@inproceedings{PhanRitzBelzneretal.2021, author = {Phan, Thomy and Ritz, Fabian and Belzner, Lenz and Altmann, Philipp and Gabor, Thomas and Linnhoff-Popien, Claudia}, title = {VAST: Value Function Factorization with Variable Agent Sub-Teams}, booktitle = {Advances in Neural Information Processing Systems 34 (NeurIPS 2021)}, publisher = {Neural Information Processing Systems Foundation, Inc. (NIPS)}, url = {https://proceedings.neurips.cc/paper/2021/hash/c97e7a5153badb6576d8939469f58336-Abstract.html}, year = {2021}, language = {en} } @inproceedings{PhanSommerAltmannetal.2022, author = {Phan, Thomy and Sommer, Felix and Altmann, Philipp and Ritz, Fabian and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent Cooperation from Mutual Acknowledgment Exchange}, booktitle = {AAMAS '22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, address = {Richland}, isbn = {978-1-4503-9213-6}, doi = {https://dl.acm.org/doi/10.5555/3535850.3535967}, pages = {1047 -- 1055}, year = {2022}, language = {en} } @inproceedings{PhanBelznerKiermeieretal.2019, author = {Phan, Thomy and Belzner, Lenz and Kiermeier, Marie and Friedrich, Markus and Schmid, Kyrill and Linnhoff-Popien, Claudia}, title = {Memory Bounded Open-Loop Planning in Large POMDPs Using Thompson Sampling}, volume = {33}, booktitle = {AAAI-19 / IAAI-19 / EAAI-20 Proceedings}, number = {1}, publisher = {AAAI Press}, address = {Palo Alto}, issn = {2374-3468}, doi = {https://doi.org/10.1609/aaai.v33i01.33017941}, pages = {7941 -- 7948}, year = {2019}, language = {en} } @inproceedings{HahnPhanGaboretal.2019, author = {Hahn, Carsten and Phan, Thomy and Gabor, Thomas and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent Escape-based Flocking behavior using Multi-Agent Reinforcement Learning}, pages = {isal_a_00226}, booktitle = {Artificial Life Conference Proceedings}, publisher = {MIT Press}, address = {Cambridge}, doi = {https://doi.org/10.1162/isal_a_00226}, pages = {598 -- 605}, year = {2019}, language = {en} } @inproceedings{PhanSchmidBelzneretal.2019, author = {Phan, Thomy and Schmid, Kyrill and Belzner, Lenz and Gabor, Thomas and Feld, Sebastian and Linnhoff-Popien, Claudia}, title = {Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies}, booktitle = {AAMAS '19: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, address = {Richland}, isbn = {978-1-4503-6309-9}, url = {https://www.ifaamas.org/Proceedings/aamas2019/forms/contents.htm}, pages = {2162 -- 2164}, year = {2019}, language = {en} } @article{SedlmeierGaborPhanetal.2019, author = {Sedlmeier, Andreas and Gabor, Thomas and Phan, Thomy and Belzner, Lenz}, title = {Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learning}, volume = {4}, journal = {Digitale Welt}, number = {1}, publisher = {Digitale Welt Academy}, address = {M{\"u}nchen}, issn = {2569-1996}, doi = {https://doi.org/10.1007/s42354-019-0238-z}, pages = {74 -- 78}, year = {2019}, language = {en} } @inproceedings{PhanBelznerGaboretal.2021, author = {Phan, Thomy and Belzner, Lenz and Gabor, Thomas and Sedlmeier, Andreas and Ritz, Fabian and Linnhoff-Popien, Claudia}, title = {Resilient multi-agent reinforcement learning with adversarial value decomposition}, volume = {35}, booktitle = {AAAI-21 / IAAI-21 / EAAI-21 Proceedings}, number = {13}, publisher = {AAAI Press}, address = {Palo Alto (CA)}, isbn = {978-1-57735-866-4}, issn = {2374-3468}, doi = {https://ojs.aaai.org/index.php/AAAI/article/view/17348}, pages = {11308 -- 11316}, year = {2021}, language = {en} } @article{GaborSedlmeierPhanetal.2020, author = {Gabor, Thomas and Sedlmeier, Andreas and Phan, Thomy and Ritz, Fabian and Kiermeier, Marie and Belzner, Lenz and Kempter, Bernhard and Klein, Cornel and Sauer, Horst and Schmid, Reiner and Wieghardt, Jan and Zeller, Marc and Linnhoff-Popien, Claudia}, title = {The scenario coevolution paradigm}, volume = {22}, journal = {International Journal on Software Tools for Technology Transfer}, subtitle = {adaptive quality assurance for adaptive systems}, number = {4}, publisher = {Springer}, address = {Berlin}, issn = {1433-2787}, doi = {https://doi.org/10.1007/s10009-020-00560-5}, pages = {457 -- 476}, year = {2020}, abstract = {Systems are becoming increasingly more adaptive, using techniques like machine learning to enhance their behavior on their own rather than only through human developers programming them. We analyze the impact the advent of these new techniques has on the discipline of rigorous software engineering, especially on the issue of quality assurance. To this end, we provide a general description of the processes related to machine learning and embed them into a formal framework for the analysis of adaptivity, recognizing that to test an adaptive system a new approach to adaptive testing is necessary. We introduce scenario coevolution as a design pattern describing how system and test can work as antagonists in the process of software evolution. While the general pattern applies to large-scale processes (including human developers further augmenting the system), we show all techniques on a smaller-scale example of an agent navigating a simple smart factory. We point out new aspects in software engineering for adaptive systems that may be tackled naturally using scenario coevolution. This work is a substantially extended take on Gabor et al. (International symposium on leveraging applications of formal methods, Springer, pp 137-154, 2018).}, language = {en} } @inproceedings{GaborSuenkelRitzetal.2020, author = {Gabor, Thomas and S{\"u}nkel, Leo and Ritz, Fabian and Phan, Thomy and Belzner, Lenz and Roch, Christoph and Feld, Sebastian and Linnhoff-Popien, Claudia}, title = {The Holy Grail of Quantum Artificial Intelligence: Major Challenges in Accelerating the Machine Learning Pipeline}, booktitle = {ICSEW'20 : Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops}, publisher = {ACM}, address = {New York}, isbn = {978-1-4503-7963-2}, doi = {https://doi.org/10.1145/3387940.3391469}, pages = {456 -- 461}, year = {2020}, language = {en} } @inproceedings{SchmidBelznerGaboretal.2018, author = {Schmid, Kyrill and Belzner, Lenz and Gabor, Thomas and Phan, Thomy}, title = {Action Markets in Deep Multi-Agent Reinforcement Learning}, booktitle = {Artificial Neural Networks and Machine Learning - ICANN 2018: 27th International Conference on Artificial Neural Networks Proceedings, Part II}, editor = {Kurkova, Vera and Manolopoulos, Yannis and Hammer, Barbara and Iliadis, Lazaros and Maglogiannis, Ilias}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-01421-6}, doi = {https://doi.org/10.1007/978-3-030-01421-6_24}, pages = {240 -- 249}, year = {2018}, language = {en} }