Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Martin A. Riedmiller
@article{DBLP:journals/corr/abs-2402-05546,
author = {Jost Tobias Springenberg and
Abbas Abdolmaleki and
Jingwei Zhang and
Oliver Groth and
Michael Bloesch and
Thomas Lampe and
Philemon Brakel and
Sarah Bechtle and
Steven Kapturowski and
Roland Hafner and
Nicolas Heess and
Martin A. Riedmiller},
title = {Offline Actor-Critic Reinforcement Learning Scales to Large Models},
journal = {CoRR},
volume = {abs/2402.05546},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.05546},
doi = {10.48550/ARXIV.2402.05546},
eprinttype = {arXiv},
eprint = {2402.05546},
timestamp = {Wed, 14 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-05546.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-06102,
author = {Mohak Bhardwaj and
Thomas Lampe and
Michael Neunert and
Francesco Romano and
Abbas Abdolmaleki and
Arunkumar Byravan and
Markus Wulfmeier and
Martin A. Riedmiller and
Jonas Buchli},
title = {Real-World Fluid Directed Rigid Body Control via Deep Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2402.06102},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.06102},
doi = {10.48550/ARXIV.2402.06102},
eprinttype = {arXiv},
eprint = {2402.06102},
timestamp = {Fri, 16 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-06102.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nature/MankowitzMZGSPL23,
author = {Daniel J. Mankowitz and
Andrea Michi and
Anton Zhernov and
Marco Gelmi and
Marco Selvi and
Cosmin Paduraru and
Edouard Leurent and
Shariq Iqbal and
Jean{-}Baptiste Lespiau and
Alex Ahern and
Thomas K{\"{o}}ppe and
Kevin Millikin and
Stephen Gaffney and
Sophie Elster and
Jackson Broshear and
Chris Gamble and
Kieran Milan and
Robert Tung and
Minjae Hwang and
A. Taylan Cemgil and
Mohammadamin Barekatain and
Yujia Li and
Amol Mandhane and
Thomas Hubert and
Julian Schrittwieser and
Demis Hassabis and
Pushmeet Kohli and
Martin A. Riedmiller and
Oriol Vinyals and
David Silver},
title = {Faster sorting algorithms discovered using deep reinforcement learning},
journal = {Nat.},
volume = {618},
number = {7964},
pages = {257--263},
year = {2023},
url = {https://doi.org/10.1038/s41586-023-06004-9},
doi = {10.1038/S41586-023-06004-9},
timestamp = {Wed, 24 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/nature/MankowitzMZGSPL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/SeydeWSGRRW23,
author = {Tim Seyde and
Peter Werner and
Wilko Schwarting and
Igor Gilitschenski and
Martin A. Riedmiller and
Daniela Rus and
Markus Wulfmeier},
title = {Solving Continuous Control via Q-learning},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=U5XOGxAgccS},
timestamp = {Fri, 30 Jun 2023 14:38:38 +0200},
biburl = {https://dblp.org/rec/conf/iclr/SeydeWSGRRW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-12617,
author = {Jingwei Zhang and
Jost Tobias Springenberg and
Arunkumar Byravan and
Leonard Hasenclever and
Abbas Abdolmaleki and
Dushyant Rao and
Nicolas Heess and
Martin A. Riedmiller},
title = {Leveraging Jumpy Models for Planning and Fast Learning in Robotic
Domains},
journal = {CoRR},
volume = {abs/2302.12617},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.12617},
doi = {10.48550/ARXIV.2302.12617},
eprinttype = {arXiv},
eprint = {2302.12617},
timestamp = {Tue, 28 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-12617.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-10912,
author = {Ingmar Schubert and
Jingwei Zhang and
Jake Bruce and
Sarah Bechtle and
Emilio Parisotto and
Martin A. Riedmiller and
Jost Tobias Springenberg and
Arunkumar Byravan and
Leonard Hasenclever and
Nicolas Heess},
title = {A Generalist Dynamics Model for Control},
journal = {CoRR},
volume = {abs/2305.10912},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.10912},
doi = {10.48550/ARXIV.2305.10912},
eprinttype = {arXiv},
eprint = {2305.10912},
timestamp = {Thu, 25 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-10912.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-11706,
author = {Konstantinos Bousmalis and
Giulia Vezzani and
Dushyant Rao and
Coline Devin and
Alex X. Lee and
Maria Bauz{\'{a}} and
Todor Davchev and
Yuxiang Zhou and
Agrim Gupta and
Akhil Raju and
Antoine Laurens and
Claudio Fantacci and
Valentin Dalibard and
Martina Zambelli and
Murilo F. Martins and
Rugile Pevceviciute and
Michiel Blokzijl and
Misha Denil and
Nathan Batchelor and
Thomas Lampe and
Emilio Parisotto and
Konrad Zolna and
Scott E. Reed and
Sergio G{\'{o}}mez Colmenarejo and
Jon Scholz and
Abbas Abdolmaleki and
Oliver Groth and
Jean{-}Baptiste Regli and
Oleg Sushkov and
Thomas Roth{\"{o}}rl and
Jose Enrique Chen and
Yusuf Aytar and
Dave Barker and
Joy Ortiz and
Martin A. Riedmiller and
Jost Tobias Springenberg and
Raia Hadsell and
Francesco Nori and
Nicolas Heess},
title = {RoboCat: {A} Self-Improving Foundation Agent for Robotic Manipulation},
journal = {CoRR},
volume = {abs/2306.11706},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.11706},
doi = {10.48550/ARXIV.2306.11706},
eprinttype = {arXiv},
eprint = {2306.11706},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-11706.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-09668,
author = {Norman Di Palo and
Arunkumar Byravan and
Leonard Hasenclever and
Markus Wulfmeier and
Nicolas Heess and
Martin A. Riedmiller},
title = {Towards {A} Unified Agent with Foundation Models},
journal = {CoRR},
volume = {abs/2307.09668},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.09668},
doi = {10.48550/ARXIV.2307.09668},
eprinttype = {arXiv},
eprint = {2307.09668},
timestamp = {Tue, 25 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-09668.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-11546,
author = {Brendan D. Tracey and
Andrea Michi and
Yuri Chervonyi and
Ian Davies and
Cosmin Paduraru and
Nevena Lazic and
Federico Felici and
Timo Ewalds and
Craig Donner and
Cristian Galperti and
Jonas Buchli and
Michael Neunert and
Andrea Huber and
Jonathan Evens and
Paula Kurylowicz and
Daniel J. Mankowitz and
Martin A. Riedmiller and
The TCV Team},
title = {Towards practical reinforcement learning for tokamak magnetic control},
journal = {CoRR},
volume = {abs/2307.11546},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.11546},
doi = {10.48550/ARXIV.2307.11546},
eprinttype = {arXiv},
eprint = {2307.11546},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-11546.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-07741,
author = {Nico G{\"{u}}rtler and
Felix Widmaier and
Cansu Sancaktar and
Sebastian Blaes and
Pavel Kolev and
Stefan Bauer and
Manuel W{\"{u}}thrich and
Markus Wulfmeier and
Martin A. Riedmiller and
Arthur Allshire and
Qiang Wang and
Robert McCarthy and
Hangyeol Kim and
Jongchan Baek and
Wookyong Kwon and
Shanliang Qian and
Yasunori Toshimitsu and
Mike Yan Michelis and
Amirhossein Kazemipour and
Arman Raayatsanati and
Hehui Zheng and
Barnabas Gavin Cangan and
Bernhard Sch{\"{o}}lkopf and
Georg Martius},
title = {Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline
Data in the Real World},
journal = {CoRR},
volume = {abs/2308.07741},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.07741},
doi = {10.48550/ARXIV.2308.07741},
eprinttype = {arXiv},
eprint = {2308.07741},
timestamp = {Fri, 01 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-07741.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-15470,
author = {Shruti Mishra and
Ankit Anand and
Jordan Hoffmann and
Nicolas Heess and
Martin A. Riedmiller and
Abbas Abdolmaleki and
Doina Precup},
title = {Policy composition in reinforcement learning via multi-objective policy
optimization},
journal = {CoRR},
volume = {abs/2308.15470},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.15470},
doi = {10.48550/ARXIV.2308.15470},
eprinttype = {arXiv},
eprint = {2308.15470},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-15470.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-07578,
author = {Cristina Pinneri and
Sarah Bechtle and
Markus Wulfmeier and
Arunkumar Byravan and
Jingwei Zhang and
William F. Whitney and
Martin A. Riedmiller},
title = {Equivariant Data Augmentation for Generalization in Offline Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2309.07578},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.07578},
doi = {10.48550/ARXIV.2309.07578},
eprinttype = {arXiv},
eprint = {2309.07578},
timestamp = {Tue, 19 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-07578.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-15951,
author = {Dhruva Tirumala and
Thomas Lampe and
Jose Enrique Chen and
Tuomas Haarnoja and
Sandy H. Huang and
Guy Lever and
Ben Moran and
Tim Hertweck and
Leonard Hasenclever and
Martin A. Riedmiller and
Nicolas Heess and
Markus Wulfmeier},
title = {Replay across Experiments: {A} Natural Extension of Off-Policy {RL}},
journal = {CoRR},
volume = {abs/2311.15951},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.15951},
doi = {10.48550/ARXIV.2311.15951},
eprinttype = {arXiv},
eprint = {2311.15951},
timestamp = {Fri, 01 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-15951.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-09120,
author = {Martin A. Riedmiller and
Tim Hertweck and
Roland Hafner},
title = {Less is more - the Dispatcher/ Executor principle for multi-task Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2312.09120},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.09120},
doi = {10.48550/ARXIV.2312.09120},
eprinttype = {arXiv},
eprint = {2312.09120},
timestamp = {Tue, 09 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-09120.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-11374,
author = {Thomas Lampe and
Abbas Abdolmaleki and
Sarah Bechtle and
Sandy H. Huang and
Jost Tobias Springenberg and
Michael Bloesch and
Oliver Groth and
Roland Hafner and
Tim Hertweck and
Michael Neunert and
Markus Wulfmeier and
Jingwei Zhang and
Francesco Nori and
Nicolas Heess and
Martin A. Riedmiller},
title = {Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement
Learning on Real Robots},
journal = {CoRR},
volume = {abs/2312.11374},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.11374},
doi = {10.48550/ARXIV.2312.11374},
eprinttype = {arXiv},
eprint = {2312.11374},
timestamp = {Tue, 16 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-11374.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nature/DegraveFBNTCEHA22,
author = {Jonas Degrave and
Federico Felici and
Jonas Buchli and
Michael Neunert and
Brendan D. Tracey and
Francesco Carpanese and
Timo Ewalds and
Roland Hafner and
Abbas Abdolmaleki and
Diego de Las Casas and
Craig Donner and
Leslie Fritz and
Cristian Galperti and
Andrea Huber and
James Keeling and
Maria Tsimpoukelli and
Jackie Kay and
Antoine Merle and
Jean{-}Marc Moret and
Seb Noury and
Federico Pesamosca and
David Pfau and
Olivier Sauter and
Cristian Sommariva and
Stefano Coda and
Basil Duval and
Ambrogio Fasoli and
Pushmeet Kohli and
Koray Kavukcuoglu and
Demis Hassabis and
Martin A. Riedmiller},
title = {Magnetic control of tokamak plasmas through deep reinforcement learning},
journal = {Nat.},
volume = {602},
number = {7897},
pages = {414--419},
year = {2022},
url = {https://doi.org/10.1038/s41586-021-04301-9},
doi = {10.1038/S41586-021-04301-9},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nature/DegraveFBNTCEHA22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/collas/SalterWTHRHR22,
author = {Sasha Salter and
Markus Wulfmeier and
Dhruva Tirumala and
Nicolas Heess and
Martin A. Riedmiller and
Raia Hadsell and
Dushyant Rao},
editor = {Sarath Chandar and
Razvan Pascanu and
Doina Precup},
title = {{MO2:} Model-Based Offline Options},
booktitle = {Conference on Lifelong Learning Agents, CoLLAs 2022, 22-24 August
2022, McGill University, Montr{\'{e}}al, Qu{\'{e}}bec, Canada},
series = {Proceedings of Machine Learning Research},
volume = {199},
pages = {902--919},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v199/salter22a.html},
timestamp = {Fri, 17 Feb 2023 16:29:10 +0100},
biburl = {https://dblp.org/rec/conf/collas/SalterWTHRHR22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/ByravanHTMITSAH22,
author = {Arunkumar Byravan and
Leonard Hasenclever and
Piotr Trochim and
Mehdi Mirza and
Alessandro Davide Ialongo and
Yuval Tassa and
Jost Tobias Springenberg and
Abbas Abdolmaleki and
Nicolas Heess and
Josh Merel and
Martin A. Riedmiller},
title = {Evaluating Model-Based Planning and Planner Amortization for Continuous
Control},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=SS8F6tFX3-},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/ByravanHTMITSAH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-11861,
author = {Nathan Lambert and
Markus Wulfmeier and
William F. Whitney and
Arunkumar Byravan and
Michael Bloesch and
Vibhavari Dasagi and
Tim Hertweck and
Martin A. Riedmiller},
title = {The Challenges of Exploration for Offline Reinforcement Learning},
journal = {CoRR},
volume = {abs/2201.11861},
year = {2022},
url = {https://arxiv.org/abs/2201.11861},
eprinttype = {arXiv},
eprint = {2201.11861},
timestamp = {Wed, 02 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-11861.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-10256,
author = {Bobak Shahriari and
Abbas Abdolmaleki and
Arunkumar Byravan and
Abe Friesen and
Siqi Liu and
Jost Tobias Springenberg and
Nicolas Heess and
Matt Hoffman and
Martin A. Riedmiller},
title = {Revisiting Gaussian mixture critics in off-policy reinforcement learning:
a sample-based approach},
journal = {CoRR},
volume = {abs/2204.10256},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.10256},
doi = {10.48550/ARXIV.2204.10256},
eprinttype = {arXiv},
eprint = {2204.10256},
timestamp = {Thu, 11 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-10256.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-01947,
author = {Sasha Salter and
Markus Wulfmeier and
Dhruva Tirumala and
Nicolas Heess and
Martin A. Riedmiller and
Raia Hadsell and
Dushyant Rao},
title = {{MO2:} Model-Based Offline Options},
journal = {CoRR},
volume = {abs/2209.01947},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.01947},
doi = {10.48550/ARXIV.2209.01947},
eprinttype = {arXiv},
eprint = {2209.01947},
timestamp = {Mon, 26 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-01947.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-12566,
author = {Tim Seyde and
Peter Werner and
Wilko Schwarting and
Igor Gilitschenski and
Martin A. Riedmiller and
Daniela Rus and
Markus Wulfmeier},
title = {Solving Continuous Control via Q-learning},
journal = {CoRR},
volume = {abs/2210.12566},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.12566},
doi = {10.48550/ARXIV.2210.12566},
eprinttype = {arXiv},
eprint = {2210.12566},
timestamp = {Fri, 28 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-12566.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-13743,
author = {Giulia Vezzani and
Dhruva Tirumala and
Markus Wulfmeier and
Dushyant Rao and
Abbas Abdolmaleki and
Ben Moran and
Tuomas Haarnoja and
Jan Humplik and
Roland Hafner and
Michael Neunert and
Claudio Fantacci and
Tim Hertweck and
Thomas Lampe and
Fereshteh Sadeghi and
Nicolas Heess and
Martin A. Riedmiller},
title = {SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended
Exploration},
journal = {CoRR},
volume = {abs/2211.13743},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.13743},
doi = {10.48550/ARXIV.2211.13743},
eprinttype = {arXiv},
eprint = {2211.13743},
timestamp = {Tue, 29 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-13743.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/HuangAVBMNBTHRH21,
author = {Sandy H. Huang and
Abbas Abdolmaleki and
Giulia Vezzani and
Philemon Brakel and
Daniel J. Mankowitz and
Michael Neunert and
Steven Bohez and
Yuval Tassa and
Nicolas Heess and
Martin A. Riedmiller and
Raia Hadsell},
editor = {Aleksandra Faust and
David Hsu and
Gerhard Neumann},
title = {A Constrained Multi-Objective Reinforcement Learning Framework},
booktitle = {Conference on Robot Learning, 8-11 November 2021, London, {UK}},
series = {Proceedings of Machine Learning Research},
volume = {164},
pages = {883--893},
publisher = {{PMLR}},
year = {2021},
url = {https://proceedings.mlr.press/v164/huang22a.html},
timestamp = {Wed, 19 Jan 2022 17:10:33 +0100},
biburl = {https://dblp.org/rec/conf/corl/HuangAVBMNBTHRH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/LeeDZLBSBAGKFCR21,
author = {Alex X. Lee and
Coline Manon Devin and
Yuxiang Zhou and
Thomas Lampe and
Konstantinos Bousmalis and
Jost Tobias Springenberg and
Arunkumar Byravan and
Abbas Abdolmaleki and
Nimrod Gileadi and
David Khosid and
Claudio Fantacci and
Jose Enrique Chen and
Akhil Raju and
Rae Jeong and
Michael Neunert and
Antoine Laurens and
Stefano Saliceti and
Federico Casarini and
Martin A. Riedmiller and
Raia Hadsell and
Francesco Nori},
editor = {Aleksandra Faust and
David Hsu and
Gerhard Neumann},
title = {Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes},
booktitle = {Conference on Robot Learning, 8-11 November 2021, London, {UK}},
series = {Proceedings of Machine Learning Research},
volume = {164},
pages = {1089--1131},
publisher = {{PMLR}},
year = {2021},
url = {https://proceedings.mlr.press/v164/lee22b.html},
timestamp = {Wed, 19 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/corl/LeeDZLBSBAGKFCR21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/BloeschHPHHBSTC21,
author = {Michael Bloesch and
Jan Humplik and
Viorica Patraucean and
Roland Hafner and
Tuomas Haarnoja and
Arunkumar Byravan and
Noah Yamamoto Siegel and
Saran Tunyasuvunakool and
Federico Casarini and
Nathan Batchelor and
Francesco Romano and
Stefano Saliceti and
Martin A. Riedmiller and
S. M. Ali Eslami and
Nicolas Heess},
editor = {Aleksandra Faust and
David Hsu and
Gerhard Neumann},
title = {Towards Real Robot Learning in the Wild: {A} Case Study in Bipedal
Locomotion},
booktitle = {Conference on Robot Learning, 8-11 November 2021, London, {UK}},
series = {Proceedings of Machine Learning Research},
volume = {164},
pages = {1502--1511},
publisher = {{PMLR}},
year = {2021},
url = {https://proceedings.mlr.press/v164/bloesch22a.html},
timestamp = {Wed, 19 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/corl/BloeschHPHHBSTC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/RiedmillerSHH21,
author = {Martin A. Riedmiller and
Jost Tobias Springenberg and
Roland Hafner and
Nicolas Heess},
editor = {Aleksandra Faust and
David Hsu and
Gerhard Neumann},
title = {Collect {\&} Infer - a fresh look at data-efficient Reinforcement
Learning},
booktitle = {Conference on Robot Learning, 8-11 November 2021, London, {UK}},
series = {Proceedings of Machine Learning Research},
volume = {164},
pages = {1736--1744},
publisher = {{PMLR}},
year = {2021},
url = {https://proceedings.mlr.press/v164/riedmiller22a.html},
timestamp = {Wed, 19 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/corl/RiedmillerSHH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WulfmeierRHLAHN21,
author = {Markus Wulfmeier and
Dushyant Rao and
Roland Hafner and
Thomas Lampe and
Abbas Abdolmaleki and
Tim Hertweck and
Michael Neunert and
Dhruva Tirumala and
Noah Y. Siegel and
Nicolas Heess and
Martin A. Riedmiller},
editor = {Marina Meila and
Tong Zhang},
title = {Data-efficient Hindsight Off-policy Option Learning},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {11340--11350},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/wulfmeier21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WulfmeierRHLAHN21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/WulfmeierBHHGKR21,
author = {Markus Wulfmeier and
Arunkumar Byravan and
Tim Hertweck and
Irina Higgins and
Ankush Gupta and
Tejas Kulkarni and
Malcolm Reynolds and
Denis Teplyashin and
Roland Hafner and
Thomas Lampe and
Martin A. Riedmiller},
title = {Representation Matters: Improving Perception and Exploration for Robotics},
booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA}
2021, Xi'an, China, May 30 - June 5, 2021},
pages = {6512--6519},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICRA48506.2021.9560733},
doi = {10.1109/ICRA48506.2021.9560733},
timestamp = {Fri, 22 Oct 2021 19:54:31 +0200},
biburl = {https://dblp.org/rec/conf/icra/WulfmeierBHHGKR21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GurtlerWSBKBWWRAWMKBKQTMKRZCSM21,
author = {Nico G{\"{u}}rtler and
Felix Widmaier and
Cansu Sancaktar and
Sebastian Blaes and
Pavel Kolev and
Stefan Bauer and
Manuel W{\"{u}}thrich and
Markus Wulfmeier and
Martin A. Riedmiller and
Arthur Allshire and
Qiang Wang and
Robert McCarthy and
Hangyeol Kim and
Jongchan Baek and
Wookyong Kwon and
Shanliang Qian and
Yasunori Toshimitsu and
Mike Yan Michelis and
Amirhossein Kazemipour and
Arman Raayatsanati and
Hehui Zheng and
Barnabas Gavin Cangan and
Bernhard Sch{\"{o}}lkopf and
Georg Martius},
editor = {Marco Ciccone and
Gustavo Stolovitzky and
Jacob Albrecht},
title = {Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline
Data in the Real World},
booktitle = {NeurIPS 2022 Competition Track, November 28 - December 9, 2022, Online},
series = {Proceedings of Machine Learning Research},
volume = {220},
pages = {133--150},
publisher = {{PMLR}},
year = {2021},
url = {https://proceedings.mlr.press/v220/gurtler22a.html},
timestamp = {Mon, 04 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/GurtlerWSBKBWWRAWMKBKQTMKRZCSM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SeydeGSSRWR21,
author = {Tim Seyde and
Igor Gilitschenski and
Wilko Schwarting and
Bartolomeo Stellato and
Martin A. Riedmiller and
Markus Wulfmeier and
Daniela Rus},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Is Bang-Bang Control All You Need? Solving Continuous Control with
Bernoulli Policies},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {27209--27221},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/e46be61f0050f9cc3a98d5d2192cb0eb-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/SeydeGSSRWR21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-09458,
author = {William F. Whitney and
Michael Bloesch and
Jost Tobias Springenberg and
Abbas Abdolmaleki and
Martin A. Riedmiller},
title = {Rethinking Exploration for Sample-Efficient Policy Learning},
journal = {CoRR},
volume = {abs/2101.09458},
year = {2021},
url = {https://arxiv.org/abs/2101.09458},
eprinttype = {arXiv},
eprint = {2101.09458},
timestamp = {Sat, 30 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-09458.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-08199,
author = {Abbas Abdolmaleki and
Sandy H. Huang and
Giulia Vezzani and
Bobak Shahriari and
Jost Tobias Springenberg and
Shruti Mishra and
Dhruva TB and
Arunkumar Byravan and
Konstantinos Bousmalis and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Raia Hadsell and
Nicolas Heess and
Martin A. Riedmiller},
title = {On Multi-objective Policy Optimization as a Tool for Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2106.08199},
year = {2021},
url = {https://arxiv.org/abs/2106.08199},
eprinttype = {arXiv},
eprint = {2106.08199},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-08199.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-10273,
author = {Martin A. Riedmiller and
Jost Tobias Springenberg and
Roland Hafner and
Nicolas Heess},
title = {Collect {\&} Infer - a fresh look at data-efficient Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2108.10273},
year = {2021},
url = {https://arxiv.org/abs/2108.10273},
eprinttype = {arXiv},
eprint = {2108.10273},
timestamp = {Fri, 27 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-10273.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-08603,
author = {Oliver Groth and
Markus Wulfmeier and
Giulia Vezzani and
Vibhavari Dasagi and
Tim Hertweck and
Roland Hafner and
Nicolas Heess and
Martin A. Riedmiller},
title = {Is Curiosity All You Need? On the Utility of Emergent Behaviours from
Curious Exploration},
journal = {CoRR},
volume = {abs/2109.08603},
year = {2021},
url = {https://arxiv.org/abs/2109.08603},
eprinttype = {arXiv},
eprint = {2109.08603},
timestamp = {Wed, 22 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-08603.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-03363,
author = {Arunkumar Byravan and
Leonard Hasenclever and
Piotr Trochim and
Mehdi Mirza and
Alessandro Davide Ialongo and
Yuval Tassa and
Jost Tobias Springenberg and
Abbas Abdolmaleki and
Nicolas Heess and
Josh Merel and
Martin A. Riedmiller},
title = {Evaluating model-based planning and planner amortization for continuous
control},
journal = {CoRR},
volume = {abs/2110.03363},
year = {2021},
url = {https://arxiv.org/abs/2110.03363},
eprinttype = {arXiv},
eprint = {2110.03363},
timestamp = {Thu, 21 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-03363.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-06192,
author = {Alex X. Lee and
Coline Devin and
Yuxiang Zhou and
Thomas Lampe and
Konstantinos Bousmalis and
Jost Tobias Springenberg and
Arunkumar Byravan and
Abbas Abdolmaleki and
Nimrod Gileadi and
David Khosid and
Claudio Fantacci and
Jose Enrique Chen and
Akhil Raju and
Rae Jeong and
Michael Neunert and
Antoine Laurens and
Stefano Saliceti and
Federico Casarini and
Martin A. Riedmiller and
Raia Hadsell and
Francesco Nori},
title = {Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes},
journal = {CoRR},
volume = {abs/2110.06192},
year = {2021},
url = {https://arxiv.org/abs/2110.06192},
eprinttype = {arXiv},
eprint = {2110.06192},
timestamp = {Fri, 22 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-06192.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-02552,
author = {Tim Seyde and
Igor Gilitschenski and
Wilko Schwarting and
Bartolomeo Stellato and
Martin A. Riedmiller and
Markus Wulfmeier and
Daniela Rus},
title = {Is Bang-Bang Control All You Need? Solving Continuous Control with
Bernoulli Policies},
journal = {CoRR},
volume = {abs/2111.02552},
year = {2021},
url = {https://arxiv.org/abs/2111.02552},
eprinttype = {arXiv},
eprint = {2111.02552},
timestamp = {Fri, 05 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-02552.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/HafnerHKBNWTHR20,
author = {Roland Hafner and
Tim Hertweck and
Philipp Kl{\"{o}}ppner and
Michael Bloesch and
Michael Neunert and
Markus Wulfmeier and
Saran Tunyasuvunakool and
Nicolas Heess and
Martin A. Riedmiller},
editor = {Jens Kober and
Fabio Ramos and
Claire J. Tomlin},
title = {Towards General and Autonomous Learning of Core Skills: {A} Case Study
in Locomotion},
booktitle = {4th Conference on Robot Learning, CoRL 2020, 16-18 November 2020,
Virtual Event / Cambridge, MA, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {155},
pages = {1084--1099},
publisher = {{PMLR}},
year = {2020},
url = {https://proceedings.mlr.press/v155/hafner21a.html},
timestamp = {Tue, 18 Oct 2022 08:35:37 +0200},
biburl = {https://dblp.org/rec/conf/corl/HafnerHKBNWTHR20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/MankowitzLJASSK20,
author = {Daniel J. Mankowitz and
Nir Levine and
Rae Jeong and
Abbas Abdolmaleki and
Jost Tobias Springenberg and
Yuanyuan Shi and
Jackie Kay and
Todd Hester and
Timothy A. Mann and
Martin A. Riedmiller},
title = {Robust Reinforcement Learning for Continuous Control with Model Misspecification},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=HJgC60EtwB},
timestamp = {Thu, 07 May 2020 17:11:47 +0200},
biburl = {https://dblp.org/rec/conf/iclr/MankowitzLJASSK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/SiegelSBANLHHR20,
author = {Noah Y. Siegel and
Jost Tobias Springenberg and
Felix Berkenkamp and
Abbas Abdolmaleki and
Michael Neunert and
Thomas Lampe and
Roland Hafner and
Nicolas Heess and
Martin A. Riedmiller},
title = {Keep Doing What Worked: Behavior Modelling Priors for Offline Reinforcement
Learning},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=rke7geHtwH},
timestamp = {Thu, 07 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/SiegelSBANLHHR20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/SongASCSRNALTHB20,
author = {H. Francis Song and
Abbas Abdolmaleki and
Jost Tobias Springenberg and
Aidan Clark and
Hubert Soyer and
Jack W. Rae and
Seb Noury and
Arun Ahuja and
Siqi Liu and
Dhruva Tirumala and
Nicolas Heess and
Dan Belov and
Martin A. Riedmiller and
Matthew M. Botvinick},
title = {{V-MPO:} On-Policy Maximum a Posteriori Policy Optimization for Discrete
and Continuous Control},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=SylOlp4FvH},
timestamp = {Thu, 11 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/SongASCSRNALTHB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AbdolmalekiHNS20,
author = {Abbas Abdolmaleki and
Sandy H. Huang and
Leonard Hasenclever and
Michael Neunert and
H. Francis Song and
Martina Zambelli and
Murilo F. Martins and
Nicolas Heess and
Raia Hadsell and
Martin A. Riedmiller},
title = {A distributional view on multi-objective policy optimization},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {11--22},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/abdolmaleki20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/AbdolmalekiHNS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/rss/WulfmeierAHSNSH20,
author = {Markus Wulfmeier and
Abbas Abdolmaleki and
Roland Hafner and
Jost Tobias Springenberg and
Michael Neunert and
Noah Y. Siegel and
Tim Hertweck and
Thomas Lampe and
Nicolas Heess and
Martin A. Riedmiller},
editor = {Marc Toussaint and
Antonio Bicchi and
Tucker Hermans},
title = {Compositional Transfer in Hierarchical Reinforcement Learning},
booktitle = {Robotics: Science and Systems XVI, Virtual Event / Corvalis, Oregon,
USA, July 12-16, 2020},
year = {2020},
url = {https://doi.org/10.15607/RSS.2020.XVI.054},
doi = {10.15607/RSS.2020.XVI.054},
timestamp = {Thu, 15 Jul 2021 18:53:52 +0200},
biburl = {https://dblp.org/rec/conf/rss/WulfmeierAHSNSH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2001-00449,
author = {Michael Neunert and
Abbas Abdolmaleki and
Markus Wulfmeier and
Thomas Lampe and
Jost Tobias Springenberg and
Roland Hafner and
Francesco Romano and
Jonas Buchli and
Nicolas Heess and
Martin A. Riedmiller},
title = {Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics},
journal = {CoRR},
volume = {abs/2001.00449},
year = {2020},
url = {http://arxiv.org/abs/2001.00449},
eprinttype = {arXiv},
eprint = {2001.00449},
timestamp = {Fri, 10 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-00449.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-08396,
author = {Noah Y. Siegel and
Jost Tobias Springenberg and
Felix Berkenkamp and
Abbas Abdolmaleki and
Michael Neunert and
Thomas Lampe and
Roland Hafner and
Nicolas Heess and
Martin A. Riedmiller},
title = {Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2002.08396},
year = {2020},
url = {https://arxiv.org/abs/2002.08396},
eprinttype = {arXiv},
eprint = {2002.08396},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-08396.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-07513,
author = {Abbas Abdolmaleki and
Sandy H. Huang and
Leonard Hasenclever and
Michael Neunert and
H. Francis Song and
Martina Zambelli and
Murilo F. Martins and
Nicolas Heess and
Raia Hadsell and
Martin A. Riedmiller},
title = {A Distributional View on Multi-Objective Policy Optimization},
journal = {CoRR},
volume = {abs/2005.07513},
year = {2020},
url = {https://arxiv.org/abs/2005.07513},
eprinttype = {arXiv},
eprint = {2005.07513},
timestamp = {Fri, 22 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-07513.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-07541,
author = {Tim Hertweck and
Martin A. Riedmiller and
Michael Bloesch and
Jost Tobias Springenberg and
Noah Y. Siegel and
Markus Wulfmeier and
Roland Hafner and
Nicolas Heess},
title = {Simple Sensor Intentions for Exploration},
journal = {CoRR},
volume = {abs/2005.07541},
year = {2020},
url = {https://arxiv.org/abs/2005.07541},
eprinttype = {arXiv},
eprint = {2005.07541},
timestamp = {Fri, 22 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-07541.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-15588,
author = {Markus Wulfmeier and
Dushyant Rao and
Roland Hafner and
Thomas Lampe and
Abbas Abdolmaleki and
Tim Hertweck and
Michael Neunert and
Dhruva Tirumala and
Noah Y. Siegel and
Nicolas Heess and
Martin A. Riedmiller},
title = {Data-efficient Hindsight Off-policy Option Learning},
journal = {CoRR},
volume = {abs/2007.15588},
year = {2020},
url = {https://arxiv.org/abs/2007.15588},
eprinttype = {arXiv},
eprint = {2007.15588},
timestamp = {Mon, 03 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-15588.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2008-12228,
author = {Roland Hafner and
Tim Hertweck and
Philipp Kl{\"{o}}ppner and
Michael Bloesch and
Michael Neunert and
Markus Wulfmeier and
Saran Tunyasuvunakool and
Nicolas Heess and
Martin A. Riedmiller},
title = {Towards General and Autonomous Learning of Core Skills: {A} Case Study
in Locomotion},
journal = {CoRR},
volume = {abs/2008.12228},
year = {2020},
url = {https://arxiv.org/abs/2008.12228},
eprinttype = {arXiv},
eprint = {2008.12228},
timestamp = {Tue, 15 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-12228.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-05545,
author = {Jost Tobias Springenberg and
Nicolas Heess and
Daniel J. Mankowitz and
Josh Merel and
Arunkumar Byravan and
Abbas Abdolmaleki and
Jackie Kay and
Jonas Degrave and
Julian Schrittwieser and
Yuval Tassa and
Jonas Buchli and
Dan Belov and
Martin A. Riedmiller},
title = {Local Search for Policy Iteration in Continuous Control},
journal = {CoRR},
volume = {abs/2010.05545},
year = {2020},
url = {https://arxiv.org/abs/2010.05545},
eprinttype = {arXiv},
eprint = {2010.05545},
timestamp = {Tue, 20 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-05545.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-10644,
author = {Daniel J. Mankowitz and
Dan A. Calian and
Rae Jeong and
Cosmin Paduraru and
Nicolas Heess and
Sumanth Dathathri and
Martin A. Riedmiller and
Timothy A. Mann},
title = {Robust Constrained Reinforcement Learning for Continuous Control with
Model Misspecification},
journal = {CoRR},
volume = {abs/2010.10644},
year = {2020},
url = {https://arxiv.org/abs/2010.10644},
eprinttype = {arXiv},
eprint = {2010.10644},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-10644.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-15492,
author = {Giulia Vezzani and
Michael Neunert and
Markus Wulfmeier and
Rae Jeong and
Thomas Lampe and
Noah Y. Siegel and
Roland Hafner and
Abbas Abdolmaleki and
Martin A. Riedmiller and
Francesco Nori},
title = {"What, not how": Solving an under-actuated insertion task
from scratch},
journal = {CoRR},
volume = {abs/2010.15492},
year = {2020},
url = {https://arxiv.org/abs/2010.15492},
eprinttype = {arXiv},
eprint = {2010.15492},
timestamp = {Tue, 03 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-15492.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-01758,
author = {Markus Wulfmeier and
Arunkumar Byravan and
Tim Hertweck and
Irina Higgins and
Ankush Gupta and
Tejas Kulkarni and
Malcolm Reynolds and
Denis Teplyashin and
Roland Hafner and
Thomas Lampe and
Martin A. Riedmiller},
title = {Representation Matters: Improving Perception and Exploration for Robotics},
journal = {CoRR},
volume = {abs/2011.01758},
year = {2020},
url = {https://arxiv.org/abs/2011.01758},
eprinttype = {arXiv},
eprint = {2011.01758},
timestamp = {Fri, 06 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-01758.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijon/WulfingKBRE19,
author = {Jan M. W{\"{u}}lfing and
Sreedhar S. Kumar and
Joschka Boedecker and
Martin A. Riedmiller and
Ulrich Egert},
title = {Adaptive long-term control of biological neural networks with Deep
Reinforcement Learning},
journal = {Neurocomputing},
volume = {342},
pages = {66--74},
year = {2019},
url = {https://doi.org/10.1016/j.neucom.2018.10.084},
doi = {10.1016/J.NEUCOM.2018.10.084},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijon/WulfingKBRE19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/ByravanSAHNLSHR19,
author = {Arunkumar Byravan and
Jost Tobias Springenberg and
Abbas Abdolmaleki and
Roland Hafner and
Michael Neunert and
Thomas Lampe and
Noah Y. Siegel and
Nicolas Heess and
Martin A. Riedmiller},
editor = {Leslie Pack Kaelbling and
Danica Kragic and
Komei Sugiura},
title = {Imagined Value Gradients: Model-Based Policy Optimization with Tranferable
Latent Dynamics Models},
booktitle = {3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan,
October 30 - November 1, 2019, Proceedings},
series = {Proceedings of Machine Learning Research},
volume = {100},
pages = {566--589},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v100/byravan20a.html},
timestamp = {Tue, 26 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/corl/ByravanSAHNLSHR19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/NeunertAWLSHRBH19,
author = {Michael Neunert and
Abbas Abdolmaleki and
Markus Wulfmeier and
Thomas Lampe and
Jost Tobias Springenberg and
Roland Hafner and
Francesco Romano and
Jonas Buchli and
Nicolas Heess and
Martin A. Riedmiller},
editor = {Leslie Pack Kaelbling and
Danica Kragic and
Komei Sugiura},
title = {Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics},
booktitle = {3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan,
October 30 - November 1, 2019, Proceedings},
series = {Proceedings of Machine Learning Research},
volume = {100},
pages = {735--751},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v100/neunert20a.html},
timestamp = {Mon, 25 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/corl/NeunertAWLSHRBH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/rss/SchwabSMNLAHHNR19,
author = {Devin Schwab and
Jost Tobias Springenberg and
Murilo Fernandes Martins and
Michael Neunert and
Thomas Lampe and
Abbas Abdolmaleki and
Tim Hertweck and
Roland Hafner and
Francesco Nori and
Martin A. Riedmiller},
editor = {Antonio Bicchi and
Hadas Kress{-}Gazit and
Seth Hutchinson},
title = {Simultaneously Learning Vision and Feature-Based Control Policies
for Real-World Ball-In-A-Cup},
booktitle = {Robotics: Science and Systems XV, University of Freiburg, Freiburg
im Breisgau, Germany, June 22-26, 2019},
year = {2019},
url = {https://doi.org/10.15607/RSS.2019.XV.027},
doi = {10.15607/RSS.2019.XV.027},
timestamp = {Thu, 01 Apr 2021 15:25:13 +0200},
biburl = {https://dblp.org/rec/conf/rss/SchwabSMNLAHHNR19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-00943,
author = {Carlos Florensa and
Jonas Degrave and
Nicolas Heess and
Jost Tobias Springenberg and
Martin A. Riedmiller},
title = {Self-supervised Learning of Image Embedding for Continuous Control},
journal = {CoRR},
volume = {abs/1901.00943},
year = {2019},
url = {http://arxiv.org/abs/1901.00943},
eprinttype = {arXiv},
eprint = {1901.00943},
timestamp = {Thu, 31 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-00943.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-04706,
author = {Devin Schwab and
Jost Tobias Springenberg and
Murilo F. Martins and
Thomas Lampe and
Michael Neunert and
Abbas Abdolmaleki and
Tim Hertweck and
Roland Hafner and
Francesco Nori and
Martin A. Riedmiller},
title = {Simultaneously Learning Vision and Feature-based Control Policies
for Real-world Ball-in-a-Cup},
journal = {CoRR},
volume = {abs/1902.04706},
year = {2019},
url = {http://arxiv.org/abs/1902.04706},
eprinttype = {arXiv},
eprint = {1902.04706},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-04706.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-07516,
author = {Daniel J. Mankowitz and
Nir Levine and
Rae Jeong and
Abbas Abdolmaleki and
Jost Tobias Springenberg and
Timothy A. Mann and
Todd Hester and
Martin A. Riedmiller},
title = {Robust Reinforcement Learning for Continuous Control with Model Misspecification},
journal = {CoRR},
volume = {abs/1906.07516},
year = {2019},
url = {http://arxiv.org/abs/1906.07516},
eprinttype = {arXiv},
eprint = {1906.07516},
timestamp = {Mon, 24 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-07516.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-11228,
author = {Markus Wulfmeier and
Abbas Abdolmaleki and
Roland Hafner and
Jost Tobias Springenberg and
Michael Neunert and
Tim Hertweck and
Thomas Lampe and
Noah Y. Siegel and
Nicolas Heess and
Martin A. Riedmiller},
title = {Regularized Hierarchical Policies for Compositional Transfer in Robotics},
journal = {CoRR},
volume = {abs/1906.11228},
year = {2019},
url = {http://arxiv.org/abs/1906.11228},
eprinttype = {arXiv},
eprint = {1906.11228},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-11228.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-12238,
author = {H. Francis Song and
Abbas Abdolmaleki and
Jost Tobias Springenberg and
Aidan Clark and
Hubert Soyer and
Jack W. Rae and
Seb Noury and
Arun Ahuja and
Siqi Liu and
Dhruva Tirumala and
Nicolas Heess and
Dan Belov and
Martin A. Riedmiller and
Matthew M. Botvinick},
title = {{V-MPO:} On-Policy Maximum a Posteriori Policy Optimization for Discrete
and Continuous Control},
journal = {CoRR},
volume = {abs/1909.12238},
year = {2019},
url = {http://arxiv.org/abs/1909.12238},
eprinttype = {arXiv},
eprint = {1909.12238},
timestamp = {Thu, 11 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-12238.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-04142,
author = {Arunkumar Byravan and
Jost Tobias Springenberg and
Abbas Abdolmaleki and
Roland Hafner and
Michael Neunert and
Thomas Lampe and
Noah Y. Siegel and
Nicolas Heess and
Martin A. Riedmiller},
title = {Imagined Value Gradients: Model-Based Policy Optimization with Transferable
Latent Dynamics Models},
journal = {CoRR},
volume = {abs/1910.04142},
year = {2019},
url = {http://arxiv.org/abs/1910.04142},
eprinttype = {arXiv},
eprint = {1910.04142},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-04142.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-01831,
author = {Jonas Degrave and
Abbas Abdolmaleki and
Jost Tobias Springenberg and
Nicolas Heess and
Martin A. Riedmiller},
title = {Quinoa: a Q-function You Infer Normalized Over Actions},
journal = {CoRR},
volume = {abs/1911.01831},
year = {2019},
url = {http://arxiv.org/abs/1911.01831},
eprinttype = {arXiv},
eprint = {1911.01831},
timestamp = {Mon, 11 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-01831.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/esann/WulfingKBRE18,
author = {Jan W{\"{u}}lfing and
Sreedhar S. Kumar and
Joschka Boedecker and
Martin A. Riedmiller and
Ulrich Egert},
title = {Controlling biological neural networks with deep reinforcement learning},
booktitle = {26th European Symposium on Artificial Neural Networks, {ESANN} 2018,
Bruges, Belgium, April 25-27, 2018},
year = {2018},
url = {https://www.esann.org/sites/default/files/proceedings/legacy/es2018-128.pdf},
timestamp = {Tue, 02 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/esann/WulfingKBRE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/AbdolmalekiSTMH18,
author = {Abbas Abdolmaleki and
Jost Tobias Springenberg and
Yuval Tassa and
R{\'{e}}mi Munos and
Nicolas Heess and
Martin A. Riedmiller},
title = {Maximum a Posteriori Policy Optimisation},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=S1ANxQW0b},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/AbdolmalekiSTMH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/HausmanS0HR18,
author = {Karol Hausman and
Jost Tobias Springenberg and
Ziyu Wang and
Nicolas Heess and
Martin A. Riedmiller},
title = {Learning an Embedding Space for Transferable Robot Skills},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=rk07ZXZRb},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/HausmanS0HR18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/RiedmillerHLNDW18,
author = {Martin A. Riedmiller and
Roland Hafner and
Thomas Lampe and
Michael Neunert and
Jonas Degrave and
Tom Van de Wiele and
Vlad Mnih and
Nicolas Heess and
Jost Tobias Springenberg},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Learning by Playing Solving Sparse Reward Tasks from Scratch},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {4341--4350},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/riedmiller18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:30 +0200},
biburl = {https://dblp.org/rec/conf/icml/RiedmillerHLNDW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Sanchez-Gonzalez18,
author = {Alvaro Sanchez{-}Gonzalez and
Nicolas Heess and
Jost Tobias Springenberg and
Josh Merel and
Martin A. Riedmiller and
Raia Hadsell and
Peter W. Battaglia},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Graph Networks as Learnable Physics Engines for Inference and Control},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {4467--4476},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/sanchez-gonzalez18a.html},
timestamp = {Wed, 24 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/Sanchez-Gonzalez18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-00690,
author = {Yuval Tassa and
Yotam Doron and
Alistair Muldal and
Tom Erez and
Yazhe Li and
Diego de Las Casas and
David Budden and
Abbas Abdolmaleki and
Josh Merel and
Andrew Lefrancq and
Timothy P. Lillicrap and
Martin A. Riedmiller},
title = {DeepMind Control Suite},
journal = {CoRR},
volume = {abs/1801.00690},
year = {2018},
url = {http://arxiv.org/abs/1801.00690},
eprinttype = {arXiv},
eprint = {1801.00690},
timestamp = {Mon, 22 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-00690.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-10567,
author = {Martin A. Riedmiller and
Roland Hafner and
Thomas Lampe and
Michael Neunert and
Jonas Degrave and
Tom Van de Wiele and
Volodymyr Mnih and
Nicolas Heess and
Jost Tobias Springenberg},
title = {Learning by Playing - Solving Sparse Reward Tasks from Scratch},
journal = {CoRR},
volume = {abs/1802.10567},
year = {2018},
url = {http://arxiv.org/abs/1802.10567},
eprinttype = {arXiv},
eprint = {1802.10567},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-10567.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-01242,
author = {Alvaro Sanchez{-}Gonzalez and
Nicolas Heess and
Jost Tobias Springenberg and
Josh Merel and
Martin A. Riedmiller and
Raia Hadsell and
Peter W. Battaglia},
title = {Graph networks as learnable physics engines for inference and control},
journal = {CoRR},
volume = {abs/1806.01242},
year = {2018},
url = {http://arxiv.org/abs/1806.01242},
eprinttype = {arXiv},
eprint = {1806.01242},
timestamp = {Wed, 24 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-01242.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-06920,
author = {Abbas Abdolmaleki and
Jost Tobias Springenberg and
Yuval Tassa and
R{\'{e}}mi Munos and
Nicolas Heess and
Martin A. Riedmiller},
title = {Maximum a Posteriori Policy Optimisation},
journal = {CoRR},
volume = {abs/1806.06920},
year = {2018},
url = {http://arxiv.org/abs/1806.06920},
eprinttype = {arXiv},
eprint = {1806.06920},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-06920.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-02256,
author = {Abbas Abdolmaleki and
Jost Tobias Springenberg and
Jonas Degrave and
Steven Bohez and
Yuval Tassa and
Dan Belov and
Nicolas Heess and
Martin A. Riedmiller},
title = {Relative Entropy Regularized Policy Iteration},
journal = {CoRR},
volume = {abs/1812.02256},
year = {2018},
url = {http://arxiv.org/abs/1812.02256},
eprinttype = {arXiv},
eprint = {1812.02256},
timestamp = {Tue, 01 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-02256.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PopovHLHBVLTER17,
author = {Ivaylo Popov and
Nicolas Heess and
Timothy P. Lillicrap and
Roland Hafner and
Gabriel Barth{-}Maron and
Matej Vecer{\'{\i}}k and
Thomas Lampe and
Yuval Tassa and
Tom Erez and
Martin A. Riedmiller},
title = {Data-efficient Deep Reinforcement Learning for Dexterous Manipulation},
journal = {CoRR},
volume = {abs/1704.03073},
year = {2017},
url = {http://arxiv.org/abs/1704.03073},
eprinttype = {arXiv},
eprint = {1704.03073},
timestamp = {Wed, 24 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PopovHLHBVLTER17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JonschkowskiHSR17,
author = {Rico Jonschkowski and
Roland Hafner and
Jonathan Scholz and
Martin A. Riedmiller},
title = {PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured
State Representations},
journal = {CoRR},
volume = {abs/1705.09805},
year = {2017},
url = {http://arxiv.org/abs/1705.09805},
eprinttype = {arXiv},
eprint = {1705.09805},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/JonschkowskiHSR17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HeessTSLMWTEWER17,
author = {Nicolas Heess and
Dhruva TB and
Srinivasan Sriram and
Jay Lemmon and
Josh Merel and
Greg Wayne and
Yuval Tassa and
Tom Erez and
Ziyu Wang and
S. M. Ali Eslami and
Martin A. Riedmiller and
David Silver},
title = {Emergence of Locomotion Behaviours in Rich Environments},
journal = {CoRR},
volume = {abs/1707.02286},
year = {2017},
url = {http://arxiv.org/abs/1707.02286},
eprinttype = {arXiv},
eprint = {1707.02286},
timestamp = {Mon, 22 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HeessTSLMWTEWER17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/VecerikHSWPPHRL17,
author = {Matej Vecer{\'{\i}}k and
Todd Hester and
Jonathan Scholz and
Fumin Wang and
Olivier Pietquin and
Bilal Piot and
Nicolas Heess and
Thomas Roth{\"{o}}rl and
Thomas Lampe and
Martin A. Riedmiller},
title = {Leveraging Demonstrations for Deep Reinforcement Learning on Robotics
Problems with Sparse Rewards},
journal = {CoRR},
volume = {abs/1707.08817},
year = {2017},
url = {http://arxiv.org/abs/1707.08817},
eprinttype = {arXiv},
eprint = {1707.08817},
timestamp = {Wed, 24 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/VecerikHSWPPHRL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/DosovitskiyFSRB16,
author = {Alexey Dosovitskiy and
Philipp Fischer and
Jost Tobias Springenberg and
Martin A. Riedmiller and
Thomas Brox},
title = {Discriminative Unsupervised Feature Learning with Exemplar Convolutional
Neural Networks},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {38},
number = {9},
pages = {1734--1747},
year = {2016},
url = {https://doi.org/10.1109/TPAMI.2015.2496141},
doi = {10.1109/TPAMI.2015.2496141},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/pami/DosovitskiyFSRB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ploscb/KumarWOBRE16,
author = {Sreedhar S. Kumar and
Jan W{\"{u}}lfing and
Samora Okujeni and
Joschka Boedecker and
Martin A. Riedmiller and
Ulrich Egert},
title = {Autonomous Optimization of Targeted Stimulation of Neuronal Networks},
journal = {PLoS Comput. Biol.},
volume = {12},
number = {8},
year = {2016},
url = {https://doi.org/10.1371/journal.pcbi.1005054},
doi = {10.1371/JOURNAL.PCBI.1005054},
timestamp = {Thu, 10 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ploscb/KumarWOBRE16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HeessWTLRS16,
author = {Nicolas Heess and
Gregory Wayne and
Yuval Tassa and
Timothy P. Lillicrap and
Martin A. Riedmiller and
David Silver},
title = {Learning and Transfer of Modulated Locomotor Controllers},
journal = {CoRR},
volume = {abs/1610.05182},
year = {2016},
url = {http://arxiv.org/abs/1610.05182},
eprinttype = {arXiv},
eprint = {1610.05182},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HeessWTLRS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ki/BohmerSBRO15,
author = {Wendelin B{\"{o}}hmer and
Jost Tobias Springenberg and
Joschka Boedecker and
Martin A. Riedmiller and
Klaus Obermayer},
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},
journal = {K{\"{u}}nstliche Intell.},
volume = {29},
number = {4},
pages = {353--362},
year = {2015},
url = {https://doi.org/10.1007/s13218-015-0356-1},
doi = {10.1007/S13218-015-0356-1},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ki/BohmerSBRO15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nature/MnihKSRVBGRFOPB15,
author = {Volodymyr Mnih and
Koray Kavukcuoglu and
David Silver and
Andrei A. Rusu and
Joel Veness and
Marc G. Bellemare and
Alex Graves and
Martin A. Riedmiller and
Andreas Fidjeland and
Georg Ostrovski and
Stig Petersen and
Charles Beattie and
Amir Sadik and
Ioannis Antonoglou and
Helen King and
Dharshan Kumaran and
Daan Wierstra and
Shane Legg and
Demis Hassabis},
title = {Human-level control through deep reinforcement learning},
journal = {Nat.},
volume = {518},
number = {7540},
pages = {529--533},
year = {2015},
url = {https://doi.org/10.1038/nature14236},
doi = {10.1038/NATURE14236},
timestamp = {Mon, 08 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nature/MnihKSRVBGRFOPB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/EitelSSRB15,
author = {Andreas Eitel and
Jost Tobias Springenberg and
Luciano Spinello and
Martin A. Riedmiller and
Wolfram Burgard},
title = {Multimodal deep learning for robust {RGB-D} object recognition},
booktitle = {2015 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, {IROS} 2015, Hamburg, Germany, September 28 - October 2,
2015},
pages = {681--687},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/IROS.2015.7353446},
doi = {10.1109/IROS.2015.7353446},
timestamp = {Sat, 05 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iros/EitelSSRB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WatterSBR15,
author = {Manuel Watter and
Jost Tobias Springenberg and
Joschka Boedecker and
Martin A. Riedmiller},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Embed to Control: {A} Locally Linear Latent Dynamics Model for Control
from Raw Images},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {2746--2754},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/a1afc58c6ca9540d057299ec3016d726-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/WatterSBR15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/corr/SpringenbergDBR14,
author = {Jost Tobias Springenberg and
Alexey Dosovitskiy and
Thomas Brox and
Martin A. Riedmiller},
editor = {Yoshua Bengio and
Yann LeCun},
title = {Striving for Simplicity: The All Convolutional Net},
booktitle = {3rd International Conference on Learning Representations, {ICLR} 2015,
San Diego, CA, USA, May 7-9, 2015, Workshop Track Proceedings},
year = {2015},
url = {http://arxiv.org/abs/1412.6806},
timestamp = {Wed, 17 Jul 2019 10:40:54 +0200},
biburl = {https://dblp.org/rec/journals/corr/SpringenbergDBR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WatterSBR15,
author = {Manuel Watter and
Jost Tobias Springenberg and
Joschka Boedecker and
Martin A. Riedmiller},
title = {Embed to Control: {A} Locally Linear Latent Dynamics Model for Control
from Raw Images},
journal = {CoRR},
volume = {abs/1506.07365},
year = {2015},
url = {http://arxiv.org/abs/1506.07365},
eprinttype = {arXiv},
eprint = {1506.07365},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WatterSBR15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/EitelSSRB15,
author = {Andreas Eitel and
Jost Tobias Springenberg and
Luciano Spinello and
Martin A. Riedmiller and
Wolfram Burgard},
title = {Multimodal Deep Learning for Robust {RGB-D} Object Recognition},
journal = {CoRR},
volume = {abs/1507.06821},
year = {2015},
url = {http://arxiv.org/abs/1507.06821},
eprinttype = {arXiv},
eprint = {1507.06821},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/EitelSSRB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adprl/BoedeckerSWR14,
author = {Joschka Boedecker and
Jost Tobias Springenberg and
Jan W{\"{u}}lfing and
Martin A. Riedmiller},
title = {Approximate real-time optimal control based on sparse Gaussian process
models},
booktitle = {2014 {IEEE} Symposium on Adaptive Dynamic Programming and Reinforcement
Learning, {ADPRL} 2014, Orlando, FL, USA, December 9-12, 2014},
pages = {1--8},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ADPRL.2014.7010608},
doi = {10.1109/ADPRL.2014.7010608},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/adprl/BoedeckerSWR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SilverLHDWR14,
author = {David Silver and
Guy Lever and
Nicolas Heess and
Thomas Degris and
Daan Wierstra and
Martin A. Riedmiller},
title = {Deterministic Policy Gradient Algorithms},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {387--395},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/silver14.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/SilverLHDWR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/LampeR14,
author = {Thomas Lampe and
Martin A. Riedmiller},
title = {Approximate model-assisted Neural Fitted Q-Iteration},
booktitle = {2014 International Joint Conference on Neural Networks, {IJCNN} 2014,
Beijing, China, July 6-11, 2014},
pages = {2698--2704},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/IJCNN.2014.6889733},
doi = {10.1109/IJCNN.2014.6889733},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/LampeR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iui/LampeFVKRB14,
author = {Thomas Lampe and
Lukas Dominique Josef Fiederer and
Martin Voelker and
Alexander Knorr and
Martin A. Riedmiller and
Tonio Ball},
editor = {Tsvi Kuflik and
Oliviero Stock and
Joyce Yue Chai and
Antonio Kr{\"{u}}ger},
title = {A brain-computer interface for high-level remote control of an autonomous,
reinforcement-learning-based robotic system for reaching and grasping},
booktitle = {19th International Conference on Intelligent User Interfaces, {IUI}
2014, Haifa, Israel, February 24-27, 2014},
pages = {83--88},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2557500.2557533},
doi = {10.1145/2557500.2557533},
timestamp = {Sat, 30 Sep 2023 09:51:13 +0200},
biburl = {https://dblp.org/rec/conf/iui/LampeFVKRB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/DosovitskiySRB14,
author = {Alexey Dosovitskiy and
Jost Tobias Springenberg and
Martin A. Riedmiller and
Thomas Brox},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {Discriminative Unsupervised Feature Learning with Convolutional Neural
Networks},
booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference
on Neural Information Processing Systems 2014, December 8-13 2014,
Montreal, Quebec, Canada},
pages = {766--774},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/07563a3fe3bbe7e3ba84431ad9d055af-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/DosovitskiySRB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/corr/SpringenbergR13,
author = {Jost Tobias Springenberg and
Martin A. Riedmiller},
editor = {Yoshua Bengio and
Yann LeCun},
title = {Improving Deep Neural Networks with Probabilistic Maxout Units},
booktitle = {2nd International Conference on Learning Representations, {ICLR} 2014,
Banff, AB, Canada, April 14-16, 2014, Workshop Track Proceedings},
year = {2014},
url = {http://arxiv.org/abs/1312.6116},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SpringenbergR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DosovitskiySRB14,
author = {Alexey Dosovitskiy and
Jost Tobias Springenberg and
Martin A. Riedmiller and
Thomas Brox},
title = {Discriminative Unsupervised Feature Learning with Convolutional Neural
Networks},
journal = {CoRR},
volume = {abs/1406.6909},
year = {2014},
url = {http://arxiv.org/abs/1406.6909},
eprinttype = {arXiv},
eprint = {1406.6909},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DosovitskiySRB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/BlumR13,
author = {Manuel Blum and
Martin A. Riedmiller},
title = {Electricity Demand Forecasting using Gaussian Processes},
booktitle = {Trading Agent Design and Analysis, Papers from the 2013 {AAAI} Workshop,
Bellevue, Washington, USA, July 15, 2013},
series = {{AAAI} Technical Report},
volume = {{WS-13-15}},
publisher = {{AAAI}},
year = {2013},
url = {http://www.aaai.org/ocs/index.php/WS/AAAIW13/paper/view/7106},
timestamp = {Tue, 05 Sep 2023 08:59:27 +0200},
biburl = {https://dblp.org/rec/conf/aaai/BlumR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/esann/BlumR13,
author = {Manuel Blum and
Martin A. Riedmiller},
title = {Optimization of Gaussian process hyperparameters using Rprop},
booktitle = {21st European Symposium on Artificial Neural Networks, {ESANN} 2013,
Bruges, Belgium, April 24-26, 2013},
year = {2013},
url = {https://www.esann.org/sites/default/files/proceedings/legacy/es2013-51.pdf},
timestamp = {Tue, 02 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/esann/BlumR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/Riedmiller13,
author = {Martin A. Riedmiller},
editor = {Heriberto Cuay{\'{a}}huitl and
Lutz Frommberger and
Nina Dethlefs and
Martijn van Otterlo},
title = {Learning machines that perceive, act and communicate},
booktitle = {Proceedings of the 2nd Workshop on Machine Learning for Interactive
Systems - Bridging the Gap Between Perception, Action and Communication,
MLIS@IJCAI 2013, Beijing, China, August 4, 2013},
pages = {5},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2493525.2493526},
doi = {10.1145/2493525.2493526},
timestamp = {Tue, 06 Nov 2018 16:57:28 +0100},
biburl = {https://dblp.org/rec/conf/ijcai/Riedmiller13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/LampeR13,
author = {Thomas Lampe and
Martin A. Riedmiller},
title = {Acquiring visual servoing reaching and grasping skills using neural
reinforcement learning},
booktitle = {The 2013 International Joint Conference on Neural Networks, {IJCNN}
2013, Dallas, TX, USA, August 4-9, 2013},
pages = {1--8},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/IJCNN.2013.6707053},
doi = {10.1109/IJCNN.2013.6707053},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/LampeR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kicss/AlvesNLR13,
author = {Jo{\~{a}}o Alves and
Jos{\'{e}} Neves and
Sascha Lange and
Martin A. Riedmiller},
editor = {Andrzej M. J. Skulimowski and
Janusz Kacprzyk},
title = {Improvement of a Web Browser Game Through the Knowledge Extracted
from Player Behavior},
booktitle = {Knowledge, Information and Creativity Support Systems: Recent Trends,
Advances and Solutions - Selected Papers from KICSS'2013 - 8th International
Conference on Knowledge, Information, and Creativity Support Systems,
November 7-9, 2013, Krak{\'{o}}w, Poland},
series = {Advances in Intelligent Systems and Computing},
volume = {364},
pages = {53--65},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-319-19090-7\_5},
doi = {10.1007/978-3-319-19090-7\_5},
timestamp = {Sun, 02 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/kicss/AlvesNLR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MnihKSGAWR13,
author = {Volodymyr Mnih and
Koray Kavukcuoglu and
David Silver and
Alex Graves and
Ioannis Antonoglou and
Daan Wierstra and
Martin A. Riedmiller},
title = {Playing Atari with Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1312.5602},
year = {2013},
url = {http://arxiv.org/abs/1312.5602},
eprinttype = {arXiv},
eprint = {1312.5602},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MnihKSGAWR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/MattnerLR12,
author = {Jan Mattner and
Sascha Lange and
Martin A. Riedmiller},
editor = {Tingwen Huang and
Zhigang Zeng and
Chuandong Li and
Chi{-}Sing Leung},
title = {Learn to Swing Up and Balance a Real Pole Based on Raw Visual Input
Data},
booktitle = {Neural Information Processing - 19th International Conference, {ICONIP}
2012, Doha, Qatar, November 12-15, 2012, Proceedings, Part {V}},
series = {Lecture Notes in Computer Science},
volume = {7667},
pages = {126--133},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-34500-5\_16},
doi = {10.1007/978-3-642-34500-5\_16},
timestamp = {Tue, 30 Jun 2020 11:04:50 +0200},
biburl = {https://dblp.org/rec/conf/iconip/MattnerLR12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/SpringenbergR12,
author = {Jost Tobias Springenberg and
Martin A. Riedmiller},
editor = {Tingwen Huang and
Zhigang Zeng and
Chuandong Li and
Chi{-}Sing Leung},
title = {Learning Temporal Coherent Features through Life-Time Sparsity},
booktitle = {Neural Information Processing - 19th International Conference, {ICONIP}
2012, Doha, Qatar, November 12-15, 2012, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {7663},
pages = {347--356},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-34475-6\_42},
doi = {10.1007/978-3-642-34475-6\_42},
timestamp = {Tue, 30 Jun 2020 11:04:50 +0200},
biburl = {https://dblp.org/rec/conf/iconip/SpringenbergR12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/BlumSWR12,
author = {Manuel Blum and
Jost Tobias Springenberg and
Jan W{\"{u}}lfing and
Martin A. Riedmiller},
title = {A learned feature descriptor for object recognition in {RGB-D} data},
booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA}
2012, 14-18 May, 2012, St. Paul, Minnesota, {USA}},
pages = {1298--1303},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICRA.2012.6225188},
doi = {10.1109/ICRA.2012.6225188},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/icra/BlumSWR12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/LangeRV12,
author = {Sascha Lange and
Martin A. Riedmiller and
Arne Voigtl{\"{a}}nder},
title = {Autonomous reinforcement learning on raw visual input data in a real
world application},
booktitle = {The 2012 International Joint Conference on Neural Networks (IJCNN),
Brisbane, Australia, June 10-15, 2012},
pages = {1--8},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/IJCNN.2012.6252823},
doi = {10.1109/IJCNN.2012.6252823},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/LangeRV12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/ObstR12,
author = {Oliver Obst and
Martin A. Riedmiller},
title = {Taming the reservoir: Feedforward training for recurrent neural networks},
booktitle = {The 2012 International Joint Conference on Neural Networks (IJCNN),
Brisbane, Australia, June 10-15, 2012},
pages = {1--7},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/IJCNN.2012.6252506},
doi = {10.1109/IJCNN.2012.6252506},
timestamp = {Fri, 02 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ijcnn/ObstR12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ismir/WulfingR12,
author = {Jan W{\"{u}}lfing and
Martin A. Riedmiller},
editor = {Fabien Gouyon and
Perfecto Herrera and
Luis Gustavo Martins and
Meinard M{\"{u}}ller},
title = {Unsupervised Learning of Local Features for Music Classification},
booktitle = {Proceedings of the 13th International Society for Music Information
Retrieval Conference, {ISMIR} 2012, Mosteiro S.Bento Da Vit{\'{o}}ria,
Porto, Portugal, October 8-12, 2012},
pages = {139--144},
publisher = {{FEUP} Edi{\c{c}}{\~{o}}es},
year = {2012},
url = {http://ismir2012.ismir.net/event/papers/139-ismir-2012.pdf},
timestamp = {Tue, 04 Jan 2022 10:38:10 +0100},
biburl = {https://dblp.org/rec/conf/ismir/WulfingR12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/sp/12/LangeGR12,
author = {Sascha Lange and
Thomas Gabel and
Martin A. Riedmiller},
editor = {Marco A. Wiering and
Martijn van Otterlo},
title = {Batch Reinforcement Learning},
booktitle = {Reinforcement Learning},
series = {Adaptation, Learning, and Optimization},
volume = {12},
pages = {45--73},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-27645-3\_2},
doi = {10.1007/978-3-642-27645-3\_2},
timestamp = {Tue, 29 Dec 2020 18:14:51 +0100},
biburl = {https://dblp.org/rec/books/sp/12/LangeGR12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/lncs/Riedmiller12,
author = {Martin A. Riedmiller},
editor = {Gr{\'{e}}goire Montavon and
Genevieve B. Orr and
Klaus{-}Robert M{\"{u}}ller},
title = {10 Steps and Some Tricks to Set up Neural Reinforcement Controllers},
booktitle = {Neural Networks: Tricks of the Trade - Second Edition},
series = {Lecture Notes in Computer Science},
volume = {7700},
pages = {735--757},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-35289-8\_39},
doi = {10.1007/978-3-642-35289-8\_39},
timestamp = {Wed, 25 Sep 2019 17:41:07 +0200},
biburl = {https://dblp.org/rec/series/lncs/Riedmiller12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/HafnerR11,
author = {Roland Hafner and
Martin A. Riedmiller},
title = {Reinforcement learning in feedback control - Challenges and benchmarks
from technical process control},
journal = {Mach. Learn.},
volume = {84},
number = {1-2},
pages = {137--169},
year = {2011},
url = {https://doi.org/10.1007/s10994-011-5235-x},
doi = {10.1007/S10994-011-5235-X},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/HafnerR11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adprl/WitschRGLR11,
author = {Andreas Witsch and
Roland Reichle and
Kurt Geihs and
Sascha Lange and
Martin A. Riedmiller},
title = {Enhancing the episodic natural actor-critic algorithm by a regularisation
term to stabilize learning of control structures},
booktitle = {2011 {IEEE} Symposium on Adaptive Dynamic Programming And Reinforcement
Learning, {ADPRL} 2011, Paris, France, April 12-14, 2011},
pages = {156--163},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ADPRL.2011.5967352},
doi = {10.1109/ADPRL.2011.5967352},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/adprl/WitschRGLR11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adprl/GabelLR11,
author = {Thomas Gabel and
Christian Lutz and
Martin A. Riedmiller},
title = {Improved neural fitted {Q} iteration applied to a novel computer gaming
and learning benchmark},
booktitle = {2011 {IEEE} Symposium on Adaptive Dynamic Programming And Reinforcement
Learning, {ADPRL} 2011, Paris, France, April 12-14, 2011},
pages = {279--286},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ADPRL.2011.5967361},
doi = {10.1109/ADPRL.2011.5967361},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/adprl/GabelLR11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cogsr/LauerHLR10,
author = {Martin Lauer and
Roland Hafner and
Sascha Lange and
Martin A. Riedmiller},
title = {Cognitive concepts in autonomous soccer playing robots},
journal = {Cogn. Syst. Res.},
volume = {11},
number = {3},
pages = {287--309},
year = {2010},
url = {https://doi.org/10.1016/j.cogsys.2009.12.003},
doi = {10.1016/J.COGSYS.2009.12.003},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/cogsr/LauerHLR10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/esann/LangeR10,
author = {Sascha Lange and
Martin A. Riedmiller},
title = {Deep learning of visual control policies},
booktitle = {18th European Symposium on Artificial Neural Networks, {ESANN} 2010,
Bruges, Belgium, April 28-30, 2010, Proceedings},
year = {2010},
url = {https://www.esann.org/sites/default/files/proceedings/legacy/es2010-87.pdf},
timestamp = {Tue, 02 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/esann/LangeR10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/LangeR10,
author = {Sascha Lange and
Martin A. Riedmiller},
title = {Deep auto-encoder neural networks in reinforcement learning},
booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2010, Barcelona,
Spain, 18-23 July, 2010},
pages = {1--8},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/IJCNN.2010.5596468},
doi = {10.1109/IJCNN.2010.5596468},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/LangeR10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/GabelR10,
author = {Thomas Gabel and
Martin A. Riedmiller},
editor = {Javier Ruiz{-}del{-}Solar and
Eric Chown and
Paul{-}Gerhard Pl{\"{o}}ger},
title = {On Progress in RoboCup: The Simulation League Showcase},
booktitle = {RoboCup 2010: Robot Soccer World Cup {XIV} [papers from the 14th annual
RoboCup International Symposium, Singapore, June 25, 2010]},
series = {Lecture Notes in Computer Science},
volume = {6556},
pages = {36--47},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-20217-9\_4},
doi = {10.1007/978-3-642-20217-9\_4},
timestamp = {Tue, 20 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/GabelR10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/arobots/RiedmillerGHL09,
author = {Martin A. Riedmiller and
Thomas Gabel and
Roland Hafner and
Sascha Lange},
title = {Reinforcement learning for robot soccer},
journal = {Auton. Robots},
volume = {27},
number = {1},
pages = {55--73},
year = {2009},
url = {https://doi.org/10.1007/s10514-009-9120-4},
doi = {10.1007/S10514-009-9120-4},
timestamp = {Thu, 18 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/arobots/RiedmillerGHL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/bc/KietzmannLR09,
author = {Tim C. Kietzmann and
Sascha Lange and
Martin A. Riedmiller},
title = {Computational object recognition: a biologically motivated approach},
journal = {Biol. Cybern.},
volume = {100},
number = {1},
pages = {59--79},
year = {2009},
url = {https://doi.org/10.1007/s00422-008-0281-6},
doi = {10.1007/S00422-008-0281-6},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/bc/KietzmannLR09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ki/TimmerR09,
author = {Stephan Timmer and
Martin A. Riedmiller},
title = {Efficient Identification of State in Reinforcement Learning},
journal = {K{\"{u}}nstliche Intell.},
volume = {23},
number = {3},
pages = {5--11},
year = {2009},
url = {http://www.kuenstliche-intelligenz.de/fileadmin/template/main/archiv/pdf/ki2009-03\_page5\_web\_teaser.pdf},
timestamp = {Fri, 27 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ki/TimmerR09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmla/KietzmannR09,
author = {Tim C. Kietzmann and
Martin A. Riedmiller},
editor = {M. Arif Wani and
Mehmed M. Kantardzic and
Vasile Palade and
Lukasz A. Kurgan and
Yuan (Alan) Qi},
title = {The Neuro Slot Car Racer: Reinforcement Learning in a Real World Setting},
booktitle = {International Conference on Machine Learning and Applications, {ICMLA}
2009, Miami Beach, Florida, USA, December 13-15, 2009},
pages = {311--316},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/ICMLA.2009.15},
doi = {10.1109/ICMLA.2009.15},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmla/KietzmannR09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/dagstuhl/2009P9371,
editor = {S{\'{a}}ndor P. Fekete and
Stefan Fischer and
Martin A. Riedmiller and
Subhash Suri},
title = {Algorithmic Methods for Distributed Cooperative Systems, 06.09. -
11.09.2009},
series = {Dagstuhl Seminar Proceedings},
volume = {09371},
publisher = {Schloss Dagstuhl - Leibniz-Zentrum f{\"{u}}r Informatik, Germany},
year = {2009},
url = {http://drops.dagstuhl.de/portals/09371/},
timestamp = {Thu, 10 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/dagstuhl/2009P9371.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dagstuhl/FeketeFRS09,
author = {S{\'{a}}ndor P. Fekete and
Stefan Fischer and
Martin A. Riedmiller and
Subhash Suri},
editor = {S{\'{a}}ndor P. Fekete and
Stefan Fischer and
Martin A. Riedmiller and
Subhash Suri},
title = {09371 Abstracts Collection - Algorithmic Methods for Distributed Cooperative
Systems},
booktitle = {Algorithmic Methods for Distributed Cooperative Systems, 06.09. -
11.09.2009},
series = {Dagstuhl Seminar Proceedings},
volume = {09371},
publisher = {Schloss Dagstuhl - Leibniz-Zentrum f{\"{u}}r Informatik, Germany},
year = {2009},
url = {http://drops.dagstuhl.de/opus/volltexte/2010/2522/},
timestamp = {Thu, 10 Jun 2021 13:02:05 +0200},
biburl = {https://dblp.org/rec/conf/dagstuhl/FeketeFRS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijon/KietzmannLR08,
author = {Tim C. Kietzmann and
Sascha Lange and
Martin A. Riedmiller},
title = {Incremental {GRLVQ:} Learning relevant features for 3D object recognition},
journal = {Neurocomputing},
volume = {71},
number = {13-15},
pages = {2868--2879},
year = {2008},
url = {https://doi.org/10.1016/j.neucom.2007.08.018},
doi = {10.1016/J.NEUCOM.2007.08.018},
timestamp = {Sat, 20 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijon/KietzmannLR08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/GabelR08,
author = {Thomas Gabel and
Martin A. Riedmiller},
editor = {Lin Padgham and
David C. Parkes and
J{\"{o}}rg P. M{\"{u}}ller and
Simon Parsons},
title = {Reinforcement learning for DEC-MDPs with changing action sets and
partially ordered dependencies},
booktitle = {7th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2008), Estoril, Portugal, May 12-16, 2008, Volume
3},
pages = {1333--1336},
publisher = {{IFAAMAS}},
year = {2008},
url = {https://dl.acm.org/citation.cfm?id=1402865},
timestamp = {Fri, 30 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/GabelR08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewcbr/GabelR08,
author = {Thomas Gabel and
Martin A. Riedmiller},
editor = {Klaus{-}Dieter Althoff and
Ralph Bergmann and
Mirjam Minor and
Alexandre Hanft},
title = {Increasing Precision of Credible Case-Based Inference},
booktitle = {Advances in Case-Based Reasoning, 9th European Conference, {ECCBR}
2008, Trier, Germany, September 1-4, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5239},
pages = {225--239},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-85502-6\_15},
doi = {10.1007/978-3-540-85502-6\_15},
timestamp = {Tue, 14 May 2019 10:00:52 +0200},
biburl = {https://dblp.org/rec/conf/ewcbr/GabelR08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/GabelR08,
author = {Thomas Gabel and
Martin A. Riedmiller},
editor = {Sertan Girgin and
Manuel Loth and
R{\'{e}}mi Munos and
Philippe Preux and
Daniil Ryabko},
title = {Evaluation of Batch-Mode Reinforcement Learning Methods for Solving
DEC-MDPs with Changing Action Sets},
booktitle = {Recent Advances in Reinforcement Learning, 8th European Workshop,
{EWRL} 2008, Villeneuve d'Ascq, France, June 30 - July 3, 2008, Revised
and Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {5323},
pages = {82--95},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-89722-4\_7},
doi = {10.1007/978-3-540-89722-4\_7},
timestamp = {Tue, 14 May 2019 10:00:48 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/GabelR08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/RiedmillerHLL08,
author = {Martin A. Riedmiller and
Roland Hafner and
Sascha Lange and
Martin Lauer},
title = {Learning to dribble on a real robot by success and failure},
booktitle = {2008 {IEEE} International Conference on Robotics and Automation, {ICRA}
2008, May 19-23, 2008, Pasadena, California, {USA}},
pages = {2207--2208},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ROBOT.2008.4543536},
doi = {10.1109/ROBOT.2008.4543536},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icra/RiedmillerHLL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mates/GabelR08,
author = {Thomas Gabel and
Martin A. Riedmiller},
editor = {Ralph Bergmann and
Gabriela Lindemann and
Stefan Kirn and
Michal Pechoucek},
title = {Joint Equilibrium Policy Search for Multi-Agent Scheduling Problems},
booktitle = {Multiagent System Technologies, 6th German Conference, {MATES} 2008,
Kaiserslautern, Germany, September 23-26, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5244},
pages = {61--72},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87805-6\_7},
doi = {10.1007/978-3-540-87805-6\_7},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/mates/GabelR08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/GabelRT08,
author = {Thomas Gabel and
Martin A. Riedmiller and
Florian Trost},
editor = {Luca Iocchi and
Hitoshi Matsubara and
Alfredo Weitzenfeld and
Changjiu Zhou},
title = {A Case Study on Improving Defense Behavior in Soccer Simulation 2D:
The NeuroHassle Approach},
booktitle = {RoboCup 2008: Robot Soccer World Cup {XII} [papers from the 12th annual
RoboCup International Symposium, Suzhou, China, July 15-18, 2008]},
series = {Lecture Notes in Computer Science},
volume = {5399},
pages = {61--72},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-642-02921-9\_6},
doi = {10.1007/978-3-642-02921-9\_6},
timestamp = {Tue, 20 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/GabelRT08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cig/RiedmillerG07,
author = {Martin A. Riedmiller and
Thomas Gabel},
title = {On Experiences in a Complex and Competitive Gaming Domain: Reinforcement
Learning Meets RoboCup},
booktitle = {Proceedings of the 2007 {IEEE} Symposium on Computational Intelligence
and Games, {CIG} 2007, Honolulu, Hawaii, USA, 1-5 April, 2007},
pages = {17--23},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/CIG.2007.368074},
doi = {10.1109/CIG.2007.368074},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/cig/RiedmillerG07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cisched/GabelR07,
author = {Thomas Gabel and
Martin A. Riedmiller},
title = {Scaling Adaptive Agent-Based Reactive Job-Shop Scheduling to Large-Scale
Problems},
booktitle = {2007 {IEEE} Symposium on Computational Intelligence in Scheduling,
CISched 2007, Honolulu, Hawaii, USA, April 2-4, 2007},
pages = {259--266},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/SCIS.2007.367699},
doi = {10.1109/SCIS.2007.367699},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/cisched/GabelR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecml/TimmerR07,
author = {Stephan Timmer and
Martin A. Riedmiller},
editor = {Joost N. Kok and
Jacek Koronacki and
Ram{\'{o}}n L{\'{o}}pez de M{\'{a}}ntaras and
Stan Matwin and
Dunja Mladenic and
Andrzej Skowron},
title = {Safe Q-Learning on Complete History Spaces},
booktitle = {Machine Learning: {ECML} 2007, 18th European Conference on Machine
Learning, Warsaw, Poland, September 17-21, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4701},
pages = {394--405},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-74958-5\_37},
doi = {10.1007/978-3-540-74958-5\_37},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/ecml/TimmerR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emcr/VoigtlanderLLR07,
author = {Arne Voigtl{\"{a}}nder and
Sascha Lange and
Martin Lauer and
Martin A. Riedmiller},
title = {Real-time 3D Ball Recognition using Perspective and Catadioptric Cameras},
booktitle = {Proceedings of the 3rd European Conference on Mobile Robots, {EMCR}
2007, September 19-21, 2007, Freiburg, Germany},
year = {2007},
url = {http://ecmr07.informatik.uni-freiburg.de/proceedings/ECMR07\_0067.pdf},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/emcr/VoigtlanderLLR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/esann/Heidrich-MeisnerLIR07,
author = {Verena Heidrich{-}Meisner and
Martin Lauer and
Christian Igel and
Martin A. Riedmiller},
title = {Reinforcement learning in a nutshell},
booktitle = {15th European Symposium on Artificial Neural Networks, {ESANN} 2007,
Bruges, Belgium, April 25-27, 2007, Proceedings},
pages = {277--288},
year = {2007},
url = {https://www.esann.org/sites/default/files/proceedings/legacy/es2007-4.pdf},
timestamp = {Tue, 02 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/esann/Heidrich-MeisnerLIR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fbit/RiedmillerMD07,
author = {Martin A. Riedmiller and
Michael Montemerlo and
Hendrik Dahlkamp},
editor = {Daniel Howard and
Phill{-}Kyu Rhee},
title = {Learning to Drive a Real Car in 20 Minutes},
booktitle = {Frontiers in the Convergence of Bioscience and Information Technologies
2007, {FBIT} 2007, Jeju Island, Korea, October 11-13, 2007},
pages = {645--650},
publisher = {{IEEE} Computer Society},
year = {2007},
url = {https://doi.org/10.1109/FBIT.2007.37},
doi = {10.1109/FBIT.2007.37},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/fbit/RiedmillerMD07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccbr/GabelR07,
author = {Thomas Gabel and
Martin A. Riedmiller},
editor = {Rosina Weber and
Michael M. Richter},
title = {An Analysis of Case-Based Value Function Approximation by Approximating
State Transition Graphs},
booktitle = {Case-Based Reasoning Research and Development, 7th International Conference
on Case-Based Reasoning, {ICCBR} 2007, Belfast, Northern Ireland,
UK, August 13-16, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4626},
pages = {344--358},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-74141-1\_24},
doi = {10.1007/978-3-540-74141-1\_24},
timestamp = {Tue, 14 May 2019 10:00:52 +0200},
biburl = {https://dblp.org/rec/conf/iccbr/GabelR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/HafnerR07,
author = {Roland Hafner and
Martin A. Riedmiller},
title = {Neural Reinforcement Learning Controllers for a Real Robot Application},
booktitle = {2007 {IEEE} International Conference on Robotics and Automation, {ICRA}
2007, 10-14 April 2007, Roma, Italy},
pages = {2098--2103},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ROBOT.2007.363631},
doi = {10.1109/ROBOT.2007.363631},
timestamp = {Mon, 22 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icra/HafnerR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ki/MullerLHLMR07,
author = {Heiko M{\"{u}}ller and
Martin Lauer and
Roland Hafner and
Sascha Lange and
Artur Merke and
Martin A. Riedmiller},
editor = {Joachim Hertzberg and
Michael Beetz and
Roman Englert},
title = {Making a Robot Learn to Play Soccer Using Reward and Punishment},
booktitle = {{KI} 2007: Advances in Artificial Intelligence, 30th Annual German
Conference on AI, {KI} 2007, Osnabr{\"{u}}ck, Germany, September
10-13, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4667},
pages = {220--234},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-74565-5\_18},
doi = {10.1007/978-3-540-74565-5\_18},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ki/MullerLHLMR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/insk/RiedmillerGHLL06,
author = {Martin A. Riedmiller and
Thomas Gabel and
Roland Hafner and
Sascha Lange and
Martin Lauer},
title = {Die Brainstormers: Entwurfsprinzipien lernf{\"{a}}higer autonomer
Roboter},
journal = {Inform. Spektrum},
volume = {29},
number = {3},
pages = {175--190},
year = {2006},
url = {https://doi.org/10.1007/s00287-006-0077-9},
doi = {10.1007/S00287-006-0077-9},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/insk/RiedmillerGHLL06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ki/GabelR06,
author = {Thomas Gabel and
Martin A. Riedmiller},
title = {Learning a Partial Behavior for a Competitive Robotic Soccer Agent},
journal = {K{\"{u}}nstliche Intell.},
volume = {20},
number = {2},
pages = {18--23},
year = {2006},
url = {http://www.kuenstliche-intelligenz.de/index.php?id=7670\&\#38;tx\_ki\_pi1\%5BshowUid\%5D=1074\&\#38;cHash=608c878635},
timestamp = {Thu, 09 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ki/GabelR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/esann/GabelR06,
author = {Thomas Gabel and
Martin A. Riedmiller},
title = {Reducing policy degradation in neuro-dynamic programming},
booktitle = {14th European Symposium on Artificial Neural Networks, {ESANN} 2006,
Bruges, Belgium, April 26-28, 2006, Proceedings},
pages = {653--658},
year = {2006},
url = {https://www.esann.org/sites/default/files/proceedings/legacy/es2006-22.pdf},
timestamp = {Tue, 02 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/esann/GabelR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewcbr/GabelR06,
author = {Thomas Gabel and
Martin A. Riedmiller},
editor = {Thomas Roth{-}Berghofer and
Mehmet H. G{\"{o}}ker and
H. Altay G{\"{u}}venir},
title = {Multi-agent Case-Based Reasoning for Cooperative Reinforcement Learners},
booktitle = {Advances in Case-Based Reasoning, 8th European Conference, {ECCBR}
2006, Fethiye, Turkey, September 4-7, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4106},
pages = {32--46},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11805816\_5},
doi = {10.1007/11805816\_5},
timestamp = {Tue, 14 May 2019 10:00:52 +0200},
biburl = {https://dblp.org/rec/conf/ewcbr/GabelR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/LangeR06,
author = {Sascha Lange and
Martin A. Riedmiller},
editor = {Gerhard Lakemeyer and
Elizabeth Sklar and
Domenico G. Sorrenti and
Tomoichi Takahashi},
title = {Appearance-Based Robot Discrimination Using Eigenimages},
booktitle = {RoboCup 2006: Robot Soccer World Cup {X}},
series = {Lecture Notes in Computer Science},
volume = {4434},
pages = {499--506},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/978-3-540-74024-7\_51},
doi = {10.1007/978-3-540-74024-7\_51},
timestamp = {Tue, 20 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/LangeR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/dagstuhl/2006P6251,
editor = {Hans{-}Dieter Burkhard and
Martin A. Riedmiller and
Uwe Schwiegelshohn and
Manuela M. Veloso},
title = {Multi-Robot Systems: Perception, Behaviors, Learning, and Action,
19.06. - 23.06.2006},
series = {Dagstuhl Seminar Proceedings},
volume = {06251},
publisher = {Internationales Begegnungs- und Forschungszentrum f{\"{u}}r Informatik
(IBFI), Schloss Dagstuhl, Germany},
year = {2006},
url = {http://drops.dagstuhl.de/portals/06251/},
timestamp = {Thu, 10 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/dagstuhl/2006P6251.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dagstuhl/BurkhardRSV06,
author = {Hans{-}Dieter Burkhard and
Martin A. Riedmiller and
Uwe Schwiegelshohn and
Manuela M. Veloso},
editor = {Hans{-}Dieter Burkhard and
Martin A. Riedmiller and
Uwe Schwiegelshohn and
Manuela M. Veloso},
title = {06251 Abstracts Collection - Multi-Robot Systems: Perception, Behaviors,
Learning, and Action},
booktitle = {Multi-Robot Systems: Perception, Behaviors, Learning, and Action,
19.06. - 23.06.2006},
series = {Dagstuhl Seminar Proceedings},
volume = {06251},
publisher = {Internationales Begegnungs- und Forschungszentrum f{\"{u}}r Informatik
(IBFI), Schloss Dagstuhl, Germany},
year = {2006},
url = {http://drops.dagstuhl.de/opus/volltexte/2006/844/},
timestamp = {Thu, 10 Jun 2021 13:02:03 +0200},
biburl = {https://dblp.org/rec/conf/dagstuhl/BurkhardRSV06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/it/RiedmillerW05,
author = {Martin A. Riedmiller and
Daniel Withopf},
title = {Effective Methods for Reinforcement Learning in Large Multi-Agent
Domains},
journal = {it Inf. Technol.},
volume = {47},
number = {5},
pages = {241--249},
year = {2005},
url = {https://doi.org/10.1524/itit.2005.47.5\_2005.241},
doi = {10.1524/ITIT.2005.47.5\_2005.241},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/it/RiedmillerW05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecml/Riedmiller05,
author = {Martin A. Riedmiller},
editor = {Jo{\~{a}}o Gama and
Rui Camacho and
Pavel Brazdil and
Al{\'{\i}}pio Jorge and
Lu{\'{\i}}s Torgo},
title = {Neural Fitted {Q} Iteration - First Experiences with a Data Efficient
Neural Reinforcement Learning Method},
booktitle = {Machine Learning: {ECML} 2005, 16th European Conference on Machine
Learning, Porto, Portugal, October 3-7, 2005, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3720},
pages = {317--328},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11564096\_32},
doi = {10.1007/11564096\_32},
timestamp = {Wed, 24 Mar 2021 17:12:00 +0100},
biburl = {https://dblp.org/rec/conf/ecml/Riedmiller05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccbr/GabelR05,
author = {Thomas Gabel and
Martin A. Riedmiller},
editor = {H{\'{e}}ctor Mu{\~{n}}oz{-}Avila and
Francesco Ricci},
title = {{CBR} for State Value Function Approximation in Reinforcement Learning},
booktitle = {Case-Based Reasoning, Research and Development, 6th International
Conference, on Case-Based Reasoning, {ICCBR} 2005, Chicago, IL, USA,
August 23-26, 2005, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3620},
pages = {206--221},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11536406\_18},
doi = {10.1007/11536406\_18},
timestamp = {Tue, 14 May 2019 10:00:52 +0200},
biburl = {https://dblp.org/rec/conf/iccbr/GabelR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ki/LauerLR05,
author = {Martin Lauer and
Sascha Lange and
Martin A. Riedmiller},
editor = {Ulrich Furbach},
title = {Modeling Moving Objects in a Dynamically Changing Robot Application},
booktitle = {{KI} 2005: Advances in Artificial Intelligence, 28th Annual German
Conference on AI, {KI} 2005, Koblenz, Germany, September 11-14, 2005,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3698},
pages = {291--303},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11551263\_24},
doi = {10.1007/11551263\_24},
timestamp = {Tue, 14 May 2019 10:00:49 +0200},
biburl = {https://dblp.org/rec/conf/ki/LauerLR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mirrorbot/SungMR05,
author = {Alexander Sung and
Artur Merke and
Martin A. Riedmiller},
editor = {Stefan Wermter and
G{\"{u}}nther Palm and
Mark Elshaw},
title = {Reinforcement Learning Using a Grid Based Function Approximator},
booktitle = {Biomimetic Neural Learning for Intelligent Robots - Intelligent Systems,
Cognitive Robotics, and Neuroscience},
series = {Lecture Notes in Computer Science},
volume = {3575},
pages = {235--244},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11521082\_14},
doi = {10.1007/11521082\_14},
timestamp = {Tue, 14 May 2019 10:00:40 +0200},
biburl = {https://dblp.org/rec/conf/mirrorbot/SungMR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/LauerLR05,
author = {Martin Lauer and
Sascha Lange and
Martin A. Riedmiller},
editor = {Ansgar Bredenfeld and
Adam Jacoff and
Itsuki Noda and
Yasutake Takahashi},
title = {Calculating the Perfect Match: An Efficient and Accurate Approach
for Robot Self-localization},
booktitle = {RoboCup 2005: Robot Soccer World Cup {IX}},
series = {Lecture Notes in Computer Science},
volume = {4020},
pages = {142--153},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11780519\_13},
doi = {10.1007/11780519\_13},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/robocup/LauerLR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smc/TimmerR05,
author = {Stephan Timmer and
Martin A. Riedmiller},
title = {Learning policies for abstract state spaces},
booktitle = {Proceedings of the {IEEE} International Conference on Systems, Man
and Cybernetics, Waikoloa, Hawaii, USA, October 10-12, 2005},
pages = {3179--3184},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICSMC.2005.1571635},
doi = {10.1109/ICSMC.2005.1571635},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/smc/TimmerR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smc/RiedmillerW05,
author = {Martin A. Riedmiller and
Daniel Withopf},
title = {Comparing different methods to speed up reinforcement learning in
a complex domain},
booktitle = {Proceedings of the {IEEE} International Conference on Systems, Man
and Cybernetics, Waikoloa, Hawaii, USA, October 10-12, 2005},
pages = {3185--3190},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICSMC.2005.1571636},
doi = {10.1109/ICSMC.2005.1571636},
timestamp = {Wed, 17 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/smc/RiedmillerW05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smc/Riedmiller05,
author = {Martin A. Riedmiller},
title = {Neural reinforcement learning to swing-up and balance a real pole},
booktitle = {Proceedings of the {IEEE} International Conference on Systems, Man
and Cybernetics, Waikoloa, Hawaii, USA, October 10-12, 2005},
pages = {3191--3196},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICSMC.2005.1571637},
doi = {10.1109/ICSMC.2005.1571637},
timestamp = {Wed, 17 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/smc/Riedmiller05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/robocup/2004,
editor = {Daniele Nardi and
Martin A. Riedmiller and
Claude Sammut and
Jos{\'{e}} Santos{-}Victor},
title = {RoboCup 2004: Robot Soccer World Cup {VIII}},
series = {Lecture Notes in Computer Science},
volume = {3276},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/b106671},
doi = {10.1007/B106671},
isbn = {3-540-25046-8},
timestamp = {Tue, 14 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/2004.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aim/PagelloMBCCJPRSST04,
author = {Enrico Pagello and
Emanuele Menegatti and
Ansgar Bredenfeld and
Paulo Costa and
Thomas Christaller and
Adam Jacoff and
Daniel Polani and
Martin A. Riedmiller and
Alessandro Saffiotti and
Elizabeth Sklar and
Takashi Tomoichi},
title = {RoboCup-2003: New Scientific and Technical Advances},
journal = {{AI} Mag.},
volume = {25},
number = {2},
pages = {81--98},
year = {2004},
url = {https://doi.org/10.1609/aimag.v25i2.1762},
doi = {10.1609/AIMAG.V25I2.1762},
timestamp = {Tue, 25 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aim/PagelloMBCCJPRSST04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ki/RiedmillerFGWS04,
author = {Martin A. Riedmiller and
Fran{\c{c}}ois Fages and
Malik Ghallab and
Wolfgang Wahlster and
J{\"{o}}rg H. Siekmann},
title = {Invited talks},
journal = {K{\"{u}}nstliche Intell.},
volume = {18},
number = {3},
pages = {44},
year = {2004},
url = {http://www.kuenstliche-intelligenz.de/archiv/2004\_3/KI-Tagung-2004-web.pdf},
timestamp = {Fri, 27 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ki/RiedmillerFGWS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/soco/SchoknechtSR04,
author = {Ralf Schoknecht and
Martin Spott and
Martin A. Riedmiller},
title = {Fynesse: An architecture for integrating prior knowledge in autonomously
learning agents},
journal = {Soft Comput.},
volume = {8},
number = {6},
pages = {397--408},
year = {2004},
url = {https://doi.org/10.1007/s00500-003-0295-x},
doi = {10.1007/S00500-003-0295-X},
timestamp = {Sat, 20 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/soco/SchoknechtSR04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/LauerR04,
author = {Martin Lauer and
Martin A. Riedmiller},
title = {Reinforcement Learning for Stochastic Cooperative Multi-Agent Systems},
booktitle = {3rd International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2004), 19-23 August 2004, New York, NY, {USA}},
pages = {1516--1517},
publisher = {{IEEE} Computer Society},
year = {2004},
url = {https://doi.ieeecomputersociety.org/10.1109/AAMAS.2004.10253},
doi = {10.1109/AAMAS.2004.10253},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/LauerR04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ki/Riedmiller04,
author = {Martin A. Riedmiller},
editor = {Susanne Biundo and
Thom W. Fr{\"{u}}hwirth and
G{\"{u}}nther Palm},
title = {Machine Learning for Autonomous Robots},
booktitle = {{KI} 2004: Advances in Artificial Intelligence, 27th Annual German
Conference on AI, {KI} 2004, Ulm, Germany, September 20-24, 2004,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3238},
pages = {52--55},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-30221-6\_5},
doi = {10.1007/978-3-540-30221-6\_5},
timestamp = {Tue, 14 May 2019 10:00:49 +0200},
biburl = {https://dblp.org/rec/conf/ki/Riedmiller04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/LangeR04,
author = {Sascha Lange and
Martin A. Riedmiller},
editor = {Daniele Nardi and
Martin A. Riedmiller and
Claude Sammut and
Jos{\'{e}} Santos{-}Victor},
title = {Evolution of Computer Vision Subsystems in Robot Navigation and Image
Classification Tasks},
booktitle = {RoboCup 2004: Robot Soccer World Cup {VIII}},
series = {Lecture Notes in Computer Science},
volume = {3276},
pages = {184--195},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-32256-6\_15},
doi = {10.1007/978-3-540-32256-6\_15},
timestamp = {Tue, 20 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/LangeR04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nca/SchoknechtR03,
author = {Ralf Schoknecht and
Martin A. Riedmiller},
title = {Reinforcement learning on explicitly specified time scales},
journal = {Neural Comput. Appl.},
volume = {12},
number = {2},
pages = {61--80},
year = {2003},
url = {https://doi.org/10.1007/s00521-003-0368-x},
doi = {10.1007/S00521-003-0368-X},
timestamp = {Thu, 10 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nca/SchoknechtR03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icann/SchoknechtR03,
author = {Ralf Schoknecht and
Martin A. Riedmiller},
editor = {Okyay Kaynak and
Ethem Alpaydin and
Erkki Oja and
Lei Xu},
title = {Learning to Control at Multiple Time Scales},
booktitle = {Artificial Neural Networks and Neural Information Processing - {ICANN/ICONIP}
2003, Joint International Conference {ICANN/ICONIP} 2003, Istanbul,
Turkey, June 26-29, 2003, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2714},
pages = {479--487},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/3-540-44989-2\_57},
doi = {10.1007/3-540-44989-2\_57},
timestamp = {Wed, 18 Dec 2019 17:28:51 +0100},
biburl = {https://dblp.org/rec/conf/icann/SchoknechtR03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ida/LauerRRBW03,
author = {Martin Lauer and
Martin A. Riedmiller and
Thomas Ragg and
Walter Baum and
Michael Wigbers},
editor = {Michael R. Berthold and
Hans{-}Joachim Lenz and
Elizabeth Bradley and
Rudolf Kruse and
Christian Borgelt},
title = {The Smaller the Better: Comparison of Two Approaches for Sales Rate
Prediction},
booktitle = {Advances in Intelligent Data Analysis V, 5th International Symposium
on Intelligent Data Analysis, {IDA} 2003, Berlin, Germany, August
28-30, 2003, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2810},
pages = {451--461},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/978-3-540-45231-7\_42},
doi = {10.1007/978-3-540-45231-7\_42},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ida/LauerRRBW03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/HafnerR03,
author = {Roland Hafner and
Martin A. Riedmiller},
title = {Reinforcement learning on an omnidirectional mobile robot},
booktitle = {2003 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, Las Vegas, Nevada, USA, October 27 - November 1, 2003},
pages = {418--423},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/IROS.2003.1250665},
doi = {10.1109/IROS.2003.1250665},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/iros/HafnerR03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/PagelloMBCCJJRST03,
author = {Enrico Pagello and
Emanuele Menegatti and
Ansgar Bredenfeld and
Paulo Costa and
Thomas Christaller and
Adam Jacoff and
Jeffrey Johnson and
Martin A. Riedmiller and
Alessandro Saffiotti and
Takashi Tomoichi},
editor = {Daniel Polani and
Brett Browning and
Andrea Bonarini and
Kazuo Yoshida},
title = {Overview of RoboCup 2003 Competition and Conferences},
booktitle = {RoboCup 2003: Robot Soccer World Cup {VII}},
series = {Lecture Notes in Computer Science},
volume = {3020},
pages = {1--14},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/978-3-540-25940-4\_1},
doi = {10.1007/978-3-540-25940-4\_1},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/PagelloMBCCJJRST03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/BurkhardABJNRSSV03,
author = {Hans{-}Dieter Burkhard and
Minoru Asada and
Andrea Bonarini and
Adam Jacoff and
Daniele Nardi and
Martin A. Riedmiller and
Claude Sammut and
Elizabeth Sklar and
Manuela M. Veloso},
editor = {Daniel Polani and
Brett Browning and
Andrea Bonarini and
Kazuo Yoshida},
title = {RoboCup: Yesterday, Today, and Tomorrow Workshop of the Executive
Committee in Blaubeuren, October 2003},
booktitle = {RoboCup 2003: Robot Soccer World Cup {VII}},
series = {Lecture Notes in Computer Science},
volume = {3020},
pages = {15--34},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/978-3-540-25940-4\_2},
doi = {10.1007/978-3-540-25940-4\_2},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/BurkhardABJNRSSV03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icann/SchoknechtR02,
author = {Ralf Schoknecht and
Martin A. Riedmiller},
editor = {Jos{\'{e}} R. Dorronsoro},
title = {Speeding-up Reinforcement Learning with Multi-step Actions},
booktitle = {Artificial Neural Networks - {ICANN} 2002, International Conference,
Madrid, Spain, August 28-30, 2002, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2415},
pages = {813--818},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-46084-5\_132},
doi = {10.1007/3-540-46084-5\_132},
timestamp = {Sun, 02 Jun 2019 21:16:26 +0200},
biburl = {https://dblp.org/rec/conf/icann/SchoknechtR02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/MerkeR01,
author = {Artur Merke and
Martin A. Riedmiller},
editor = {Andreas Birk and
Silvia Coradeschi and
Satoshi Tadokoro},
title = {Karlsruhe Brainstormers - {A} Reinforcement Learning Approach to Robotic
Soccer},
booktitle = {RoboCup 2001: Robot Soccer World Cup {V}},
series = {Lecture Notes in Computer Science},
volume = {2377},
pages = {435--440},
publisher = {Springer},
year = {2001},
url = {https://doi.org/10.1007/3-540-45603-1\_56},
doi = {10.1007/3-540-45603-1\_56},
timestamp = {Tue, 14 May 2019 10:00:53 +0200},
biburl = {https://dblp.org/rec/conf/robocup/MerkeR01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecaiw/RiedmillerMS00,
author = {Martin A. Riedmiller and
Andrew W. Moore and
Jeff G. Schneider},
editor = {Markus Hannebauer and
Jan Wendler and
Enrico Pagello},
title = {Reinforcement Learning for Cooperating and Communicating Reactive
Agents in Electrical Power Grids},
booktitle = {Balancing Reactivity and Social Deliberation in Multi-Agent Systems,
From RoboCup to Real-World Applications (selected papers from the
{ECAI} 2000 Workshop and additional contributions)},
series = {Lecture Notes in Computer Science},
volume = {2103},
pages = {137--149},
publisher = {Springer},
year = {2000},
url = {https://doi.org/10.1007/3-540-44568-4\_9},
doi = {10.1007/3-540-44568-4\_9},
timestamp = {Tue, 14 May 2019 10:00:49 +0200},
biburl = {https://dblp.org/rec/conf/ecaiw/RiedmillerMS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LauerR00,
author = {Martin Lauer and
Martin A. Riedmiller},
editor = {Pat Langley},
title = {An Algorithm for Distributed Reinforcement Learning in Cooperative
Multi-Agent Systems},
booktitle = {Proceedings of the Seventeenth International Conference on Machine
Learning {(ICML} 2000), Stanford University, Stanford, CA, USA, June
29 - July 2, 2000},
pages = {535--542},
publisher = {Morgan Kaufmann},
year = {2000},
timestamp = {Sun, 21 Feb 2010 20:54:50 +0100},
biburl = {https://dblp.org/rec/conf/icml/LauerR00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pricai/BuckR00,
author = {Sebastian Buck and
Martin A. Riedmiller},
editor = {Riichiro Mizoguchi and
John K. Slaney},
title = {Learning Situation Dependent Success Rates of Actions in a RoboCup
Scenario},
booktitle = {{PRICAI} 2000, Topics in Artificial Intelligence, 6th Pacific Rim
International Conference on Artificial Intelligence, Melbourne, Australia,
August 28 - September 1, 2000, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1886},
pages = {809},
publisher = {Springer},
year = {2000},
url = {https://doi.org/10.1007/3-540-44533-1\_98},
doi = {10.1007/3-540-44533-1\_98},
timestamp = {Sat, 07 Sep 2019 11:59:26 +0200},
biburl = {https://dblp.org/rec/conf/pricai/BuckR00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/RiedmillerMMHSTE00,
author = {Martin A. Riedmiller and
Artur Merke and
David Meier and
Andreas Hoffmann and
Alex Sinner and
Ortwin Thate and
R. Ehrmann},
editor = {Peter Stone and
Tucker R. Balch and
Gerhard K. Kraetzschmar},
title = {Karlsruhe Brainstormers - {A} Reinforcement Learning Approach to Robotic
Soccer},
booktitle = {RoboCup 2000: Robot Soccer World Cup {IV}},
series = {Lecture Notes in Computer Science},
volume = {2019},
pages = {367--372},
publisher = {Springer},
year = {2000},
url = {https://doi.org/10.1007/3-540-45324-5\_40},
doi = {10.1007/3-540-45324-5\_40},
timestamp = {Tue, 14 May 2019 10:00:53 +0200},
biburl = {https://dblp.org/rec/conf/robocup/RiedmillerMMHSTE00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/RiedmillerMMHST00,
author = {Martin A. Riedmiller and
Artur Merke and
David Meier and
Andreas Hoffmann and
Alex Sinner and
Ortwin Thate},
editor = {Peter Stone and
Tucker R. Balch and
Gerhard K. Kraetzschmar},
title = {Karlsruhe Brainstormers 2000 Team Description},
booktitle = {RoboCup 2000: Robot Soccer World Cup {IV}},
series = {Lecture Notes in Computer Science},
volume = {2019},
pages = {485--488},
publisher = {Springer},
year = {2000},
url = {https://doi.org/10.1007/3-540-45324-5\_67},
doi = {10.1007/3-540-45324-5\_67},
timestamp = {Mon, 08 Jan 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/robocup/RiedmillerMMHST00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nca/Riedmiller99,
author = {Martin A. Riedmiller},
title = {Concepts and Facilities of a Neural Reinforcement Learning Control
Architecture for Technical Process Control},
journal = {Neural Comput. Appl.},
volume = {8},
number = {4},
pages = {323--338},
year = {1999},
url = {https://doi.org/10.1007/s005210050038},
doi = {10.1007/S005210050038},
timestamp = {Thu, 10 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nca/Riedmiller99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SchneiderWMR99,
author = {Jeff G. Schneider and
Weng{-}Keen Wong and
Andrew W. Moore and
Martin A. Riedmiller},
editor = {Ivan Bratko and
Saso Dzeroski},
title = {Distributed Value Functions},
booktitle = {Proceedings of the Sixteenth International Conference on Machine Learning
{(ICML} 1999), Bled, Slovenia, June 27 - 30, 1999},
pages = {371--378},
publisher = {Morgan Kaufmann},
year = {1999},
timestamp = {Thu, 16 Oct 2014 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/SchneiderWMR99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/RiedmillerR99,
author = {Simone C. Riedmiller and
Martin A. Riedmiller},
editor = {Thomas Dean},
title = {A Neural Reinforcement Learning Approach to Learn Local Dispatching
Policies in Production Scheduling},
booktitle = {Proceedings of the Sixteenth International Joint Conference on Artificial
Intelligence, {IJCAI} 99, Stockholm, Sweden, July 31 - August 6, 1999.
2 Volumes, 1450 pages},
pages = {764--771},
publisher = {Morgan Kaufmann},
year = {1999},
url = {http://ijcai.org/Proceedings/99-2/Papers/016.pdf},
timestamp = {Tue, 20 Aug 2019 16:18:16 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/RiedmillerR99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/RiedmillerBMETDSHF99,
author = {Martin A. Riedmiller and
Sebastian Buck and
Artur Merke and
R. Ehrmann and
Ortwin Thate and
S. Dilger and
Alex Sinner and
Andreas Hoffmann and
Lutz Frommberger},
editor = {Manuela M. Veloso and
Enrico Pagello and
Hiroaki Kitano},
title = {Karlsruhe Brainstormers - Design Principles},
booktitle = {RoboCup-99: Robot Soccer World Cup {III}},
series = {Lecture Notes in Computer Science},
volume = {1856},
pages = {588--591},
publisher = {Springer},
year = {1999},
url = {https://doi.org/10.1007/3-540-45327-X\_57},
doi = {10.1007/3-540-45327-X\_57},
timestamp = {Tue, 14 May 2019 10:00:53 +0200},
biburl = {https://dblp.org/rec/conf/robocup/RiedmillerBMETDSHF99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jirs/SantaMR98,
author = {Karoly Santa and
Michael Mews and
Martin A. Riedmiller},
title = {A Neural Approach for the Control of Piezoelectric Micromanipulation
Robots},
journal = {J. Intell. Robotic Syst.},
volume = {22},
number = {3-4},
pages = {351--374},
year = {1998},
url = {https://doi.org/10.1023/A:1008006308260},
doi = {10.1023/A:1008006308260},
timestamp = {Tue, 07 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jirs/SantaMR98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/dnb/Riedmiller97,
author = {Martin A. Riedmiller},
title = {Selbst{\"{a}}ndig lernende neuronale Steuerungen},
school = {Karlsruhe Institute of Technology},
year = {1997},
url = {https://d-nb.info/95060903X},
isbn = {3-18-362608-X},
timestamp = {Sat, 17 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/dnb/Riedmiller97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/esann/Riedmiller97,
author = {Martin A. Riedmiller},
editor = {Michel Verleysen},
title = {Application of a self-learning controller with continuous control
signals based on the DOE-approach},
booktitle = {5th Eurorean Symposium on Artificial Neural Networks, {ESANN} 1997,
Bruges, Belgium, April 16-18, 1997, Proceedings},
publisher = {D-Facto public},
year = {1997},
url = {https://www.esann.org/sites/default/files/proceedings/legacy/es1997-67-S.pdf},
timestamp = {Tue, 02 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/esann/Riedmiller97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icnn/WigbersR97,
author = {Michael Wigbers and
Martin A. Riedmiller},
title = {A new method for the analysis of neural reference model control},
booktitle = {Proceedings of International Conference on Neural Networks (ICNN'97),
Houston, TX, USA, June 9-12, 1997},
pages = {739--743},
publisher = {{IEEE}},
year = {1997},
url = {https://doi.org/10.1109/ICNN.1997.616114},
doi = {10.1109/ICNN.1997.616114},
timestamp = {Fri, 16 Aug 2019 17:38:27 +0200},
biburl = {https://dblp.org/rec/conf/icnn/WigbersR97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icnn/Riedmiller96,
author = {Martin A. Riedmiller},
title = {Application of sequential reinforcement learning to control dynamic
systems},
booktitle = {Proceedings of International Conference on Neural Networks (ICNN'96),
Washington, DC, USA, June 3-6, 1996},
pages = {167--172},
publisher = {{IEEE}},
year = {1996},
url = {https://doi.org/10.1109/ICNN.1996.548885},
doi = {10.1109/ICNN.1996.548885},
timestamp = {Wed, 02 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icnn/Riedmiller96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/StahlbergerR96,
author = {Achim Stahlberger and
Martin A. Riedmiller},
editor = {Michael Mozer and
Michael I. Jordan and
Thomas Petsche},
title = {Fast Network Pruning and Feature Extraction by using the Unit-OBS
Algorithm},
booktitle = {Advances in Neural Information Processing Systems 9, NIPS, Denver,
CO, USA, December 2-5, 1996},
pages = {655--661},
publisher = {{MIT} Press},
year = {1996},
url = {http://papers.nips.cc/paper/1233-fast-network-pruning-and-feature-extraction-by-using-the-unit-obs-algorithm},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/StahlbergerR96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icannga/KollRB95,
author = {D. Koll and
Martin A. Riedmiller and
Heinrich Braun},
editor = {David W. Pearson and
Nigel C. Steele and
Rudolf F. Albrecht},
title = {Massively Parallel Training of Multi Layer Perceptrons With Irregular
Topologies},
booktitle = {Artificial Neural Nets and Genetic Algorithms, {ICANNGA} 1995, Proceedings
of the International Conference in Al{\`{e}}s, France, 1995},
pages = {293--296},
publisher = {Springer},
year = {1995},
url = {https://doi.org/10.1007/978-3-7091-7535-4\_77},
doi = {10.1007/978-3-7091-7535-4\_77},
timestamp = {Tue, 01 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icannga/KollRB95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icnn/JanuszR95,
author = {Barbara Janusz and
Martin A. Riedmiller},
title = {Self-learning neural control of a mobile robot},
booktitle = {Proceedings of International Conference on Neural Networks (ICNN'95),
Perth, WA, Australia, November 27 - December 1, 1995},
pages = {2358--2363},
publisher = {{IEEE}},
year = {1995},
url = {https://doi.org/10.1109/ICNN.1995.487730},
doi = {10.1109/ICNN.1995.487730},
timestamp = {Wed, 02 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icnn/JanuszR95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icnn/RiedmillerB93,
author = {Martin A. Riedmiller and
Heinrich Braun},
title = {A direct adaptive method for faster backpropagation learning: the
{RPROP} algorithm},
booktitle = {Proceedings of International Conference on Neural Networks (ICNN'88),
San Francisco, CA, USA, March 28 - April 1, 1993},
pages = {586--591},
publisher = {{IEEE}},
year = {1993},
url = {https://doi.org/10.1109/ICNN.1993.298623},
doi = {10.1109/ICNN.1993.298623},
timestamp = {Wed, 02 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icnn/RiedmillerB93.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-02-19 20:08 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
