},
  year = {2005}
}

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. Bibtex

@InProceedings{LLR:RoboCup05,
  AUTHOR = {M. Lauer and S. Lange and M. Riedmiller},
  booktitle = {RoboCup-2005: Robot Soccer World Cup IX, LNCS},
  EDITOR = {A. Bredenfeld  and A. Jacoff  and I. Noda and Y. Takahasi},
  publisher = {Springer},
  TITLE = {Calculating the Perfect Match: An Efficient and Accurate Approach for Robot Self-Localisation},
  YEAR = {2005},
  self = {p},
  keywords = {Soccer}
}

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

@InProceedings{RS04,
  author = {A. Sung and A. Merke and M. Riedmiller},
  title = {Reinforcement Learning using a Grid-Based Function Approximator},
  booktitle = {Biomimetic Neural Learning for Intelligent Robots},
  editors = {Stefan Wermter and Günther Palm and Mark Elshaw},
  series = {Lecture Notes in Artificial Intelligence, Vol. 3575},
  year = {2005},
}

2004

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

@InProceedings{Rie04,
  author = {M. Riedmiller},
  title = {Machine Learning for Autonomous Robots. Keynote Speech.},
  booktitle = {Proceedings of the KI '04, Ulm, Germany},
  year = {2004},
  month = {September},
}

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. Bibtex

@Article{SR03:Softcomputing,
  author = {R. Schoknecht and M. Spott and M. Riedmiller},
  title = { textsc{Fynesse}: An Architecture for Integrating Prior Knowledge in Autonomously Learning Agents},
  journal = {Soft Computing},
  year = {2004},
  month = {May},
  publisher = {Springer},
  PAGES = {397-408},
  VOLUME = {8},
  NUMBER = {6},
  self = {j}
}

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). Bibtex

@Article{Robocup03:AI,
  author = {Enrico Pagello and Emanuele Menegatti and Daniel Polani and Ansgar Bredenfel and Paulo Costa and Thomas Christaller and Adam Jacoff and Martin Riedmiller and Alessandro Saffiotti and Elizabeth Sklar and Takashi Tomoichi},
  title = {RoboCup-2003: New Scientific and Technical Advances},
  journal = {AI Magazine}, 
  publisher = {American Association for Artificial Intelligence (AAAI)},
  year = {2004},
  keywords = {Soccer}
}

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

@InProceedings{LR04,
  author = {M. Lauer and M. Riedmiller},
  title = {Reinforcement Learning for Stochastic Cooperative Multi-Agent Systems},
  booktitle = {Proceedings of the AAMAS '04, New York},
  year = {2004},
}

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. Bibtex

@InProceedings{MWR04,
  AUTHOR = {A. Merke and S. Welker and M. Riedmiller},
  booktitle = {ECAI Workshop on Agents in Dynamic and Real-Time Environments},
  TITLE = {Line Base Robot Localisation under Natural Light Conditions},
  YEAR = {2004},
  self = {p}
}

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. Bibtex

@InProceedings{RoboCup04,
  AUTHOR = {S. Lange and M. Riedmiller},
  booktitle = {RoboCup-2004: Robot Soccer World Cup VIII, LNCS},
  EDITOR = {D. Nardi and M. Riedmiller and C. Sammut and J. Santos-Victor},
  publisher = {Springer},
  TITLE = {Evolution of Computer Vision Subsystems in Robot Navigation and Image Classification Tasks},
  YEAR = {2004},
  self = {p},
  keywords = {Soccer}
}

2003

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

@Article{SR03:NCAF,
  author = {R. Schoknecht and M. Riedmiller},
  title = {Reinforcement Learning on Explicitly Specified Time-scales},
  journal = {Neural Computing & Applications},
  year = {2003},
  month = {November},
  publisher = {Springer},
  PAGES = {61-80},
  VOLUME = {12},
  NUMBER = {2},
  self = {j}
}

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. Bibtex

@InProceedings{BS03tribots,
  author = {M. Arbatzat and S. Freitag and M. Fricke and R. Hafner and C. Heermann and K. Hegelich and A. Krause and J. Krüger and M. Lauer and M. Lewandowski and A. Merke and H. Müller and M. Riedmiller and J. Schanko and M. Schulte-Hobein and M. Theile and S. Welker and D. Withopf},
  title = {Creating a Robot Soccer Team from Scratch: the Brainstormers Tribots},
  booktitle = {CD attached to Robocup 2003 Proceedings, Padua, Italy},
  year = {2003},
  keywords = {Soccer}
}

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

@InProceedings{BS03,
  author = {M. Riedmiller and A. Merke and W. Nowak and M. Nickschas and D. Withopf},
  title = {Brainstormers 2003 - Team Description},
  booktitle = {CD attached to Robocup 2003 Proceedings, Padua, Italy},
  year = {2003},
  keywords = {Soccer}
}

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. Bibtex

@InProceedings{HR03,
  author = {Roland Hafner and Martin Riedmiller},
  title = {Reinforcement Learning on an omnidirectional mobile robot},
  booktitle = {Proceedings of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003), Las Vegas},
  year = {2003},
}

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. Bibtex

@InProceedings{SR03,
  author = {R. Schoknecht and M. Riedmiller},
  title = {Learning to Control at Multiple Time Scales},
  booktitle = {Proceedings of the Thirteenth International Conference on Artificial Neural Networks (ICANN)},
  pages = {479--487},
  year = {2003},
  editor = {O. Kaynak, E. Alpaydin, E. Oja and L. Xu},
  series = {Lecture Notes in Computer Science (LNCS) 2714},
  OPTaddress = {Istanbul, Turkey},
  publisher = {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. Bibtex

@InProceedings{LR03,
  author = {Martin Lauer and Martin Riedmiller and Thomas Ragg and Walter Baum and Michael Wigbers},
  title = {The Smaller the Better: Comparison of Two Approaches for Sales Rate Prediction},
  editor = {M. R. Berthold and H.-J. Lenz and E. Bradley and R. Kruse and C. Borgelt},
  booktitle = {Advances in Intelligent Data Analysis V},
  pages = {451-461},
  publisher = {Springer},
  year = {2003}
}

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

@incollection{RM02,
  AUTHOR = {M. Riedmiller and A. Merke},
  booktitle = {Adaptivity and Learning},
  EDITOR = {I. Stamatescu and W. Menzel and M. Richter and U. Ratsch},
  publisher = {Springer},
  TITLE = {Using machine learning techniques in complex multi-agent domains},
  YEAR = {2003},
  self = {c}
}

2002

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

@CONFERENCE{SR02,
  AUTHOR = {R. Schoknecht and M. Riedmiller},
  ADDRESS = {Madrid, Spain},
  BOOKTITLE = {Proceedings of International Conference on Artificial Neuraln Networks, ICANN'02},
  TITLE = {Speeding up Reinforcement Learning with Multi-Step Actions},
  YEAR = {2002},
  self = {p}
}

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. Bibtex

@CONFERENCE{LR02,
  AUTHOR = {M. Lauer and M. Riedmiller},
  ADDRESS = {},
  PAGES = {100-107},
  EDITOR = {Gabriella Kokai and Jens Zeidler},
  BOOKTITLE = {Proceedings of the FGML Workshop 2002},
  TITLE = {Generalisation in Reinforcement Learning and the Use of Observation-Based Learning},
  YEAR = {2002},
  self = {p}
}

2001

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

@InProceedings{schoknecht01:EWRL,
  author = {Schoknecht, R. and Riedmiller, M.},
  title = {Using Multi-step Actions for Faster Reinforcement Learning},
  booktitle = {Fifth European Workshop on Reinforcement Learning},
  year = 2001,
  OPTaddress = {Utrecht, Netherlands}
}

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

@InProceedings{HR01,
  author = {W. Hunger and M. Riedmiller},
  title = {Scheduling with adaptive agents - an empirical evaluation},
  booktitle = {Fifth European Workshop on Reinforcement Learning},
  year = {2001},
  self = {p}
}

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. Bibtex

@incollection{RoboCup01,
  AUTHOR = {A. Merke and M. Riedmiller},
  booktitle = {RoboCup-2001: Robot Soccer World Cup V, LNCS},
  EDITOR = {A. Birk and S. Coradeschi and S. Tadokoro},
  publisher = {Springer},
  TITLE = {Karlsruhe Brainstormers - A Reinforcement Learning Way to Robotic Soccer II},
  YEAR = {2001},
  pages = {322-327},
  self = {p},
  keywords = {Soccer}
}

Martin Riedmiller (2001) Wie {R}oboter von {G}ehirnen lernen. In Kosmos Gehirn. BMBF. Bibtex

@incollection{Rie01IB,
  author = {Martin Riedmiller},
  address = {},
  booktitle = {Kosmos Gehirn},
  editor = {},
  publisher = {BMBF},
  title = {Wie {R}oboter von {G}ehirnen lernen},
  note = {Eingeladener {B}eitrag},
  year = {2001},
}

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. Bibtex

@incollection{Rie01,
  author = {Martin Riedmiller and Andrew Moore and Jeff Schneider},
  address = {},
  booktitle = {Balancing Reactivity and Social Deliberation in Multi-agent Systems},
  editor = { Markus Hannebauer, Jan Wendler, Enrico Pagello},
  publisher = {Springer, LNAI 2103},
  title = {Reinforcement Learning for Cooperating and Communicating Reactive Agents in Electrical Power Grids},
  year = {2001},
  pages = {137-149},
  self = {c}
}

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. Bibtex

@ARTICLE{Rie00,
  AUTHOR = {M. Riedmiller},
  journal = {Neural Computing & Applications},
  PAGES = {323-338},
  TITLE = {Concepts and facilities of a neural reinforcement learning control architecture for technical process control},
  VOLUME = {8},
  YEAR = {2000},
  publisher = {Springer},
  self = {j}
}

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. Bibtex

@incollection{RoboCup00,
  AUTHOR = {M. Riedmiller and A. Merke and D. Meier and A. Hoffmann and A. Sinner and O. Thate and C. Kill and R. Ehrmann},
  booktitle = {RoboCup-2000: Robot Soccer World Cup IV, LNCS},
  EDITOR = {A. Jennings and  P. Stone},
  publisher = {Springer},
  TITLE = {Karlsruhe Brainstormers - A Reinforcement Learning Way to Robotic Soccer},
  YEAR = {2000},
  self = {p},
  keywords = {Soccer}
}

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

@CONFERENCE{BR00,
  AUTHOR = {S. Buck and M. Riedmiller},
  ADDRESS = {Melbourne, Australia},
  BOOKTITLE = {Proceedings of PRICAI '00},
  TITLE = {Learning Situation Dependent Sucess Rates Of Actions In A RoboCup Scenario},
  YEAR = {2000},
  PAGES = {809},
  self = {p},
  keywords = {Soccer}
}

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. Bibtex

@CONFERENCE{LR00,
  AUTHOR = {M. Lauer and M. Riedmiller},
  ADDRESS = {Stanford, CA},
  BOOKTITLE = {Proceedings of International Conference on Machine Learning, ICML '00},
  TITLE = {An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems},
  YEAR = {2000},
  PAGES = {535-542},
  self = {p}
}

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

@incollection{SSR99,
  author = {Schoknecht, R. and Spott, M. and Riedmiller, M.},
  address = {},
  booktitle = {Deep Fusion of Computational and Symbolic Processing},
  editor = {Furuhashi, T. and Tano, S. and Jacobsen, H.A.},
  publisher = {Physica},
  title = {Design of self-learning controllers using { sc Fynesse}},
  year = {2000},
  self = {c}
}

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. Bibtex

@InProceedings{spottEUFIT99,
  author = {Spott, M. and Schoknecht, R. and Riedmiller, M.},
  title = {Approaches for the integration of a priori knowledge into an autonomously learning control architecture.},
  booktitle = {Proc.  of EUFIT99},
  year = 1999,
  address = {Aachen, Germany},
  note = {(Invited paper)},
  self = {p}
}

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. Bibtex

@CONFERENCE{SWMR,
  AUTHOR = { J. Schneider and W. Wong and A. Moore and M. Riedmiller},
  ADDRESS = {Bled, Slovenia},
  BOOKTITLE = {Proceedings of International Conference on Machine Learning, ICML'99},
  PAGES = {371-378},
  TITLE = {Distributed Value Functions},
  YEAR = {1999},
  self = {p}
}

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. Bibtex

@InProceedings{SSLR99,
  author = {R. Schoknecht and M. Spott and F. Liekweg and M. Riedmiller},
  title = {Search Space Reduction for Strategy Learning in Sequential Decision Processes},
  booktitle = {Proceedings of the International Conference on Neural Information Processing (ICONIP '99)},
  year = 1999,
  address = {Perth, Australia},
  self = {p}
}

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. Bibtex

@incollection{RoboCup99,
  AUTHOR = {M. Riedmiller and S. Buck and  A. Merke and  R. Ehrmann and  O. Thate and  S. Dilger and  A. Sinner and  A. Hofmann and  L. Frommberger},
  booktitle = {RoboCup-1999: Robot Soccer World Cup III, LNCS},
  EDITOR = {},
  publisher = {Springer},
  TITLE = {Karlsruhe Brainstormers - Design Principles},
  YEAR = {1999},
  self = {p},
  keywords = {Soccer}
}

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

@CONFERENCE{SR99,
  AUTHOR = {R. Schoknecht and M. Riedmiller},
  ADDRESS = {Edinburgh},
  BOOKTITLE = {Proceedings of International Conference on Artificial Neuraln Networks, ICANN'99},
  TITLE = {Using reinforcement learning for engine control},
  YEAR = {1999},
  self = {p}
}

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

@CONFERENCE{GSRS99,
  AUTHOR = {T. Gaul and M. Spott and M. Riedmiller and R. Schoknecht},
  ADDRESS = {New York},
  BOOKTITLE = {Conference-Proceedings},
  TITLE = {Fuzzy-Neuro-Controlled Verified Instruction Scheduler},
  YEAR = {1999},
  self = {p}
}

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. Bibtex

@CONFERENCE{RR99,
  AUTHOR = {S. Riedmiller and M. Riedmiller},
  ADDRESS = {Stockholm},
  BOOKTITLE = {Proceedings of International Joint Conference on Artificial Intelligence, ICJAI'99},
  TITLE = {A neural reinforcement learning approach to learn local dispatching policies in production scheduling},
  YEAR = {1999},
  self = {p}
}

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

@incollection{RSW99,
  AUTHOR = {M. Riedmiller and M. Spott and J. Weisbrod},
  booktitle = {Knowledge Based Neuro Computing},
  EDITOR = {I. Cloete and J.M. Zurada},
  publisher = {MIT Press},
  TITLE = {Fynesse: A hybrid architecture for self-learning control},
  YEAR = {1999},
  self = {c}
}

1998

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

@CONFERENCE{SSR98,
  AUTHOR = {Schoknecht, R. and Spott, M. and Riedmiller, M},
  TITLE = {Design of self-learning controllers using { sc Fynesse} (in German)},
  ADDRESS = {Karlsruhe},
  BOOKTITLE = {Fuzzy Karlsruhe '98},
  YEAR = {1998},
  self = {p}
}

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. Bibtex

@ARTICLE{RieRobotic98,
  AUTHOR = {K. Santa and M. Mews and M. Riedmiller},
  JOURNAL = {Journal of Intelligent and Robotic Systems},
  PAGES = {351-374},
  TITLE = {A Neural Approach for the Control of Piezoelectric Micromanipulation Robots},
  VOLUME = {22},
  YEAR = {1998},
  self = {j}
}

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

@CONFERENCE{RieConald98,
  AUTHOR = {M. Riedmiller},
  ADDRESS = {Carnegie-Mellon-University},
  BOOKTITLE = {Proceedings of the Conald Workshop 1998},
  TITLE = {High quality thermostat control by reinforcement learning - a case study},
  YEAR = {1998},
  self = {p}
}

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

@CONFERENCE{RieVDI98,
  AUTHOR = {M. Riedmiller and R. Schoknecht},
  ADDRESS = {Berlin},
  BOOKTITLE = {Proceedings of VDI/GMA -Aussprachetag},
  TITLE = {Self-learning controllers in automotive applications (in German)},
  YEAR = {1998},
  self = {p}
}

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. M{ü}nchen, Deutschland. Bibtex

@InProceedings{RieSpott98,
  author = {Spott, M. and Riedmiller, M.},
  title = {Improving a priori control knowledge by reinforcement learning},
  booktitle = {Proceedings in Artificial Intelligence: Fuzzy-Neuro-Systems '98},
  publisher = {infix Verlag}, 
  pages = {146--153}, 
  year = 1998,
  address = {M{ü}nchen, Deutschland},
  self = {p}
}

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

@CONFERENCE{RieICNN98,
  AUTHOR = {M. Riedmiller},
  ADDRESS = {Anchorage, Alaska},
  BOOKTITLE = {Proc. of the International Joint Conference on Neural Networks, IJCNN '98},
  TITLE = {Reinforcement learning without an explicit terminal state},
  YEAR = {1998},
  self = {p}
}

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. Bibtex

@CONFERENCE{RieICNN97,
  AUTHOR = {M. Riedmiller and M. Wigbers},
  ADDRESS = {Huston, Texas},
  BOOKTITLE = {IEEE International Conference on Neural Networks ICNN;97},
  TITLE = {A New Method for the Analysis of Neural Reference Model Control},
  YEAR = {1997},
  self = {p}
}

G. Goos, M. Spott, J. Weisbrod, M. Riedmiller (1997) Interpretation und {A}daption unscharfer {R}elationen innerhalb einer hybriden selbstlernenden {S}teuerungsarchitektur. In Proceedings in Artificial Intelligence: Fuzzy-Neuro-Systeme '97. pp. 332–339. infix Verlag. Soest, Deutschland. Bibtex

@InProceedings{RieSpott97,
  author = {Goos, G. and Spott, M. and Weisbrod, J. and Riedmiller, M.},
  title = {Interpretation und {A}daption unscharfer {R}elationen innerhalb einer hybriden selbstlernenden {S}teuerungsarchitektur},
  booktitle = {Proceedings in Artificial Intelligence: Fuzzy-Neuro-Systeme '97},
  publisher = {infix Verlag}, 
  pages = {332--339},
  year = 1997,
  address = {Soest, Deutschland},
  self = {p}
}

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

@CONFERENCE{RieESANN97,
  AUTHOR = {M. Riedmiller},
  ADDRESS = {Bruges},
  BOOKTITLE = {European Symposium on Artificial Neural Networks, ESANN'97},
  TITLE = {Generating continuous control signals for reinforcement controllers using dynamic output elements},
  YEAR = {1997},
  self = {p}
}

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. Bibtex

@CONFERENCE{RieAerospace97,
  AUTHOR = {M. Riedmiller and M. Spott and J. Weisbrod},
  ADDRESS = {Aspen, USA},
  BOOKTITLE = {IEEE 1997 International Aerospace Conference},
  PAGES = {421--434},
  TITLE = {First Results on the Application of the Fynesse Control Architecture},
  YEAR = {1997},
  self = {p}
}

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

@CONFERENCE{RieDOLLAR96,
  AUTHOR = {M. Riedmiller and S. Gutjahr and J. Klingemann},
  ADDRESS = {Singapore},
  BOOKTITLE = {Joint International Conference on Expert Systems (PACES/SPICES '97)},
  TITLE = {Predicting exchange rates using neural networks},
  YEAR = {1997},
  self = {p}
}

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. Bibtex

@INPROCEEDINGS{RieOBS96,
  AUTHOR = {A. Stahlberger and M. Riedmiller},
  BOOKTITLE = {Advances in Neural Information Processing Systems 9},
  EDITOR = {M. Jordan},
  PUBLISHER = {MIT Press},
  TITLE = {Fast Network Pruning and Feature Extraction using the Unit-OBS Algorithm},
  YEAR = {1997},
  self = {p}
}

1996

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

@CONFERENCE{RieICNN96,
  AUTHOR = {M. Riedmiller},
  ADDRESS = {Washington},
  BOOKTITLE = {IEEE Intenational Conference on Neural Networks (ICNN '96)},
  TITLE = {Application of sequential reinforcement learning to control dynamic systems},
  YEAR = {1996},
  self = {p}
}

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

@INPROCEEDINGS{RieEMCSR96,
  AUTHOR = {M. Riedmiller},
  ADDRESS = {Vienna},
  BOOKTITLE = {Proceedings of the 13th. European Meeting on Cybernetics and Systems Research - 1996 (EMCSR '96)},
  EDITOR = {Robert Trappl},
  TITLE = {Learning to Control Dynamic Systems},
  YEAR = {1996},
  self = {p}
}

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

@BOOK{RieDiss,
  AUTHOR = {M. Riedmiller},
  NOTE = {Dissertation Universität Karlsruhe},
  PUBLISHER = {VDI-Verlag},
  SCHOOL = {Universität Karlsruhe},
  TITLE = {Selbständig lernende neuronale Steuerungen},
  YEAR = {1996},
  self = {o}
}

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. Bibtex

@INPROCEEDINGS{RieAI95,
  AUTHOR = {M. Riedmiller and B. Janusz},
  ADDRESS = {Singapore},
  BOOKTITLE = {Proceedings of the 8th. Australian Conference on Artificial Intelligence (AI '95)},
  EDITOR = {Xin Yao},
  PUBLISHER = {World Scientific Publishing},
  TITLE = {Using Neural Reinforcement Controllers in Robotics},
  YEAR = {1995},
  self = {p}
}

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

@INPROCEEDINGS{RieICNN95,
  AUTHOR = {M. Riedmiller and B. Janusz},
  ADDRESS = {Perth, Australia},
  BOOKTITLE = {Proceedings of the IEEE ICNN '95},
  TITLE = {Self learning control of a mobile robot},
  YEAR = {1995},
  self = {p}
}

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. Bibtex

@INPROCEEDINGS{RieICANNGA95,
  AUTHOR = {D. Koll and M. Riedmiller and H. Braun},
  ADDRESS = {Ales, France},
  BOOKTITLE = {Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms ICANNGA95},
  PUBLISHER = {Springer (Vienna)},
  TITLE = {Massively Parallel Training of Multi Layer Perceptrons with Irregular Topologies},
  YEAR = {1995},
  self = {p}
}

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. Bibtex

@INPROCEEDINGS{RieSMC94,
  AUTHOR = {M. Riedmiller},
  ADDRESS = {San Antonio, Texas},
  BOOKTITLE = {Proceedings of the IEEE International Conference on Systems, Man and Cybernetics},
  MONTH = oct,
  TITLE = {Aspects of Learning Neural Control},
  YEAR = {1994},
  self = {p}
}

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. Bibtex

@ARTICLE{RieCSI94,
  AUTHOR = {M. Riedmiller},
  JOURNAL = {Int. Journal of Computer Standards and Interfaces},
  NOTE = {Special Issue on Neural Networks},
  PAGES = {265-278},
  TITLE = {Advanced Supervised Learning in Multi-layer Perceptrons - From Backpropagation to Adaptive Learning Algorithms},
  VOLUME = {16},
  YEAR = {1994},
  self = {j}
}

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. Bibtex

@INPROCEEDINGS{RieSMC93,
  AUTHOR = {M. Riedmiller},
  ADDRESS = {Le Touquet},
  BOOKTITLE = {Proceedings of the IEEE International Conference on Systems, Man and Cybernetics},
  MONTH = oct,
  TITLE = {Controlling an Inverted Pendulum by Neural Plant Identification},
  YEAR = {1993},
  self = {p}
}

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

@INPROCEEDINGS{RieSNNS93,
  AUTHOR = {M. Riedmiller},
  ADDRESS = {Stuttgart},
  BOOKTITLE = {SNNS 1993 Workshop-Proceedings},
  EDITOR = {A. Zell},
  MONTH = sep,
  PAGES = {107 - 116},
  TITLE = {{Untersuchungen zu Konvergenz und Generalisierungsverhalten überwachter Lernverfahren mit dem SNNS}},
  YEAR = {1993},
  self = {p}
}

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. Bibtex

@INPROCEEDINGS{RieICNN93,
  AUTHOR = {M. Riedmiller and H. Braun},
  ADDRESS = {San Francisco},
  BOOKTITLE = {Proceedings of the IEEE International Conference on Neural Networks (ICNN)},
  EDITOR = {H. Ruspini},
  PAGES = {586 - 591},
  TITLE = {A Direct Adaptive Method for Faster Backpropagation Learning: The {RPROP} Algorithm},
  YEAR = {1993},
  self = {p}
}

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

@INPROCEEDINGS{RieACNN93,
  AUTHOR = {M. Riedmiller and H. Braun},
  ADDRESS = {Melbourne},
  BOOKTITLE = {Fourth Australian Conference on Neural Networks},
  EDITOR = {Marwan Jabri},
  PAGES = {169 - 172},
  TITLE = {{RPROP}: A Fast and Robust Backpropagation Learning Strategy},
  YEAR = {1993},
  self = {p}
}

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. Bibtex

@INPROCEEDINGS{RieISCIS92,
  AUTHOR = {M. Riedmiller and H. Braun},
  ADDRESS = {Antalya, Turkey},
  BOOKTITLE = {International Symposium on Computer and Information Science VII},
  EDITOR = {E. Gelenbe},
  PAGES = {279 - 286},
  TITLE = {{RPROP}: A Fast Adaptive Learning Algorithm},
  YEAR = {1992},
  self = {p}
}