@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{SedlmeierGaborPhanetal.2020, author = {Sedlmeier, Andreas and Gabor, Thomas and Phan, Thomy and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Uncertainty-based out-of-distribution classification in deep reinforcement learning}, booktitle = {Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART}, editor = {Rocha, Ana and Steels, Luc and Herik, Jaap van den}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-395-7}, issn = {2184-433X}, doi = {https://doi.org/10.5220/0008949905220529}, pages = {522 -- 529}, year = {2020}, abstract = {Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. As a first step towards a solution, we consider the problem of detecting such data in a value-based deep reinforcement learning (RL) setting. Modelling this problem as a one-class classification problem, we propose a framework for uncertainty-based OOD classification: UBOOD. It is based on the effect that an agent's epistemic uncertainty is reduced for situations encountered during training (in-distribution), and thus lower than for unencountered (OOD) situations. Being agnostic towards the approach used for estimating epistemic uncertainty, combinations with different uncertainty estimation methods, e.g. approximate Bayesian inference methods or ensembling techniques are possible. Evaluation shows that the framework produces reliable classification results when combined with ensemble-based estimators, while the combination with concrete dropout-based estimators fails to r eliably detect OOD situations.}, 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{FeldSedlmeierFriedrichetal.2019, author = {Feld, Sebastian and Sedlmeier, Andreas and Friedrich, Markus and Franz, Jan and Belzner, Lenz}, title = {Bayesian Surprise in Indoor Environments}, booktitle = {SIGSPATIAL '19 : Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems}, publisher = {ACM}, address = {New York}, isbn = {978-1-4503-6909-1}, doi = {https://doi.org/10.1145/3347146.3359358}, year = {2019}, language = {en} } @inproceedings{FeldSedlmeierIlliumetal.2018, author = {Feld, Sebastian and Sedlmeier, Andreas and Illium, Steffen and Belzner, Lenz}, title = {Trajectory annotation using sequences of spatial perception}, booktitle = {SIGSPATIAL '18 : Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems}, publisher = {ACM}, address = {New York}, isbn = {978-1-4503-5889-7}, doi = {https://doi.org/10.1145/3274895.3274968}, pages = {329 -- 338}, year = {2018}, 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} }