@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}, booktitle = {ICSEW'20 : Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops}, subtitle = {major challenges in accelerating the machine learning pipeline}, 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{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} } @inproceedings{RitzRatkePhanetal.2021, author = {Ritz, Fabian and Ratke, Daniel and Phan, Thomy and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {A sustainable ecosystem through emergent cooperation in multi-agent reinforcement learning}, volume = {2021}, pages = {isal_a_00399}, booktitle = {Proceedings of the Artificial Life Conference 2021}, publisher = {MIT Press}, address = {Cambridge}, doi = {https://doi.org/10.1162/isal_a_00399}, year = {2021}, language = {en} } @unpublished{PhanSommerRitzetal.2022, author = {Phan, Thomy and Sommer, Felix and Ritz, Fabian and Altmann, Philipp and N{\"u}ßlein, Jonas and K{\"o}lle, Michael and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent Cooperation from Mutual Acknowledgment Exchange in Multi-Agent Reinforcement Learning}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-2315844/v1}, year = {2022}, abstract = {Peer incentivization (PI) is a recent approach, where all agents learn to reward or to penalize each other in a distributed fashion which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in order to exchange rewards. These rewards are directly integrated into the learning process without any chance to respond with feedback. Furthermore, most PI approaches rely on global information which limits scalability and applicability to real-world scenarios, where only local information is accessible. In this paper, we propose Mutual Acknowledgment Token Exchange (MATE), a PI approach defined by a two-phase communication protocol to mutually exchange acknowledgment tokens to shape individual rewards. Each agent evaluates the monotonic improvement of its individual situation in order to accept or reject acknowledgment requests from other agents. MATE is completely decentralized and only requires local communication and information. We evaluate MATE in three social dilemma domains. Our results show that MATE is able to achieve and maintain significantly higher levels of cooperation than previous PI approaches. In addition, we evaluate the robustness of MATE in more realistic scenarios, where agents can defect from the protocol and where communication failures can occur. We also evaluate the sensitivity of MATE w.r.t. the choice of token values.}, language = {en} } @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 = {Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022)}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, address = {Richland}, isbn = {978-1-4503-9213-6}, url = {https://dl.acm.org/doi/10.5555/3535850.3535967}, pages = {1047 -- 1055}, year = {2022}, language = {en} }