@article{DBLP:journals/corr/abs-2404-10017,
author = {Simon Eisenmann and
Daniel Hein and
Steffen Udluft and
Thomas A. Runkler},
title = {Model-based Offline Quantum Reinforcement Learning},
journal = {CoRR},
volume = {abs/2404.10017},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2404.10017},
doi = {10.48550/ARXIV.2404.10017},
eprinttype = {arXiv},
eprint = {2404.10017},
timestamp = {Fri, 31 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2404-10017.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2407-11751,
author = {Philipp Wissmann and
Daniel Hein and
Steffen Udluft and
Volker Tresp},
title = {Why long model-based rollouts are no reason for bad Q-value estimates},
journal = {CoRR},
volume = {abs/2407.11751},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2407.11751},
doi = {10.48550/ARXIV.2407.11751},
eprinttype = {arXiv},
eprint = {2407.11751},
timestamp = {Fri, 23 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2407-11751.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmlr/WiedemannHUM23,
author = {Simon Wiedemann and
Daniel Hein and
Steffen Udluft and
Christian B. Mendl},
title = {Quantum Policy Iteration via Amplitude Estimation and Grover Search
- Towards Quantum Advantage for Reinforcement Learning},
journal = {Trans. Mach. Learn. Res.},
volume = {2023},
year = {2023},
url = {https://openreview.net/forum?id=HG11PAmwQ6},
timestamp = {Thu, 18 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmlr/WiedemannHUM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/qce/TrespUHHLMSM23,
author = {Volker Tresp and
Steffen Udluft and
Daniel Hein and
Werner Hauptmann and
Martin Leib and
Christopher Mutschler and
Daniel D. Scherer and
Wolfgang Mauerer},
editor = {Brian La Cour and
Lia Yeh and
Marek Osinski},
title = {Workshop Summary: Quantum Machine Learning},
booktitle = {{IEEE} International Conference on Quantum Computing and Engineering,
{QCE} 2023, Bellevue, WA, USA, September 17-22, 2023},
pages = {1--3},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/QCE57702.2023.10174},
doi = {10.1109/QCE57702.2023.10174},
timestamp = {Fri, 15 Dec 2023 20:24:40 +0100},
biburl = {https://dblp.org/rec/conf/qce/TrespUHHLMSM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ssci/WeberSHUS23,
author = {Marc Weber and
Phillip Swazinna and
Daniel Hein and
Steffen Udluft and
Volkmar Sterzing},
title = {Learning Control Policies for Variable Objectives from Offline Data},
booktitle = {{IEEE} Symposium Series on Computational Intelligence, {SSCI} 2023,
Mexico City, Mexico, December 5-8, 2023},
pages = {1674--1681},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/SSCI52147.2023.10371978},
doi = {10.1109/SSCI52147.2023.10371978},
timestamp = {Mon, 15 Jan 2024 21:26:31 +0100},
biburl = {https://dblp.org/rec/conf/ssci/WeberSHUS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-06127,
author = {Marc Weber and
Phillip Swazinna and
Daniel Hein and
Steffen Udluft and
Volkmar Sterzing},
title = {Learning Control Policies for Variable Objectives from Offline Data},
journal = {CoRR},
volume = {abs/2308.06127},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.06127},
doi = {10.48550/ARXIV.2308.06127},
eprinttype = {arXiv},
eprint = {2308.06127},
timestamp = {Wed, 23 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-06127.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/MeessGHSE22,
author = {Henri Meess and
Jeremias Gerner and
Daniel Hein and
Stefanie Schmidtner and
Gordon Elger},
editor = {Piotr Faliszewski and
Viviana Mascardi and
Catherine Pelachaud and
Matthew E. Taylor},
title = {Reinforcement Learning for Traffic Signal Control Optimization: {A}
Concept for Real-World Implementation},
booktitle = {21st International Conference on Autonomous Agents and Multiagent
Systems, {AAMAS} 2022, Auckland, New Zealand, May 9-13, 2022},
pages = {1699--1701},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems
{(IFAAMAS)}},
year = {2022},
url = {https://www.ifaamas.org/Proceedings/aamas2022/pdfs/p1699.pdf},
doi = {10.5555/3535850.3536081},
timestamp = {Mon, 18 Jul 2022 17:13:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/MeessGHSE22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-05433,
author = {Phillip Swazinna and
Steffen Udluft and
Daniel Hein and
Thomas A. Runkler},
title = {Comparing Model-free and Model-based Algorithms for Offline Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2201.05433},
year = {2022},
url = {https://arxiv.org/abs/2201.05433},
eprinttype = {arXiv},
eprint = {2201.05433},
timestamp = {Thu, 20 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-05433.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-04741,
author = {Simon Wiedemann and
Daniel Hein and
Steffen Udluft and
Christian B. Mendl},
title = {Quantum Policy Iteration via Amplitude Estimation and Grover Search
- Towards Quantum Advantage for Reinforcement Learning},
journal = {CoRR},
volume = {abs/2206.04741},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.04741},
doi = {10.48550/ARXIV.2206.04741},
eprinttype = {arXiv},
eprint = {2206.04741},
timestamp = {Thu, 18 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-04741.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/esann/SwazinnaU0R21,
author = {Phillip Swazinna and
Steffen Udluft and
Daniel Hein and
Thomas A. Runkler},
title = {Behavior Constraining in Weight Space for Offline Reinforcement Learning},
booktitle = {29th European Symposium on Artificial Neural Networks, Computational
Intelligence and Machine Learning, {ESANN} 2021, Online event (Bruges,
Belgium), October 6-8, 2021},
year = {2021},
url = {https://doi.org/10.14428/esann/2021.ES2021-83},
doi = {10.14428/ESANN/2021.ES2021-83},
timestamp = {Tue, 31 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/esann/SwazinnaU0R21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gecco/0001L21,
author = {Daniel Hein and
Daniel Labisch},
editor = {Krzysztof Krawiec},
title = {Trustworthy {AI} for process automation on a Chylla-Haase polymerization
reactor},
booktitle = {{GECCO} '21: Genetic and Evolutionary Computation Conference, Companion
Volume, Lille, France, July 10-14, 2021},
pages = {1570--1578},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3449726.3463131},
doi = {10.1145/3449726.3463131},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/gecco/0001L21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-05479,
author = {Phillip Swazinna and
Steffen Udluft and
Daniel Hein and
Thomas A. Runkler},
title = {Behavior Constraining in Weight Space for Offline Reinforcement Learning},
journal = {CoRR},
volume = {abs/2107.05479},
year = {2021},
url = {https://arxiv.org/abs/2107.05479},
eprinttype = {arXiv},
eprint = {2107.05479},
timestamp = {Tue, 20 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-05479.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-13381,
author = {Daniel Hein and
Daniel Labisch},
title = {Trustworthy {AI} for Process Automation on a Chylla-Haase Polymerization
Reactor},
journal = {CoRR},
volume = {abs/2108.13381},
year = {2021},
url = {https://arxiv.org/abs/2108.13381},
eprinttype = {arXiv},
eprint = {2108.13381},
timestamp = {Fri, 03 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-13381.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-09964,
author = {Daniel Hein and
Steffen Limmer and
Thomas A. Runkler},
title = {Interpretable Control by Reinforcement Learning},
journal = {CoRR},
volume = {abs/2007.09964},
year = {2020},
url = {https://arxiv.org/abs/2007.09964},
eprinttype = {arXiv},
eprint = {2007.09964},
timestamp = {Tue, 28 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-09964.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/dnb/Hein19,
author = {Daniel Hein},
title = {Interpretable Reinforcement Learning Policies by Evolutionary Computation},
school = {Technical University of Munich, Germany},
year = {2019},
url = {https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20191009-1467616-1-1},
urn = {urn:nbn:de:bvb:91-diss-20191009-1467616-1-1},
timestamp = {Sat, 17 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/dnb/Hein19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gecco/0001UR19,
author = {Daniel Hein and
Steffen Udluft and
Thomas A. Runkler},
editor = {Manuel L{\'{o}}pez{-}Ib{\'{a}}{\~{n}}ez and
Anne Auger and
Thomas St{\"{u}}tzle},
title = {Generating interpretable reinforcement learning policies using genetic
programming},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference
Companion, {GECCO} 2019, Prague, Czech Republic, July 13-17, 2019},
pages = {23--24},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3319619.3326755},
doi = {10.1145/3319619.3326755},
timestamp = {Thu, 23 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/gecco/0001UR19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/eaai/HeinUR18,
author = {Daniel Hein and
Steffen Udluft and
Thomas A. Runkler},
title = {Interpretable policies for reinforcement learning by genetic programming},
journal = {Eng. Appl. Artif. Intell.},
volume = {76},
pages = {158--169},
year = {2018},
url = {https://doi.org/10.1016/j.engappai.2018.09.007},
doi = {10.1016/J.ENGAPPAI.2018.09.007},
timestamp = {Tue, 16 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/eaai/HeinUR18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gecco/HeinUR18,
author = {Daniel Hein and
Steffen Udluft and
Thomas A. Runkler},
editor = {Hern{\'{a}}n E. Aguirre and
Keiki Takadama},
title = {Generating interpretable fuzzy controllers using particle swarm optimization
and genetic programming},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference
Companion, {GECCO} 2018, Kyoto, Japan, July 15-19, 2018},
pages = {1268--1275},
publisher = {{ACM}},
year = {2018},
url = {https://doi.org/10.1145/3205651.3208277},
doi = {10.1145/3205651.3208277},
timestamp = {Fri, 02 Aug 2024 15:50:42 +0200},
biburl = {https://dblp.org/rec/conf/gecco/HeinUR18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-10960,
author = {Daniel Hein and
Steffen Udluft and
Thomas A. Runkler},
title = {Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization
and Genetic Programming},
journal = {CoRR},
volume = {abs/1804.10960},
year = {2018},
url = {http://arxiv.org/abs/1804.10960},
eprinttype = {arXiv},
eprint = {1804.10960},
timestamp = {Tue, 04 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-10960.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/eaai/HeinHRU17,
author = {Daniel Hein and
Alexander Hentschel and
Thomas A. Runkler and
Steffen Udluft},
title = {Particle swarm optimization for generating interpretable fuzzy reinforcement
learning policies},
journal = {Eng. Appl. Artif. Intell.},
volume = {65},
pages = {87--98},
year = {2017},
url = {https://doi.org/10.1016/j.engappai.2017.07.005},
doi = {10.1016/J.ENGAPPAI.2017.07.005},
timestamp = {Tue, 16 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/eaai/HeinHRU17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/HeinUTHRS17,
author = {Daniel Hein and
Steffen Udluft and
Michel Tokic and
Alexander Hentschel and
Thomas A. Runkler and
Volkmar Sterzing},
title = {Batch reinforcement learning on the industrial benchmark: First experiences},
booktitle = {2017 International Joint Conference on Neural Networks, {IJCNN} 2017,
Anchorage, AK, USA, May 14-19, 2017},
pages = {4214--4221},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/IJCNN.2017.7966389},
doi = {10.1109/IJCNN.2017.7966389},
timestamp = {Thu, 23 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/HeinUTHRS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ssci/HeinDTUHRS17,
author = {Daniel Hein and
Stefan Depeweg and
Michel Tokic and
Steffen Udluft and
Alexander Hentschel and
Thomas A. Runkler and
Volkmar Sterzing},
title = {A benchmark environment motivated by industrial control problems},
booktitle = {2017 {IEEE} Symposium Series on Computational Intelligence, {SSCI}
2017, Honolulu, HI, USA, November 27 - Dec. 1, 2017},
pages = {1--8},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/SSCI.2017.8280935},
doi = {10.1109/SSCI.2017.8280935},
timestamp = {Thu, 23 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ssci/HeinDTUHRS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HeinUTHRS17,
author = {Daniel Hein and
Steffen Udluft and
Michel Tokic and
Alexander Hentschel and
Thomas A. Runkler and
Volkmar Sterzing},
title = {Batch Reinforcement Learning on the Industrial Benchmark: First Experiences},
journal = {CoRR},
volume = {abs/1705.07262},
year = {2017},
url = {http://arxiv.org/abs/1705.07262},
eprinttype = {arXiv},
eprint = {1705.07262},
timestamp = {Tue, 04 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/HeinUTHRS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-09480,
author = {Daniel Hein and
Stefan Depeweg and
Michel Tokic and
Steffen Udluft and
Alexander Hentschel and
Thomas A. Runkler and
Volkmar Sterzing},
title = {A Benchmark Environment Motivated by Industrial Control Problems},
journal = {CoRR},
volume = {abs/1709.09480},
year = {2017},
url = {http://arxiv.org/abs/1709.09480},
eprinttype = {arXiv},
eprint = {1709.09480},
timestamp = {Tue, 04 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-09480.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-04170,
author = {Daniel Hein and
Steffen Udluft and
Thomas A. Runkler},
title = {Interpretable Policies for Reinforcement Learning by Genetic Programming},
journal = {CoRR},
volume = {abs/1712.04170},
year = {2017},
url = {http://arxiv.org/abs/1712.04170},
eprinttype = {arXiv},
eprint = {1712.04170},
timestamp = {Tue, 04 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-04170.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijsir/HeinHRU16,
author = {Daniel Hein and
Alexander Hentschel and
Thomas A. Runkler and
Steffen Udluft},
title = {Reinforcement Learning with Particle Swarm Optimization Policy {(PSO-P)}
in Continuous State and Action Spaces},
journal = {Int. J. Swarm Intell. Res.},
volume = {7},
number = {3},
pages = {23--42},
year = {2016},
url = {https://doi.org/10.4018/IJSIR.2016070102},
doi = {10.4018/IJSIR.2016070102},
timestamp = {Tue, 29 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijsir/HeinHRU16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HeinHSTU16,
author = {Daniel Hein and
Alexander Hentschel and
Volkmar Sterzing and
Michel Tokic and
Steffen Udluft},
title = {Introduction to the "Industrial Benchmark"},
journal = {CoRR},
volume = {abs/1610.03793},
year = {2016},
url = {http://arxiv.org/abs/1610.03793},
eprinttype = {arXiv},
eprint = {1610.03793},
timestamp = {Tue, 04 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/HeinHSTU16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HeinHRU16,
author = {Daniel Hein and
Alexander Hentschel and
Thomas A. Runkler and
Steffen Udluft},
title = {Particle Swarm Optimization for Generating Fuzzy Reinforcement Learning
Policies},
journal = {CoRR},
volume = {abs/1610.05984},
year = {2016},
url = {http://arxiv.org/abs/1610.05984},
eprinttype = {arXiv},
eprint = {1610.05984},
timestamp = {Tue, 04 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/HeinHRU16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
